Upload folder using huggingface_hub
Browse files- added_tokens.json +11 -0
- config.json +488 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1091 -0
- special_tokens_map.json +47 -0
- tokenization_internlm2.py +235 -0
- tokenizer.model +3 -0
- tokenizer_config.json +179 -0
- trainer_state.json +2133 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</box>": 92552,
|
| 3 |
+
"</img>": 92545,
|
| 4 |
+
"</quad>": 92548,
|
| 5 |
+
"</ref>": 92550,
|
| 6 |
+
"<IMG_CONTEXT>": 92546,
|
| 7 |
+
"<box>": 92551,
|
| 8 |
+
"<img>": 92544,
|
| 9 |
+
"<quad>": 92547,
|
| 10 |
+
"<ref>": 92549
|
| 11 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,488 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": null,
|
| 3 |
+
"_name_or_path": "/workspace/aether_vla/Go-1-training/AgiBot-World/pretrained/GO-1",
|
| 4 |
+
"action_chunk_size": 30,
|
| 5 |
+
"action_config": {
|
| 6 |
+
"_attn_implementation_autoset": true,
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"action_chunk_size": 30,
|
| 9 |
+
"action_dim": 16,
|
| 10 |
+
"add_cross_attention": false,
|
| 11 |
+
"architectures": [
|
| 12 |
+
"ActionExpertModel"
|
| 13 |
+
],
|
| 14 |
+
"attn_implementation": "eager",
|
| 15 |
+
"auto_map": {
|
| 16 |
+
"AutoConfig": "configuration_action_expert.ActionExpertConfig",
|
| 17 |
+
"AutoModel": "modeling_action_expert.ActionExpertModel"
|
| 18 |
+
},
|
| 19 |
+
"bad_words_ids": null,
|
| 20 |
+
"begin_suppress_tokens": null,
|
| 21 |
+
"bias": false,
|
| 22 |
+
"bos_token_id": null,
|
| 23 |
+
"chunk_size_feed_forward": 0,
|
| 24 |
+
"cross_attention_hidden_size": null,
|
| 25 |
+
"decoder_start_token_id": null,
|
| 26 |
+
"diversity_penalty": 0.0,
|
| 27 |
+
"do_sample": false,
|
| 28 |
+
"early_stopping": false,
|
| 29 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 30 |
+
"eos_token_id": null,
|
| 31 |
+
"exponential_decay_length_penalty": null,
|
| 32 |
+
"finetuning_task": null,
|
| 33 |
+
"forced_bos_token_id": null,
|
| 34 |
+
"forced_eos_token_id": null,
|
| 35 |
+
"head_dim": 64,
|
| 36 |
+
"hidden_act": "silu",
|
| 37 |
+
"hidden_size": 1024,
|
| 38 |
+
"id2label": {
|
| 39 |
+
"0": "LABEL_0",
|
| 40 |
+
"1": "LABEL_1"
|
| 41 |
+
},
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"input_hidden_size": 2048,
|
| 44 |
+
"intermediate_size": 4096,
|
| 45 |
+
"is_decoder": false,
|
| 46 |
+
"is_encoder_decoder": false,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"LABEL_0": 0,
|
| 49 |
+
"LABEL_1": 1
|
| 50 |
+
},
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 20,
|
| 53 |
+
"max_position_embeddings": 32768,
|
| 54 |
+
"min_length": 0,
|
| 55 |
+
"model_type": "action_expert",
|
| 56 |
+
"no_repeat_ngram_size": 0,
|
| 57 |
+
"num_attention_heads": 16,
|
| 58 |
+
"num_beam_groups": 1,
|
| 59 |
+
"num_beams": 1,
|
| 60 |
+
"num_hidden_layers": 24,
|
| 61 |
+
"num_key_value_heads": 8,
|
| 62 |
+
"num_return_sequences": 1,
|
| 63 |
+
"output_attentions": false,
|
| 64 |
+
"output_hidden_states": false,
|
| 65 |
+
"output_scores": false,
|
| 66 |
+
"pad_token_id": 2,
|
| 67 |
+
"prefix": null,
|
| 68 |
+
"problem_type": null,
|
| 69 |
+
"pruned_heads": {},
|
| 70 |
+
"remove_invalid_values": false,
|
| 71 |
+
"repetition_penalty": 1.0,
|
| 72 |
+
"return_dict": true,
|
| 73 |
+
"return_dict_in_generate": false,
|
| 74 |
+
"rms_norm_eps": 1e-05,
|
| 75 |
+
"rope_scaling": {
|
| 76 |
+
"factor": 2.0,
|
| 77 |
+
"type": "dynamic"
|
| 78 |
+
},
|
| 79 |
+
"rope_theta": 1000000,
|
| 80 |
+
"sep_token_id": null,
|
| 81 |
+
"state_dim": 16,
|
| 82 |
+
"state_token_num": 3,
|
| 83 |
+
"suppress_tokens": null,
|
| 84 |
+
"task_specific_params": null,
|
| 85 |
+
"temperature": 1.0,
|
| 86 |
+
"tf_legacy_loss": false,
|
| 87 |
+
"tie_encoder_decoder": false,
|
| 88 |
+
"tie_word_embeddings": true,
|
| 89 |
+
"tokenizer_class": null,
|
| 90 |
+
"top_k": 50,
|
| 91 |
+
"top_p": 1.0,
|
| 92 |
+
"torch_dtype": "bfloat16",
|
| 93 |
+
"torchscript": false,
|
| 94 |
+
"transformers_version": "4.46.3",
|
| 95 |
+
"typical_p": 1.0,
|
| 96 |
+
"use_bfloat16": true,
|
| 97 |
+
"use_cache": true,
|
| 98 |
+
"use_flash_attn": false
|
| 99 |
+
},
|
| 100 |
+
"architectures": [
|
| 101 |
+
"GO1Model"
|
| 102 |
+
],
|
| 103 |
+
"auto_map": {
|
| 104 |
+
"AutoConfig": "configuration_go1.GO1ModelConfig",
|
| 105 |
+
"AutoModel": "modeling_go1.GO1Model",
|
| 106 |
+
"AutoModelForCausalLM": "modeling_internlm2_go1.py.InternLM2ForCausalLMGO1"
|
| 107 |
+
},
|
| 108 |
+
"downsample_ratio": 0.5,
|
| 109 |
+
"dynamic_image_size": false,
|
| 110 |
+
"force_image_size": 448,
|
| 111 |
+
"img_context_token_id": 92546,
|
| 112 |
+
"latent_action_config": {
|
| 113 |
+
"_attn_implementation_autoset": false,
|
| 114 |
+
"_name_or_path": "",
|
| 115 |
+
"action_dim": 1,
|
| 116 |
+
"action_horizon": 30,
|
| 117 |
+
"add_cross_attention": false,
|
| 118 |
+
"architectures": null,
|
| 119 |
+
"attn_implementation": "eager",
|
| 120 |
+
"bad_words_ids": null,
|
| 121 |
+
"begin_suppress_tokens": null,
|
| 122 |
+
"bias": false,
|
| 123 |
+
"bos_token_id": null,
|
| 124 |
+
"chunk_size_feed_forward": 0,
|
| 125 |
+
"cross_attention_hidden_size": null,
|
| 126 |
+
"decoder_start_token_id": null,
|
| 127 |
+
"diffusion": false,
|
| 128 |
+
"discrete": true,
|
| 129 |
+
"diversity_penalty": 0.0,
|
| 130 |
+
"do_sample": false,
|
| 131 |
+
"early_stopping": false,
|
| 132 |
+
"enable_act_training": true,
|
| 133 |
+
"enable_ntp_training": false,
|
| 134 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 135 |
+
"eos_token_id": null,
|
| 136 |
+
"exponential_decay_length_penalty": null,
|
| 137 |
+
"final_use_diffusion": true,
|
| 138 |
+
"finetuning_task": null,
|
| 139 |
+
"forced_bos_token_id": null,
|
| 140 |
+
"forced_eos_token_id": null,
|
| 141 |
+
"head_dim": 64,
|
| 142 |
+
"hidden_act": "silu",
|
| 143 |
+
"hidden_size": 1024,
|
| 144 |
+
"id2label": {
|
| 145 |
+
"0": "LABEL_0",
|
| 146 |
+
"1": "LABEL_1"
|
| 147 |
+
},
|
| 148 |
+
"img_context_token_id": 92546,
|
| 149 |
+
"initializer_range": 0.02,
|
| 150 |
+
"input_hidden_size": 2048,
|
| 151 |
+
"intermediate_size": 2048,
|
| 152 |
+
"is_decoder": false,
|
| 153 |
+
"is_encoder_decoder": false,
|
| 154 |
+
"label2id": {
|
| 155 |
+
"LABEL_0": 0,
|
| 156 |
+
"LABEL_1": 1
|
| 157 |
+
},
|
| 158 |
+
"length_penalty": 1.0,
|
| 159 |
+
"llm_stop_token_ids": 92542,
|
| 160 |
+
"mask_vision_head_prob": 0.0,
|
| 161 |
+
"mask_vision_wrist_prob": 0.0,
|
| 162 |
+
"max_length": 20,
|
| 163 |
+
"max_position_embeddings": 2048,
|
| 164 |
+
"min_length": 0,
|
| 165 |
+
"model_type": "intermidiate_action_expert",
|
| 166 |
+
"no_repeat_ngram_size": 0,
|
| 167 |
+
"ntp_loss_weight": 0.1,
|
| 168 |
+
"num_attention_heads": 16,
|
| 169 |
+
"num_beam_groups": 1,
|
| 170 |
+
"num_beams": 1,
|
| 171 |
+
"num_hidden_layers": 24,
|
| 172 |
+
"num_key_value_heads": 8,
|
| 173 |
+
"num_return_sequences": 1,
|
| 174 |
+
"output_attentions": false,
|
| 175 |
+
"output_hidden_states": false,
|
| 176 |
+
"output_scores": false,
|
| 177 |
+
"pad_token_id": null,
|
| 178 |
+
"prefix": null,
|
| 179 |
+
"problem_type": null,
|
| 180 |
+
"pruned_heads": {},
|
| 181 |
+
"remove_invalid_values": false,
|
| 182 |
+
"repetition_penalty": 1.0,
|
| 183 |
+
"return_dict": true,
|
| 184 |
+
"return_dict_in_generate": false,
|
| 185 |
+
"rms_norm_eps": 1e-06,
|
| 186 |
+
"rope_scaling": null,
|
| 187 |
+
"rope_theta": 10000,
|
| 188 |
+
"sep_token_id": null,
|
| 189 |
+
"state_token_num": 0,
|
| 190 |
+
"suppress_tokens": null,
|
| 191 |
+
"task_specific_params": null,
|
| 192 |
+
"temperature": 1.0,
|
| 193 |
+
"tf_legacy_loss": false,
|
| 194 |
+
"tie_encoder_decoder": false,
|
| 195 |
+
"tie_word_embeddings": true,
|
| 196 |
+
"tokenizer_class": null,
|
| 197 |
+
"top_k": 50,
|
| 198 |
+
"top_p": 1.0,
|
| 199 |
+
"torch_dtype": null,
|
| 200 |
+
"torchscript": false,
|
| 201 |
+
"transformers_version": "4.46.3",
|
| 202 |
+
"typical_p": 1.0,
|
| 203 |
+
"use_bfloat16": false,
|
| 204 |
+
"use_cache": true,
|
| 205 |
+
"vocab_size": 32
|
| 206 |
+
},
|
| 207 |
+
"latent_planner_config": {
|
| 208 |
+
"_attn_implementation_autoset": false,
|
| 209 |
+
"_name_or_path": "",
|
| 210 |
+
"action_dim": 1,
|
| 211 |
+
"add_cross_attention": false,
|
| 212 |
+
"architectures": null,
|
| 213 |
+
"attn_implementation": "eager",
|
| 214 |
+
"bad_words_ids": null,
|
| 215 |
+
"begin_suppress_tokens": null,
|
| 216 |
+
"bias": false,
|
| 217 |
+
"bos_token_id": null,
|
| 218 |
+
"chunk_size_feed_forward": 0,
|
| 219 |
+
"cross_attention_hidden_size": null,
|
| 220 |
+
"decoder_start_token_id": null,
|
| 221 |
+
"diversity_penalty": 0.0,
|
| 222 |
+
"do_sample": false,
|
| 223 |
+
"early_stopping": false,
|
| 224 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 225 |
+
"eos_token_id": null,
|
| 226 |
+
"exponential_decay_length_penalty": null,
|
| 227 |
+
"finetuning_task": null,
|
| 228 |
+
"forced_bos_token_id": null,
|
| 229 |
+
"forced_eos_token_id": null,
|
| 230 |
+
"head_dim": 64,
|
| 231 |
+
"hidden_act": "silu",
|
| 232 |
+
"hidden_size": 1024,
|
| 233 |
+
"id2label": {
|
| 234 |
+
"0": "LABEL_0",
|
| 235 |
+
"1": "LABEL_1"
|
| 236 |
+
},
|
| 237 |
+
"initializer_range": 0.02,
|
| 238 |
+
"input_hidden_size": 2048,
|
| 239 |
+
"intermediate_size": 2048,
|
| 240 |
+
"is_decoder": false,
|
| 241 |
+
"is_encoder_decoder": false,
|
| 242 |
+
"label2id": {
|
| 243 |
+
"LABEL_0": 0,
|
| 244 |
+
"LABEL_1": 1
|
| 245 |
+
},
|
| 246 |
+
"length_penalty": 1.0,
|
| 247 |
+
"max_length": 20,
|
| 248 |
+
"max_position_embeddings": 2048,
|
| 249 |
+
"min_length": 0,
|
| 250 |
+
"model_type": "intermidiate_action_expert",
|
| 251 |
+
"no_repeat_ngram_size": 0,
|
| 252 |
+
"num_attention_heads": 16,
|
| 253 |
+
"num_beam_groups": 1,
|
| 254 |
+
"num_beams": 1,
|
| 255 |
+
"num_hidden_layers": 24,
|
| 256 |
+
"num_key_value_heads": 8,
|
| 257 |
+
"num_return_sequences": 1,
|
| 258 |
+
"output_attentions": false,
|
| 259 |
+
"output_hidden_states": false,
|
| 260 |
+
"output_scores": false,
|
| 261 |
+
"pad_token_id": null,
|
| 262 |
+
"prefix": null,
|
| 263 |
+
"problem_type": null,
|
| 264 |
+
"pruned_heads": {},
|
| 265 |
+
"remove_invalid_values": false,
|
| 266 |
+
"repetition_penalty": 1.0,
|
| 267 |
+
"return_dict": true,
|
| 268 |
+
"return_dict_in_generate": false,
|
| 269 |
+
"rms_norm_eps": 1e-06,
|
| 270 |
+
"rope_scaling": null,
|
| 271 |
+
"rope_theta": 10000,
|
| 272 |
+
"sep_token_id": null,
|
| 273 |
+
"state_token_num": 0,
|
| 274 |
+
"suppress_tokens": null,
|
| 275 |
+
"task_specific_params": null,
|
| 276 |
+
"temperature": 1.0,
|
| 277 |
+
"tf_legacy_loss": false,
|
| 278 |
+
"tie_encoder_decoder": false,
|
| 279 |
+
"tie_word_embeddings": true,
|
| 280 |
+
"tokenizer_class": null,
|
| 281 |
+
"top_k": 50,
|
| 282 |
+
"top_p": 1.0,
|
| 283 |
+
"torch_dtype": null,
|
| 284 |
+
"torchscript": false,
|
| 285 |
+
"transformers_version": "4.46.3",
|
| 286 |
+
"typical_p": 1.0,
|
| 287 |
+
"use_bfloat16": false,
|
| 288 |
+
"use_cache": true,
|
| 289 |
+
"vocab_size": 32
|
| 290 |
+
},
|
| 291 |
+
"latent_planning": true,
|
| 292 |
+
"llm_config": {
|
| 293 |
+
"_attn_implementation_autoset": true,
|
| 294 |
+
"_name_or_path": "",
|
| 295 |
+
"add_cross_attention": false,
|
| 296 |
+
"architectures": [
|
| 297 |
+
"InternLM2ForCausalLMGO1"
|
| 298 |
+
],
|
| 299 |
+
"attn_implementation": "flash_attention_2",
|
| 300 |
+
"auto_map": {
|
| 301 |
+
"AutoConfig": "configuration_internlm2.InternLM2Config",
|
| 302 |
+
"AutoModel": "modeling_internlm2_go1.InternLM2ForCausalLMGO1",
|
| 303 |
+
"AutoModelForCausalLM": "modeling_internlm2_go1.py.InternLM2ForCausalLMGO1"
|
| 304 |
+
},
|
| 305 |
+
"bad_words_ids": null,
|
| 306 |
+
"begin_suppress_tokens": null,
|
| 307 |
+
"bias": false,
|
| 308 |
+
"bos_token_id": 1,
|
| 309 |
+
"chunk_size_feed_forward": 0,
|
| 310 |
+
"cross_attention_hidden_size": null,
|
| 311 |
+
"decoder_start_token_id": null,
|
| 312 |
+
"diversity_penalty": 0.0,
|
| 313 |
+
"do_sample": false,
|
| 314 |
+
"early_stopping": false,
|
| 315 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 316 |
+
"eos_token_id": 2,
|
| 317 |
+
"exponential_decay_length_penalty": null,
|
| 318 |
+
"finetuning_task": null,
|
| 319 |
+
"forced_bos_token_id": null,
|
| 320 |
+
"forced_eos_token_id": null,
|
| 321 |
+
"hidden_act": "silu",
|
| 322 |
+
"hidden_size": 2048,
|
| 323 |
+
"id2label": {
|
| 324 |
+
"0": "LABEL_0",
|
| 325 |
+
"1": "LABEL_1"
|
| 326 |
+
},
|
| 327 |
+
"initializer_range": 0.02,
|
| 328 |
+
"intermediate_size": 8192,
|
| 329 |
+
"is_decoder": false,
|
| 330 |
+
"is_encoder_decoder": false,
|
| 331 |
+
"label2id": {
|
| 332 |
+
"LABEL_0": 0,
|
| 333 |
+
"LABEL_1": 1
|
| 334 |
+
},
|
| 335 |
+
"length_penalty": 1.0,
|
| 336 |
+
"max_length": 20,
|
| 337 |
+
"max_position_embeddings": 32768,
|
| 338 |
+
"min_length": 0,
|
| 339 |
+
"model_type": "internlm2",
|
| 340 |
+
"no_repeat_ngram_size": 0,
|
| 341 |
+
"num_attention_heads": 16,
|
| 342 |
+
"num_beam_groups": 1,
|
| 343 |
+
"num_beams": 1,
|
| 344 |
+
"num_hidden_layers": 24,
|
| 345 |
+
"num_key_value_heads": 8,
|
| 346 |
+
"num_return_sequences": 1,
|
| 347 |
+
"output_attentions": false,
|
| 348 |
+
"output_hidden_states": false,
|
| 349 |
+
"output_scores": false,
|
| 350 |
+
"pad_token_id": 2,
|
| 351 |
+
"prefix": null,
|
| 352 |
+
"problem_type": null,
|
| 353 |
+
"pruned_heads": {},
|
| 354 |
+
"remove_invalid_values": false,
|
| 355 |
+
"repetition_penalty": 1.0,
|
| 356 |
+
"return_dict": true,
|
| 357 |
+
"return_dict_in_generate": false,
|
| 358 |
+
"rms_norm_eps": 1e-05,
|
| 359 |
+
"rope_scaling": {
|
| 360 |
+
"factor": 2.0,
|
| 361 |
+
"type": "dynamic"
|
| 362 |
+
},
|
| 363 |
+
"rope_theta": 1000000,
|
| 364 |
+
"sep_token_id": null,
|
| 365 |
+
"suppress_tokens": null,
|
| 366 |
+
"task_specific_params": null,
|
| 367 |
+
"temperature": 1.0,
|
| 368 |
+
"tf_legacy_loss": false,
|
| 369 |
+
"tie_encoder_decoder": false,
|
| 370 |
+
"tie_word_embeddings": false,
|
| 371 |
+
"tokenizer_class": null,
|
| 372 |
+
"top_k": 50,
|
| 373 |
+
"top_p": 1.0,
|
| 374 |
+
"torch_dtype": "bfloat16",
|
| 375 |
+
"torchscript": false,
|
| 376 |
+
"transformers_version": "4.46.3",
|
| 377 |
+
"typical_p": 1.0,
|
| 378 |
+
"use_bfloat16": true,
|
| 379 |
+
"use_cache": true,
|
| 380 |
+
"vocab_size": 92553
|
| 381 |
+
},
|
| 382 |
+
"max_dynamic_patch": 6,
|
| 383 |
+
"min_dynamic_patch": 1,
|
| 384 |
+
"model_type": "go1",
|
| 385 |
+
"noise_scheduler_config": {
|
| 386 |
+
"beta_schedule": "squaredcos_cap_v2",
|
| 387 |
+
"clip_sample": false,
|
| 388 |
+
"num_inference_timesteps": 5,
|
| 389 |
+
"num_train_timesteps": 1000,
|
| 390 |
+
"prediction_type": "sample"
|
| 391 |
+
},
|
| 392 |
+
"norm": true,
|
| 393 |
+
"pad2square": false,
|
| 394 |
+
"pad_token_id": 2,
|
| 395 |
+
"ps_version": "v2",
|
| 396 |
+
"select_layer": -1,
|
| 397 |
+
"template": "internlm2-chat",
|
| 398 |
+
"torch_dtype": "bfloat16",
|
| 399 |
+
"transformers_version": null,
|
| 400 |
+
"use_backbone_lora": 0,
|
| 401 |
+
"use_llm_lora": 0,
|
| 402 |
+
"use_thumbnail": false,
|
| 403 |
+
"vision_config": {
|
| 404 |
+
"_attn_implementation_autoset": true,
|
| 405 |
+
"_name_or_path": "",
|
| 406 |
+
"add_cross_attention": false,
|
| 407 |
+
"architectures": [
|
| 408 |
+
"InternVisionModel"
|
| 409 |
+
],
|
| 410 |
+
"attention_dropout": 0.0,
|
| 411 |
+
"bad_words_ids": null,
|
| 412 |
+
"begin_suppress_tokens": null,
|
| 413 |
+
"bos_token_id": null,
|
| 414 |
+
"chunk_size_feed_forward": 0,
|
| 415 |
+
"cross_attention_hidden_size": null,
|
| 416 |
+
"decoder_start_token_id": null,
|
| 417 |
+
"diversity_penalty": 0.0,
|
| 418 |
+
"do_sample": false,
|
| 419 |
+
"drop_path_rate": 0.1,
|
| 420 |
+
"dropout": 0.0,
|
| 421 |
+
"early_stopping": false,
|
| 422 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 423 |
+
"eos_token_id": null,
|
| 424 |
+
"exponential_decay_length_penalty": null,
|
| 425 |
+
"finetuning_task": null,
|
| 426 |
+
"forced_bos_token_id": null,
|
| 427 |
+
"forced_eos_token_id": null,
|
| 428 |
+
"hidden_act": "gelu",
|
| 429 |
+
"hidden_size": 1024,
|
| 430 |
+
"id2label": {
|
| 431 |
+
"0": "LABEL_0",
|
| 432 |
+
"1": "LABEL_1"
|
| 433 |
+
},
|
| 434 |
+
"image_size": 448,
|
| 435 |
+
"initializer_factor": 1.0,
|
| 436 |
+
"initializer_range": 0.02,
|
| 437 |
+
"intermediate_size": 4096,
|
| 438 |
+
"is_decoder": false,
|
| 439 |
+
"is_encoder_decoder": false,
|
| 440 |
+
"label2id": {
|
| 441 |
+
"LABEL_0": 0,
|
| 442 |
+
"LABEL_1": 1
|
| 443 |
+
},
|
| 444 |
+
"layer_norm_eps": 1e-06,
|
| 445 |
+
"length_penalty": 1.0,
|
| 446 |
+
"max_length": 20,
|
| 447 |
+
"min_length": 0,
|
| 448 |
+
"model_type": "intern_vit_6b",
|
| 449 |
+
"no_repeat_ngram_size": 0,
|
| 450 |
+
"norm_type": "layer_norm",
|
| 451 |
+
"num_attention_heads": 16,
|
| 452 |
+
"num_beam_groups": 1,
|
| 453 |
+
"num_beams": 1,
|
| 454 |
+
"num_channels": 3,
|
| 455 |
+
"num_hidden_layers": 24,
|
| 456 |
+
"num_return_sequences": 1,
|
| 457 |
+
"output_attentions": false,
|
| 458 |
+
"output_hidden_states": false,
|
| 459 |
+
"output_scores": false,
|
| 460 |
+
"pad_token_id": null,
|
| 461 |
+
"patch_size": 14,
|
| 462 |
+
"prefix": null,
|
| 463 |
+
"problem_type": null,
|
| 464 |
+
"pruned_heads": {},
|
| 465 |
+
"qk_normalization": false,
|
| 466 |
+
"qkv_bias": true,
|
| 467 |
+
"remove_invalid_values": false,
|
| 468 |
+
"repetition_penalty": 1.0,
|
| 469 |
+
"return_dict": true,
|
| 470 |
+
"return_dict_in_generate": false,
|
| 471 |
+
"sep_token_id": null,
|
| 472 |
+
"suppress_tokens": null,
|
| 473 |
+
"task_specific_params": null,
|
| 474 |
+
"temperature": 1.0,
|
| 475 |
+
"tf_legacy_loss": false,
|
| 476 |
+
"tie_encoder_decoder": false,
|
| 477 |
+
"tie_word_embeddings": true,
|
| 478 |
+
"tokenizer_class": null,
|
| 479 |
+
"top_k": 50,
|
| 480 |
+
"top_p": 1.0,
|
| 481 |
+
"torch_dtype": "bfloat16",
|
| 482 |
+
"torchscript": false,
|
| 483 |
+
"transformers_version": "4.46.3",
|
| 484 |
+
"typical_p": 1.0,
|
| 485 |
+
"use_bfloat16": true,
|
| 486 |
+
"use_flash_attn": true
|
| 487 |
+
}
|
| 488 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a58dfbe16c7690bae32120e6aeec186f6ee42b55161cb9e091f400b512a8e9b
|
| 3 |
+
size 4992571160
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7feba592ac841cd2ca863b4a1e02f602053b2700b283cfa4824d65f57210021
|
| 3 |
+
size 650642770
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1091 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 5643083810
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"action_adaptor.0.bias": "model-00002-of-00002.safetensors",
|
| 7 |
+
"action_adaptor.0.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"action_adaptor.2.bias": "model-00002-of-00002.safetensors",
|
| 9 |
+
"action_adaptor.2.weight": "model-00002-of-00002.safetensors",
|
| 10 |
+
"action_adaptor.4.bias": "model-00002-of-00002.safetensors",
|
| 11 |
+
"action_adaptor.4.weight": "model-00002-of-00002.safetensors",
|
| 12 |
+
"action_model.layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"action_model.layers.0.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"action_model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"action_model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"action_model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"action_model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"action_model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"action_model.layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"action_model.layers.1.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"action_model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"action_model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"action_model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"action_model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"action_model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"action_model.layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"action_model.layers.10.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"action_model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"action_model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"action_model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"action_model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"action_model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"action_model.layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"action_model.layers.11.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"action_model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"action_model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"action_model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"action_model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"action_model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"action_model.layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"action_model.layers.12.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"action_model.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"action_model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"action_model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"action_model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"action_model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"action_model.layers.13.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"action_model.layers.13.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"action_model.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"action_model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"action_model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"action_model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"action_model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"action_model.layers.14.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"action_model.layers.14.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"action_model.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"action_model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"action_model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"action_model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"action_model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"action_model.layers.15.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"action_model.layers.15.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"action_model.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"action_model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"action_model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"action_model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"action_model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"action_model.layers.16.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"action_model.layers.16.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"action_model.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"action_model.layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"action_model.layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"action_model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"action_model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"action_model.layers.17.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"action_model.layers.17.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"action_model.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"action_model.layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"action_model.layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"action_model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"action_model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"action_model.layers.18.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"action_model.layers.18.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"action_model.layers.18.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 85 |
+
"action_model.layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"action_model.layers.18.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 87 |
+
"action_model.layers.18.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"action_model.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 89 |
+
"action_model.layers.19.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"action_model.layers.19.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 91 |
+
"action_model.layers.19.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"action_model.layers.19.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 93 |
+
"action_model.layers.19.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"action_model.layers.19.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 95 |
+
"action_model.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"action_model.layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"action_model.layers.2.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"action_model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"action_model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"action_model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"action_model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"action_model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"action_model.layers.20.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"action_model.layers.20.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 105 |
+
"action_model.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"action_model.layers.20.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 107 |
+
"action_model.layers.20.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"action_model.layers.20.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"action_model.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"action_model.layers.21.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"action_model.layers.21.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"action_model.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"action_model.layers.21.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"action_model.layers.21.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"action_model.layers.21.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"action_model.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"action_model.layers.22.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"action_model.layers.22.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"action_model.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"action_model.layers.22.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"action_model.layers.22.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"action_model.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"action_model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"action_model.layers.23.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"action_model.layers.23.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"action_model.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"action_model.layers.23.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"action_model.layers.23.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"action_model.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"action_model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"action_model.layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"action_model.layers.3.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"action_model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"action_model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"action_model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"action_model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"action_model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"action_model.layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"action_model.layers.4.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"action_model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"action_model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"action_model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"action_model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"action_model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"action_model.layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"action_model.layers.5.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"action_model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"action_model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"action_model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"action_model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"action_model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"action_model.layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"action_model.layers.6.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"action_model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"action_model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"action_model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"action_model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"action_model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"action_model.layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"action_model.layers.7.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"action_model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"action_model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"action_model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"action_model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"action_model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"action_model.layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"action_model.layers.8.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"action_model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"action_model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"action_model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"action_model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"action_model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"action_model.layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"action_model.layers.9.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"action_model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"action_model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"action_model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"action_model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"action_model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"action_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"final_layer.ffn_final.fc1.bias": "model-00002-of-00002.safetensors",
|
| 182 |
+
"final_layer.ffn_final.fc1.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"final_layer.ffn_final.fc2.bias": "model-00002-of-00002.safetensors",
|
| 184 |
+
"final_layer.ffn_final.fc2.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"final_layer.norm_final.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"freq_embedder.mlp.0.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"freq_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"freq_embedder.mlp.2.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"freq_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"k_proj_layers.0.bias": "model-00002-of-00002.safetensors",
|
| 191 |
+
"k_proj_layers.0.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"k_proj_layers.1.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"k_proj_layers.1.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"k_proj_layers.10.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"k_proj_layers.10.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"k_proj_layers.11.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"k_proj_layers.11.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"k_proj_layers.12.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"k_proj_layers.12.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"k_proj_layers.13.bias": "model-00002-of-00002.safetensors",
|
| 201 |
+
"k_proj_layers.13.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"k_proj_layers.14.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"k_proj_layers.14.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"k_proj_layers.15.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"k_proj_layers.15.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"k_proj_layers.16.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"k_proj_layers.16.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"k_proj_layers.17.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"k_proj_layers.17.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"k_proj_layers.18.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"k_proj_layers.18.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"k_proj_layers.19.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"k_proj_layers.19.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"k_proj_layers.2.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"k_proj_layers.2.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"k_proj_layers.20.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"k_proj_layers.20.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"k_proj_layers.21.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"k_proj_layers.21.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"k_proj_layers.22.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"k_proj_layers.22.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"k_proj_layers.23.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"k_proj_layers.23.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"k_proj_layers.3.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"k_proj_layers.3.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"k_proj_layers.4.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"k_proj_layers.4.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"k_proj_layers.5.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"k_proj_layers.5.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"k_proj_layers.6.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"k_proj_layers.6.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"k_proj_layers.7.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"k_proj_layers.7.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"k_proj_layers.8.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"k_proj_layers.8.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"k_proj_layers.9.bias": "model-00002-of-00002.safetensors",
|
| 237 |
+
"k_proj_layers.9.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"language_model.model.layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"language_model.model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"language_model.model.layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"language_model.model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"language_model.model.layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"language_model.model.layers.10.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"language_model.model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"language_model.model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"language_model.model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"language_model.model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"language_model.model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"language_model.model.layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"language_model.model.layers.11.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"language_model.model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"language_model.model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"language_model.model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"language_model.model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"language_model.model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"language_model.model.layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"language_model.model.layers.12.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"language_model.model.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"language_model.model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"language_model.model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"language_model.model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"language_model.model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"language_model.model.layers.13.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"language_model.model.layers.13.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"language_model.model.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"language_model.model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"language_model.model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"language_model.model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"language_model.model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"language_model.model.layers.14.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"language_model.model.layers.14.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"language_model.model.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"language_model.model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"language_model.model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"language_model.model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"language_model.model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"language_model.model.layers.15.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"language_model.model.layers.15.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"language_model.model.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"language_model.model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"language_model.model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"language_model.model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"language_model.model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"language_model.model.layers.16.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"language_model.model.layers.16.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"language_model.model.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"language_model.model.layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"language_model.model.layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"language_model.model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"language_model.model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"language_model.model.layers.17.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"language_model.model.layers.17.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"language_model.model.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"language_model.model.layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"language_model.model.layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"language_model.model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"language_model.model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"language_model.model.layers.18.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"language_model.model.layers.18.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"language_model.model.layers.18.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"language_model.model.layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"language_model.model.layers.18.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"language_model.model.layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"language_model.model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"language_model.model.layers.19.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"language_model.model.layers.19.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"language_model.model.layers.19.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"language_model.model.layers.19.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"language_model.model.layers.19.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"language_model.model.layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"language_model.model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"language_model.model.layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"language_model.model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"language_model.model.layers.20.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"language_model.model.layers.20.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"language_model.model.layers.20.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"language_model.model.layers.20.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"language_model.model.layers.20.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"language_model.model.layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"language_model.model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"language_model.model.layers.21.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"language_model.model.layers.21.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"language_model.model.layers.21.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"language_model.model.layers.21.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"language_model.model.layers.21.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"language_model.model.layers.21.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"language_model.model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"language_model.model.layers.22.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"language_model.model.layers.22.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"language_model.model.layers.22.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"language_model.model.layers.22.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"language_model.model.layers.22.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"language_model.model.layers.22.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"language_model.model.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"language_model.model.layers.23.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"language_model.model.layers.23.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"language_model.model.layers.23.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"language_model.model.layers.23.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"language_model.model.layers.23.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"language_model.model.layers.23.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"language_model.model.layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"language_model.model.layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"language_model.model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"language_model.model.layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"language_model.model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"language_model.model.layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"language_model.model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"language_model.model.layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"language_model.model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"language_model.model.layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"language_model.model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"language_model.model.layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"language_model.model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"language_model.model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"language_model.model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"language_model.model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"language_model.model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"language_model.model.layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"language_model.model.layers.9.attention.wqkv.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"language_model.model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"language_model.model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"language_model.model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"language_model.model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"language_model.model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"language_model.model.norm.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"language_model.model.tok_embeddings.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"language_model.output.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"latent_planner.latent_action_expert.layers.0.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"latent_planner.latent_action_expert.layers.0.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 411 |
+
"latent_planner.latent_action_expert.layers.0.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"latent_planner.latent_action_expert.layers.0.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 413 |
+
"latent_planner.latent_action_expert.layers.0.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"latent_planner.latent_action_expert.layers.0.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 415 |
+
"latent_planner.latent_action_expert.layers.0.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"latent_planner.latent_action_expert.layers.1.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 417 |
+
"latent_planner.latent_action_expert.layers.1.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"latent_planner.latent_action_expert.layers.1.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 419 |
+
"latent_planner.latent_action_expert.layers.1.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"latent_planner.latent_action_expert.layers.1.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 421 |
+
"latent_planner.latent_action_expert.layers.1.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"latent_planner.latent_action_expert.layers.1.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 423 |
+
"latent_planner.latent_action_expert.layers.10.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"latent_planner.latent_action_expert.layers.10.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 425 |
+
"latent_planner.latent_action_expert.layers.10.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"latent_planner.latent_action_expert.layers.10.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 427 |
+
"latent_planner.latent_action_expert.layers.10.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"latent_planner.latent_action_expert.layers.10.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 429 |
+
"latent_planner.latent_action_expert.layers.10.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"latent_planner.latent_action_expert.layers.11.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"latent_planner.latent_action_expert.layers.11.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"latent_planner.latent_action_expert.layers.11.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 433 |
+
"latent_planner.latent_action_expert.layers.11.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"latent_planner.latent_action_expert.layers.11.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 435 |
+
"latent_planner.latent_action_expert.layers.11.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"latent_planner.latent_action_expert.layers.11.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"latent_planner.latent_action_expert.layers.12.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"latent_planner.latent_action_expert.layers.12.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"latent_planner.latent_action_expert.layers.12.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"latent_planner.latent_action_expert.layers.12.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"latent_planner.latent_action_expert.layers.12.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"latent_planner.latent_action_expert.layers.12.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 443 |
+
"latent_planner.latent_action_expert.layers.12.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"latent_planner.latent_action_expert.layers.13.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 445 |
+
"latent_planner.latent_action_expert.layers.13.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"latent_planner.latent_action_expert.layers.13.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 447 |
+
"latent_planner.latent_action_expert.layers.13.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"latent_planner.latent_action_expert.layers.13.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"latent_planner.latent_action_expert.layers.13.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"latent_planner.latent_action_expert.layers.13.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"latent_planner.latent_action_expert.layers.14.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"latent_planner.latent_action_expert.layers.14.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"latent_planner.latent_action_expert.layers.14.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"latent_planner.latent_action_expert.layers.14.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"latent_planner.latent_action_expert.layers.14.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"latent_planner.latent_action_expert.layers.14.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"latent_planner.latent_action_expert.layers.14.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"latent_planner.latent_action_expert.layers.15.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"latent_planner.latent_action_expert.layers.15.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"latent_planner.latent_action_expert.layers.15.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"latent_planner.latent_action_expert.layers.15.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"latent_planner.latent_action_expert.layers.15.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"latent_planner.latent_action_expert.layers.15.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"latent_planner.latent_action_expert.layers.15.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"latent_planner.latent_action_expert.layers.16.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"latent_planner.latent_action_expert.layers.16.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 467 |
+
"latent_planner.latent_action_expert.layers.16.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"latent_planner.latent_action_expert.layers.16.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"latent_planner.latent_action_expert.layers.16.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"latent_planner.latent_action_expert.layers.16.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"latent_planner.latent_action_expert.layers.16.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"latent_planner.latent_action_expert.layers.17.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 473 |
+
"latent_planner.latent_action_expert.layers.17.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"latent_planner.latent_action_expert.layers.17.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 475 |
+
"latent_planner.latent_action_expert.layers.17.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"latent_planner.latent_action_expert.layers.17.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"latent_planner.latent_action_expert.layers.17.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"latent_planner.latent_action_expert.layers.17.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"latent_planner.latent_action_expert.layers.18.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"latent_planner.latent_action_expert.layers.18.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"latent_planner.latent_action_expert.layers.18.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"latent_planner.latent_action_expert.layers.18.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"latent_planner.latent_action_expert.layers.18.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"latent_planner.latent_action_expert.layers.18.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 485 |
+
"latent_planner.latent_action_expert.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"latent_planner.latent_action_expert.layers.19.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"latent_planner.latent_action_expert.layers.19.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"latent_planner.latent_action_expert.layers.19.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"latent_planner.latent_action_expert.layers.19.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"latent_planner.latent_action_expert.layers.19.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"latent_planner.latent_action_expert.layers.19.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"latent_planner.latent_action_expert.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"latent_planner.latent_action_expert.layers.2.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"latent_planner.latent_action_expert.layers.2.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"latent_planner.latent_action_expert.layers.2.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"latent_planner.latent_action_expert.layers.2.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"latent_planner.latent_action_expert.layers.2.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"latent_planner.latent_action_expert.layers.2.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"latent_planner.latent_action_expert.layers.2.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"latent_planner.latent_action_expert.layers.20.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"latent_planner.latent_action_expert.layers.20.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"latent_planner.latent_action_expert.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 503 |
+
"latent_planner.latent_action_expert.layers.20.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"latent_planner.latent_action_expert.layers.20.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"latent_planner.latent_action_expert.layers.20.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"latent_planner.latent_action_expert.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"latent_planner.latent_action_expert.layers.21.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"latent_planner.latent_action_expert.layers.21.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"latent_planner.latent_action_expert.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"latent_planner.latent_action_expert.layers.21.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"latent_planner.latent_action_expert.layers.21.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"latent_planner.latent_action_expert.layers.21.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"latent_planner.latent_action_expert.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"latent_planner.latent_action_expert.layers.22.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"latent_planner.latent_action_expert.layers.22.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"latent_planner.latent_action_expert.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"latent_planner.latent_action_expert.layers.22.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"latent_planner.latent_action_expert.layers.22.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"latent_planner.latent_action_expert.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"latent_planner.latent_action_expert.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"latent_planner.latent_action_expert.layers.23.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"latent_planner.latent_action_expert.layers.23.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 523 |
+
"latent_planner.latent_action_expert.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"latent_planner.latent_action_expert.layers.23.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"latent_planner.latent_action_expert.layers.23.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"latent_planner.latent_action_expert.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 527 |
+
"latent_planner.latent_action_expert.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"latent_planner.latent_action_expert.layers.3.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 529 |
+
"latent_planner.latent_action_expert.layers.3.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"latent_planner.latent_action_expert.layers.3.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"latent_planner.latent_action_expert.layers.3.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"latent_planner.latent_action_expert.layers.3.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"latent_planner.latent_action_expert.layers.3.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"latent_planner.latent_action_expert.layers.3.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"latent_planner.latent_action_expert.layers.4.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"latent_planner.latent_action_expert.layers.4.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"latent_planner.latent_action_expert.layers.4.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"latent_planner.latent_action_expert.layers.4.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"latent_planner.latent_action_expert.layers.4.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"latent_planner.latent_action_expert.layers.4.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"latent_planner.latent_action_expert.layers.4.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"latent_planner.latent_action_expert.layers.5.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"latent_planner.latent_action_expert.layers.5.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"latent_planner.latent_action_expert.layers.5.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"latent_planner.latent_action_expert.layers.5.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"latent_planner.latent_action_expert.layers.5.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 547 |
+
"latent_planner.latent_action_expert.layers.5.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"latent_planner.latent_action_expert.layers.5.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"latent_planner.latent_action_expert.layers.6.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"latent_planner.latent_action_expert.layers.6.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"latent_planner.latent_action_expert.layers.6.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"latent_planner.latent_action_expert.layers.6.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"latent_planner.latent_action_expert.layers.6.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"latent_planner.latent_action_expert.layers.6.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"latent_planner.latent_action_expert.layers.6.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"latent_planner.latent_action_expert.layers.7.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"latent_planner.latent_action_expert.layers.7.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"latent_planner.latent_action_expert.layers.7.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"latent_planner.latent_action_expert.layers.7.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"latent_planner.latent_action_expert.layers.7.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"latent_planner.latent_action_expert.layers.7.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"latent_planner.latent_action_expert.layers.7.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 563 |
+
"latent_planner.latent_action_expert.layers.8.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"latent_planner.latent_action_expert.layers.8.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"latent_planner.latent_action_expert.layers.8.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"latent_planner.latent_action_expert.layers.8.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"latent_planner.latent_action_expert.layers.8.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"latent_planner.latent_action_expert.layers.8.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"latent_planner.latent_action_expert.layers.8.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"latent_planner.latent_action_expert.layers.9.attention.wo.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"latent_planner.latent_action_expert.layers.9.attention.wqkv.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"latent_planner.latent_action_expert.layers.9.attention_norm.weight": "model-00002-of-00002.safetensors",
|
| 573 |
+
"latent_planner.latent_action_expert.layers.9.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"latent_planner.latent_action_expert.layers.9.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"latent_planner.latent_action_expert.layers.9.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"latent_planner.latent_action_expert.layers.9.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"latent_planner.latent_action_expert.norm.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"latent_planner.latent_final_layer.ffn_final.fc1.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"latent_planner.latent_final_layer.ffn_final.fc1.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"latent_planner.latent_final_layer.ffn_final.fc2.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"latent_planner.latent_final_layer.ffn_final.fc2.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"latent_planner.latent_final_layer.norm_final.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"latent_planner.latent_k_proj_layers.0.bias": "model-00002-of-00002.safetensors",
|
| 584 |
+
"latent_planner.latent_k_proj_layers.0.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"latent_planner.latent_k_proj_layers.1.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"latent_planner.latent_k_proj_layers.1.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"latent_planner.latent_k_proj_layers.10.bias": "model-00002-of-00002.safetensors",
|
| 588 |
+
"latent_planner.latent_k_proj_layers.10.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"latent_planner.latent_k_proj_layers.11.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"latent_planner.latent_k_proj_layers.11.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"latent_planner.latent_k_proj_layers.12.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"latent_planner.latent_k_proj_layers.12.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"latent_planner.latent_k_proj_layers.13.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"latent_planner.latent_k_proj_layers.13.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"latent_planner.latent_k_proj_layers.14.bias": "model-00002-of-00002.safetensors",
|
| 596 |
+
"latent_planner.latent_k_proj_layers.14.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"latent_planner.latent_k_proj_layers.15.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"latent_planner.latent_k_proj_layers.15.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"latent_planner.latent_k_proj_layers.16.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"latent_planner.latent_k_proj_layers.16.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"latent_planner.latent_k_proj_layers.17.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"latent_planner.latent_k_proj_layers.17.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"latent_planner.latent_k_proj_layers.18.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"latent_planner.latent_k_proj_layers.18.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"latent_planner.latent_k_proj_layers.19.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"latent_planner.latent_k_proj_layers.19.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"latent_planner.latent_k_proj_layers.2.bias": "model-00002-of-00002.safetensors",
|
| 608 |
+
"latent_planner.latent_k_proj_layers.2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"latent_planner.latent_k_proj_layers.20.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"latent_planner.latent_k_proj_layers.20.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"latent_planner.latent_k_proj_layers.21.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"latent_planner.latent_k_proj_layers.21.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"latent_planner.latent_k_proj_layers.22.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"latent_planner.latent_k_proj_layers.22.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"latent_planner.latent_k_proj_layers.23.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"latent_planner.latent_k_proj_layers.23.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"latent_planner.latent_k_proj_layers.3.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"latent_planner.latent_k_proj_layers.3.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"latent_planner.latent_k_proj_layers.4.bias": "model-00002-of-00002.safetensors",
|
| 620 |
+
"latent_planner.latent_k_proj_layers.4.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"latent_planner.latent_k_proj_layers.5.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"latent_planner.latent_k_proj_layers.5.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"latent_planner.latent_k_proj_layers.6.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"latent_planner.latent_k_proj_layers.6.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"latent_planner.latent_k_proj_layers.7.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"latent_planner.latent_k_proj_layers.7.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"latent_planner.latent_k_proj_layers.8.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"latent_planner.latent_k_proj_layers.8.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"latent_planner.latent_k_proj_layers.9.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"latent_planner.latent_k_proj_layers.9.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"latent_planner.latent_state_action_adaptor.0.bias": "model-00002-of-00002.safetensors",
|
| 632 |
+
"latent_planner.latent_state_action_adaptor.0.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"latent_planner.latent_state_action_adaptor.2.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"latent_planner.latent_state_action_adaptor.2.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"latent_planner.latent_state_action_adaptor.4.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"latent_planner.latent_state_action_adaptor.4.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"latent_planner.latent_v_proj_layers.0.bias": "model-00002-of-00002.safetensors",
|
| 638 |
+
"latent_planner.latent_v_proj_layers.0.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"latent_planner.latent_v_proj_layers.1.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"latent_planner.latent_v_proj_layers.1.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"latent_planner.latent_v_proj_layers.10.bias": "model-00002-of-00002.safetensors",
|
| 642 |
+
"latent_planner.latent_v_proj_layers.10.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"latent_planner.latent_v_proj_layers.11.bias": "model-00002-of-00002.safetensors",
|
| 644 |
+
"latent_planner.latent_v_proj_layers.11.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"latent_planner.latent_v_proj_layers.12.bias": "model-00002-of-00002.safetensors",
|
| 646 |
+
"latent_planner.latent_v_proj_layers.12.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"latent_planner.latent_v_proj_layers.13.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"latent_planner.latent_v_proj_layers.13.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"latent_planner.latent_v_proj_layers.14.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"latent_planner.latent_v_proj_layers.14.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"latent_planner.latent_v_proj_layers.15.bias": "model-00002-of-00002.safetensors",
|
| 652 |
+
"latent_planner.latent_v_proj_layers.15.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"latent_planner.latent_v_proj_layers.16.bias": "model-00002-of-00002.safetensors",
|
| 654 |
+
"latent_planner.latent_v_proj_layers.16.weight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"latent_planner.latent_v_proj_layers.17.bias": "model-00002-of-00002.safetensors",
|
| 656 |
+
"latent_planner.latent_v_proj_layers.17.weight": "model-00002-of-00002.safetensors",
|
| 657 |
+
"latent_planner.latent_v_proj_layers.18.bias": "model-00002-of-00002.safetensors",
|
| 658 |
+
"latent_planner.latent_v_proj_layers.18.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"latent_planner.latent_v_proj_layers.19.bias": "model-00002-of-00002.safetensors",
|
| 660 |
+
"latent_planner.latent_v_proj_layers.19.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"latent_planner.latent_v_proj_layers.2.bias": "model-00002-of-00002.safetensors",
|
| 662 |
+
"latent_planner.latent_v_proj_layers.2.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"latent_planner.latent_v_proj_layers.20.bias": "model-00002-of-00002.safetensors",
|
| 664 |
+
"latent_planner.latent_v_proj_layers.20.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"latent_planner.latent_v_proj_layers.21.bias": "model-00002-of-00002.safetensors",
|
| 666 |
+
"latent_planner.latent_v_proj_layers.21.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"latent_planner.latent_v_proj_layers.22.bias": "model-00002-of-00002.safetensors",
|
| 668 |
+
"latent_planner.latent_v_proj_layers.22.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"latent_planner.latent_v_proj_layers.23.bias": "model-00002-of-00002.safetensors",
|
| 670 |
+
"latent_planner.latent_v_proj_layers.23.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"latent_planner.latent_v_proj_layers.3.bias": "model-00002-of-00002.safetensors",
|
| 672 |
+
"latent_planner.latent_v_proj_layers.3.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"latent_planner.latent_v_proj_layers.4.bias": "model-00002-of-00002.safetensors",
|
| 674 |
+
"latent_planner.latent_v_proj_layers.4.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"latent_planner.latent_v_proj_layers.5.bias": "model-00002-of-00002.safetensors",
|
| 676 |
+
"latent_planner.latent_v_proj_layers.5.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"latent_planner.latent_v_proj_layers.6.bias": "model-00002-of-00002.safetensors",
|
| 678 |
+
"latent_planner.latent_v_proj_layers.6.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"latent_planner.latent_v_proj_layers.7.bias": "model-00002-of-00002.safetensors",
|
| 680 |
+
"latent_planner.latent_v_proj_layers.7.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"latent_planner.latent_v_proj_layers.8.bias": "model-00002-of-00002.safetensors",
|
| 682 |
+
"latent_planner.latent_v_proj_layers.8.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"latent_planner.latent_v_proj_layers.9.bias": "model-00002-of-00002.safetensors",
|
| 684 |
+
"latent_planner.latent_v_proj_layers.9.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"latent_planner.score.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"mlp1.0.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"mlp1.0.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"mlp1.1.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"mlp1.1.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"mlp1.3.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"mlp1.3.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"state_adaptor.0.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"state_adaptor.0.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"state_adaptor.2.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"state_adaptor.2.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"state_adaptor.4.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"state_adaptor.4.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"time_embedder.mlp.0.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"time_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"time_embedder.mlp.2.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"time_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"v_proj_layers.0.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"v_proj_layers.0.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"v_proj_layers.1.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"v_proj_layers.1.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"v_proj_layers.10.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"v_proj_layers.10.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"v_proj_layers.11.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"v_proj_layers.11.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"v_proj_layers.12.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"v_proj_layers.12.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"v_proj_layers.13.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"v_proj_layers.13.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"v_proj_layers.14.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"v_proj_layers.14.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"v_proj_layers.15.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"v_proj_layers.15.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"v_proj_layers.16.bias": "model-00002-of-00002.safetensors",
|
| 719 |
+
"v_proj_layers.16.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"v_proj_layers.17.bias": "model-00002-of-00002.safetensors",
|
| 721 |
+
"v_proj_layers.17.weight": "model-00002-of-00002.safetensors",
|
| 722 |
+
"v_proj_layers.18.bias": "model-00002-of-00002.safetensors",
|
| 723 |
+
"v_proj_layers.18.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"v_proj_layers.19.bias": "model-00002-of-00002.safetensors",
|
| 725 |
+
"v_proj_layers.19.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"v_proj_layers.2.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"v_proj_layers.2.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"v_proj_layers.20.bias": "model-00002-of-00002.safetensors",
|
| 729 |
+
"v_proj_layers.20.weight": "model-00002-of-00002.safetensors",
|
| 730 |
+
"v_proj_layers.21.bias": "model-00002-of-00002.safetensors",
|
| 731 |
+
"v_proj_layers.21.weight": "model-00002-of-00002.safetensors",
|
| 732 |
+
"v_proj_layers.22.bias": "model-00002-of-00002.safetensors",
|
| 733 |
+
"v_proj_layers.22.weight": "model-00002-of-00002.safetensors",
|
| 734 |
+
"v_proj_layers.23.bias": "model-00002-of-00002.safetensors",
|
| 735 |
+
"v_proj_layers.23.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"v_proj_layers.3.bias": "model-00002-of-00002.safetensors",
|
| 737 |
+
"v_proj_layers.3.weight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"v_proj_layers.4.bias": "model-00002-of-00002.safetensors",
|
| 739 |
+
"v_proj_layers.4.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"v_proj_layers.5.bias": "model-00002-of-00002.safetensors",
|
| 741 |
+
"v_proj_layers.5.weight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"v_proj_layers.6.bias": "model-00002-of-00002.safetensors",
|
| 743 |
+
"v_proj_layers.6.weight": "model-00002-of-00002.safetensors",
|
| 744 |
+
"v_proj_layers.7.bias": "model-00002-of-00002.safetensors",
|
| 745 |
+
"v_proj_layers.7.weight": "model-00002-of-00002.safetensors",
|
| 746 |
+
"v_proj_layers.8.bias": "model-00002-of-00002.safetensors",
|
| 747 |
+
"v_proj_layers.8.weight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"v_proj_layers.9.bias": "model-00002-of-00002.safetensors",
|
| 749 |
+
"v_proj_layers.9.weight": "model-00002-of-00002.safetensors",
|
| 750 |
+
"vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
|
| 751 |
+
"vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
| 752 |
+
"vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 753 |
+
"vision_model.embeddings.position_embedding": "model-00001-of-00002.safetensors",
|
| 754 |
+
"vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"vision_model.encoder.layers.0.ls1": "model-00001-of-00002.safetensors",
|
| 759 |
+
"vision_model.encoder.layers.0.ls2": "model-00001-of-00002.safetensors",
|
| 760 |
+
"vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 763 |
+
"vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"vision_model.encoder.layers.1.ls1": "model-00001-of-00002.safetensors",
|
| 773 |
+
"vision_model.encoder.layers.1.ls2": "model-00001-of-00002.safetensors",
|
| 774 |
+
"vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 775 |
+
"vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"vision_model.encoder.layers.10.ls1": "model-00001-of-00002.safetensors",
|
| 787 |
+
"vision_model.encoder.layers.10.ls2": "model-00001-of-00002.safetensors",
|
| 788 |
+
"vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"vision_model.encoder.layers.11.ls1": "model-00001-of-00002.safetensors",
|
| 801 |
+
"vision_model.encoder.layers.11.ls2": "model-00001-of-00002.safetensors",
|
| 802 |
+
"vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 808 |
+
"vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 809 |
+
"vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 810 |
+
"vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 811 |
+
"vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 813 |
+
"vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 814 |
+
"vision_model.encoder.layers.12.ls1": "model-00001-of-00002.safetensors",
|
| 815 |
+
"vision_model.encoder.layers.12.ls2": "model-00001-of-00002.safetensors",
|
| 816 |
+
"vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 817 |
+
"vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 818 |
+
"vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 819 |
+
"vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 820 |
+
"vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 821 |
+
"vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 822 |
+
"vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 823 |
+
"vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 825 |
+
"vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 826 |
+
"vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 827 |
+
"vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 828 |
+
"vision_model.encoder.layers.13.ls1": "model-00001-of-00002.safetensors",
|
| 829 |
+
"vision_model.encoder.layers.13.ls2": "model-00001-of-00002.safetensors",
|
| 830 |
+
"vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 831 |
+
"vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 832 |
+
"vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 833 |
+
"vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 834 |
+
"vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 835 |
+
"vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 836 |
+
"vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 837 |
+
"vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 838 |
+
"vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 839 |
+
"vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 840 |
+
"vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 841 |
+
"vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 842 |
+
"vision_model.encoder.layers.14.ls1": "model-00001-of-00002.safetensors",
|
| 843 |
+
"vision_model.encoder.layers.14.ls2": "model-00001-of-00002.safetensors",
|
| 844 |
+
"vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 845 |
+
"vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 846 |
+
"vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 847 |
+
"vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 848 |
+
"vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 849 |
+
"vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 850 |
+
"vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 851 |
+
"vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 852 |
+
"vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 853 |
+
"vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 854 |
+
"vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 855 |
+
"vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 856 |
+
"vision_model.encoder.layers.15.ls1": "model-00001-of-00002.safetensors",
|
| 857 |
+
"vision_model.encoder.layers.15.ls2": "model-00001-of-00002.safetensors",
|
| 858 |
+
"vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 859 |
+
"vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 860 |
+
"vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 861 |
+
"vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 862 |
+
"vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 863 |
+
"vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 864 |
+
"vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 865 |
+
"vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 866 |
+
"vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 867 |
+
"vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 868 |
+
"vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 869 |
+
"vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 870 |
+
"vision_model.encoder.layers.16.ls1": "model-00001-of-00002.safetensors",
|
| 871 |
+
"vision_model.encoder.layers.16.ls2": "model-00001-of-00002.safetensors",
|
| 872 |
+
"vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 873 |
+
"vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 874 |
+
"vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 875 |
+
"vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 876 |
+
"vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 877 |
+
"vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 878 |
+
"vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 879 |
+
"vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 880 |
+
"vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 881 |
+
"vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 882 |
+
"vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 883 |
+
"vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 884 |
+
"vision_model.encoder.layers.17.ls1": "model-00001-of-00002.safetensors",
|
| 885 |
+
"vision_model.encoder.layers.17.ls2": "model-00001-of-00002.safetensors",
|
| 886 |
+
"vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 887 |
+
"vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 888 |
+
"vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 889 |
+
"vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 890 |
+
"vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 891 |
+
"vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 892 |
+
"vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 893 |
+
"vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 894 |
+
"vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 895 |
+
"vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 896 |
+
"vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 897 |
+
"vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 898 |
+
"vision_model.encoder.layers.18.ls1": "model-00001-of-00002.safetensors",
|
| 899 |
+
"vision_model.encoder.layers.18.ls2": "model-00001-of-00002.safetensors",
|
| 900 |
+
"vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 901 |
+
"vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 902 |
+
"vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 903 |
+
"vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 904 |
+
"vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 905 |
+
"vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 906 |
+
"vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 907 |
+
"vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 908 |
+
"vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 909 |
+
"vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 910 |
+
"vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 911 |
+
"vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 912 |
+
"vision_model.encoder.layers.19.ls1": "model-00001-of-00002.safetensors",
|
| 913 |
+
"vision_model.encoder.layers.19.ls2": "model-00001-of-00002.safetensors",
|
| 914 |
+
"vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 915 |
+
"vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 916 |
+
"vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 917 |
+
"vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 918 |
+
"vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 919 |
+
"vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 920 |
+
"vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 921 |
+
"vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 922 |
+
"vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 923 |
+
"vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 924 |
+
"vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 925 |
+
"vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 926 |
+
"vision_model.encoder.layers.2.ls1": "model-00001-of-00002.safetensors",
|
| 927 |
+
"vision_model.encoder.layers.2.ls2": "model-00001-of-00002.safetensors",
|
| 928 |
+
"vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 929 |
+
"vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 930 |
+
"vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 931 |
+
"vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 932 |
+
"vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 933 |
+
"vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 934 |
+
"vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 935 |
+
"vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 936 |
+
"vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 937 |
+
"vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 938 |
+
"vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 939 |
+
"vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 940 |
+
"vision_model.encoder.layers.20.ls1": "model-00001-of-00002.safetensors",
|
| 941 |
+
"vision_model.encoder.layers.20.ls2": "model-00001-of-00002.safetensors",
|
| 942 |
+
"vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 943 |
+
"vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 944 |
+
"vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 945 |
+
"vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 946 |
+
"vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 947 |
+
"vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 948 |
+
"vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 949 |
+
"vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 950 |
+
"vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 951 |
+
"vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 952 |
+
"vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 953 |
+
"vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 954 |
+
"vision_model.encoder.layers.21.ls1": "model-00001-of-00002.safetensors",
|
| 955 |
+
"vision_model.encoder.layers.21.ls2": "model-00001-of-00002.safetensors",
|
| 956 |
+
"vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 957 |
+
"vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 958 |
+
"vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 959 |
+
"vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 960 |
+
"vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 961 |
+
"vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 962 |
+
"vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 963 |
+
"vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 964 |
+
"vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 965 |
+
"vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 966 |
+
"vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 967 |
+
"vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 968 |
+
"vision_model.encoder.layers.22.ls1": "model-00001-of-00002.safetensors",
|
| 969 |
+
"vision_model.encoder.layers.22.ls2": "model-00001-of-00002.safetensors",
|
| 970 |
+
"vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 971 |
+
"vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 972 |
+
"vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 973 |
+
"vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 974 |
+
"vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 975 |
+
"vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 976 |
+
"vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 977 |
+
"vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 978 |
+
"vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 979 |
+
"vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 980 |
+
"vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 981 |
+
"vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 982 |
+
"vision_model.encoder.layers.23.ls1": "model-00001-of-00002.safetensors",
|
| 983 |
+
"vision_model.encoder.layers.23.ls2": "model-00001-of-00002.safetensors",
|
| 984 |
+
"vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 985 |
+
"vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 986 |
+
"vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 987 |
+
"vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 988 |
+
"vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 989 |
+
"vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 990 |
+
"vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 991 |
+
"vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 992 |
+
"vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 993 |
+
"vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 994 |
+
"vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 995 |
+
"vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 996 |
+
"vision_model.encoder.layers.3.ls1": "model-00001-of-00002.safetensors",
|
| 997 |
+
"vision_model.encoder.layers.3.ls2": "model-00001-of-00002.safetensors",
|
| 998 |
+
"vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 999 |
+
"vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1000 |
+
"vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1001 |
+
"vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1002 |
+
"vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 1003 |
+
"vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 1004 |
+
"vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 1005 |
+
"vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 1006 |
+
"vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 1007 |
+
"vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 1008 |
+
"vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 1009 |
+
"vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 1010 |
+
"vision_model.encoder.layers.4.ls1": "model-00001-of-00002.safetensors",
|
| 1011 |
+
"vision_model.encoder.layers.4.ls2": "model-00001-of-00002.safetensors",
|
| 1012 |
+
"vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1013 |
+
"vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1014 |
+
"vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1015 |
+
"vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1016 |
+
"vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 1017 |
+
"vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 1018 |
+
"vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 1019 |
+
"vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 1020 |
+
"vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 1021 |
+
"vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 1022 |
+
"vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 1023 |
+
"vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 1024 |
+
"vision_model.encoder.layers.5.ls1": "model-00001-of-00002.safetensors",
|
| 1025 |
+
"vision_model.encoder.layers.5.ls2": "model-00001-of-00002.safetensors",
|
| 1026 |
+
"vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1027 |
+
"vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1028 |
+
"vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1029 |
+
"vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1030 |
+
"vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 1031 |
+
"vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 1032 |
+
"vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 1033 |
+
"vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 1034 |
+
"vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 1035 |
+
"vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 1036 |
+
"vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 1037 |
+
"vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 1038 |
+
"vision_model.encoder.layers.6.ls1": "model-00001-of-00002.safetensors",
|
| 1039 |
+
"vision_model.encoder.layers.6.ls2": "model-00001-of-00002.safetensors",
|
| 1040 |
+
"vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1041 |
+
"vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1042 |
+
"vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1043 |
+
"vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1044 |
+
"vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 1045 |
+
"vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 1046 |
+
"vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 1047 |
+
"vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 1048 |
+
"vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 1049 |
+
"vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 1050 |
+
"vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 1051 |
+
"vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 1052 |
+
"vision_model.encoder.layers.7.ls1": "model-00001-of-00002.safetensors",
|
| 1053 |
+
"vision_model.encoder.layers.7.ls2": "model-00001-of-00002.safetensors",
|
| 1054 |
+
"vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1055 |
+
"vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1056 |
+
"vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1057 |
+
"vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1058 |
+
"vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 1059 |
+
"vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 1060 |
+
"vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 1061 |
+
"vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 1062 |
+
"vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 1063 |
+
"vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 1064 |
+
"vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 1065 |
+
"vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 1066 |
+
"vision_model.encoder.layers.8.ls1": "model-00001-of-00002.safetensors",
|
| 1067 |
+
"vision_model.encoder.layers.8.ls2": "model-00001-of-00002.safetensors",
|
| 1068 |
+
"vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1069 |
+
"vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1070 |
+
"vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1071 |
+
"vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1072 |
+
"vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 1073 |
+
"vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 1074 |
+
"vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 1075 |
+
"vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 1076 |
+
"vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 1077 |
+
"vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 1078 |
+
"vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 1079 |
+
"vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 1080 |
+
"vision_model.encoder.layers.9.ls1": "model-00001-of-00002.safetensors",
|
| 1081 |
+
"vision_model.encoder.layers.9.ls2": "model-00001-of-00002.safetensors",
|
| 1082 |
+
"vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 1083 |
+
"vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 1084 |
+
"vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 1085 |
+
"vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 1086 |
+
"vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 1087 |
+
"vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 1088 |
+
"vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 1089 |
+
"vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00002.safetensors"
|
| 1090 |
+
}
|
| 1091 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|action_start|>",
|
| 6 |
+
"<|action_end|>",
|
| 7 |
+
"<|interpreter|>",
|
| 8 |
+
"<|plugin|>",
|
| 9 |
+
"<img>",
|
| 10 |
+
"</img>",
|
| 11 |
+
"<IMG_CONTEXT>",
|
| 12 |
+
"<quad>",
|
| 13 |
+
"</quad>",
|
| 14 |
+
"<ref>",
|
| 15 |
+
"</ref>",
|
| 16 |
+
"<box>",
|
| 17 |
+
"</box>"
|
| 18 |
+
],
|
| 19 |
+
"bos_token": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "</s>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "</s>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
},
|
| 40 |
+
"unk_token": {
|
| 41 |
+
"content": "<unk>",
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"normalized": false,
|
| 44 |
+
"rstrip": false,
|
| 45 |
+
"single_word": false
|
| 46 |
+
}
|
| 47 |
+
}
|
tokenization_internlm2.py
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
|
| 2 |
+
#
|
| 3 |
+
# This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
|
| 4 |
+
#
|
| 5 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 6 |
+
# you may not use this file except in compliance with the License.
|
| 7 |
+
# You may obtain a copy of the License at
|
| 8 |
+
#
|
| 9 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 10 |
+
#
|
| 11 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 12 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 13 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 14 |
+
# See the License for the specific language governing permissions and
|
| 15 |
+
# limitations under the License.
|
| 16 |
+
|
| 17 |
+
"""Tokenization classes for InternLM."""
|
| 18 |
+
import os
|
| 19 |
+
from shutil import copyfile
|
| 20 |
+
from typing import Any, Dict, List, Optional, Tuple
|
| 21 |
+
|
| 22 |
+
import sentencepiece as spm
|
| 23 |
+
from transformers.tokenization_utils import PreTrainedTokenizer
|
| 24 |
+
from transformers.utils import logging
|
| 25 |
+
|
| 26 |
+
logger = logging.get_logger(__name__)
|
| 27 |
+
|
| 28 |
+
VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
|
| 29 |
+
|
| 30 |
+
PRETRAINED_VOCAB_FILES_MAP = {}
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
# Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
|
| 34 |
+
class InternLM2Tokenizer(PreTrainedTokenizer):
|
| 35 |
+
"""
|
| 36 |
+
Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
|
| 37 |
+
|
| 38 |
+
Args:
|
| 39 |
+
vocab_file (`str`):
|
| 40 |
+
Path to the vocabulary file.
|
| 41 |
+
"""
|
| 42 |
+
|
| 43 |
+
vocab_files_names = VOCAB_FILES_NAMES
|
| 44 |
+
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
|
| 45 |
+
model_input_names = ['input_ids', 'attention_mask']
|
| 46 |
+
_auto_class = 'AutoTokenizer'
|
| 47 |
+
|
| 48 |
+
def __init__(
|
| 49 |
+
self,
|
| 50 |
+
vocab_file,
|
| 51 |
+
unk_token='<unk>',
|
| 52 |
+
bos_token='<s>',
|
| 53 |
+
eos_token='</s>',
|
| 54 |
+
pad_token='</s>',
|
| 55 |
+
sp_model_kwargs: Optional[Dict[str, Any]] = None,
|
| 56 |
+
add_bos_token=True,
|
| 57 |
+
add_eos_token=False,
|
| 58 |
+
decode_with_prefix_space=False,
|
| 59 |
+
clean_up_tokenization_spaces=False,
|
| 60 |
+
**kwargs,
|
| 61 |
+
):
|
| 62 |
+
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
|
| 63 |
+
self.vocab_file = vocab_file
|
| 64 |
+
self.add_bos_token = add_bos_token
|
| 65 |
+
self.add_eos_token = add_eos_token
|
| 66 |
+
self.decode_with_prefix_space = decode_with_prefix_space
|
| 67 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
| 68 |
+
self.sp_model.Load(vocab_file)
|
| 69 |
+
self._no_prefix_space_tokens = None
|
| 70 |
+
super().__init__(
|
| 71 |
+
bos_token=bos_token,
|
| 72 |
+
eos_token=eos_token,
|
| 73 |
+
unk_token=unk_token,
|
| 74 |
+
pad_token=pad_token,
|
| 75 |
+
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
| 76 |
+
**kwargs,
|
| 77 |
+
)
|
| 78 |
+
|
| 79 |
+
@property
|
| 80 |
+
def no_prefix_space_tokens(self):
|
| 81 |
+
if self._no_prefix_space_tokens is None:
|
| 82 |
+
vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
|
| 83 |
+
self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
|
| 84 |
+
return self._no_prefix_space_tokens
|
| 85 |
+
|
| 86 |
+
@property
|
| 87 |
+
def vocab_size(self):
|
| 88 |
+
"""Returns vocab size"""
|
| 89 |
+
return self.sp_model.get_piece_size()
|
| 90 |
+
|
| 91 |
+
@property
|
| 92 |
+
def bos_token_id(self) -> Optional[int]:
|
| 93 |
+
return self.sp_model.bos_id()
|
| 94 |
+
|
| 95 |
+
@property
|
| 96 |
+
def eos_token_id(self) -> Optional[int]:
|
| 97 |
+
return self.sp_model.eos_id()
|
| 98 |
+
|
| 99 |
+
def get_vocab(self):
|
| 100 |
+
"""Returns vocab as a dict"""
|
| 101 |
+
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
| 102 |
+
vocab.update(self.added_tokens_encoder)
|
| 103 |
+
return vocab
|
| 104 |
+
|
| 105 |
+
def _tokenize(self, text):
|
| 106 |
+
"""Returns a tokenized string."""
|
| 107 |
+
return self.sp_model.encode(text, out_type=str)
|
| 108 |
+
|
| 109 |
+
def _convert_token_to_id(self, token):
|
| 110 |
+
"""Converts a token (str) in an id using the vocab."""
|
| 111 |
+
return self.sp_model.piece_to_id(token)
|
| 112 |
+
|
| 113 |
+
def _convert_id_to_token(self, index):
|
| 114 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
| 115 |
+
token = self.sp_model.IdToPiece(index)
|
| 116 |
+
return token
|
| 117 |
+
|
| 118 |
+
def _maybe_add_prefix_space(self, tokens, decoded):
|
| 119 |
+
if tokens and tokens[0] not in self.no_prefix_space_tokens:
|
| 120 |
+
return ' ' + decoded
|
| 121 |
+
else:
|
| 122 |
+
return decoded
|
| 123 |
+
|
| 124 |
+
def convert_tokens_to_string(self, tokens):
|
| 125 |
+
"""Converts a sequence of tokens (string) in a single string."""
|
| 126 |
+
current_sub_tokens = []
|
| 127 |
+
out_string = ''
|
| 128 |
+
prev_is_special = False
|
| 129 |
+
for token in tokens:
|
| 130 |
+
# make sure that special tokens are not decoded using sentencepiece model
|
| 131 |
+
if token in self.all_special_tokens:
|
| 132 |
+
if not prev_is_special:
|
| 133 |
+
out_string += ' '
|
| 134 |
+
out_string += self.sp_model.decode(current_sub_tokens) + token
|
| 135 |
+
prev_is_special = True
|
| 136 |
+
current_sub_tokens = []
|
| 137 |
+
else:
|
| 138 |
+
current_sub_tokens.append(token)
|
| 139 |
+
prev_is_special = False
|
| 140 |
+
out_string += self.sp_model.decode(current_sub_tokens)
|
| 141 |
+
out_string = self.clean_up_tokenization(out_string)
|
| 142 |
+
out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
|
| 143 |
+
return out_string[1:]
|
| 144 |
+
|
| 145 |
+
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
| 146 |
+
"""
|
| 147 |
+
Save the vocabulary and special tokens file to a directory.
|
| 148 |
+
|
| 149 |
+
Args:
|
| 150 |
+
save_directory (`str`):
|
| 151 |
+
The directory in which to save the vocabulary.
|
| 152 |
+
|
| 153 |
+
Returns:
|
| 154 |
+
`Tuple(str)`: Paths to the files saved.
|
| 155 |
+
"""
|
| 156 |
+
if not os.path.isdir(save_directory):
|
| 157 |
+
logger.error(f'Vocabulary path ({save_directory}) should be a directory')
|
| 158 |
+
return
|
| 159 |
+
out_vocab_file = os.path.join(
|
| 160 |
+
save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
|
| 161 |
+
)
|
| 162 |
+
|
| 163 |
+
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
|
| 164 |
+
copyfile(self.vocab_file, out_vocab_file)
|
| 165 |
+
elif not os.path.isfile(self.vocab_file):
|
| 166 |
+
with open(out_vocab_file, 'wb') as fi:
|
| 167 |
+
content_spiece_model = self.sp_model.serialized_model_proto()
|
| 168 |
+
fi.write(content_spiece_model)
|
| 169 |
+
|
| 170 |
+
return (out_vocab_file,)
|
| 171 |
+
|
| 172 |
+
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
| 173 |
+
if self.add_bos_token:
|
| 174 |
+
bos_token_ids = [self.bos_token_id]
|
| 175 |
+
else:
|
| 176 |
+
bos_token_ids = []
|
| 177 |
+
|
| 178 |
+
output = bos_token_ids + token_ids_0
|
| 179 |
+
|
| 180 |
+
if token_ids_1 is not None:
|
| 181 |
+
output = output + token_ids_1
|
| 182 |
+
|
| 183 |
+
if self.add_eos_token:
|
| 184 |
+
output = output + [self.eos_token_id]
|
| 185 |
+
|
| 186 |
+
return output
|
| 187 |
+
|
| 188 |
+
def get_special_tokens_mask(
|
| 189 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
|
| 190 |
+
) -> List[int]:
|
| 191 |
+
"""
|
| 192 |
+
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
|
| 193 |
+
special tokens using the tokenizer `prepare_for_model` method.
|
| 194 |
+
|
| 195 |
+
Args:
|
| 196 |
+
token_ids_0 (`List[int]`):
|
| 197 |
+
List of IDs.
|
| 198 |
+
token_ids_1 (`List[int]`, *optional*):
|
| 199 |
+
Optional second list of IDs for sequence pairs.
|
| 200 |
+
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
|
| 201 |
+
Whether or not the token list is already formatted with special tokens for the model.
|
| 202 |
+
|
| 203 |
+
Returns:
|
| 204 |
+
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
|
| 205 |
+
"""
|
| 206 |
+
if already_has_special_tokens:
|
| 207 |
+
return super().get_special_tokens_mask(
|
| 208 |
+
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
|
| 209 |
+
)
|
| 210 |
+
|
| 211 |
+
if token_ids_1 is None:
|
| 212 |
+
return [1] + ([0] * len(token_ids_0)) + [1]
|
| 213 |
+
return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
|
| 214 |
+
|
| 215 |
+
def create_token_type_ids_from_sequences(
|
| 216 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
| 217 |
+
) -> List[int]:
|
| 218 |
+
"""
|
| 219 |
+
Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
|
| 220 |
+
use of token type ids, therefore a list of zeros is returned.
|
| 221 |
+
|
| 222 |
+
Args:
|
| 223 |
+
token_ids_0 (`List[int]`):
|
| 224 |
+
List of IDs.
|
| 225 |
+
token_ids_1 (`List[int]`, *optional*):
|
| 226 |
+
Optional second list of IDs for sequence pairs.
|
| 227 |
+
|
| 228 |
+
Returns:
|
| 229 |
+
`List[int]`: List of zeros.
|
| 230 |
+
"""
|
| 231 |
+
eos = [self.eos_token_id]
|
| 232 |
+
|
| 233 |
+
if token_ids_1 is None:
|
| 234 |
+
return len(token_ids_0 + eos) * [0]
|
| 235 |
+
return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
|
| 3 |
+
size 1477754
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,179 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"92538": {
|
| 28 |
+
"content": "<|plugin|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"92539": {
|
| 36 |
+
"content": "<|interpreter|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"92540": {
|
| 44 |
+
"content": "<|action_end|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"92541": {
|
| 52 |
+
"content": "<|action_start|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"92542": {
|
| 60 |
+
"content": "<|im_end|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"92543": {
|
| 68 |
+
"content": "<|im_start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"92544": {
|
| 76 |
+
"content": "<img>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"92545": {
|
| 84 |
+
"content": "</img>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"92546": {
|
| 92 |
+
"content": "<IMG_CONTEXT>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"92547": {
|
| 100 |
+
"content": "<quad>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"92548": {
|
| 108 |
+
"content": "</quad>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"92549": {
|
| 116 |
+
"content": "<ref>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"92550": {
|
| 124 |
+
"content": "</ref>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"92551": {
|
| 132 |
+
"content": "<box>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"92552": {
|
| 140 |
+
"content": "</box>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
}
|
| 147 |
+
},
|
| 148 |
+
"additional_special_tokens": [
|
| 149 |
+
"<|im_start|>",
|
| 150 |
+
"<|im_end|>",
|
| 151 |
+
"<|action_start|>",
|
| 152 |
+
"<|action_end|>",
|
| 153 |
+
"<|interpreter|>",
|
| 154 |
+
"<|plugin|>",
|
| 155 |
+
"<img>",
|
| 156 |
+
"</img>",
|
| 157 |
+
"<IMG_CONTEXT>",
|
| 158 |
+
"<quad>",
|
| 159 |
+
"</quad>",
|
| 160 |
+
"<ref>",
|
| 161 |
+
"</ref>",
|
| 162 |
+
"<box>",
|
| 163 |
+
"</box>"
|
| 164 |
+
],
|
| 165 |
+
"auto_map": {
|
| 166 |
+
"AutoTokenizer": [
|
| 167 |
+
"tokenization_internlm2.InternLM2Tokenizer",
|
| 168 |
+
null
|
| 169 |
+
]
|
| 170 |
+
},
|
| 171 |
+
"bos_token": "<s>",
|
| 172 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "</s>",
|
| 175 |
+
"model_max_length": 4096,
|
| 176 |
+
"pad_token": "</s>",
|
| 177 |
+
"tokenizer_class": "InternLM2Tokenizer",
|
| 178 |
+
"unk_token": "<unk>"
|
| 179 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1162340178225494,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0003874467260751647,
|
| 13 |
+
"grad_norm": 1.3797279596328735,
|
| 14 |
+
"learning_rate": 5.000000000000001e-07,
|
| 15 |
+
"loss": 0.1281,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0007748934521503294,
|
| 20 |
+
"grad_norm": 1.427977204322815,
|
| 21 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 22 |
+
"loss": 0.1382,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.001162340178225494,
|
| 27 |
+
"grad_norm": 1.578859806060791,
|
| 28 |
+
"learning_rate": 1.5e-06,
|
| 29 |
+
"loss": 0.1277,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0015497869043006587,
|
| 34 |
+
"grad_norm": 1.1599618196487427,
|
| 35 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 36 |
+
"loss": 0.1158,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0019372336303758234,
|
| 41 |
+
"grad_norm": 0.6949732303619385,
|
| 42 |
+
"learning_rate": 2.5e-06,
|
| 43 |
+
"loss": 0.1041,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.002324680356450988,
|
| 48 |
+
"grad_norm": 1.1288537979125977,
|
| 49 |
+
"learning_rate": 3e-06,
|
| 50 |
+
"loss": 0.0945,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0027121270825261525,
|
| 55 |
+
"grad_norm": 0.6135454773902893,
|
| 56 |
+
"learning_rate": 3.5e-06,
|
| 57 |
+
"loss": 0.0876,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0030995738086013174,
|
| 62 |
+
"grad_norm": 0.5220204591751099,
|
| 63 |
+
"learning_rate": 4.000000000000001e-06,
|
| 64 |
+
"loss": 0.0867,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.003487020534676482,
|
| 69 |
+
"grad_norm": 0.4550929665565491,
|
| 70 |
+
"learning_rate": 4.5e-06,
|
| 71 |
+
"loss": 0.0709,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0038744672607516468,
|
| 76 |
+
"grad_norm": 0.6910421252250671,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.0747,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.004261913986826811,
|
| 83 |
+
"grad_norm": 0.41561511158943176,
|
| 84 |
+
"learning_rate": 5.500000000000001e-06,
|
| 85 |
+
"loss": 0.0689,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.004649360712901976,
|
| 90 |
+
"grad_norm": 0.4896767735481262,
|
| 91 |
+
"learning_rate": 6e-06,
|
| 92 |
+
"loss": 0.0702,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.005036807438977141,
|
| 97 |
+
"grad_norm": 0.4564349949359894,
|
| 98 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 99 |
+
"loss": 0.0665,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.005424254165052305,
|
| 104 |
+
"grad_norm": 0.4900062382221222,
|
| 105 |
+
"learning_rate": 7e-06,
|
| 106 |
+
"loss": 0.061,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.00581170089112747,
|
| 111 |
+
"grad_norm": 0.49792054295539856,
|
| 112 |
+
"learning_rate": 7.500000000000001e-06,
|
| 113 |
+
"loss": 0.0628,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.006199147617202635,
|
| 118 |
+
"grad_norm": 0.43068310618400574,
|
| 119 |
+
"learning_rate": 8.000000000000001e-06,
|
| 120 |
+
"loss": 0.0593,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0065865943432778,
|
| 125 |
+
"grad_norm": 0.537997305393219,
|
| 126 |
+
"learning_rate": 8.5e-06,
|
| 127 |
+
"loss": 0.0591,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.006974041069352964,
|
| 132 |
+
"grad_norm": 0.4407069981098175,
|
| 133 |
+
"learning_rate": 9e-06,
|
| 134 |
+
"loss": 0.0596,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.007361487795428129,
|
| 139 |
+
"grad_norm": 0.41794413328170776,
|
| 140 |
+
"learning_rate": 9.5e-06,
|
| 141 |
+
"loss": 0.0582,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.0077489345215032935,
|
| 146 |
+
"grad_norm": 0.47180089354515076,
|
| 147 |
+
"learning_rate": 1e-05,
|
| 148 |
+
"loss": 0.0582,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.008136381247578458,
|
| 153 |
+
"grad_norm": 0.4743525981903076,
|
| 154 |
+
"learning_rate": 1.0500000000000001e-05,
|
| 155 |
+
"loss": 0.059,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.008523827973653622,
|
| 160 |
+
"grad_norm": 0.45391592383384705,
|
| 161 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 162 |
+
"loss": 0.0516,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.008911274699728787,
|
| 167 |
+
"grad_norm": 0.3695983290672302,
|
| 168 |
+
"learning_rate": 1.15e-05,
|
| 169 |
+
"loss": 0.0553,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.009298721425803952,
|
| 174 |
+
"grad_norm": 0.43914660811424255,
|
| 175 |
+
"learning_rate": 1.2e-05,
|
| 176 |
+
"loss": 0.0517,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.009686168151879117,
|
| 181 |
+
"grad_norm": 0.49351632595062256,
|
| 182 |
+
"learning_rate": 1.25e-05,
|
| 183 |
+
"loss": 0.0508,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.010073614877954282,
|
| 188 |
+
"grad_norm": 0.4090370237827301,
|
| 189 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 190 |
+
"loss": 0.049,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.010461061604029445,
|
| 195 |
+
"grad_norm": 0.38544005155563354,
|
| 196 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 197 |
+
"loss": 0.0493,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.01084850833010461,
|
| 202 |
+
"grad_norm": 0.4323033094406128,
|
| 203 |
+
"learning_rate": 1.4e-05,
|
| 204 |
+
"loss": 0.0477,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.011235955056179775,
|
| 209 |
+
"grad_norm": 0.38994646072387695,
|
| 210 |
+
"learning_rate": 1.45e-05,
|
| 211 |
+
"loss": 0.0466,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.01162340178225494,
|
| 216 |
+
"grad_norm": 0.42939314246177673,
|
| 217 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 218 |
+
"loss": 0.0469,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.012010848508330105,
|
| 223 |
+
"grad_norm": 0.39899009466171265,
|
| 224 |
+
"learning_rate": 1.55e-05,
|
| 225 |
+
"loss": 0.0453,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.01239829523440527,
|
| 230 |
+
"grad_norm": 0.43023446202278137,
|
| 231 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 232 |
+
"loss": 0.0409,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.012785741960480435,
|
| 237 |
+
"grad_norm": 0.42153412103652954,
|
| 238 |
+
"learning_rate": 1.65e-05,
|
| 239 |
+
"loss": 0.041,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.0131731886865556,
|
| 244 |
+
"grad_norm": 0.3974706530570984,
|
| 245 |
+
"learning_rate": 1.7e-05,
|
| 246 |
+
"loss": 0.0392,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.013560635412630763,
|
| 251 |
+
"grad_norm": 0.5288010239601135,
|
| 252 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 253 |
+
"loss": 0.0347,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.013948082138705927,
|
| 258 |
+
"grad_norm": 0.35372209548950195,
|
| 259 |
+
"learning_rate": 1.8e-05,
|
| 260 |
+
"loss": 0.0293,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.014335528864781092,
|
| 265 |
+
"grad_norm": 0.28720059990882874,
|
| 266 |
+
"learning_rate": 1.8500000000000002e-05,
|
| 267 |
+
"loss": 0.0262,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.014722975590856257,
|
| 272 |
+
"grad_norm": 0.2670063078403473,
|
| 273 |
+
"learning_rate": 1.9e-05,
|
| 274 |
+
"loss": 0.0255,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.015110422316931422,
|
| 279 |
+
"grad_norm": 0.1942087560892105,
|
| 280 |
+
"learning_rate": 1.95e-05,
|
| 281 |
+
"loss": 0.0227,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.015497869043006587,
|
| 286 |
+
"grad_norm": 0.2093353122472763,
|
| 287 |
+
"learning_rate": 2e-05,
|
| 288 |
+
"loss": 0.0159,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.01588531576908175,
|
| 293 |
+
"grad_norm": 0.2362644374370575,
|
| 294 |
+
"learning_rate": 1.999996332640321e-05,
|
| 295 |
+
"loss": 0.0181,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.016272762495156915,
|
| 300 |
+
"grad_norm": 0.2892892360687256,
|
| 301 |
+
"learning_rate": 1.9999853305881828e-05,
|
| 302 |
+
"loss": 0.0184,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.01666020922123208,
|
| 307 |
+
"grad_norm": 1.0565048456192017,
|
| 308 |
+
"learning_rate": 1.9999669939242817e-05,
|
| 309 |
+
"loss": 0.015,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.017047655947307245,
|
| 314 |
+
"grad_norm": 0.1855366826057434,
|
| 315 |
+
"learning_rate": 1.9999413227831133e-05,
|
| 316 |
+
"loss": 0.0157,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.01743510267338241,
|
| 321 |
+
"grad_norm": 0.1555640548467636,
|
| 322 |
+
"learning_rate": 1.999908317352967e-05,
|
| 323 |
+
"loss": 0.0132,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.017822549399457575,
|
| 328 |
+
"grad_norm": 0.5774663090705872,
|
| 329 |
+
"learning_rate": 1.9998679778759294e-05,
|
| 330 |
+
"loss": 0.0135,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.01820999612553274,
|
| 335 |
+
"grad_norm": 0.20720309019088745,
|
| 336 |
+
"learning_rate": 1.9998203046478784e-05,
|
| 337 |
+
"loss": 0.0134,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.018597442851607904,
|
| 342 |
+
"grad_norm": 0.2124570906162262,
|
| 343 |
+
"learning_rate": 1.999765298018484e-05,
|
| 344 |
+
"loss": 0.0117,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01898488957768307,
|
| 349 |
+
"grad_norm": 0.2567868232727051,
|
| 350 |
+
"learning_rate": 1.999702958391205e-05,
|
| 351 |
+
"loss": 0.0136,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.019372336303758234,
|
| 356 |
+
"grad_norm": 0.22264684736728668,
|
| 357 |
+
"learning_rate": 1.9996332862232843e-05,
|
| 358 |
+
"loss": 0.0156,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.0197597830298334,
|
| 363 |
+
"grad_norm": 0.18246963620185852,
|
| 364 |
+
"learning_rate": 1.9995562820257475e-05,
|
| 365 |
+
"loss": 0.0129,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.020147229755908564,
|
| 370 |
+
"grad_norm": 0.19054433703422546,
|
| 371 |
+
"learning_rate": 1.9994719463633996e-05,
|
| 372 |
+
"loss": 0.0115,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.02053467648198373,
|
| 377 |
+
"grad_norm": 0.21489836275577545,
|
| 378 |
+
"learning_rate": 1.9993802798548185e-05,
|
| 379 |
+
"loss": 0.01,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.02092212320805889,
|
| 384 |
+
"grad_norm": 0.18399657309055328,
|
| 385 |
+
"learning_rate": 1.9992812831723527e-05,
|
| 386 |
+
"loss": 0.0105,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.021309569934134055,
|
| 391 |
+
"grad_norm": 0.17456519603729248,
|
| 392 |
+
"learning_rate": 1.9991749570421146e-05,
|
| 393 |
+
"loss": 0.0097,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.02169701666020922,
|
| 398 |
+
"grad_norm": 0.23350177705287933,
|
| 399 |
+
"learning_rate": 1.999061302243977e-05,
|
| 400 |
+
"loss": 0.0106,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.022084463386284385,
|
| 405 |
+
"grad_norm": 0.26445719599723816,
|
| 406 |
+
"learning_rate": 1.9989403196115656e-05,
|
| 407 |
+
"loss": 0.0097,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.02247191011235955,
|
| 412 |
+
"grad_norm": 0.30252763628959656,
|
| 413 |
+
"learning_rate": 1.998812010032254e-05,
|
| 414 |
+
"loss": 0.011,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.022859356838434715,
|
| 419 |
+
"grad_norm": 0.3056206703186035,
|
| 420 |
+
"learning_rate": 1.998676374447157e-05,
|
| 421 |
+
"loss": 0.0114,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.02324680356450988,
|
| 426 |
+
"grad_norm": 0.17039866745471954,
|
| 427 |
+
"learning_rate": 1.998533413851124e-05,
|
| 428 |
+
"loss": 0.0092,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.023634250290585045,
|
| 433 |
+
"grad_norm": 0.1324278861284256,
|
| 434 |
+
"learning_rate": 1.9983831292927305e-05,
|
| 435 |
+
"loss": 0.0116,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.02402169701666021,
|
| 440 |
+
"grad_norm": 0.18124036490917206,
|
| 441 |
+
"learning_rate": 1.9982255218742715e-05,
|
| 442 |
+
"loss": 0.0084,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.024409143742735374,
|
| 447 |
+
"grad_norm": 0.18300756812095642,
|
| 448 |
+
"learning_rate": 1.998060592751753e-05,
|
| 449 |
+
"loss": 0.0105,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.02479659046881054,
|
| 454 |
+
"grad_norm": 0.18791139125823975,
|
| 455 |
+
"learning_rate": 1.9978883431348845e-05,
|
| 456 |
+
"loss": 0.0114,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.025184037194885704,
|
| 461 |
+
"grad_norm": 0.15705984830856323,
|
| 462 |
+
"learning_rate": 1.9977087742870683e-05,
|
| 463 |
+
"loss": 0.0091,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.02557148392096087,
|
| 468 |
+
"grad_norm": 0.15753675997257233,
|
| 469 |
+
"learning_rate": 1.997521887525391e-05,
|
| 470 |
+
"loss": 0.009,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.025958930647036034,
|
| 475 |
+
"grad_norm": 0.17778246104717255,
|
| 476 |
+
"learning_rate": 1.997327684220615e-05,
|
| 477 |
+
"loss": 0.0097,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.0263463773731112,
|
| 482 |
+
"grad_norm": 0.2148500233888626,
|
| 483 |
+
"learning_rate": 1.997126165797167e-05,
|
| 484 |
+
"loss": 0.01,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.02673382409918636,
|
| 489 |
+
"grad_norm": 0.16575461626052856,
|
| 490 |
+
"learning_rate": 1.9969173337331283e-05,
|
| 491 |
+
"loss": 0.0084,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.027121270825261525,
|
| 496 |
+
"grad_norm": 0.14615203440189362,
|
| 497 |
+
"learning_rate": 1.996701189560223e-05,
|
| 498 |
+
"loss": 0.01,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.02750871755133669,
|
| 503 |
+
"grad_norm": 0.19437825679779053,
|
| 504 |
+
"learning_rate": 1.9964777348638083e-05,
|
| 505 |
+
"loss": 0.0099,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.027896164277411855,
|
| 510 |
+
"grad_norm": 0.16040682792663574,
|
| 511 |
+
"learning_rate": 1.9962469712828613e-05,
|
| 512 |
+
"loss": 0.0081,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.02828361100348702,
|
| 517 |
+
"grad_norm": 0.24002408981323242,
|
| 518 |
+
"learning_rate": 1.9960089005099686e-05,
|
| 519 |
+
"loss": 0.009,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.028671057729562185,
|
| 524 |
+
"grad_norm": 0.19318589568138123,
|
| 525 |
+
"learning_rate": 1.9957635242913124e-05,
|
| 526 |
+
"loss": 0.0082,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.02905850445563735,
|
| 531 |
+
"grad_norm": 0.12690387666225433,
|
| 532 |
+
"learning_rate": 1.9955108444266585e-05,
|
| 533 |
+
"loss": 0.009,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.029445951181712515,
|
| 538 |
+
"grad_norm": 0.141282320022583,
|
| 539 |
+
"learning_rate": 1.995250862769342e-05,
|
| 540 |
+
"loss": 0.0091,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.02983339790778768,
|
| 545 |
+
"grad_norm": 0.1491638422012329,
|
| 546 |
+
"learning_rate": 1.9949835812262566e-05,
|
| 547 |
+
"loss": 0.0081,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.030220844633862844,
|
| 552 |
+
"grad_norm": 0.18488113582134247,
|
| 553 |
+
"learning_rate": 1.9947090017578363e-05,
|
| 554 |
+
"loss": 0.0088,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.03060829135993801,
|
| 559 |
+
"grad_norm": 0.12061460316181183,
|
| 560 |
+
"learning_rate": 1.994427126378045e-05,
|
| 561 |
+
"loss": 0.0067,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.030995738086013174,
|
| 566 |
+
"grad_norm": 0.16431978344917297,
|
| 567 |
+
"learning_rate": 1.9941379571543597e-05,
|
| 568 |
+
"loss": 0.0073,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.031383184812088336,
|
| 573 |
+
"grad_norm": 0.17443543672561646,
|
| 574 |
+
"learning_rate": 1.9938414962077552e-05,
|
| 575 |
+
"loss": 0.0081,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.0317706315381635,
|
| 580 |
+
"grad_norm": 0.12979194521903992,
|
| 581 |
+
"learning_rate": 1.9935377457126893e-05,
|
| 582 |
+
"loss": 0.0083,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.032158078264238665,
|
| 587 |
+
"grad_norm": 0.15405865013599396,
|
| 588 |
+
"learning_rate": 1.993226707897087e-05,
|
| 589 |
+
"loss": 0.0068,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.03254552499031383,
|
| 594 |
+
"grad_norm": 0.16082651913166046,
|
| 595 |
+
"learning_rate": 1.9929083850423226e-05,
|
| 596 |
+
"loss": 0.0074,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.032932971716388995,
|
| 601 |
+
"grad_norm": 0.14032596349716187,
|
| 602 |
+
"learning_rate": 1.9925827794832057e-05,
|
| 603 |
+
"loss": 0.0077,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.03332041844246416,
|
| 608 |
+
"grad_norm": 0.14939086139202118,
|
| 609 |
+
"learning_rate": 1.9922498936079612e-05,
|
| 610 |
+
"loss": 0.0099,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.033707865168539325,
|
| 615 |
+
"grad_norm": 0.14590921998023987,
|
| 616 |
+
"learning_rate": 1.9919097298582142e-05,
|
| 617 |
+
"loss": 0.0073,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.03409531189461449,
|
| 622 |
+
"grad_norm": 0.17522308230400085,
|
| 623 |
+
"learning_rate": 1.9915622907289695e-05,
|
| 624 |
+
"loss": 0.0084,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.034482758620689655,
|
| 629 |
+
"grad_norm": 0.13548927009105682,
|
| 630 |
+
"learning_rate": 1.9912075787685964e-05,
|
| 631 |
+
"loss": 0.0068,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.03487020534676482,
|
| 636 |
+
"grad_norm": 0.1186554878950119,
|
| 637 |
+
"learning_rate": 1.990845596578807e-05,
|
| 638 |
+
"loss": 0.0082,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.035257652072839984,
|
| 643 |
+
"grad_norm": 0.1406015306711197,
|
| 644 |
+
"learning_rate": 1.9904763468146394e-05,
|
| 645 |
+
"loss": 0.0081,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.03564509879891515,
|
| 650 |
+
"grad_norm": 0.11095679551362991,
|
| 651 |
+
"learning_rate": 1.9900998321844367e-05,
|
| 652 |
+
"loss": 0.0084,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.036032545524990314,
|
| 657 |
+
"grad_norm": 0.11735799908638,
|
| 658 |
+
"learning_rate": 1.9897160554498285e-05,
|
| 659 |
+
"loss": 0.0079,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.03641999225106548,
|
| 664 |
+
"grad_norm": 0.11704786866903305,
|
| 665 |
+
"learning_rate": 1.9893250194257087e-05,
|
| 666 |
+
"loss": 0.0069,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.036807438977140644,
|
| 671 |
+
"grad_norm": 0.16678492724895477,
|
| 672 |
+
"learning_rate": 1.988926726980218e-05,
|
| 673 |
+
"loss": 0.0087,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.03719488570321581,
|
| 678 |
+
"grad_norm": 0.1538490206003189,
|
| 679 |
+
"learning_rate": 1.9885211810347185e-05,
|
| 680 |
+
"loss": 0.0091,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.037582332429290974,
|
| 685 |
+
"grad_norm": 0.12139847874641418,
|
| 686 |
+
"learning_rate": 1.9881083845637764e-05,
|
| 687 |
+
"loss": 0.0082,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.03796977915536614,
|
| 692 |
+
"grad_norm": 0.13453418016433716,
|
| 693 |
+
"learning_rate": 1.9876883405951378e-05,
|
| 694 |
+
"loss": 0.0087,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.038357225881441304,
|
| 699 |
+
"grad_norm": 0.1216122955083847,
|
| 700 |
+
"learning_rate": 1.987261052209708e-05,
|
| 701 |
+
"loss": 0.0074,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.03874467260751647,
|
| 706 |
+
"grad_norm": 0.10939031839370728,
|
| 707 |
+
"learning_rate": 1.9868265225415263e-05,
|
| 708 |
+
"loss": 0.0075,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.03913211933359163,
|
| 713 |
+
"grad_norm": 0.16390249133110046,
|
| 714 |
+
"learning_rate": 1.9863847547777467e-05,
|
| 715 |
+
"loss": 0.007,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.0395195660596668,
|
| 720 |
+
"grad_norm": 0.13085976243019104,
|
| 721 |
+
"learning_rate": 1.9859357521586115e-05,
|
| 722 |
+
"loss": 0.008,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.03990701278574196,
|
| 727 |
+
"grad_norm": 0.14601804316043854,
|
| 728 |
+
"learning_rate": 1.9854795179774288e-05,
|
| 729 |
+
"loss": 0.008,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.04029445951181713,
|
| 734 |
+
"grad_norm": 0.17783567309379578,
|
| 735 |
+
"learning_rate": 1.9850160555805485e-05,
|
| 736 |
+
"loss": 0.0073,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.04068190623789229,
|
| 741 |
+
"grad_norm": 0.11501951515674591,
|
| 742 |
+
"learning_rate": 1.984545368367337e-05,
|
| 743 |
+
"loss": 0.0069,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.04106935296396746,
|
| 748 |
+
"grad_norm": 0.13545309007167816,
|
| 749 |
+
"learning_rate": 1.9840674597901533e-05,
|
| 750 |
+
"loss": 0.0077,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.041456799690042616,
|
| 755 |
+
"grad_norm": 0.12369155138731003,
|
| 756 |
+
"learning_rate": 1.983582333354322e-05,
|
| 757 |
+
"loss": 0.0079,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.04184424641611778,
|
| 762 |
+
"grad_norm": 0.14605672657489777,
|
| 763 |
+
"learning_rate": 1.9830899926181103e-05,
|
| 764 |
+
"loss": 0.0062,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.042231693142192946,
|
| 769 |
+
"grad_norm": 0.11621249467134476,
|
| 770 |
+
"learning_rate": 1.9825904411926983e-05,
|
| 771 |
+
"loss": 0.0071,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.04261913986826811,
|
| 776 |
+
"grad_norm": 0.122838094830513,
|
| 777 |
+
"learning_rate": 1.982083682742156e-05,
|
| 778 |
+
"loss": 0.0075,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.043006586594343275,
|
| 783 |
+
"grad_norm": 0.11120407283306122,
|
| 784 |
+
"learning_rate": 1.981569720983415e-05,
|
| 785 |
+
"loss": 0.0065,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.04339403332041844,
|
| 790 |
+
"grad_norm": 0.0935436561703682,
|
| 791 |
+
"learning_rate": 1.981048559686239e-05,
|
| 792 |
+
"loss": 0.0084,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.043781480046493605,
|
| 797 |
+
"grad_norm": 0.11046198755502701,
|
| 798 |
+
"learning_rate": 1.9805202026732018e-05,
|
| 799 |
+
"loss": 0.0076,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.04416892677256877,
|
| 804 |
+
"grad_norm": 0.1548909842967987,
|
| 805 |
+
"learning_rate": 1.9799846538196524e-05,
|
| 806 |
+
"loss": 0.0074,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.044556373498643935,
|
| 811 |
+
"grad_norm": 0.09135284274816513,
|
| 812 |
+
"learning_rate": 1.9794419170536918e-05,
|
| 813 |
+
"loss": 0.0068,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.0449438202247191,
|
| 818 |
+
"grad_norm": 0.1384485512971878,
|
| 819 |
+
"learning_rate": 1.9788919963561423e-05,
|
| 820 |
+
"loss": 0.009,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.045331266950794265,
|
| 825 |
+
"grad_norm": 0.10797080397605896,
|
| 826 |
+
"learning_rate": 1.978334895760517e-05,
|
| 827 |
+
"loss": 0.009,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.04571871367686943,
|
| 832 |
+
"grad_norm": 0.10121048241853714,
|
| 833 |
+
"learning_rate": 1.9777706193529927e-05,
|
| 834 |
+
"loss": 0.007,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.046106160402944595,
|
| 839 |
+
"grad_norm": 0.14966851472854614,
|
| 840 |
+
"learning_rate": 1.977199171272379e-05,
|
| 841 |
+
"loss": 0.0069,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.04649360712901976,
|
| 846 |
+
"grad_norm": 0.1313655823469162,
|
| 847 |
+
"learning_rate": 1.976620555710087e-05,
|
| 848 |
+
"loss": 0.0072,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.046881053855094924,
|
| 853 |
+
"grad_norm": 0.11657986044883728,
|
| 854 |
+
"learning_rate": 1.976034776910099e-05,
|
| 855 |
+
"loss": 0.0076,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.04726850058117009,
|
| 860 |
+
"grad_norm": 0.13987232744693756,
|
| 861 |
+
"learning_rate": 1.9754418391689384e-05,
|
| 862 |
+
"loss": 0.0068,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.047655947307245254,
|
| 867 |
+
"grad_norm": 0.12414025515317917,
|
| 868 |
+
"learning_rate": 1.9748417468356374e-05,
|
| 869 |
+
"loss": 0.0075,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.04804339403332042,
|
| 874 |
+
"grad_norm": 0.1323256641626358,
|
| 875 |
+
"learning_rate": 1.9742345043117045e-05,
|
| 876 |
+
"loss": 0.0087,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.048430840759395584,
|
| 881 |
+
"grad_norm": 0.11190538108348846,
|
| 882 |
+
"learning_rate": 1.9736201160510933e-05,
|
| 883 |
+
"loss": 0.007,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.04881828748547075,
|
| 888 |
+
"grad_norm": 0.11807341128587723,
|
| 889 |
+
"learning_rate": 1.972998586560169e-05,
|
| 890 |
+
"loss": 0.0076,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.049205734211545914,
|
| 895 |
+
"grad_norm": 0.10347302258014679,
|
| 896 |
+
"learning_rate": 1.9723699203976768e-05,
|
| 897 |
+
"loss": 0.0082,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.04959318093762108,
|
| 902 |
+
"grad_norm": 0.10547901690006256,
|
| 903 |
+
"learning_rate": 1.9717341221747056e-05,
|
| 904 |
+
"loss": 0.0068,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.049980627663696243,
|
| 909 |
+
"grad_norm": 0.09318678081035614,
|
| 910 |
+
"learning_rate": 1.9710911965546577e-05,
|
| 911 |
+
"loss": 0.0067,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.05036807438977141,
|
| 916 |
+
"grad_norm": 0.16719457507133484,
|
| 917 |
+
"learning_rate": 1.9704411482532116e-05,
|
| 918 |
+
"loss": 0.0074,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.05075552111584657,
|
| 923 |
+
"grad_norm": 0.14071008563041687,
|
| 924 |
+
"learning_rate": 1.969783982038289e-05,
|
| 925 |
+
"loss": 0.0063,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.05114296784192174,
|
| 930 |
+
"grad_norm": 0.09480374306440353,
|
| 931 |
+
"learning_rate": 1.9691197027300208e-05,
|
| 932 |
+
"loss": 0.0069,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.0515304145679969,
|
| 937 |
+
"grad_norm": 0.1424514651298523,
|
| 938 |
+
"learning_rate": 1.968448315200708e-05,
|
| 939 |
+
"loss": 0.0069,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.05191786129407207,
|
| 944 |
+
"grad_norm": 0.12241359800100327,
|
| 945 |
+
"learning_rate": 1.96776982437479e-05,
|
| 946 |
+
"loss": 0.0066,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.05230530802014723,
|
| 951 |
+
"grad_norm": 0.13578863441944122,
|
| 952 |
+
"learning_rate": 1.967084235228807e-05,
|
| 953 |
+
"loss": 0.007,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.0526927547462224,
|
| 958 |
+
"grad_norm": 0.15467995405197144,
|
| 959 |
+
"learning_rate": 1.9663915527913628e-05,
|
| 960 |
+
"loss": 0.0081,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.053080201472297556,
|
| 965 |
+
"grad_norm": 0.15875425934791565,
|
| 966 |
+
"learning_rate": 1.9656917821430883e-05,
|
| 967 |
+
"loss": 0.0083,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.05346764819837272,
|
| 972 |
+
"grad_norm": 0.08851481229066849,
|
| 973 |
+
"learning_rate": 1.9649849284166052e-05,
|
| 974 |
+
"loss": 0.0066,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.053855094924447885,
|
| 979 |
+
"grad_norm": 0.08082897216081619,
|
| 980 |
+
"learning_rate": 1.9642709967964877e-05,
|
| 981 |
+
"loss": 0.0063,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.05424254165052305,
|
| 986 |
+
"grad_norm": 0.09030059725046158,
|
| 987 |
+
"learning_rate": 1.963549992519223e-05,
|
| 988 |
+
"loss": 0.0072,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.054629988376598215,
|
| 993 |
+
"grad_norm": 0.14087818562984467,
|
| 994 |
+
"learning_rate": 1.9628219208731756e-05,
|
| 995 |
+
"loss": 0.0065,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.05501743510267338,
|
| 1000 |
+
"grad_norm": 0.10587012767791748,
|
| 1001 |
+
"learning_rate": 1.9620867871985467e-05,
|
| 1002 |
+
"loss": 0.0064,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.055404881828748545,
|
| 1007 |
+
"grad_norm": 0.10362262278795242,
|
| 1008 |
+
"learning_rate": 1.9613445968873352e-05,
|
| 1009 |
+
"loss": 0.0068,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.05579232855482371,
|
| 1014 |
+
"grad_norm": 0.13274861872196198,
|
| 1015 |
+
"learning_rate": 1.9605953553832987e-05,
|
| 1016 |
+
"loss": 0.0072,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.056179775280898875,
|
| 1021 |
+
"grad_norm": 0.10128219425678253,
|
| 1022 |
+
"learning_rate": 1.9598390681819138e-05,
|
| 1023 |
+
"loss": 0.0069,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.05656722200697404,
|
| 1028 |
+
"grad_norm": 0.15282753109931946,
|
| 1029 |
+
"learning_rate": 1.959075740830335e-05,
|
| 1030 |
+
"loss": 0.0071,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.056954668733049205,
|
| 1035 |
+
"grad_norm": 0.12651081383228302,
|
| 1036 |
+
"learning_rate": 1.9583053789273534e-05,
|
| 1037 |
+
"loss": 0.0074,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.05734211545912437,
|
| 1042 |
+
"grad_norm": 0.124647356569767,
|
| 1043 |
+
"learning_rate": 1.9575279881233578e-05,
|
| 1044 |
+
"loss": 0.008,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.057729562185199534,
|
| 1049 |
+
"grad_norm": 0.11204249411821365,
|
| 1050 |
+
"learning_rate": 1.9567435741202917e-05,
|
| 1051 |
+
"loss": 0.0058,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.0581170089112747,
|
| 1056 |
+
"grad_norm": 0.13926751911640167,
|
| 1057 |
+
"learning_rate": 1.955952142671612e-05,
|
| 1058 |
+
"loss": 0.0068,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.058504455637349864,
|
| 1063 |
+
"grad_norm": 0.10197625309228897,
|
| 1064 |
+
"learning_rate": 1.9551536995822452e-05,
|
| 1065 |
+
"loss": 0.0061,
|
| 1066 |
+
"step": 755
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.05889190236342503,
|
| 1070 |
+
"grad_norm": 0.09653060883283615,
|
| 1071 |
+
"learning_rate": 1.9543482507085484e-05,
|
| 1072 |
+
"loss": 0.0067,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.059279349089500194,
|
| 1077 |
+
"grad_norm": 0.13161785900592804,
|
| 1078 |
+
"learning_rate": 1.9535358019582624e-05,
|
| 1079 |
+
"loss": 0.0072,
|
| 1080 |
+
"step": 765
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.05966679581557536,
|
| 1084 |
+
"grad_norm": 0.09690017998218536,
|
| 1085 |
+
"learning_rate": 1.9527163592904707e-05,
|
| 1086 |
+
"loss": 0.0061,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.060054242541650524,
|
| 1091 |
+
"grad_norm": 0.11521229147911072,
|
| 1092 |
+
"learning_rate": 1.9518899287155558e-05,
|
| 1093 |
+
"loss": 0.0066,
|
| 1094 |
+
"step": 775
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.06044168926772569,
|
| 1098 |
+
"grad_norm": 0.08923397958278656,
|
| 1099 |
+
"learning_rate": 1.9510565162951538e-05,
|
| 1100 |
+
"loss": 0.0057,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.060829135993800854,
|
| 1105 |
+
"grad_norm": 0.09332666546106339,
|
| 1106 |
+
"learning_rate": 1.9502161281421107e-05,
|
| 1107 |
+
"loss": 0.0071,
|
| 1108 |
+
"step": 785
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.06121658271987602,
|
| 1112 |
+
"grad_norm": 0.10926046222448349,
|
| 1113 |
+
"learning_rate": 1.9493687704204382e-05,
|
| 1114 |
+
"loss": 0.0066,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.06160402944595118,
|
| 1119 |
+
"grad_norm": 0.1336076855659485,
|
| 1120 |
+
"learning_rate": 1.9485144493452672e-05,
|
| 1121 |
+
"loss": 0.0078,
|
| 1122 |
+
"step": 795
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.06199147617202635,
|
| 1126 |
+
"grad_norm": 0.11809663474559784,
|
| 1127 |
+
"learning_rate": 1.9476531711828027e-05,
|
| 1128 |
+
"loss": 0.006,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.06237892289810151,
|
| 1133 |
+
"grad_norm": 0.10250601917505264,
|
| 1134 |
+
"learning_rate": 1.9467849422502786e-05,
|
| 1135 |
+
"loss": 0.0062,
|
| 1136 |
+
"step": 805
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.06276636962417667,
|
| 1140 |
+
"grad_norm": 0.06555704772472382,
|
| 1141 |
+
"learning_rate": 1.9459097689159104e-05,
|
| 1142 |
+
"loss": 0.0055,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.06315381635025184,
|
| 1147 |
+
"grad_norm": 0.11264653503894806,
|
| 1148 |
+
"learning_rate": 1.9450276575988493e-05,
|
| 1149 |
+
"loss": 0.005,
|
| 1150 |
+
"step": 815
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.063541263076327,
|
| 1154 |
+
"grad_norm": 0.12369207292795181,
|
| 1155 |
+
"learning_rate": 1.9441386147691336e-05,
|
| 1156 |
+
"loss": 0.008,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.06392870980240217,
|
| 1161 |
+
"grad_norm": 0.10422497987747192,
|
| 1162 |
+
"learning_rate": 1.9432426469476432e-05,
|
| 1163 |
+
"loss": 0.0058,
|
| 1164 |
+
"step": 825
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.06431615652847733,
|
| 1168 |
+
"grad_norm": 0.08945394307374954,
|
| 1169 |
+
"learning_rate": 1.9423397607060507e-05,
|
| 1170 |
+
"loss": 0.0059,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.0647036032545525,
|
| 1175 |
+
"grad_norm": 0.10614626109600067,
|
| 1176 |
+
"learning_rate": 1.9414299626667733e-05,
|
| 1177 |
+
"loss": 0.0061,
|
| 1178 |
+
"step": 835
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.06509104998062766,
|
| 1182 |
+
"grad_norm": 0.08883573114871979,
|
| 1183 |
+
"learning_rate": 1.940513259502924e-05,
|
| 1184 |
+
"loss": 0.0068,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.06547849670670283,
|
| 1189 |
+
"grad_norm": 0.13218294084072113,
|
| 1190 |
+
"learning_rate": 1.939589657938264e-05,
|
| 1191 |
+
"loss": 0.007,
|
| 1192 |
+
"step": 845
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.06586594343277799,
|
| 1196 |
+
"grad_norm": 0.1291383057832718,
|
| 1197 |
+
"learning_rate": 1.9386591647471508e-05,
|
| 1198 |
+
"loss": 0.0065,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.06625339015885316,
|
| 1203 |
+
"grad_norm": 0.13212865591049194,
|
| 1204 |
+
"learning_rate": 1.937721786754491e-05,
|
| 1205 |
+
"loss": 0.007,
|
| 1206 |
+
"step": 855
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.06664083688492832,
|
| 1210 |
+
"grad_norm": 0.12437047064304352,
|
| 1211 |
+
"learning_rate": 1.9367775308356892e-05,
|
| 1212 |
+
"loss": 0.0057,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.06702828361100349,
|
| 1217 |
+
"grad_norm": 0.096067875623703,
|
| 1218 |
+
"learning_rate": 1.9358264039165976e-05,
|
| 1219 |
+
"loss": 0.0079,
|
| 1220 |
+
"step": 865
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.06741573033707865,
|
| 1224 |
+
"grad_norm": 0.15886329114437103,
|
| 1225 |
+
"learning_rate": 1.9348684129734652e-05,
|
| 1226 |
+
"loss": 0.0074,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.06780317706315382,
|
| 1231 |
+
"grad_norm": 0.10266343504190445,
|
| 1232 |
+
"learning_rate": 1.933903565032887e-05,
|
| 1233 |
+
"loss": 0.0065,
|
| 1234 |
+
"step": 875
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.06819062378922898,
|
| 1238 |
+
"grad_norm": 0.09206750988960266,
|
| 1239 |
+
"learning_rate": 1.932931867171751e-05,
|
| 1240 |
+
"loss": 0.0056,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.06857807051530415,
|
| 1245 |
+
"grad_norm": 0.1066446453332901,
|
| 1246 |
+
"learning_rate": 1.931953326517189e-05,
|
| 1247 |
+
"loss": 0.0064,
|
| 1248 |
+
"step": 885
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.06896551724137931,
|
| 1252 |
+
"grad_norm": 0.1061030849814415,
|
| 1253 |
+
"learning_rate": 1.9309679502465225e-05,
|
| 1254 |
+
"loss": 0.005,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.06935296396745448,
|
| 1259 |
+
"grad_norm": 0.09487008303403854,
|
| 1260 |
+
"learning_rate": 1.929975745587209e-05,
|
| 1261 |
+
"loss": 0.0053,
|
| 1262 |
+
"step": 895
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.06974041069352964,
|
| 1266 |
+
"grad_norm": 0.12475048750638962,
|
| 1267 |
+
"learning_rate": 1.9289767198167918e-05,
|
| 1268 |
+
"loss": 0.0079,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.07012785741960481,
|
| 1273 |
+
"grad_norm": 0.09674495458602905,
|
| 1274 |
+
"learning_rate": 1.9279708802628437e-05,
|
| 1275 |
+
"loss": 0.0057,
|
| 1276 |
+
"step": 905
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.07051530414567997,
|
| 1280 |
+
"grad_norm": 0.12408360838890076,
|
| 1281 |
+
"learning_rate": 1.926958234302917e-05,
|
| 1282 |
+
"loss": 0.0068,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.07090275087175513,
|
| 1287 |
+
"grad_norm": 0.10904911160469055,
|
| 1288 |
+
"learning_rate": 1.9259387893644847e-05,
|
| 1289 |
+
"loss": 0.0054,
|
| 1290 |
+
"step": 915
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.0712901975978303,
|
| 1294 |
+
"grad_norm": 0.09366695582866669,
|
| 1295 |
+
"learning_rate": 1.924912552924889e-05,
|
| 1296 |
+
"loss": 0.0053,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.07167764432390546,
|
| 1301 |
+
"grad_norm": 0.09137874841690063,
|
| 1302 |
+
"learning_rate": 1.9238795325112867e-05,
|
| 1303 |
+
"loss": 0.0053,
|
| 1304 |
+
"step": 925
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.07206509104998063,
|
| 1308 |
+
"grad_norm": 0.129123717546463,
|
| 1309 |
+
"learning_rate": 1.922839735700593e-05,
|
| 1310 |
+
"loss": 0.0074,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.07245253777605579,
|
| 1315 |
+
"grad_norm": 0.10229382663965225,
|
| 1316 |
+
"learning_rate": 1.921793170119425e-05,
|
| 1317 |
+
"loss": 0.0062,
|
| 1318 |
+
"step": 935
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.07283998450213096,
|
| 1322 |
+
"grad_norm": 0.09574132412672043,
|
| 1323 |
+
"learning_rate": 1.9207398434440478e-05,
|
| 1324 |
+
"loss": 0.0074,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.07322743122820612,
|
| 1329 |
+
"grad_norm": 0.11554568260908127,
|
| 1330 |
+
"learning_rate": 1.919679763400317e-05,
|
| 1331 |
+
"loss": 0.0052,
|
| 1332 |
+
"step": 945
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.07361487795428129,
|
| 1336 |
+
"grad_norm": 0.10633377730846405,
|
| 1337 |
+
"learning_rate": 1.918612937763622e-05,
|
| 1338 |
+
"loss": 0.0063,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.07400232468035645,
|
| 1343 |
+
"grad_norm": 0.10467655956745148,
|
| 1344 |
+
"learning_rate": 1.9175393743588297e-05,
|
| 1345 |
+
"loss": 0.0063,
|
| 1346 |
+
"step": 955
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.07438977140643162,
|
| 1350 |
+
"grad_norm": 0.09323202073574066,
|
| 1351 |
+
"learning_rate": 1.9164590810602262e-05,
|
| 1352 |
+
"loss": 0.0065,
|
| 1353 |
+
"step": 960
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.07477721813250678,
|
| 1357 |
+
"grad_norm": 0.099956214427948,
|
| 1358 |
+
"learning_rate": 1.9153720657914597e-05,
|
| 1359 |
+
"loss": 0.0051,
|
| 1360 |
+
"step": 965
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.07516466485858195,
|
| 1364 |
+
"grad_norm": 0.11138712614774704,
|
| 1365 |
+
"learning_rate": 1.9142783365254826e-05,
|
| 1366 |
+
"loss": 0.0065,
|
| 1367 |
+
"step": 970
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.0755521115846571,
|
| 1371 |
+
"grad_norm": 0.12999290227890015,
|
| 1372 |
+
"learning_rate": 1.9131779012844914e-05,
|
| 1373 |
+
"loss": 0.0061,
|
| 1374 |
+
"step": 975
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.07593955831073228,
|
| 1378 |
+
"grad_norm": 0.11701661348342896,
|
| 1379 |
+
"learning_rate": 1.91207076813987e-05,
|
| 1380 |
+
"loss": 0.006,
|
| 1381 |
+
"step": 980
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.07632700503680744,
|
| 1385 |
+
"grad_norm": 0.1041875034570694,
|
| 1386 |
+
"learning_rate": 1.9109569452121294e-05,
|
| 1387 |
+
"loss": 0.006,
|
| 1388 |
+
"step": 985
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.07671445176288261,
|
| 1392 |
+
"grad_norm": 0.10007134824991226,
|
| 1393 |
+
"learning_rate": 1.9098364406708482e-05,
|
| 1394 |
+
"loss": 0.0058,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.07710189848895777,
|
| 1399 |
+
"grad_norm": 0.11660099029541016,
|
| 1400 |
+
"learning_rate": 1.908709262734613e-05,
|
| 1401 |
+
"loss": 0.0079,
|
| 1402 |
+
"step": 995
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.07748934521503294,
|
| 1406 |
+
"grad_norm": 0.10171498358249664,
|
| 1407 |
+
"learning_rate": 1.9075754196709574e-05,
|
| 1408 |
+
"loss": 0.0059,
|
| 1409 |
+
"step": 1000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.0778767919411081,
|
| 1413 |
+
"grad_norm": 0.09439248591661453,
|
| 1414 |
+
"learning_rate": 1.9064349197963015e-05,
|
| 1415 |
+
"loss": 0.0063,
|
| 1416 |
+
"step": 1005
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.07826423866718327,
|
| 1420 |
+
"grad_norm": 0.15760357677936554,
|
| 1421 |
+
"learning_rate": 1.9052877714758926e-05,
|
| 1422 |
+
"loss": 0.0062,
|
| 1423 |
+
"step": 1010
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.07865168539325842,
|
| 1427 |
+
"grad_norm": 0.11133988201618195,
|
| 1428 |
+
"learning_rate": 1.9041339831237416e-05,
|
| 1429 |
+
"loss": 0.0057,
|
| 1430 |
+
"step": 1015
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.0790391321193336,
|
| 1434 |
+
"grad_norm": 0.12682966887950897,
|
| 1435 |
+
"learning_rate": 1.9029735632025618e-05,
|
| 1436 |
+
"loss": 0.007,
|
| 1437 |
+
"step": 1020
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.07942657884540875,
|
| 1441 |
+
"grad_norm": 0.1026381179690361,
|
| 1442 |
+
"learning_rate": 1.9018065202237083e-05,
|
| 1443 |
+
"loss": 0.0058,
|
| 1444 |
+
"step": 1025
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.07981402557148393,
|
| 1448 |
+
"grad_norm": 0.11611684411764145,
|
| 1449 |
+
"learning_rate": 1.9006328627471133e-05,
|
| 1450 |
+
"loss": 0.0058,
|
| 1451 |
+
"step": 1030
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.08020147229755908,
|
| 1455 |
+
"grad_norm": 0.0950181856751442,
|
| 1456 |
+
"learning_rate": 1.8994525993812252e-05,
|
| 1457 |
+
"loss": 0.006,
|
| 1458 |
+
"step": 1035
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.08058891902363426,
|
| 1462 |
+
"grad_norm": 0.10637630522251129,
|
| 1463 |
+
"learning_rate": 1.8982657387829447e-05,
|
| 1464 |
+
"loss": 0.0059,
|
| 1465 |
+
"step": 1040
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.08097636574970941,
|
| 1469 |
+
"grad_norm": 0.08024627715349197,
|
| 1470 |
+
"learning_rate": 1.8970722896575608e-05,
|
| 1471 |
+
"loss": 0.0053,
|
| 1472 |
+
"step": 1045
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.08136381247578459,
|
| 1476 |
+
"grad_norm": 0.11056095361709595,
|
| 1477 |
+
"learning_rate": 1.8958722607586883e-05,
|
| 1478 |
+
"loss": 0.0068,
|
| 1479 |
+
"step": 1050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.08175125920185974,
|
| 1483 |
+
"grad_norm": 0.09633923321962357,
|
| 1484 |
+
"learning_rate": 1.894665660888202e-05,
|
| 1485 |
+
"loss": 0.0052,
|
| 1486 |
+
"step": 1055
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.08213870592793492,
|
| 1490 |
+
"grad_norm": 0.11852028965950012,
|
| 1491 |
+
"learning_rate": 1.893452498896174e-05,
|
| 1492 |
+
"loss": 0.0062,
|
| 1493 |
+
"step": 1060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.08252615265401007,
|
| 1497 |
+
"grad_norm": 0.11247052252292633,
|
| 1498 |
+
"learning_rate": 1.892232783680806e-05,
|
| 1499 |
+
"loss": 0.0063,
|
| 1500 |
+
"step": 1065
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.08291359938008523,
|
| 1504 |
+
"grad_norm": 0.09401384741067886,
|
| 1505 |
+
"learning_rate": 1.891006524188368e-05,
|
| 1506 |
+
"loss": 0.0065,
|
| 1507 |
+
"step": 1070
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.0833010461061604,
|
| 1511 |
+
"grad_norm": 0.08759772032499313,
|
| 1512 |
+
"learning_rate": 1.8897737294131288e-05,
|
| 1513 |
+
"loss": 0.0056,
|
| 1514 |
+
"step": 1075
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.08368849283223556,
|
| 1518 |
+
"grad_norm": 0.103630930185318,
|
| 1519 |
+
"learning_rate": 1.8885344083972912e-05,
|
| 1520 |
+
"loss": 0.0059,
|
| 1521 |
+
"step": 1080
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.08407593955831073,
|
| 1525 |
+
"grad_norm": 0.08127617090940475,
|
| 1526 |
+
"learning_rate": 1.8872885702309283e-05,
|
| 1527 |
+
"loss": 0.0055,
|
| 1528 |
+
"step": 1085
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.08446338628438589,
|
| 1532 |
+
"grad_norm": 0.13204775750637054,
|
| 1533 |
+
"learning_rate": 1.886036224051913e-05,
|
| 1534 |
+
"loss": 0.0061,
|
| 1535 |
+
"step": 1090
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.08485083301046106,
|
| 1539 |
+
"grad_norm": 0.09941404312849045,
|
| 1540 |
+
"learning_rate": 1.884777379045853e-05,
|
| 1541 |
+
"loss": 0.0053,
|
| 1542 |
+
"step": 1095
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.08523827973653622,
|
| 1546 |
+
"grad_norm": 0.08837231993675232,
|
| 1547 |
+
"learning_rate": 1.883512044446023e-05,
|
| 1548 |
+
"loss": 0.0054,
|
| 1549 |
+
"step": 1100
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.08562572646261139,
|
| 1553 |
+
"grad_norm": 0.08981067687273026,
|
| 1554 |
+
"learning_rate": 1.8822402295332972e-05,
|
| 1555 |
+
"loss": 0.0053,
|
| 1556 |
+
"step": 1105
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.08601317318868655,
|
| 1560 |
+
"grad_norm": 0.1063075065612793,
|
| 1561 |
+
"learning_rate": 1.8809619436360816e-05,
|
| 1562 |
+
"loss": 0.0062,
|
| 1563 |
+
"step": 1110
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.08640061991476172,
|
| 1567 |
+
"grad_norm": 0.08444508165121078,
|
| 1568 |
+
"learning_rate": 1.879677196130244e-05,
|
| 1569 |
+
"loss": 0.0059,
|
| 1570 |
+
"step": 1115
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.08678806664083688,
|
| 1574 |
+
"grad_norm": 0.11189703643321991,
|
| 1575 |
+
"learning_rate": 1.8783859964390466e-05,
|
| 1576 |
+
"loss": 0.0059,
|
| 1577 |
+
"step": 1120
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.08717551336691205,
|
| 1581 |
+
"grad_norm": 0.09602108597755432,
|
| 1582 |
+
"learning_rate": 1.877088354033077e-05,
|
| 1583 |
+
"loss": 0.0061,
|
| 1584 |
+
"step": 1125
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.08756296009298721,
|
| 1588 |
+
"grad_norm": 0.08872901648283005,
|
| 1589 |
+
"learning_rate": 1.8757842784301786e-05,
|
| 1590 |
+
"loss": 0.0054,
|
| 1591 |
+
"step": 1130
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.08795040681906238,
|
| 1595 |
+
"grad_norm": 0.09550667554140091,
|
| 1596 |
+
"learning_rate": 1.874473779195379e-05,
|
| 1597 |
+
"loss": 0.0055,
|
| 1598 |
+
"step": 1135
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.08833785354513754,
|
| 1602 |
+
"grad_norm": 0.09804882854223251,
|
| 1603 |
+
"learning_rate": 1.873156865940823e-05,
|
| 1604 |
+
"loss": 0.0057,
|
| 1605 |
+
"step": 1140
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.08872530027121271,
|
| 1609 |
+
"grad_norm": 0.07303327322006226,
|
| 1610 |
+
"learning_rate": 1.8718335483257e-05,
|
| 1611 |
+
"loss": 0.0059,
|
| 1612 |
+
"step": 1145
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.08911274699728787,
|
| 1616 |
+
"grad_norm": 0.104513980448246,
|
| 1617 |
+
"learning_rate": 1.8705038360561724e-05,
|
| 1618 |
+
"loss": 0.0063,
|
| 1619 |
+
"step": 1150
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.08950019372336304,
|
| 1623 |
+
"grad_norm": 0.07896976172924042,
|
| 1624 |
+
"learning_rate": 1.869167738885307e-05,
|
| 1625 |
+
"loss": 0.0061,
|
| 1626 |
+
"step": 1155
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.0898876404494382,
|
| 1630 |
+
"grad_norm": 0.09948602318763733,
|
| 1631 |
+
"learning_rate": 1.8678252666130016e-05,
|
| 1632 |
+
"loss": 0.0054,
|
| 1633 |
+
"step": 1160
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.09027508717551337,
|
| 1637 |
+
"grad_norm": 0.1102101057767868,
|
| 1638 |
+
"learning_rate": 1.8664764290859136e-05,
|
| 1639 |
+
"loss": 0.0063,
|
| 1640 |
+
"step": 1165
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.09066253390158853,
|
| 1644 |
+
"grad_norm": 0.08791438490152359,
|
| 1645 |
+
"learning_rate": 1.8651212361973877e-05,
|
| 1646 |
+
"loss": 0.0055,
|
| 1647 |
+
"step": 1170
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.0910499806276637,
|
| 1651 |
+
"grad_norm": 0.08494678884744644,
|
| 1652 |
+
"learning_rate": 1.8637596978873834e-05,
|
| 1653 |
+
"loss": 0.0064,
|
| 1654 |
+
"step": 1175
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.09143742735373886,
|
| 1658 |
+
"grad_norm": 0.08456923067569733,
|
| 1659 |
+
"learning_rate": 1.8623918241424023e-05,
|
| 1660 |
+
"loss": 0.0051,
|
| 1661 |
+
"step": 1180
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.09182487407981403,
|
| 1665 |
+
"grad_norm": 0.10810911655426025,
|
| 1666 |
+
"learning_rate": 1.861017624995414e-05,
|
| 1667 |
+
"loss": 0.0055,
|
| 1668 |
+
"step": 1185
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.09221232080588919,
|
| 1672 |
+
"grad_norm": 0.10361585766077042,
|
| 1673 |
+
"learning_rate": 1.8596371105257834e-05,
|
| 1674 |
+
"loss": 0.006,
|
| 1675 |
+
"step": 1190
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.09259976753196436,
|
| 1679 |
+
"grad_norm": 0.0990578904747963,
|
| 1680 |
+
"learning_rate": 1.8582502908591977e-05,
|
| 1681 |
+
"loss": 0.0064,
|
| 1682 |
+
"step": 1195
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.09298721425803952,
|
| 1686 |
+
"grad_norm": 0.07855784147977829,
|
| 1687 |
+
"learning_rate": 1.8568571761675893e-05,
|
| 1688 |
+
"loss": 0.005,
|
| 1689 |
+
"step": 1200
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.09337466098411469,
|
| 1693 |
+
"grad_norm": 0.10020443052053452,
|
| 1694 |
+
"learning_rate": 1.8554577766690636e-05,
|
| 1695 |
+
"loss": 0.0058,
|
| 1696 |
+
"step": 1205
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.09376210771018985,
|
| 1700 |
+
"grad_norm": 0.07697867602109909,
|
| 1701 |
+
"learning_rate": 1.8540521026278232e-05,
|
| 1702 |
+
"loss": 0.0058,
|
| 1703 |
+
"step": 1210
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.094149554436265,
|
| 1707 |
+
"grad_norm": 0.07031143456697464,
|
| 1708 |
+
"learning_rate": 1.8526401643540924e-05,
|
| 1709 |
+
"loss": 0.0057,
|
| 1710 |
+
"step": 1215
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.09453700116234018,
|
| 1714 |
+
"grad_norm": 0.08743724226951599,
|
| 1715 |
+
"learning_rate": 1.8512219722040426e-05,
|
| 1716 |
+
"loss": 0.0061,
|
| 1717 |
+
"step": 1220
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.09492444788841534,
|
| 1721 |
+
"grad_norm": 0.11691045761108398,
|
| 1722 |
+
"learning_rate": 1.849797536579715e-05,
|
| 1723 |
+
"loss": 0.006,
|
| 1724 |
+
"step": 1225
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.09531189461449051,
|
| 1728 |
+
"grad_norm": 0.0990758165717125,
|
| 1729 |
+
"learning_rate": 1.8483668679289452e-05,
|
| 1730 |
+
"loss": 0.0058,
|
| 1731 |
+
"step": 1230
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.09569934134056567,
|
| 1735 |
+
"grad_norm": 0.07349522411823273,
|
| 1736 |
+
"learning_rate": 1.8469299767452864e-05,
|
| 1737 |
+
"loss": 0.005,
|
| 1738 |
+
"step": 1235
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.09608678806664084,
|
| 1742 |
+
"grad_norm": 0.08687637001276016,
|
| 1743 |
+
"learning_rate": 1.845486873567932e-05,
|
| 1744 |
+
"loss": 0.0063,
|
| 1745 |
+
"step": 1240
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.096474234792716,
|
| 1749 |
+
"grad_norm": 0.099228136241436,
|
| 1750 |
+
"learning_rate": 1.8440375689816387e-05,
|
| 1751 |
+
"loss": 0.0055,
|
| 1752 |
+
"step": 1245
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.09686168151879117,
|
| 1756 |
+
"grad_norm": 0.07230998575687408,
|
| 1757 |
+
"learning_rate": 1.8425820736166492e-05,
|
| 1758 |
+
"loss": 0.0058,
|
| 1759 |
+
"step": 1250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.09724912824486633,
|
| 1763 |
+
"grad_norm": 0.09425082802772522,
|
| 1764 |
+
"learning_rate": 1.8411203981486135e-05,
|
| 1765 |
+
"loss": 0.0063,
|
| 1766 |
+
"step": 1255
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.0976365749709415,
|
| 1770 |
+
"grad_norm": 0.07735039293766022,
|
| 1771 |
+
"learning_rate": 1.839652553298511e-05,
|
| 1772 |
+
"loss": 0.0058,
|
| 1773 |
+
"step": 1260
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.09802402169701666,
|
| 1777 |
+
"grad_norm": 0.09144142270088196,
|
| 1778 |
+
"learning_rate": 1.838178549832571e-05,
|
| 1779 |
+
"loss": 0.0066,
|
| 1780 |
+
"step": 1265
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.09841146842309183,
|
| 1784 |
+
"grad_norm": 0.14690975844860077,
|
| 1785 |
+
"learning_rate": 1.836698398562196e-05,
|
| 1786 |
+
"loss": 0.0051,
|
| 1787 |
+
"step": 1270
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.09879891514916699,
|
| 1791 |
+
"grad_norm": 0.12115617096424103,
|
| 1792 |
+
"learning_rate": 1.8352121103438804e-05,
|
| 1793 |
+
"loss": 0.0054,
|
| 1794 |
+
"step": 1275
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.09918636187524216,
|
| 1798 |
+
"grad_norm": 0.09853852540254593,
|
| 1799 |
+
"learning_rate": 1.8337196960791305e-05,
|
| 1800 |
+
"loss": 0.0057,
|
| 1801 |
+
"step": 1280
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.09957380860131732,
|
| 1805 |
+
"grad_norm": 0.11039669066667557,
|
| 1806 |
+
"learning_rate": 1.832221166714386e-05,
|
| 1807 |
+
"loss": 0.0058,
|
| 1808 |
+
"step": 1285
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.09996125532739249,
|
| 1812 |
+
"grad_norm": 0.08724901080131531,
|
| 1813 |
+
"learning_rate": 1.8307165332409404e-05,
|
| 1814 |
+
"loss": 0.0059,
|
| 1815 |
+
"step": 1290
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.10034870205346764,
|
| 1819 |
+
"grad_norm": 0.12327704578638077,
|
| 1820 |
+
"learning_rate": 1.829205806694857e-05,
|
| 1821 |
+
"loss": 0.0048,
|
| 1822 |
+
"step": 1295
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.10073614877954282,
|
| 1826 |
+
"grad_norm": 0.08107170462608337,
|
| 1827 |
+
"learning_rate": 1.827688998156891e-05,
|
| 1828 |
+
"loss": 0.0049,
|
| 1829 |
+
"step": 1300
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.10112359550561797,
|
| 1833 |
+
"grad_norm": 0.06302095204591751,
|
| 1834 |
+
"learning_rate": 1.8261661187524074e-05,
|
| 1835 |
+
"loss": 0.0046,
|
| 1836 |
+
"step": 1305
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.10151104223169315,
|
| 1840 |
+
"grad_norm": 0.1211981549859047,
|
| 1841 |
+
"learning_rate": 1.8246371796512995e-05,
|
| 1842 |
+
"loss": 0.0066,
|
| 1843 |
+
"step": 1310
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.1018984889577683,
|
| 1847 |
+
"grad_norm": 0.14916694164276123,
|
| 1848 |
+
"learning_rate": 1.8231021920679067e-05,
|
| 1849 |
+
"loss": 0.0047,
|
| 1850 |
+
"step": 1315
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.10228593568384348,
|
| 1854 |
+
"grad_norm": 0.08771459013223648,
|
| 1855 |
+
"learning_rate": 1.8215611672609316e-05,
|
| 1856 |
+
"loss": 0.0069,
|
| 1857 |
+
"step": 1320
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.10267338240991863,
|
| 1861 |
+
"grad_norm": 0.09507758915424347,
|
| 1862 |
+
"learning_rate": 1.8200141165333592e-05,
|
| 1863 |
+
"loss": 0.0051,
|
| 1864 |
+
"step": 1325
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.1030608291359938,
|
| 1868 |
+
"grad_norm": 0.07304011285305023,
|
| 1869 |
+
"learning_rate": 1.818461051232372e-05,
|
| 1870 |
+
"loss": 0.0049,
|
| 1871 |
+
"step": 1330
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.10344827586206896,
|
| 1875 |
+
"grad_norm": 0.11238119006156921,
|
| 1876 |
+
"learning_rate": 1.8169019827492684e-05,
|
| 1877 |
+
"loss": 0.0049,
|
| 1878 |
+
"step": 1335
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.10383572258814414,
|
| 1882 |
+
"grad_norm": 0.10092518478631973,
|
| 1883 |
+
"learning_rate": 1.8153369225193782e-05,
|
| 1884 |
+
"loss": 0.0056,
|
| 1885 |
+
"step": 1340
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.1042231693142193,
|
| 1889 |
+
"grad_norm": 0.0644020363688469,
|
| 1890 |
+
"learning_rate": 1.8137658820219787e-05,
|
| 1891 |
+
"loss": 0.0053,
|
| 1892 |
+
"step": 1345
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.10461061604029447,
|
| 1896 |
+
"grad_norm": 0.10352007299661636,
|
| 1897 |
+
"learning_rate": 1.8121888727802113e-05,
|
| 1898 |
+
"loss": 0.0051,
|
| 1899 |
+
"step": 1350
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.10499806276636962,
|
| 1903 |
+
"grad_norm": 0.0957900807261467,
|
| 1904 |
+
"learning_rate": 1.810605906360996e-05,
|
| 1905 |
+
"loss": 0.0046,
|
| 1906 |
+
"step": 1355
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.1053855094924448,
|
| 1910 |
+
"grad_norm": 0.07484105229377747,
|
| 1911 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 1912 |
+
"loss": 0.0046,
|
| 1913 |
+
"step": 1360
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.10577295621851995,
|
| 1917 |
+
"grad_norm": 0.09927642345428467,
|
| 1918 |
+
"learning_rate": 1.807422148476289e-05,
|
| 1919 |
+
"loss": 0.0053,
|
| 1920 |
+
"step": 1365
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.10616040294459511,
|
| 1924 |
+
"grad_norm": 0.07936850935220718,
|
| 1925 |
+
"learning_rate": 1.805821380362768e-05,
|
| 1926 |
+
"loss": 0.0042,
|
| 1927 |
+
"step": 1370
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.10654784967067028,
|
| 1931 |
+
"grad_norm": 0.08534638583660126,
|
| 1932 |
+
"learning_rate": 1.804214701775569e-05,
|
| 1933 |
+
"loss": 0.0053,
|
| 1934 |
+
"step": 1375
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.10693529639674544,
|
| 1938 |
+
"grad_norm": 0.09789389371871948,
|
| 1939 |
+
"learning_rate": 1.802602124499229e-05,
|
| 1940 |
+
"loss": 0.0052,
|
| 1941 |
+
"step": 1380
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.10732274312282061,
|
| 1945 |
+
"grad_norm": 0.10937155038118362,
|
| 1946 |
+
"learning_rate": 1.8009836603615492e-05,
|
| 1947 |
+
"loss": 0.005,
|
| 1948 |
+
"step": 1385
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.10771018984889577,
|
| 1952 |
+
"grad_norm": 0.09280149638652802,
|
| 1953 |
+
"learning_rate": 1.7993593212335098e-05,
|
| 1954 |
+
"loss": 0.0058,
|
| 1955 |
+
"step": 1390
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.10809763657497094,
|
| 1959 |
+
"grad_norm": 0.08343416452407837,
|
| 1960 |
+
"learning_rate": 1.7977291190291827e-05,
|
| 1961 |
+
"loss": 0.0052,
|
| 1962 |
+
"step": 1395
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.1084850833010461,
|
| 1966 |
+
"grad_norm": 0.10159525275230408,
|
| 1967 |
+
"learning_rate": 1.796093065705644e-05,
|
| 1968 |
+
"loss": 0.0043,
|
| 1969 |
+
"step": 1400
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.10887253002712127,
|
| 1973 |
+
"grad_norm": 0.06880492717027664,
|
| 1974 |
+
"learning_rate": 1.794451173262885e-05,
|
| 1975 |
+
"loss": 0.0048,
|
| 1976 |
+
"step": 1405
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.10925997675319643,
|
| 1980 |
+
"grad_norm": 0.07566852122545242,
|
| 1981 |
+
"learning_rate": 1.7928034537437263e-05,
|
| 1982 |
+
"loss": 0.0056,
|
| 1983 |
+
"step": 1410
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.1096474234792716,
|
| 1987 |
+
"grad_norm": 0.08274251967668533,
|
| 1988 |
+
"learning_rate": 1.791149919233728e-05,
|
| 1989 |
+
"loss": 0.0053,
|
| 1990 |
+
"step": 1415
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.11003487020534676,
|
| 1994 |
+
"grad_norm": 0.0768815353512764,
|
| 1995 |
+
"learning_rate": 1.789490581861102e-05,
|
| 1996 |
+
"loss": 0.0045,
|
| 1997 |
+
"step": 1420
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.11042231693142193,
|
| 2001 |
+
"grad_norm": 0.11294172704219818,
|
| 2002 |
+
"learning_rate": 1.787825453796622e-05,
|
| 2003 |
+
"loss": 0.0059,
|
| 2004 |
+
"step": 1425
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.11080976365749709,
|
| 2008 |
+
"grad_norm": 0.15366220474243164,
|
| 2009 |
+
"learning_rate": 1.786154547253535e-05,
|
| 2010 |
+
"loss": 0.0054,
|
| 2011 |
+
"step": 1430
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.11119721038357226,
|
| 2015 |
+
"grad_norm": 0.09102647006511688,
|
| 2016 |
+
"learning_rate": 1.7844778744874715e-05,
|
| 2017 |
+
"loss": 0.0052,
|
| 2018 |
+
"step": 1435
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.11158465710964742,
|
| 2022 |
+
"grad_norm": 0.12378168106079102,
|
| 2023 |
+
"learning_rate": 1.782795447796356e-05,
|
| 2024 |
+
"loss": 0.0057,
|
| 2025 |
+
"step": 1440
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.11197210383572259,
|
| 2029 |
+
"grad_norm": 0.08235283195972443,
|
| 2030 |
+
"learning_rate": 1.781107279520316e-05,
|
| 2031 |
+
"loss": 0.0055,
|
| 2032 |
+
"step": 1445
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.11235955056179775,
|
| 2036 |
+
"grad_norm": 0.0910840630531311,
|
| 2037 |
+
"learning_rate": 1.7794133820415916e-05,
|
| 2038 |
+
"loss": 0.0044,
|
| 2039 |
+
"step": 1450
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.11274699728787292,
|
| 2043 |
+
"grad_norm": 0.09277354925870895,
|
| 2044 |
+
"learning_rate": 1.7777137677844463e-05,
|
| 2045 |
+
"loss": 0.0048,
|
| 2046 |
+
"step": 1455
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.11313444401394808,
|
| 2050 |
+
"grad_norm": 0.08550482988357544,
|
| 2051 |
+
"learning_rate": 1.7760084492150733e-05,
|
| 2052 |
+
"loss": 0.0047,
|
| 2053 |
+
"step": 1460
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.11352189074002325,
|
| 2057 |
+
"grad_norm": 0.10471171885728836,
|
| 2058 |
+
"learning_rate": 1.7742974388415054e-05,
|
| 2059 |
+
"loss": 0.006,
|
| 2060 |
+
"step": 1465
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.11390933746609841,
|
| 2064 |
+
"grad_norm": 0.07290663570165634,
|
| 2065 |
+
"learning_rate": 1.7725807492135238e-05,
|
| 2066 |
+
"loss": 0.0049,
|
| 2067 |
+
"step": 1470
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.11429678419217358,
|
| 2071 |
+
"grad_norm": 0.10590043663978577,
|
| 2072 |
+
"learning_rate": 1.770858392922565e-05,
|
| 2073 |
+
"loss": 0.0046,
|
| 2074 |
+
"step": 1475
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.11468423091824874,
|
| 2078 |
+
"grad_norm": 0.10638522356748581,
|
| 2079 |
+
"learning_rate": 1.769130382601629e-05,
|
| 2080 |
+
"loss": 0.0051,
|
| 2081 |
+
"step": 1480
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.11507167764432391,
|
| 2085 |
+
"grad_norm": 0.1076829582452774,
|
| 2086 |
+
"learning_rate": 1.7673967309251868e-05,
|
| 2087 |
+
"loss": 0.0054,
|
| 2088 |
+
"step": 1485
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.11545912437039907,
|
| 2092 |
+
"grad_norm": 0.06817775219678879,
|
| 2093 |
+
"learning_rate": 1.765657450609087e-05,
|
| 2094 |
+
"loss": 0.0043,
|
| 2095 |
+
"step": 1490
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.11584657109647424,
|
| 2099 |
+
"grad_norm": 0.08475981652736664,
|
| 2100 |
+
"learning_rate": 1.7639125544104624e-05,
|
| 2101 |
+
"loss": 0.0056,
|
| 2102 |
+
"step": 1495
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.1162340178225494,
|
| 2106 |
+
"grad_norm": 0.13820545375347137,
|
| 2107 |
+
"learning_rate": 1.7621620551276366e-05,
|
| 2108 |
+
"loss": 0.0043,
|
| 2109 |
+
"step": 1500
|
| 2110 |
+
}
|
| 2111 |
+
],
|
| 2112 |
+
"logging_steps": 5,
|
| 2113 |
+
"max_steps": 6000,
|
| 2114 |
+
"num_input_tokens_seen": 0,
|
| 2115 |
+
"num_train_epochs": 1,
|
| 2116 |
+
"save_steps": 500,
|
| 2117 |
+
"stateful_callbacks": {
|
| 2118 |
+
"TrainerControl": {
|
| 2119 |
+
"args": {
|
| 2120 |
+
"should_epoch_stop": false,
|
| 2121 |
+
"should_evaluate": false,
|
| 2122 |
+
"should_log": false,
|
| 2123 |
+
"should_save": true,
|
| 2124 |
+
"should_training_stop": false
|
| 2125 |
+
},
|
| 2126 |
+
"attributes": {}
|
| 2127 |
+
}
|
| 2128 |
+
},
|
| 2129 |
+
"total_flos": 8.215368583714387e+21,
|
| 2130 |
+
"train_batch_size": 8,
|
| 2131 |
+
"trial_name": null,
|
| 2132 |
+
"trial_params": null
|
| 2133 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15ba7f8c8e5c29f3f4952d1b15df303a1968d6ad20ff6ecbcaa90e1564fad780
|
| 3 |
+
size 7160
|