Upload Mamba1 (368M) pretrained on FineWeb-Edu 10BT (4768 steps)
Browse files- config.json +37 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +3375 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MambaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"conv_kernel": 4,
|
| 7 |
+
"dt_init_floor": 0.0001,
|
| 8 |
+
"dt_init_scheme": "random",
|
| 9 |
+
"dt_max": 0.1,
|
| 10 |
+
"dt_min": 0.001,
|
| 11 |
+
"dt_rank": 64,
|
| 12 |
+
"dt_scale": 1.0,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"expand": 2,
|
| 16 |
+
"fuse_cross_entropy": true,
|
| 17 |
+
"fuse_linear_cross_entropy": false,
|
| 18 |
+
"fuse_norm": true,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 2048,
|
| 23 |
+
"model_type": "mamba",
|
| 24 |
+
"norm_eps": 1e-05,
|
| 25 |
+
"num_hidden_layers": 48,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"rescale_prenorm_residual": false,
|
| 28 |
+
"residual_in_fp32": false,
|
| 29 |
+
"state_size": 16,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"transformers_version": "5.5.0",
|
| 32 |
+
"use_bias": false,
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"use_conv_bias": true,
|
| 35 |
+
"use_l2warp": false,
|
| 36 |
+
"vocab_size": 32000
|
| 37 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "5.5.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:332cfc61c15a6738c0e1feca1b706d6688d7804134bf38c5579f0b01711b900b
|
| 3 |
+
size 771184168
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "<unk>",
|
| 10 |
+
"sp_model_kwargs": {},
|
| 11 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 12 |
+
"unk_token": "<unk>",
|
| 13 |
+
"use_default_system_prompt": false
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4768,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0020973154362416107,
|
| 14 |
+
"grad_norm": 432.3580017089844,
|
| 15 |
+
"learning_rate": 7.500000000000001e-05,
|
| 16 |
+
"loss": 2560.12109375,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0041946308724832215,
|
| 21 |
+
"grad_norm": 248.64732360839844,
|
| 22 |
+
"learning_rate": 0.00015833333333333332,
|
| 23 |
+
"loss": 2143.7953125,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.006291946308724832,
|
| 28 |
+
"grad_norm": 132.24789428710938,
|
| 29 |
+
"learning_rate": 0.00024166666666666667,
|
| 30 |
+
"loss": 1870.5203125,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.008389261744966443,
|
| 35 |
+
"grad_norm": 167.39337158203125,
|
| 36 |
+
"learning_rate": 0.00032500000000000004,
|
| 37 |
+
"loss": 1728.409765625,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.010486577181208054,
|
| 42 |
+
"grad_norm": 139.81005859375,
|
| 43 |
+
"learning_rate": 0.00039999996012889783,
|
| 44 |
+
"loss": 1605.034765625,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.012583892617449664,
|
| 49 |
+
"grad_norm": 165.83798217773438,
|
| 50 |
+
"learning_rate": 0.0003999951756180062,
|
| 51 |
+
"loss": 1494.68759765625,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.014681208053691275,
|
| 56 |
+
"grad_norm": 107.8211669921875,
|
| 57 |
+
"learning_rate": 0.00039998241712954386,
|
| 58 |
+
"loss": 1407.76708984375,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.016778523489932886,
|
| 63 |
+
"grad_norm": 106.40216827392578,
|
| 64 |
+
"learning_rate": 0.00039996168522872554,
|
| 65 |
+
"loss": 1347.30556640625,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.018875838926174497,
|
| 70 |
+
"grad_norm": 107.21435546875,
|
| 71 |
+
"learning_rate": 0.00039993298083399625,
|
| 72 |
+
"loss": 1307.0609375,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.02097315436241611,
|
| 77 |
+
"grad_norm": 82.80896759033203,
|
| 78 |
+
"learning_rate": 0.0003998963052169914,
|
| 79 |
+
"loss": 1265.7685546875,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02307046979865772,
|
| 84 |
+
"grad_norm": 112.75000762939453,
|
| 85 |
+
"learning_rate": 0.0003998516600024797,
|
| 86 |
+
"loss": 1228.41376953125,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.025167785234899327,
|
| 91 |
+
"grad_norm": 109.4422836303711,
|
| 92 |
+
"learning_rate": 0.00039979904716829157,
|
| 93 |
+
"loss": 1204.2453125,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.02726510067114094,
|
| 98 |
+
"grad_norm": 134.94847106933594,
|
| 99 |
+
"learning_rate": 0.0003997384690452316,
|
| 100 |
+
"loss": 1183.50576171875,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.02936241610738255,
|
| 105 |
+
"grad_norm": 68.75386047363281,
|
| 106 |
+
"learning_rate": 0.0003996699283169749,
|
| 107 |
+
"loss": 1160.85048828125,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.031459731543624164,
|
| 112 |
+
"grad_norm": 128.99111938476562,
|
| 113 |
+
"learning_rate": 0.0003995934280199486,
|
| 114 |
+
"loss": 1137.86796875,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.03355704697986577,
|
| 119 |
+
"grad_norm": 96.78877258300781,
|
| 120 |
+
"learning_rate": 0.00039950897154319715,
|
| 121 |
+
"loss": 1123.6431640625,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03565436241610738,
|
| 126 |
+
"grad_norm": 99.28411865234375,
|
| 127 |
+
"learning_rate": 0.0003994165626282323,
|
| 128 |
+
"loss": 1115.12412109375,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.037751677852348994,
|
| 133 |
+
"grad_norm": 89.26158905029297,
|
| 134 |
+
"learning_rate": 0.0003993162053688671,
|
| 135 |
+
"loss": 1099.6396484375,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.0398489932885906,
|
| 140 |
+
"grad_norm": 86.16292572021484,
|
| 141 |
+
"learning_rate": 0.0003992079042110349,
|
| 142 |
+
"loss": 1081.5064453125,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.04194630872483222,
|
| 147 |
+
"grad_norm": 117.42514038085938,
|
| 148 |
+
"learning_rate": 0.0003990916639525919,
|
| 149 |
+
"loss": 1074.983984375,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.044043624161073824,
|
| 154 |
+
"grad_norm": 78.53323364257812,
|
| 155 |
+
"learning_rate": 0.0003989674897431053,
|
| 156 |
+
"loss": 1065.10068359375,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.04614093959731544,
|
| 161 |
+
"grad_norm": 101.44924926757812,
|
| 162 |
+
"learning_rate": 0.00039883538708362454,
|
| 163 |
+
"loss": 1046.9310546875,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04823825503355705,
|
| 168 |
+
"grad_norm": 82.18006134033203,
|
| 169 |
+
"learning_rate": 0.0003986953618264376,
|
| 170 |
+
"loss": 1035.0302734375,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.050335570469798654,
|
| 175 |
+
"grad_norm": 105.84237670898438,
|
| 176 |
+
"learning_rate": 0.0003985474201748124,
|
| 177 |
+
"loss": 1032.61591796875,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.05243288590604027,
|
| 182 |
+
"grad_norm": 73.59429168701172,
|
| 183 |
+
"learning_rate": 0.00039839156868272125,
|
| 184 |
+
"loss": 1025.34921875,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.05453020134228188,
|
| 189 |
+
"grad_norm": 89.02239227294922,
|
| 190 |
+
"learning_rate": 0.0003982278142545509,
|
| 191 |
+
"loss": 1014.68466796875,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.05662751677852349,
|
| 196 |
+
"grad_norm": 82.29888916015625,
|
| 197 |
+
"learning_rate": 0.00039805616414479654,
|
| 198 |
+
"loss": 1002.25478515625,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.0587248322147651,
|
| 203 |
+
"grad_norm": 62.16850662231445,
|
| 204 |
+
"learning_rate": 0.00039787662595774047,
|
| 205 |
+
"loss": 1002.7884765625,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.060822147651006714,
|
| 210 |
+
"grad_norm": 79.44703674316406,
|
| 211 |
+
"learning_rate": 0.00039768920764711517,
|
| 212 |
+
"loss": 998.8552734375,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.06291946308724833,
|
| 217 |
+
"grad_norm": 64.72073364257812,
|
| 218 |
+
"learning_rate": 0.00039749391751575094,
|
| 219 |
+
"loss": 985.01357421875,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.06501677852348993,
|
| 224 |
+
"grad_norm": 68.88458251953125,
|
| 225 |
+
"learning_rate": 0.00039729076421520827,
|
| 226 |
+
"loss": 974.8654296875,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.06711409395973154,
|
| 231 |
+
"grad_norm": 67.44086456298828,
|
| 232 |
+
"learning_rate": 0.0003970797567453941,
|
| 233 |
+
"loss": 971.33193359375,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.06921140939597316,
|
| 238 |
+
"grad_norm": 78.49050903320312,
|
| 239 |
+
"learning_rate": 0.0003968609044541637,
|
| 240 |
+
"loss": 971.046875,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.07130872483221476,
|
| 245 |
+
"grad_norm": 65.71349334716797,
|
| 246 |
+
"learning_rate": 0.0003966342170369062,
|
| 247 |
+
"loss": 961.2708984375,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.07340604026845637,
|
| 252 |
+
"grad_norm": 72.90547943115234,
|
| 253 |
+
"learning_rate": 0.000396399704536115,
|
| 254 |
+
"loss": 953.9611328125,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.07550335570469799,
|
| 259 |
+
"grad_norm": 59.775489807128906,
|
| 260 |
+
"learning_rate": 0.0003961573773409431,
|
| 261 |
+
"loss": 950.950390625,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.0776006711409396,
|
| 266 |
+
"grad_norm": 69.97833251953125,
|
| 267 |
+
"learning_rate": 0.00039590724618674295,
|
| 268 |
+
"loss": 951.301953125,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0796979865771812,
|
| 273 |
+
"grad_norm": 57.928466796875,
|
| 274 |
+
"learning_rate": 0.00039564932215459036,
|
| 275 |
+
"loss": 938.84296875,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.08179530201342282,
|
| 280 |
+
"grad_norm": 63.261505126953125,
|
| 281 |
+
"learning_rate": 0.0003953836166707941,
|
| 282 |
+
"loss": 933.84169921875,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.08389261744966443,
|
| 287 |
+
"grad_norm": 54.047210693359375,
|
| 288 |
+
"learning_rate": 0.00039511014150638945,
|
| 289 |
+
"loss": 926.5919921875,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.08598993288590603,
|
| 294 |
+
"grad_norm": 78.32682037353516,
|
| 295 |
+
"learning_rate": 0.00039482890877661685,
|
| 296 |
+
"loss": 925.966015625,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.08808724832214765,
|
| 301 |
+
"grad_norm": 47.812320709228516,
|
| 302 |
+
"learning_rate": 0.0003945399309403852,
|
| 303 |
+
"loss": 919.83203125,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.09018456375838926,
|
| 308 |
+
"grad_norm": 54.73347473144531,
|
| 309 |
+
"learning_rate": 0.00039424322079971956,
|
| 310 |
+
"loss": 913.32080078125,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.09228187919463088,
|
| 315 |
+
"grad_norm": 50.86581039428711,
|
| 316 |
+
"learning_rate": 0.00039393879149919467,
|
| 317 |
+
"loss": 908.5560546875,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.09437919463087248,
|
| 322 |
+
"grad_norm": 59.764652252197266,
|
| 323 |
+
"learning_rate": 0.0003936266565253521,
|
| 324 |
+
"loss": 913.7609375,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.0964765100671141,
|
| 329 |
+
"grad_norm": 56.112552642822266,
|
| 330 |
+
"learning_rate": 0.00039330682970610276,
|
| 331 |
+
"loss": 905.3310546875,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.09857382550335571,
|
| 336 |
+
"grad_norm": 56.61573028564453,
|
| 337 |
+
"learning_rate": 0.00039297932521011465,
|
| 338 |
+
"loss": 899.1501953125,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.10067114093959731,
|
| 343 |
+
"grad_norm": 58.438987731933594,
|
| 344 |
+
"learning_rate": 0.0003926441575461852,
|
| 345 |
+
"loss": 897.4177734375,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.10276845637583892,
|
| 350 |
+
"grad_norm": 57.88336944580078,
|
| 351 |
+
"learning_rate": 0.0003923013415625978,
|
| 352 |
+
"loss": 899.0765625,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.10486577181208054,
|
| 357 |
+
"grad_norm": 53.40110397338867,
|
| 358 |
+
"learning_rate": 0.00039195089244646516,
|
| 359 |
+
"loss": 891.66181640625,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.10696308724832215,
|
| 364 |
+
"grad_norm": 52.10205078125,
|
| 365 |
+
"learning_rate": 0.00039159282572305543,
|
| 366 |
+
"loss": 884.9646484375,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.10906040268456375,
|
| 371 |
+
"grad_norm": 56.75968933105469,
|
| 372 |
+
"learning_rate": 0.00039122715725510506,
|
| 373 |
+
"loss": 882.880078125,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.11115771812080537,
|
| 378 |
+
"grad_norm": 46.76315689086914,
|
| 379 |
+
"learning_rate": 0.00039085390324211563,
|
| 380 |
+
"loss": 886.416015625,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.11325503355704698,
|
| 385 |
+
"grad_norm": 61.728546142578125,
|
| 386 |
+
"learning_rate": 0.0003904730802196368,
|
| 387 |
+
"loss": 881.79140625,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.11535234899328858,
|
| 392 |
+
"grad_norm": 49.4840087890625,
|
| 393 |
+
"learning_rate": 0.00039008470505853306,
|
| 394 |
+
"loss": 874.3978515625,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.1174496644295302,
|
| 399 |
+
"grad_norm": 52.824913024902344,
|
| 400 |
+
"learning_rate": 0.00038968879496423687,
|
| 401 |
+
"loss": 870.12294921875,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.11954697986577181,
|
| 406 |
+
"grad_norm": 51.651973724365234,
|
| 407 |
+
"learning_rate": 0.000389285367475986,
|
| 408 |
+
"loss": 871.175,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.12164429530201343,
|
| 413 |
+
"grad_norm": 55.0900764465332,
|
| 414 |
+
"learning_rate": 0.0003888744404660472,
|
| 415 |
+
"loss": 868.1658203125,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.12374161073825503,
|
| 420 |
+
"grad_norm": 46.64694595336914,
|
| 421 |
+
"learning_rate": 0.00038845603213892344,
|
| 422 |
+
"loss": 859.77978515625,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.12583892617449666,
|
| 427 |
+
"grad_norm": 48.35624313354492,
|
| 428 |
+
"learning_rate": 0.0003880301610305485,
|
| 429 |
+
"loss": 861.89365234375,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.12793624161073824,
|
| 434 |
+
"grad_norm": 48.568016052246094,
|
| 435 |
+
"learning_rate": 0.00038759684600746496,
|
| 436 |
+
"loss": 864.978125,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.13003355704697986,
|
| 441 |
+
"grad_norm": 46.272010803222656,
|
| 442 |
+
"learning_rate": 0.00038715610626598884,
|
| 443 |
+
"loss": 856.43916015625,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.13213087248322147,
|
| 448 |
+
"grad_norm": 49.437721252441406,
|
| 449 |
+
"learning_rate": 0.00038670796133135916,
|
| 450 |
+
"loss": 853.705859375,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.1342281879194631,
|
| 455 |
+
"grad_norm": 51.41856002807617,
|
| 456 |
+
"learning_rate": 0.0003862524310568727,
|
| 457 |
+
"loss": 850.9275390625,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.1363255033557047,
|
| 462 |
+
"grad_norm": 50.722129821777344,
|
| 463 |
+
"learning_rate": 0.0003857895356230049,
|
| 464 |
+
"loss": 856.30986328125,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.13842281879194632,
|
| 469 |
+
"grad_norm": 51.90019989013672,
|
| 470 |
+
"learning_rate": 0.00038531929553651525,
|
| 471 |
+
"loss": 850.203125,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.14052013422818793,
|
| 476 |
+
"grad_norm": 49.493263244628906,
|
| 477 |
+
"learning_rate": 0.0003848417316295394,
|
| 478 |
+
"loss": 842.3240234375,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.14261744966442952,
|
| 483 |
+
"grad_norm": 43.617515563964844,
|
| 484 |
+
"learning_rate": 0.00038435686505866595,
|
| 485 |
+
"loss": 835.8236328125,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.14471476510067113,
|
| 490 |
+
"grad_norm": 40.38718032836914,
|
| 491 |
+
"learning_rate": 0.0003838647173039994,
|
| 492 |
+
"loss": 846.9615234375,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.14681208053691275,
|
| 497 |
+
"grad_norm": 39.99060821533203,
|
| 498 |
+
"learning_rate": 0.00038336531016820805,
|
| 499 |
+
"loss": 837.17314453125,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.14890939597315436,
|
| 504 |
+
"grad_norm": 45.416568756103516,
|
| 505 |
+
"learning_rate": 0.000382858665775559,
|
| 506 |
+
"loss": 836.13984375,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.15100671140939598,
|
| 511 |
+
"grad_norm": 41.88158416748047,
|
| 512 |
+
"learning_rate": 0.0003823448065709373,
|
| 513 |
+
"loss": 830.47421875,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.1531040268456376,
|
| 518 |
+
"grad_norm": 48.792327880859375,
|
| 519 |
+
"learning_rate": 0.0003818237553188516,
|
| 520 |
+
"loss": 838.256640625,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.1552013422818792,
|
| 525 |
+
"grad_norm": 47.30402755737305,
|
| 526 |
+
"learning_rate": 0.00038129553510242626,
|
| 527 |
+
"loss": 832.5138671875,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.1572986577181208,
|
| 532 |
+
"grad_norm": 46.606544494628906,
|
| 533 |
+
"learning_rate": 0.00038076016932237823,
|
| 534 |
+
"loss": 817.96171875,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.1593959731543624,
|
| 539 |
+
"grad_norm": 42.48833465576172,
|
| 540 |
+
"learning_rate": 0.0003802176816959805,
|
| 541 |
+
"loss": 822.3994140625,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.16149328859060402,
|
| 546 |
+
"grad_norm": 49.13645553588867,
|
| 547 |
+
"learning_rate": 0.00037966809625601146,
|
| 548 |
+
"loss": 826.9443359375,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.16359060402684564,
|
| 553 |
+
"grad_norm": 48.193199157714844,
|
| 554 |
+
"learning_rate": 0.0003791114373496902,
|
| 555 |
+
"loss": 821.3197265625,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.16568791946308725,
|
| 560 |
+
"grad_norm": 49.94052505493164,
|
| 561 |
+
"learning_rate": 0.00037854772963759786,
|
| 562 |
+
"loss": 814.4888671875,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.16778523489932887,
|
| 567 |
+
"grad_norm": 42.485595703125,
|
| 568 |
+
"learning_rate": 0.0003779769980925852,
|
| 569 |
+
"loss": 811.553369140625,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.16988255033557048,
|
| 574 |
+
"grad_norm": 44.533050537109375,
|
| 575 |
+
"learning_rate": 0.0003773992679986661,
|
| 576 |
+
"loss": 828.06875,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.17197986577181207,
|
| 581 |
+
"grad_norm": 41.512874603271484,
|
| 582 |
+
"learning_rate": 0.00037681456494989785,
|
| 583 |
+
"loss": 813.058349609375,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.17407718120805368,
|
| 588 |
+
"grad_norm": 42.67609405517578,
|
| 589 |
+
"learning_rate": 0.00037622291484924676,
|
| 590 |
+
"loss": 808.00771484375,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.1761744966442953,
|
| 595 |
+
"grad_norm": 45.48208999633789,
|
| 596 |
+
"learning_rate": 0.00037562434390744123,
|
| 597 |
+
"loss": 810.965771484375,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.1782718120805369,
|
| 602 |
+
"grad_norm": 43.91945266723633,
|
| 603 |
+
"learning_rate": 0.00037501887864180994,
|
| 604 |
+
"loss": 816.663232421875,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.18036912751677853,
|
| 609 |
+
"grad_norm": 49.31304168701172,
|
| 610 |
+
"learning_rate": 0.00037440654587510774,
|
| 611 |
+
"loss": 807.310546875,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.18246644295302014,
|
| 616 |
+
"grad_norm": 36.273887634277344,
|
| 617 |
+
"learning_rate": 0.00037378737273432696,
|
| 618 |
+
"loss": 798.728369140625,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.18456375838926176,
|
| 623 |
+
"grad_norm": 44.13105392456055,
|
| 624 |
+
"learning_rate": 0.0003731613866494956,
|
| 625 |
+
"loss": 805.8744140625,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.18666107382550334,
|
| 630 |
+
"grad_norm": 45.374900817871094,
|
| 631 |
+
"learning_rate": 0.00037252861535246273,
|
| 632 |
+
"loss": 806.17021484375,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.18875838926174496,
|
| 637 |
+
"grad_norm": 41.498138427734375,
|
| 638 |
+
"learning_rate": 0.0003718890868756691,
|
| 639 |
+
"loss": 798.01435546875,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.19085570469798657,
|
| 644 |
+
"grad_norm": 44.652252197265625,
|
| 645 |
+
"learning_rate": 0.00037124282955090603,
|
| 646 |
+
"loss": 797.1451171875,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.1929530201342282,
|
| 651 |
+
"grad_norm": 41.43980026245117,
|
| 652 |
+
"learning_rate": 0.0003705898720080597,
|
| 653 |
+
"loss": 803.592626953125,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.1950503355704698,
|
| 658 |
+
"grad_norm": 44.510902404785156,
|
| 659 |
+
"learning_rate": 0.0003699302431738433,
|
| 660 |
+
"loss": 797.47109375,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.19714765100671142,
|
| 665 |
+
"grad_norm": 37.388824462890625,
|
| 666 |
+
"learning_rate": 0.0003692639722705152,
|
| 667 |
+
"loss": 790.10703125,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.19924496644295303,
|
| 672 |
+
"grad_norm": 36.10209655761719,
|
| 673 |
+
"learning_rate": 0.00036859108881458436,
|
| 674 |
+
"loss": 789.671240234375,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.20134228187919462,
|
| 679 |
+
"grad_norm": 36.71262741088867,
|
| 680 |
+
"learning_rate": 0.0003679116226155031,
|
| 681 |
+
"loss": 797.35458984375,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.20343959731543623,
|
| 686 |
+
"grad_norm": 43.58747482299805,
|
| 687 |
+
"learning_rate": 0.0003672256037743462,
|
| 688 |
+
"loss": 787.1970703125,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.20553691275167785,
|
| 693 |
+
"grad_norm": 38.86661148071289,
|
| 694 |
+
"learning_rate": 0.0003665330626824772,
|
| 695 |
+
"loss": 785.28095703125,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.20763422818791946,
|
| 700 |
+
"grad_norm": 37.13184356689453,
|
| 701 |
+
"learning_rate": 0.00036583403002020274,
|
| 702 |
+
"loss": 784.462646484375,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.20973154362416108,
|
| 707 |
+
"grad_norm": 40.659400939941406,
|
| 708 |
+
"learning_rate": 0.00036512853675541246,
|
| 709 |
+
"loss": 791.35859375,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.2118288590604027,
|
| 714 |
+
"grad_norm": 44.29231643676758,
|
| 715 |
+
"learning_rate": 0.00036441661414220785,
|
| 716 |
+
"loss": 784.15751953125,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.2139261744966443,
|
| 721 |
+
"grad_norm": 40.54804611206055,
|
| 722 |
+
"learning_rate": 0.0003636982937195172,
|
| 723 |
+
"loss": 782.91201171875,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.2160234899328859,
|
| 728 |
+
"grad_norm": 37.70088577270508,
|
| 729 |
+
"learning_rate": 0.0003629736073096987,
|
| 730 |
+
"loss": 782.441162109375,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.2181208053691275,
|
| 735 |
+
"grad_norm": 36.9510612487793,
|
| 736 |
+
"learning_rate": 0.0003622425870171304,
|
| 737 |
+
"loss": 786.77060546875,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.22021812080536912,
|
| 742 |
+
"grad_norm": 38.41440963745117,
|
| 743 |
+
"learning_rate": 0.0003615052652267882,
|
| 744 |
+
"loss": 778.93291015625,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.22231543624161074,
|
| 749 |
+
"grad_norm": 43.160770416259766,
|
| 750 |
+
"learning_rate": 0.000360761674602811,
|
| 751 |
+
"loss": 775.032421875,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.22441275167785235,
|
| 756 |
+
"grad_norm": 38.03440856933594,
|
| 757 |
+
"learning_rate": 0.0003600118480870538,
|
| 758 |
+
"loss": 770.278173828125,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.22651006711409397,
|
| 763 |
+
"grad_norm": 38.17487716674805,
|
| 764 |
+
"learning_rate": 0.0003592558188976279,
|
| 765 |
+
"loss": 786.5306640625,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.22860738255033558,
|
| 770 |
+
"grad_norm": 39.2180061340332,
|
| 771 |
+
"learning_rate": 0.00035849362052743004,
|
| 772 |
+
"loss": 780.42021484375,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.23070469798657717,
|
| 777 |
+
"grad_norm": 36.615989685058594,
|
| 778 |
+
"learning_rate": 0.00035772528674265803,
|
| 779 |
+
"loss": 773.95361328125,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.23280201342281878,
|
| 784 |
+
"grad_norm": 37.757266998291016,
|
| 785 |
+
"learning_rate": 0.000356950851581315,
|
| 786 |
+
"loss": 767.45908203125,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.2348993288590604,
|
| 791 |
+
"grad_norm": 34.517276763916016,
|
| 792 |
+
"learning_rate": 0.0003561703493517017,
|
| 793 |
+
"loss": 778.86240234375,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.236996644295302,
|
| 798 |
+
"grad_norm": 35.07598114013672,
|
| 799 |
+
"learning_rate": 0.00035538381463089645,
|
| 800 |
+
"loss": 772.373095703125,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.23909395973154363,
|
| 805 |
+
"grad_norm": 36.75849151611328,
|
| 806 |
+
"learning_rate": 0.0003545912822632232,
|
| 807 |
+
"loss": 766.216015625,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.24119127516778524,
|
| 812 |
+
"grad_norm": 35.139984130859375,
|
| 813 |
+
"learning_rate": 0.0003537927873587081,
|
| 814 |
+
"loss": 763.338525390625,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.24328859060402686,
|
| 819 |
+
"grad_norm": 36.147621154785156,
|
| 820 |
+
"learning_rate": 0.000352988365291524,
|
| 821 |
+
"loss": 773.221142578125,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.24538590604026847,
|
| 826 |
+
"grad_norm": 40.629539489746094,
|
| 827 |
+
"learning_rate": 0.0003521780516984234,
|
| 828 |
+
"loss": 766.941748046875,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.24748322147651006,
|
| 833 |
+
"grad_norm": 33.118160247802734,
|
| 834 |
+
"learning_rate": 0.00035136188247715967,
|
| 835 |
+
"loss": 761.17802734375,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.24958053691275167,
|
| 840 |
+
"grad_norm": 33.310420989990234,
|
| 841 |
+
"learning_rate": 0.0003505398937848967,
|
| 842 |
+
"loss": 761.124462890625,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.2516778523489933,
|
| 847 |
+
"grad_norm": 34.028202056884766,
|
| 848 |
+
"learning_rate": 0.0003497121220366071,
|
| 849 |
+
"loss": 771.833837890625,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.2537751677852349,
|
| 854 |
+
"grad_norm": 36.89501953125,
|
| 855 |
+
"learning_rate": 0.0003488786039034591,
|
| 856 |
+
"loss": 759.81103515625,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.2558724832214765,
|
| 861 |
+
"grad_norm": 33.90177536010742,
|
| 862 |
+
"learning_rate": 0.0003480393763111917,
|
| 863 |
+
"loss": 759.73125,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.25796979865771813,
|
| 868 |
+
"grad_norm": 37.61647415161133,
|
| 869 |
+
"learning_rate": 0.00034719447643847927,
|
| 870 |
+
"loss": 756.5494140625,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.2600671140939597,
|
| 875 |
+
"grad_norm": 32.71785354614258,
|
| 876 |
+
"learning_rate": 0.00034634394171528403,
|
| 877 |
+
"loss": 767.09501953125,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.26216442953020136,
|
| 882 |
+
"grad_norm": 35.68928909301758,
|
| 883 |
+
"learning_rate": 0.00034548780982119806,
|
| 884 |
+
"loss": 755.03046875,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.26426174496644295,
|
| 889 |
+
"grad_norm": 37.2677116394043,
|
| 890 |
+
"learning_rate": 0.00034462611868377424,
|
| 891 |
+
"loss": 755.941796875,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.2663590604026846,
|
| 896 |
+
"grad_norm": 35.99335861206055,
|
| 897 |
+
"learning_rate": 0.0003437589064768457,
|
| 898 |
+
"loss": 753.703564453125,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.2684563758389262,
|
| 903 |
+
"grad_norm": 34.95077896118164,
|
| 904 |
+
"learning_rate": 0.0003428862116188348,
|
| 905 |
+
"loss": 764.32802734375,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.27055369127516776,
|
| 910 |
+
"grad_norm": 32.43818664550781,
|
| 911 |
+
"learning_rate": 0.0003420080727710512,
|
| 912 |
+
"loss": 756.809033203125,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.2726510067114094,
|
| 917 |
+
"grad_norm": 33.54920959472656,
|
| 918 |
+
"learning_rate": 0.0003411245288359792,
|
| 919 |
+
"loss": 751.679833984375,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.274748322147651,
|
| 924 |
+
"grad_norm": 33.81038284301758,
|
| 925 |
+
"learning_rate": 0.00034023561895555395,
|
| 926 |
+
"loss": 754.639111328125,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.27684563758389263,
|
| 931 |
+
"grad_norm": 36.19585418701172,
|
| 932 |
+
"learning_rate": 0.000339341382509428,
|
| 933 |
+
"loss": 763.320654296875,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.2789429530201342,
|
| 938 |
+
"grad_norm": 32.98769760131836,
|
| 939 |
+
"learning_rate": 0.00033844185911322623,
|
| 940 |
+
"loss": 753.488671875,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.28104026845637586,
|
| 945 |
+
"grad_norm": 33.56504821777344,
|
| 946 |
+
"learning_rate": 0.000337537088616791,
|
| 947 |
+
"loss": 747.947998046875,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.28313758389261745,
|
| 952 |
+
"grad_norm": 32.269737243652344,
|
| 953 |
+
"learning_rate": 0.00033662711110241697,
|
| 954 |
+
"loss": 750.63203125,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.28523489932885904,
|
| 959 |
+
"grad_norm": 33.046749114990234,
|
| 960 |
+
"learning_rate": 0.000335711966883075,
|
| 961 |
+
"loss": 759.793017578125,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.2873322147651007,
|
| 966 |
+
"grad_norm": 36.37275695800781,
|
| 967 |
+
"learning_rate": 0.0003347916965006266,
|
| 968 |
+
"loss": 744.22412109375,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.28942953020134227,
|
| 973 |
+
"grad_norm": 32.7099494934082,
|
| 974 |
+
"learning_rate": 0.00033386634072402776,
|
| 975 |
+
"loss": 746.197607421875,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.2915268456375839,
|
| 980 |
+
"grad_norm": 31.205947875976562,
|
| 981 |
+
"learning_rate": 0.0003329359405475228,
|
| 982 |
+
"loss": 748.474365234375,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.2936241610738255,
|
| 987 |
+
"grad_norm": 28.828580856323242,
|
| 988 |
+
"learning_rate": 0.00033200053718882835,
|
| 989 |
+
"loss": 751.84599609375,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.29572147651006714,
|
| 994 |
+
"grad_norm": 34.22489547729492,
|
| 995 |
+
"learning_rate": 0.0003310601720873073,
|
| 996 |
+
"loss": 746.10986328125,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.2978187919463087,
|
| 1001 |
+
"grad_norm": 29.78771209716797,
|
| 1002 |
+
"learning_rate": 0.00033011488690213296,
|
| 1003 |
+
"loss": 741.93037109375,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.2999161073825503,
|
| 1008 |
+
"grad_norm": 39.27846145629883,
|
| 1009 |
+
"learning_rate": 0.0003291647235104438,
|
| 1010 |
+
"loss": 743.660400390625,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.30201342281879195,
|
| 1015 |
+
"grad_norm": 31.457706451416016,
|
| 1016 |
+
"learning_rate": 0.00032820972400548766,
|
| 1017 |
+
"loss": 754.897265625,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.30411073825503354,
|
| 1022 |
+
"grad_norm": 32.80243682861328,
|
| 1023 |
+
"learning_rate": 0.00032724993069475764,
|
| 1024 |
+
"loss": 742.11484375,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.3062080536912752,
|
| 1029 |
+
"grad_norm": 34.35562515258789,
|
| 1030 |
+
"learning_rate": 0.00032628538609811745,
|
| 1031 |
+
"loss": 742.219775390625,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.30830536912751677,
|
| 1036 |
+
"grad_norm": 33.573577880859375,
|
| 1037 |
+
"learning_rate": 0.0003253161329459178,
|
| 1038 |
+
"loss": 745.37138671875,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.3104026845637584,
|
| 1043 |
+
"grad_norm": 32.058101654052734,
|
| 1044 |
+
"learning_rate": 0.00032434221417710333,
|
| 1045 |
+
"loss": 753.84130859375,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.3125,
|
| 1050 |
+
"grad_norm": 31.893978118896484,
|
| 1051 |
+
"learning_rate": 0.0003233636729373106,
|
| 1052 |
+
"loss": 741.5162109375,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.3145973154362416,
|
| 1057 |
+
"grad_norm": 36.885005950927734,
|
| 1058 |
+
"learning_rate": 0.00032238055257695645,
|
| 1059 |
+
"loss": 734.73974609375,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.31669463087248323,
|
| 1064 |
+
"grad_norm": 42.988834381103516,
|
| 1065 |
+
"learning_rate": 0.0003213928966493177,
|
| 1066 |
+
"loss": 739.119580078125,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.3187919463087248,
|
| 1071 |
+
"grad_norm": 29.642290115356445,
|
| 1072 |
+
"learning_rate": 0.00032040074890860156,
|
| 1073 |
+
"loss": 752.603564453125,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.32088926174496646,
|
| 1078 |
+
"grad_norm": 29.82461929321289,
|
| 1079 |
+
"learning_rate": 0.00031940415330800737,
|
| 1080 |
+
"loss": 734.8591796875,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.32298657718120805,
|
| 1085 |
+
"grad_norm": 34.89297866821289,
|
| 1086 |
+
"learning_rate": 0.0003184031539977794,
|
| 1087 |
+
"loss": 732.84501953125,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.3250838926174497,
|
| 1092 |
+
"grad_norm": 34.86556625366211,
|
| 1093 |
+
"learning_rate": 0.0003173977953232508,
|
| 1094 |
+
"loss": 736.87841796875,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.3271812080536913,
|
| 1099 |
+
"grad_norm": 32.03319549560547,
|
| 1100 |
+
"learning_rate": 0.0003163881218228794,
|
| 1101 |
+
"loss": 742.657666015625,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.32927852348993286,
|
| 1106 |
+
"grad_norm": 30.916311264038086,
|
| 1107 |
+
"learning_rate": 0.0003153741782262743,
|
| 1108 |
+
"loss": 734.43837890625,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.3313758389261745,
|
| 1113 |
+
"grad_norm": 31.965553283691406,
|
| 1114 |
+
"learning_rate": 0.0003143560094522143,
|
| 1115 |
+
"loss": 730.24296875,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.3334731543624161,
|
| 1120 |
+
"grad_norm": 31.810258865356445,
|
| 1121 |
+
"learning_rate": 0.0003133336606066583,
|
| 1122 |
+
"loss": 732.60625,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.33557046979865773,
|
| 1127 |
+
"grad_norm": 30.140993118286133,
|
| 1128 |
+
"learning_rate": 0.0003123071769807465,
|
| 1129 |
+
"loss": 744.71767578125,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.3376677852348993,
|
| 1134 |
+
"grad_norm": 60.086910247802734,
|
| 1135 |
+
"learning_rate": 0.00031127660404879463,
|
| 1136 |
+
"loss": 730.52451171875,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.33976510067114096,
|
| 1141 |
+
"grad_norm": 29.318464279174805,
|
| 1142 |
+
"learning_rate": 0.00031024198746627867,
|
| 1143 |
+
"loss": 727.399609375,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.34186241610738255,
|
| 1148 |
+
"grad_norm": 32.13727951049805,
|
| 1149 |
+
"learning_rate": 0.00030920337306781284,
|
| 1150 |
+
"loss": 729.554833984375,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.34395973154362414,
|
| 1155 |
+
"grad_norm": 30.829389572143555,
|
| 1156 |
+
"learning_rate": 0.00030816080686511875,
|
| 1157 |
+
"loss": 743.65224609375,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.3460570469798658,
|
| 1162 |
+
"grad_norm": 28.18938446044922,
|
| 1163 |
+
"learning_rate": 0.0003071143350449872,
|
| 1164 |
+
"loss": 729.828125,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.34815436241610737,
|
| 1169 |
+
"grad_norm": 27.202878952026367,
|
| 1170 |
+
"learning_rate": 0.00030606400396723186,
|
| 1171 |
+
"loss": 724.96044921875,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.350251677852349,
|
| 1176 |
+
"grad_norm": 39.66158676147461,
|
| 1177 |
+
"learning_rate": 0.0003050098601626359,
|
| 1178 |
+
"loss": 727.02880859375,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.3523489932885906,
|
| 1183 |
+
"grad_norm": 28.056537628173828,
|
| 1184 |
+
"learning_rate": 0.00030395195033089005,
|
| 1185 |
+
"loss": 737.3568359375,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.35444630872483224,
|
| 1190 |
+
"grad_norm": 28.82770347595215,
|
| 1191 |
+
"learning_rate": 0.0003028903213385242,
|
| 1192 |
+
"loss": 732.960888671875,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.3565436241610738,
|
| 1197 |
+
"grad_norm": 30.616226196289062,
|
| 1198 |
+
"learning_rate": 0.0003018250202168308,
|
| 1199 |
+
"loss": 725.4568359375,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.3586409395973154,
|
| 1204 |
+
"grad_norm": 27.57636070251465,
|
| 1205 |
+
"learning_rate": 0.00030075609415978203,
|
| 1206 |
+
"loss": 718.759716796875,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.36073825503355705,
|
| 1211 |
+
"grad_norm": 31.625394821166992,
|
| 1212 |
+
"learning_rate": 0.00029968359052193785,
|
| 1213 |
+
"loss": 725.88857421875,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.36283557046979864,
|
| 1218 |
+
"grad_norm": 27.597814559936523,
|
| 1219 |
+
"learning_rate": 0.00029860755681634953,
|
| 1220 |
+
"loss": 730.74892578125,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.3649328859060403,
|
| 1225 |
+
"grad_norm": 28.66240119934082,
|
| 1226 |
+
"learning_rate": 0.0002975280407124536,
|
| 1227 |
+
"loss": 722.49345703125,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.36703020134228187,
|
| 1232 |
+
"grad_norm": 27.074068069458008,
|
| 1233 |
+
"learning_rate": 0.00029644509003396075,
|
| 1234 |
+
"loss": 734.28369140625,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.3691275167785235,
|
| 1239 |
+
"grad_norm": 29.8409366607666,
|
| 1240 |
+
"learning_rate": 0.00029535875275673706,
|
| 1241 |
+
"loss": 738.629541015625,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.3712248322147651,
|
| 1246 |
+
"grad_norm": 28.747722625732422,
|
| 1247 |
+
"learning_rate": 0.0002942690770066783,
|
| 1248 |
+
"loss": 736.925048828125,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.3733221476510067,
|
| 1253 |
+
"grad_norm": 26.50994110107422,
|
| 1254 |
+
"learning_rate": 0.00029317611105757836,
|
| 1255 |
+
"loss": 733.42626953125,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.37541946308724833,
|
| 1260 |
+
"grad_norm": 27.646202087402344,
|
| 1261 |
+
"learning_rate": 0.00029207990332899016,
|
| 1262 |
+
"loss": 733.86328125,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.3775167785234899,
|
| 1267 |
+
"grad_norm": 28.608095169067383,
|
| 1268 |
+
"learning_rate": 0.00029098050238408137,
|
| 1269 |
+
"loss": 734.38486328125,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.37961409395973156,
|
| 1274 |
+
"grad_norm": 27.358755111694336,
|
| 1275 |
+
"learning_rate": 0.0002898779569274819,
|
| 1276 |
+
"loss": 733.97880859375,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.38171140939597314,
|
| 1281 |
+
"grad_norm": 29.266138076782227,
|
| 1282 |
+
"learning_rate": 0.00028877231580312743,
|
| 1283 |
+
"loss": 731.997412109375,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.3838087248322148,
|
| 1288 |
+
"grad_norm": 28.123027801513672,
|
| 1289 |
+
"learning_rate": 0.0002876636279920948,
|
| 1290 |
+
"loss": 732.208837890625,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.3859060402684564,
|
| 1295 |
+
"grad_norm": 28.35926628112793,
|
| 1296 |
+
"learning_rate": 0.0002865519426104322,
|
| 1297 |
+
"loss": 730.1966796875,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.38800335570469796,
|
| 1302 |
+
"grad_norm": 26.62183952331543,
|
| 1303 |
+
"learning_rate": 0.00028543730890698353,
|
| 1304 |
+
"loss": 730.421484375,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.3901006711409396,
|
| 1309 |
+
"grad_norm": 26.039772033691406,
|
| 1310 |
+
"learning_rate": 0.00028431977626120657,
|
| 1311 |
+
"loss": 731.6849609375,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.3921979865771812,
|
| 1316 |
+
"grad_norm": 28.390792846679688,
|
| 1317 |
+
"learning_rate": 0.00028319939418098493,
|
| 1318 |
+
"loss": 728.848291015625,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.39429530201342283,
|
| 1323 |
+
"grad_norm": 28.321779251098633,
|
| 1324 |
+
"learning_rate": 0.0002820762123004356,
|
| 1325 |
+
"loss": 729.0255859375,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.3963926174496644,
|
| 1330 |
+
"grad_norm": 28.969951629638672,
|
| 1331 |
+
"learning_rate": 0.0002809502803777095,
|
| 1332 |
+
"loss": 729.58837890625,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.39848993288590606,
|
| 1337 |
+
"grad_norm": 25.39800453186035,
|
| 1338 |
+
"learning_rate": 0.00027982164829278754,
|
| 1339 |
+
"loss": 727.68134765625,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.40058724832214765,
|
| 1344 |
+
"grad_norm": 29.222623825073242,
|
| 1345 |
+
"learning_rate": 0.00027869036604527043,
|
| 1346 |
+
"loss": 729.85634765625,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.40268456375838924,
|
| 1351 |
+
"grad_norm": 30.955928802490234,
|
| 1352 |
+
"learning_rate": 0.000277556483752164,
|
| 1353 |
+
"loss": 727.31318359375,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.4047818791946309,
|
| 1358 |
+
"grad_norm": 29.15259552001953,
|
| 1359 |
+
"learning_rate": 0.0002764200516456589,
|
| 1360 |
+
"loss": 728.60517578125,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.40687919463087246,
|
| 1365 |
+
"grad_norm": 28.483592987060547,
|
| 1366 |
+
"learning_rate": 0.00027528112007090525,
|
| 1367 |
+
"loss": 729.50048828125,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.4089765100671141,
|
| 1372 |
+
"grad_norm": 27.479665756225586,
|
| 1373 |
+
"learning_rate": 0.0002741397394837821,
|
| 1374 |
+
"loss": 725.64970703125,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.4110738255033557,
|
| 1379 |
+
"grad_norm": 31.93459701538086,
|
| 1380 |
+
"learning_rate": 0.0002729959604486626,
|
| 1381 |
+
"loss": 728.76865234375,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.41317114093959734,
|
| 1386 |
+
"grad_norm": 29.415254592895508,
|
| 1387 |
+
"learning_rate": 0.0002718498336361734,
|
| 1388 |
+
"loss": 727.822216796875,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.4152684563758389,
|
| 1393 |
+
"grad_norm": 25.998945236206055,
|
| 1394 |
+
"learning_rate": 0.0002707014098209505,
|
| 1395 |
+
"loss": 725.624560546875,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.4173657718120805,
|
| 1400 |
+
"grad_norm": 33.45818328857422,
|
| 1401 |
+
"learning_rate": 0.00026955073987938933,
|
| 1402 |
+
"loss": 730.52978515625,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.41946308724832215,
|
| 1407 |
+
"grad_norm": 28.501672744750977,
|
| 1408 |
+
"learning_rate": 0.0002683978747873912,
|
| 1409 |
+
"loss": 725.5873046875,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.42156040268456374,
|
| 1414 |
+
"grad_norm": 28.55805206298828,
|
| 1415 |
+
"learning_rate": 0.0002672428656181049,
|
| 1416 |
+
"loss": 723.09990234375,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.4236577181208054,
|
| 1421 |
+
"grad_norm": 27.068178176879883,
|
| 1422 |
+
"learning_rate": 0.0002660857635396641,
|
| 1423 |
+
"loss": 723.821875,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.42575503355704697,
|
| 1428 |
+
"grad_norm": 27.90006446838379,
|
| 1429 |
+
"learning_rate": 0.0002649266198129206,
|
| 1430 |
+
"loss": 718.319140625,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.4278523489932886,
|
| 1435 |
+
"grad_norm": 28.625322341918945,
|
| 1436 |
+
"learning_rate": 0.00026376548578917343,
|
| 1437 |
+
"loss": 724.609619140625,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.4299496644295302,
|
| 1442 |
+
"grad_norm": 31.34563636779785,
|
| 1443 |
+
"learning_rate": 0.0002626024129078938,
|
| 1444 |
+
"loss": 719.7814453125,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.4320469798657718,
|
| 1449 |
+
"grad_norm": 26.983905792236328,
|
| 1450 |
+
"learning_rate": 0.00026143745269444643,
|
| 1451 |
+
"loss": 722.23017578125,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.4341442953020134,
|
| 1456 |
+
"grad_norm": 29.680858612060547,
|
| 1457 |
+
"learning_rate": 0.0002602706567578069,
|
| 1458 |
+
"loss": 720.07890625,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.436241610738255,
|
| 1463 |
+
"grad_norm": 31.25922966003418,
|
| 1464 |
+
"learning_rate": 0.000259102076788275,
|
| 1465 |
+
"loss": 720.61064453125,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.43833892617449666,
|
| 1470 |
+
"grad_norm": 25.962329864501953,
|
| 1471 |
+
"learning_rate": 0.00025793176455518547,
|
| 1472 |
+
"loss": 724.55810546875,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.44043624161073824,
|
| 1477 |
+
"grad_norm": 27.091432571411133,
|
| 1478 |
+
"learning_rate": 0.000256759771904614,
|
| 1479 |
+
"loss": 721.320458984375,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.4425335570469799,
|
| 1484 |
+
"grad_norm": 33.23907470703125,
|
| 1485 |
+
"learning_rate": 0.00025558615075708057,
|
| 1486 |
+
"loss": 719.5658203125,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.4446308724832215,
|
| 1491 |
+
"grad_norm": 27.312124252319336,
|
| 1492 |
+
"learning_rate": 0.0002544109531052492,
|
| 1493 |
+
"loss": 723.623046875,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.44672818791946306,
|
| 1498 |
+
"grad_norm": 25.877601623535156,
|
| 1499 |
+
"learning_rate": 0.00025323423101162484,
|
| 1500 |
+
"loss": 723.46025390625,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.4488255033557047,
|
| 1505 |
+
"grad_norm": 26.769596099853516,
|
| 1506 |
+
"learning_rate": 0.00025205603660624675,
|
| 1507 |
+
"loss": 718.48427734375,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.4509228187919463,
|
| 1512 |
+
"grad_norm": 25.944448471069336,
|
| 1513 |
+
"learning_rate": 0.00025087642208437936,
|
| 1514 |
+
"loss": 716.782421875,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.45302013422818793,
|
| 1519 |
+
"grad_norm": 28.341115951538086,
|
| 1520 |
+
"learning_rate": 0.00024969543970419956,
|
| 1521 |
+
"loss": 720.827490234375,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.4551174496644295,
|
| 1526 |
+
"grad_norm": 26.407798767089844,
|
| 1527 |
+
"learning_rate": 0.00024851314178448184,
|
| 1528 |
+
"loss": 720.140234375,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.45721476510067116,
|
| 1533 |
+
"grad_norm": 28.054893493652344,
|
| 1534 |
+
"learning_rate": 0.0002473295807022806,
|
| 1535 |
+
"loss": 714.789990234375,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.45931208053691275,
|
| 1540 |
+
"grad_norm": 26.11944007873535,
|
| 1541 |
+
"learning_rate": 0.00024614480889060956,
|
| 1542 |
+
"loss": 719.75595703125,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.46140939597315433,
|
| 1547 |
+
"grad_norm": 26.539321899414062,
|
| 1548 |
+
"learning_rate": 0.0002449588788361192,
|
| 1549 |
+
"loss": 716.24951171875,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.463506711409396,
|
| 1554 |
+
"grad_norm": 27.907739639282227,
|
| 1555 |
+
"learning_rate": 0.0002437718430767712,
|
| 1556 |
+
"loss": 718.15361328125,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.46560402684563756,
|
| 1561 |
+
"grad_norm": 26.146020889282227,
|
| 1562 |
+
"learning_rate": 0.00024258375419951124,
|
| 1563 |
+
"loss": 718.4966796875,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.4677013422818792,
|
| 1568 |
+
"grad_norm": 29.019397735595703,
|
| 1569 |
+
"learning_rate": 0.00024139466483793926,
|
| 1570 |
+
"loss": 718.3244140625,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.4697986577181208,
|
| 1575 |
+
"grad_norm": 27.466388702392578,
|
| 1576 |
+
"learning_rate": 0.00024020462766997764,
|
| 1577 |
+
"loss": 717.709375,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.47189597315436244,
|
| 1582 |
+
"grad_norm": 28.666629791259766,
|
| 1583 |
+
"learning_rate": 0.0002390136954155377,
|
| 1584 |
+
"loss": 720.43193359375,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.473993288590604,
|
| 1589 |
+
"grad_norm": 34.103336334228516,
|
| 1590 |
+
"learning_rate": 0.00023782192083418395,
|
| 1591 |
+
"loss": 718.31767578125,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.47609060402684567,
|
| 1596 |
+
"grad_norm": 29.75569725036621,
|
| 1597 |
+
"learning_rate": 0.00023662935672279684,
|
| 1598 |
+
"loss": 715.5525390625,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.47818791946308725,
|
| 1603 |
+
"grad_norm": 26.467947006225586,
|
| 1604 |
+
"learning_rate": 0.0002354360559132341,
|
| 1605 |
+
"loss": 718.21328125,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.48028523489932884,
|
| 1610 |
+
"grad_norm": 27.470417022705078,
|
| 1611 |
+
"learning_rate": 0.0002342420712699895,
|
| 1612 |
+
"loss": 713.359033203125,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.4823825503355705,
|
| 1617 |
+
"grad_norm": 28.60648536682129,
|
| 1618 |
+
"learning_rate": 0.0002330474556878519,
|
| 1619 |
+
"loss": 715.951904296875,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.48447986577181207,
|
| 1624 |
+
"grad_norm": 29.705326080322266,
|
| 1625 |
+
"learning_rate": 0.00023185226208956107,
|
| 1626 |
+
"loss": 716.36962890625,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.4865771812080537,
|
| 1631 |
+
"grad_norm": 26.422521591186523,
|
| 1632 |
+
"learning_rate": 0.00023065654342346363,
|
| 1633 |
+
"loss": 717.31083984375,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.4886744966442953,
|
| 1638 |
+
"grad_norm": 49.67610168457031,
|
| 1639 |
+
"learning_rate": 0.0002294603526611672,
|
| 1640 |
+
"loss": 717.445703125,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.49077181208053694,
|
| 1645 |
+
"grad_norm": 27.15092658996582,
|
| 1646 |
+
"learning_rate": 0.0002282637427951939,
|
| 1647 |
+
"loss": 717.614111328125,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.4928691275167785,
|
| 1652 |
+
"grad_norm": 26.76052474975586,
|
| 1653 |
+
"learning_rate": 0.00022706676683663239,
|
| 1654 |
+
"loss": 716.904833984375,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.4949664429530201,
|
| 1659 |
+
"grad_norm": 27.0493106842041,
|
| 1660 |
+
"learning_rate": 0.00022586947781278976,
|
| 1661 |
+
"loss": 715.82685546875,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.49706375838926176,
|
| 1666 |
+
"grad_norm": 27.63730812072754,
|
| 1667 |
+
"learning_rate": 0.00022467192876484223,
|
| 1668 |
+
"loss": 713.4669921875,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.49916107382550334,
|
| 1673 |
+
"grad_norm": 26.431467056274414,
|
| 1674 |
+
"learning_rate": 0.00022347417274548524,
|
| 1675 |
+
"loss": 716.6283203125,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.5012583892617449,
|
| 1680 |
+
"grad_norm": 26.240686416625977,
|
| 1681 |
+
"learning_rate": 0.00022227626281658353,
|
| 1682 |
+
"loss": 716.108740234375,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.5033557046979866,
|
| 1687 |
+
"grad_norm": 27.485626220703125,
|
| 1688 |
+
"learning_rate": 0.0002210782520468199,
|
| 1689 |
+
"loss": 713.7689453125,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.5054530201342282,
|
| 1694 |
+
"grad_norm": 28.32665252685547,
|
| 1695 |
+
"learning_rate": 0.00021988019350934469,
|
| 1696 |
+
"loss": 716.45576171875,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.5075503355704698,
|
| 1701 |
+
"grad_norm": 29.576181411743164,
|
| 1702 |
+
"learning_rate": 0.00021868214027942435,
|
| 1703 |
+
"loss": 712.18935546875,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.5096476510067114,
|
| 1708 |
+
"grad_norm": 27.404142379760742,
|
| 1709 |
+
"learning_rate": 0.00021748414543209014,
|
| 1710 |
+
"loss": 709.567724609375,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.511744966442953,
|
| 1715 |
+
"grad_norm": 25.870176315307617,
|
| 1716 |
+
"learning_rate": 0.000216286262039787,
|
| 1717 |
+
"loss": 712.60595703125,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.5138422818791947,
|
| 1722 |
+
"grad_norm": 25.011234283447266,
|
| 1723 |
+
"learning_rate": 0.00021508854317002244,
|
| 1724 |
+
"loss": 712.865966796875,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.5159395973154363,
|
| 1729 |
+
"grad_norm": 26.89911460876465,
|
| 1730 |
+
"learning_rate": 0.00021389104188301498,
|
| 1731 |
+
"loss": 713.5578125,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.5180369127516778,
|
| 1736 |
+
"grad_norm": 25.816125869750977,
|
| 1737 |
+
"learning_rate": 0.0002126938112293445,
|
| 1738 |
+
"loss": 714.549267578125,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.5201342281879194,
|
| 1743 |
+
"grad_norm": 24.598859786987305,
|
| 1744 |
+
"learning_rate": 0.00021149690424760115,
|
| 1745 |
+
"loss": 710.9453125,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.522231543624161,
|
| 1750 |
+
"grad_norm": 25.585561752319336,
|
| 1751 |
+
"learning_rate": 0.00021030037396203648,
|
| 1752 |
+
"loss": 710.580859375,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.5243288590604027,
|
| 1757 |
+
"grad_norm": 26.241941452026367,
|
| 1758 |
+
"learning_rate": 0.00020910427338021354,
|
| 1759 |
+
"loss": 710.328271484375,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.5264261744966443,
|
| 1764 |
+
"grad_norm": 24.599651336669922,
|
| 1765 |
+
"learning_rate": 0.0002079086554906594,
|
| 1766 |
+
"loss": 712.6861328125,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.5285234899328859,
|
| 1771 |
+
"grad_norm": 26.42645835876465,
|
| 1772 |
+
"learning_rate": 0.00020671357326051712,
|
| 1773 |
+
"loss": 712.0703125,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.5306208053691275,
|
| 1778 |
+
"grad_norm": 28.313579559326172,
|
| 1779 |
+
"learning_rate": 0.00020551907963319957,
|
| 1780 |
+
"loss": 710.93173828125,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.5327181208053692,
|
| 1785 |
+
"grad_norm": 24.56991958618164,
|
| 1786 |
+
"learning_rate": 0.00020432522752604398,
|
| 1787 |
+
"loss": 711.9142578125,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.5348154362416108,
|
| 1792 |
+
"grad_norm": 25.90009117126465,
|
| 1793 |
+
"learning_rate": 0.00020313206982796743,
|
| 1794 |
+
"loss": 710.29892578125,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.5369127516778524,
|
| 1799 |
+
"grad_norm": 26.455686569213867,
|
| 1800 |
+
"learning_rate": 0.00020193965939712397,
|
| 1801 |
+
"loss": 704.16845703125,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.5390100671140939,
|
| 1806 |
+
"grad_norm": 24.865222930908203,
|
| 1807 |
+
"learning_rate": 0.000200748049058563,
|
| 1808 |
+
"loss": 706.30869140625,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.5411073825503355,
|
| 1813 |
+
"grad_norm": 24.55437469482422,
|
| 1814 |
+
"learning_rate": 0.0001995572916018888,
|
| 1815 |
+
"loss": 705.83759765625,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.5432046979865772,
|
| 1820 |
+
"grad_norm": 25.504764556884766,
|
| 1821 |
+
"learning_rate": 0.00019836743977892223,
|
| 1822 |
+
"loss": 708.3240234375,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.5453020134228188,
|
| 1827 |
+
"grad_norm": 25.164077758789062,
|
| 1828 |
+
"learning_rate": 0.0001971785463013636,
|
| 1829 |
+
"loss": 705.59912109375,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.5473993288590604,
|
| 1834 |
+
"grad_norm": 23.877357482910156,
|
| 1835 |
+
"learning_rate": 0.00019599066383845743,
|
| 1836 |
+
"loss": 708.88505859375,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.549496644295302,
|
| 1841 |
+
"grad_norm": 27.058509826660156,
|
| 1842 |
+
"learning_rate": 0.00019480384501465925,
|
| 1843 |
+
"loss": 707.0541015625,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.5515939597315436,
|
| 1848 |
+
"grad_norm": 29.5660343170166,
|
| 1849 |
+
"learning_rate": 0.0001936181424073043,
|
| 1850 |
+
"loss": 709.3982421875,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.5536912751677853,
|
| 1855 |
+
"grad_norm": 25.05129051208496,
|
| 1856 |
+
"learning_rate": 0.00019243360854427808,
|
| 1857 |
+
"loss": 708.7525390625,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.5557885906040269,
|
| 1862 |
+
"grad_norm": 26.034975051879883,
|
| 1863 |
+
"learning_rate": 0.0001912502959016897,
|
| 1864 |
+
"loss": 705.56171875,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.5578859060402684,
|
| 1869 |
+
"grad_norm": 25.737016677856445,
|
| 1870 |
+
"learning_rate": 0.00019006825690154683,
|
| 1871 |
+
"loss": 708.69892578125,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.55998322147651,
|
| 1876 |
+
"grad_norm": 26.19977569580078,
|
| 1877 |
+
"learning_rate": 0.00018888754390943325,
|
| 1878 |
+
"loss": 706.80400390625,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.5620805369127517,
|
| 1883 |
+
"grad_norm": 25.73967933654785,
|
| 1884 |
+
"learning_rate": 0.0001877082092321895,
|
| 1885 |
+
"loss": 703.82470703125,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.5641778523489933,
|
| 1890 |
+
"grad_norm": 24.554115295410156,
|
| 1891 |
+
"learning_rate": 0.00018653030511559497,
|
| 1892 |
+
"loss": 701.961083984375,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.5662751677852349,
|
| 1897 |
+
"grad_norm": 27.607160568237305,
|
| 1898 |
+
"learning_rate": 0.0001853538837420539,
|
| 1899 |
+
"loss": 702.956298828125,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.5683724832214765,
|
| 1904 |
+
"grad_norm": 27.145713806152344,
|
| 1905 |
+
"learning_rate": 0.00018417899722828341,
|
| 1906 |
+
"loss": 701.333984375,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.5704697986577181,
|
| 1911 |
+
"grad_norm": 26.37285041809082,
|
| 1912 |
+
"learning_rate": 0.0001830056976230047,
|
| 1913 |
+
"loss": 700.68173828125,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.5725671140939598,
|
| 1918 |
+
"grad_norm": 28.513526916503906,
|
| 1919 |
+
"learning_rate": 0.00018183403690463708,
|
| 1920 |
+
"loss": 704.793017578125,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.5746644295302014,
|
| 1925 |
+
"grad_norm": 27.879859924316406,
|
| 1926 |
+
"learning_rate": 0.00018066406697899576,
|
| 1927 |
+
"loss": 704.948876953125,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.576761744966443,
|
| 1932 |
+
"grad_norm": 26.13296890258789,
|
| 1933 |
+
"learning_rate": 0.00017949583967699168,
|
| 1934 |
+
"loss": 705.763671875,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.5788590604026845,
|
| 1939 |
+
"grad_norm": 24.964950561523438,
|
| 1940 |
+
"learning_rate": 0.0001783294067523359,
|
| 1941 |
+
"loss": 701.885009765625,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.5809563758389261,
|
| 1946 |
+
"grad_norm": 24.55069351196289,
|
| 1947 |
+
"learning_rate": 0.00017716481987924674,
|
| 1948 |
+
"loss": 703.38232421875,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.5830536912751678,
|
| 1953 |
+
"grad_norm": 23.53226661682129,
|
| 1954 |
+
"learning_rate": 0.00017600213065016012,
|
| 1955 |
+
"loss": 700.89462890625,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.5851510067114094,
|
| 1960 |
+
"grad_norm": 24.06133270263672,
|
| 1961 |
+
"learning_rate": 0.00017484139057344472,
|
| 1962 |
+
"loss": 701.2154296875,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.587248322147651,
|
| 1967 |
+
"grad_norm": 25.854036331176758,
|
| 1968 |
+
"learning_rate": 0.00017368265107111944,
|
| 1969 |
+
"loss": 702.04521484375,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.5893456375838926,
|
| 1974 |
+
"grad_norm": 24.032381057739258,
|
| 1975 |
+
"learning_rate": 0.00017252596347657574,
|
| 1976 |
+
"loss": 699.448583984375,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.5914429530201343,
|
| 1981 |
+
"grad_norm": 24.54527473449707,
|
| 1982 |
+
"learning_rate": 0.00017137137903230323,
|
| 1983 |
+
"loss": 693.13505859375,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.5935402684563759,
|
| 1988 |
+
"grad_norm": 25.05814552307129,
|
| 1989 |
+
"learning_rate": 0.00017021894888761998,
|
| 1990 |
+
"loss": 696.93486328125,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.5956375838926175,
|
| 1995 |
+
"grad_norm": 23.6625919342041,
|
| 1996 |
+
"learning_rate": 0.00016906872409640607,
|
| 1997 |
+
"loss": 697.78701171875,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.597734899328859,
|
| 2002 |
+
"grad_norm": 23.811920166015625,
|
| 2003 |
+
"learning_rate": 0.00016792075561484216,
|
| 2004 |
+
"loss": 698.3015625,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.5998322147651006,
|
| 2009 |
+
"grad_norm": 23.187089920043945,
|
| 2010 |
+
"learning_rate": 0.00016677509429915198,
|
| 2011 |
+
"loss": 699.289208984375,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.6019295302013423,
|
| 2016 |
+
"grad_norm": 24.96914291381836,
|
| 2017 |
+
"learning_rate": 0.0001656317909033494,
|
| 2018 |
+
"loss": 699.05029296875,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.6040268456375839,
|
| 2023 |
+
"grad_norm": 22.78306770324707,
|
| 2024 |
+
"learning_rate": 0.0001644908960769899,
|
| 2025 |
+
"loss": 699.95283203125,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.6061241610738255,
|
| 2030 |
+
"grad_norm": 25.343849182128906,
|
| 2031 |
+
"learning_rate": 0.00016335246036292675,
|
| 2032 |
+
"loss": 696.755615234375,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.6082214765100671,
|
| 2037 |
+
"grad_norm": 26.005495071411133,
|
| 2038 |
+
"learning_rate": 0.00016221653419507207,
|
| 2039 |
+
"loss": 699.58486328125,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.6103187919463087,
|
| 2044 |
+
"grad_norm": 24.401639938354492,
|
| 2045 |
+
"learning_rate": 0.00016108316789616213,
|
| 2046 |
+
"loss": 696.3732421875,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.6124161073825504,
|
| 2051 |
+
"grad_norm": 24.31859588623047,
|
| 2052 |
+
"learning_rate": 0.00015995241167552856,
|
| 2053 |
+
"loss": 700.176953125,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.614513422818792,
|
| 2058 |
+
"grad_norm": 31.25603675842285,
|
| 2059 |
+
"learning_rate": 0.00015882431562687366,
|
| 2060 |
+
"loss": 698.004443359375,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.6166107382550335,
|
| 2065 |
+
"grad_norm": 25.79340934753418,
|
| 2066 |
+
"learning_rate": 0.00015769892972605125,
|
| 2067 |
+
"loss": 698.315625,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.6187080536912751,
|
| 2072 |
+
"grad_norm": 23.582733154296875,
|
| 2073 |
+
"learning_rate": 0.0001565763038288528,
|
| 2074 |
+
"loss": 691.946630859375,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.6208053691275168,
|
| 2079 |
+
"grad_norm": 26.264375686645508,
|
| 2080 |
+
"learning_rate": 0.0001554564876687986,
|
| 2081 |
+
"loss": 699.2384765625,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.6229026845637584,
|
| 2086 |
+
"grad_norm": 26.286468505859375,
|
| 2087 |
+
"learning_rate": 0.0001543395308549346,
|
| 2088 |
+
"loss": 697.033544921875,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.625,
|
| 2093 |
+
"grad_norm": 25.956165313720703,
|
| 2094 |
+
"learning_rate": 0.00015322548286963476,
|
| 2095 |
+
"loss": 698.5783203125,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.6270973154362416,
|
| 2100 |
+
"grad_norm": 26.558116912841797,
|
| 2101 |
+
"learning_rate": 0.0001521143930664087,
|
| 2102 |
+
"loss": 695.806298828125,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.6291946308724832,
|
| 2107 |
+
"grad_norm": 24.454757690429688,
|
| 2108 |
+
"learning_rate": 0.00015100631066771562,
|
| 2109 |
+
"loss": 698.87841796875,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.6312919463087249,
|
| 2114 |
+
"grad_norm": 24.38653564453125,
|
| 2115 |
+
"learning_rate": 0.00014990128476278337,
|
| 2116 |
+
"loss": 696.64560546875,
|
| 2117 |
+
"step": 3010
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.6333892617449665,
|
| 2121 |
+
"grad_norm": 25.045244216918945,
|
| 2122 |
+
"learning_rate": 0.00014879936430543385,
|
| 2123 |
+
"loss": 697.28154296875,
|
| 2124 |
+
"step": 3020
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.635486577181208,
|
| 2128 |
+
"grad_norm": 24.258338928222656,
|
| 2129 |
+
"learning_rate": 0.00014770059811191447,
|
| 2130 |
+
"loss": 700.28935546875,
|
| 2131 |
+
"step": 3030
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.6375838926174496,
|
| 2135 |
+
"grad_norm": 24.587146759033203,
|
| 2136 |
+
"learning_rate": 0.00014660503485873535,
|
| 2137 |
+
"loss": 698.47548828125,
|
| 2138 |
+
"step": 3040
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.6396812080536913,
|
| 2142 |
+
"grad_norm": 24.621126174926758,
|
| 2143 |
+
"learning_rate": 0.0001455127230805128,
|
| 2144 |
+
"loss": 697.98115234375,
|
| 2145 |
+
"step": 3050
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.6417785234899329,
|
| 2149 |
+
"grad_norm": 23.170021057128906,
|
| 2150 |
+
"learning_rate": 0.0001444237111678195,
|
| 2151 |
+
"loss": 693.545849609375,
|
| 2152 |
+
"step": 3060
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.6438758389261745,
|
| 2156 |
+
"grad_norm": 24.980670928955078,
|
| 2157 |
+
"learning_rate": 0.00014333804736504056,
|
| 2158 |
+
"loss": 694.336376953125,
|
| 2159 |
+
"step": 3070
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.6459731543624161,
|
| 2163 |
+
"grad_norm": 27.34921646118164,
|
| 2164 |
+
"learning_rate": 0.00014225577976823627,
|
| 2165 |
+
"loss": 699.40654296875,
|
| 2166 |
+
"step": 3080
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.6480704697986577,
|
| 2170 |
+
"grad_norm": 25.38248062133789,
|
| 2171 |
+
"learning_rate": 0.00014117695632301139,
|
| 2172 |
+
"loss": 696.404150390625,
|
| 2173 |
+
"step": 3090
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.6501677852348994,
|
| 2177 |
+
"grad_norm": 25.941797256469727,
|
| 2178 |
+
"learning_rate": 0.00014010162482239088,
|
| 2179 |
+
"loss": 696.0484375,
|
| 2180 |
+
"step": 3100
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.652265100671141,
|
| 2184 |
+
"grad_norm": 25.004669189453125,
|
| 2185 |
+
"learning_rate": 0.00013902983290470317,
|
| 2186 |
+
"loss": 696.5728515625,
|
| 2187 |
+
"step": 3110
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.6543624161073825,
|
| 2191 |
+
"grad_norm": 23.577775955200195,
|
| 2192 |
+
"learning_rate": 0.0001379616280514692,
|
| 2193 |
+
"loss": 696.34404296875,
|
| 2194 |
+
"step": 3120
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.6564597315436241,
|
| 2198 |
+
"grad_norm": 24.280529022216797,
|
| 2199 |
+
"learning_rate": 0.0001368970575852993,
|
| 2200 |
+
"loss": 697.48203125,
|
| 2201 |
+
"step": 3130
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.6585570469798657,
|
| 2205 |
+
"grad_norm": 23.28042984008789,
|
| 2206 |
+
"learning_rate": 0.00013583616866779652,
|
| 2207 |
+
"loss": 690.66455078125,
|
| 2208 |
+
"step": 3140
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.6606543624161074,
|
| 2212 |
+
"grad_norm": 24.422304153442383,
|
| 2213 |
+
"learning_rate": 0.00013477900829746725,
|
| 2214 |
+
"loss": 694.853955078125,
|
| 2215 |
+
"step": 3150
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.662751677852349,
|
| 2219 |
+
"grad_norm": 22.98871421813965,
|
| 2220 |
+
"learning_rate": 0.00013372562330763943,
|
| 2221 |
+
"loss": 696.26904296875,
|
| 2222 |
+
"step": 3160
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.6648489932885906,
|
| 2226 |
+
"grad_norm": 25.702192306518555,
|
| 2227 |
+
"learning_rate": 0.00013267606036438762,
|
| 2228 |
+
"loss": 693.992333984375,
|
| 2229 |
+
"step": 3170
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.6669463087248322,
|
| 2233 |
+
"grad_norm": 23.169281005859375,
|
| 2234 |
+
"learning_rate": 0.00013163036596446564,
|
| 2235 |
+
"loss": 691.390869140625,
|
| 2236 |
+
"step": 3180
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.6690436241610739,
|
| 2240 |
+
"grad_norm": 24.02280044555664,
|
| 2241 |
+
"learning_rate": 0.00013058858643324675,
|
| 2242 |
+
"loss": 692.553173828125,
|
| 2243 |
+
"step": 3190
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.6711409395973155,
|
| 2247 |
+
"grad_norm": 23.723628997802734,
|
| 2248 |
+
"learning_rate": 0.00012955076792267134,
|
| 2249 |
+
"loss": 687.7876953125,
|
| 2250 |
+
"step": 3200
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.673238255033557,
|
| 2254 |
+
"grad_norm": 23.922508239746094,
|
| 2255 |
+
"learning_rate": 0.00012851695640920228,
|
| 2256 |
+
"loss": 691.37255859375,
|
| 2257 |
+
"step": 3210
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.6753355704697986,
|
| 2261 |
+
"grad_norm": 23.9777889251709,
|
| 2262 |
+
"learning_rate": 0.00012748719769178836,
|
| 2263 |
+
"loss": 689.18642578125,
|
| 2264 |
+
"step": 3220
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.6774328859060402,
|
| 2268 |
+
"grad_norm": 23.559240341186523,
|
| 2269 |
+
"learning_rate": 0.00012646153738983518,
|
| 2270 |
+
"loss": 688.249755859375,
|
| 2271 |
+
"step": 3230
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.6795302013422819,
|
| 2275 |
+
"grad_norm": 25.408052444458008,
|
| 2276 |
+
"learning_rate": 0.0001254400209411841,
|
| 2277 |
+
"loss": 691.2591796875,
|
| 2278 |
+
"step": 3240
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.6816275167785235,
|
| 2282 |
+
"grad_norm": 22.419090270996094,
|
| 2283 |
+
"learning_rate": 0.00012442269360009943,
|
| 2284 |
+
"loss": 692.08369140625,
|
| 2285 |
+
"step": 3250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.6837248322147651,
|
| 2289 |
+
"grad_norm": 25.38911247253418,
|
| 2290 |
+
"learning_rate": 0.00012340960043526354,
|
| 2291 |
+
"loss": 693.0171875,
|
| 2292 |
+
"step": 3260
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.6858221476510067,
|
| 2296 |
+
"grad_norm": 26.608829498291016,
|
| 2297 |
+
"learning_rate": 0.0001224007863277804,
|
| 2298 |
+
"loss": 691.488037109375,
|
| 2299 |
+
"step": 3270
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.6879194630872483,
|
| 2303 |
+
"grad_norm": 23.240951538085938,
|
| 2304 |
+
"learning_rate": 0.00012139629596918692,
|
| 2305 |
+
"loss": 691.84345703125,
|
| 2306 |
+
"step": 3280
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.69001677852349,
|
| 2310 |
+
"grad_norm": 23.333946228027344,
|
| 2311 |
+
"learning_rate": 0.00012039617385947362,
|
| 2312 |
+
"loss": 693.92431640625,
|
| 2313 |
+
"step": 3290
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.6921140939597316,
|
| 2317 |
+
"grad_norm": 26.162805557250977,
|
| 2318 |
+
"learning_rate": 0.0001194004643051128,
|
| 2319 |
+
"loss": 690.355908203125,
|
| 2320 |
+
"step": 3300
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.6942114093959731,
|
| 2324 |
+
"grad_norm": 21.26649284362793,
|
| 2325 |
+
"learning_rate": 0.00011840921141709596,
|
| 2326 |
+
"loss": 691.67705078125,
|
| 2327 |
+
"step": 3310
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.6963087248322147,
|
| 2331 |
+
"grad_norm": 23.431072235107422,
|
| 2332 |
+
"learning_rate": 0.00011742245910897946,
|
| 2333 |
+
"loss": 691.683349609375,
|
| 2334 |
+
"step": 3320
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.6984060402684564,
|
| 2338 |
+
"grad_norm": 23.77557945251465,
|
| 2339 |
+
"learning_rate": 0.00011644025109493925,
|
| 2340 |
+
"loss": 687.243115234375,
|
| 2341 |
+
"step": 3330
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.700503355704698,
|
| 2345 |
+
"grad_norm": 23.87569236755371,
|
| 2346 |
+
"learning_rate": 0.0001154626308878342,
|
| 2347 |
+
"loss": 687.0201171875,
|
| 2348 |
+
"step": 3340
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.7026006711409396,
|
| 2352 |
+
"grad_norm": 21.87002944946289,
|
| 2353 |
+
"learning_rate": 0.00011448964179727846,
|
| 2354 |
+
"loss": 687.4349609375,
|
| 2355 |
+
"step": 3350
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.7046979865771812,
|
| 2359 |
+
"grad_norm": 23.286794662475586,
|
| 2360 |
+
"learning_rate": 0.00011352132692772275,
|
| 2361 |
+
"loss": 690.5765625,
|
| 2362 |
+
"step": 3360
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.7067953020134228,
|
| 2366 |
+
"grad_norm": 27.445226669311523,
|
| 2367 |
+
"learning_rate": 0.0001125577291765449,
|
| 2368 |
+
"loss": 691.41484375,
|
| 2369 |
+
"step": 3370
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.7088926174496645,
|
| 2373 |
+
"grad_norm": 23.718297958374023,
|
| 2374 |
+
"learning_rate": 0.00011159889123214947,
|
| 2375 |
+
"loss": 691.42841796875,
|
| 2376 |
+
"step": 3380
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.7109899328859061,
|
| 2380 |
+
"grad_norm": 24.48626708984375,
|
| 2381 |
+
"learning_rate": 0.00011064485557207618,
|
| 2382 |
+
"loss": 688.381884765625,
|
| 2383 |
+
"step": 3390
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.7130872483221476,
|
| 2387 |
+
"grad_norm": 25.892141342163086,
|
| 2388 |
+
"learning_rate": 0.00010969566446111879,
|
| 2389 |
+
"loss": 690.50966796875,
|
| 2390 |
+
"step": 3400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.7151845637583892,
|
| 2394 |
+
"grad_norm": 23.631595611572266,
|
| 2395 |
+
"learning_rate": 0.00010875135994945229,
|
| 2396 |
+
"loss": 690.73642578125,
|
| 2397 |
+
"step": 3410
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.7172818791946308,
|
| 2401 |
+
"grad_norm": 25.584020614624023,
|
| 2402 |
+
"learning_rate": 0.00010781198387077007,
|
| 2403 |
+
"loss": 691.406640625,
|
| 2404 |
+
"step": 3420
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.7193791946308725,
|
| 2408 |
+
"grad_norm": 25.226858139038086,
|
| 2409 |
+
"learning_rate": 0.00010687757784043082,
|
| 2410 |
+
"loss": 689.0376953125,
|
| 2411 |
+
"step": 3430
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.7214765100671141,
|
| 2415 |
+
"grad_norm": 23.374839782714844,
|
| 2416 |
+
"learning_rate": 0.00010594818325361471,
|
| 2417 |
+
"loss": 688.791650390625,
|
| 2418 |
+
"step": 3440
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.7235738255033557,
|
| 2422 |
+
"grad_norm": 24.697153091430664,
|
| 2423 |
+
"learning_rate": 0.00010502384128348954,
|
| 2424 |
+
"loss": 689.23720703125,
|
| 2425 |
+
"step": 3450
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.7256711409395973,
|
| 2429 |
+
"grad_norm": 25.77028465270996,
|
| 2430 |
+
"learning_rate": 0.00010410459287938703,
|
| 2431 |
+
"loss": 687.74521484375,
|
| 2432 |
+
"step": 3460
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.727768456375839,
|
| 2436 |
+
"grad_norm": 25.273399353027344,
|
| 2437 |
+
"learning_rate": 0.00010319047876498844,
|
| 2438 |
+
"loss": 688.24140625,
|
| 2439 |
+
"step": 3470
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.7298657718120806,
|
| 2443 |
+
"grad_norm": 25.190956115722656,
|
| 2444 |
+
"learning_rate": 0.00010228153943652041,
|
| 2445 |
+
"loss": 684.262451171875,
|
| 2446 |
+
"step": 3480
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.7319630872483222,
|
| 2450 |
+
"grad_norm": 24.785213470458984,
|
| 2451 |
+
"learning_rate": 0.0001013778151609613,
|
| 2452 |
+
"loss": 685.20732421875,
|
| 2453 |
+
"step": 3490
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.7340604026845637,
|
| 2457 |
+
"grad_norm": 24.36125946044922,
|
| 2458 |
+
"learning_rate": 0.00010047934597425688,
|
| 2459 |
+
"loss": 685.501708984375,
|
| 2460 |
+
"step": 3500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.7361577181208053,
|
| 2464 |
+
"grad_norm": 26.047834396362305,
|
| 2465 |
+
"learning_rate": 9.958617167954706e-05,
|
| 2466 |
+
"loss": 683.8818359375,
|
| 2467 |
+
"step": 3510
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.738255033557047,
|
| 2471 |
+
"grad_norm": 22.43846893310547,
|
| 2472 |
+
"learning_rate": 9.869833184540213e-05,
|
| 2473 |
+
"loss": 687.33955078125,
|
| 2474 |
+
"step": 3520
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.7403523489932886,
|
| 2478 |
+
"grad_norm": 22.825130462646484,
|
| 2479 |
+
"learning_rate": 9.781586580407048e-05,
|
| 2480 |
+
"loss": 685.4853515625,
|
| 2481 |
+
"step": 3530
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.7424496644295302,
|
| 2485 |
+
"grad_norm": 23.325157165527344,
|
| 2486 |
+
"learning_rate": 9.693881264973552e-05,
|
| 2487 |
+
"loss": 685.995556640625,
|
| 2488 |
+
"step": 3540
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.7445469798657718,
|
| 2492 |
+
"grad_norm": 23.20819664001465,
|
| 2493 |
+
"learning_rate": 9.606721123678415e-05,
|
| 2494 |
+
"loss": 685.19609375,
|
| 2495 |
+
"step": 3550
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.7466442953020134,
|
| 2499 |
+
"grad_norm": 24.189987182617188,
|
| 2500 |
+
"learning_rate": 9.520110017808516e-05,
|
| 2501 |
+
"loss": 683.45908203125,
|
| 2502 |
+
"step": 3560
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.7487416107382551,
|
| 2506 |
+
"grad_norm": 26.871835708618164,
|
| 2507 |
+
"learning_rate": 9.434051784327894e-05,
|
| 2508 |
+
"loss": 685.9505859375,
|
| 2509 |
+
"step": 3570
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.7508389261744967,
|
| 2513 |
+
"grad_norm": 22.42962646484375,
|
| 2514 |
+
"learning_rate": 9.348550235707753e-05,
|
| 2515 |
+
"loss": 686.2205078125,
|
| 2516 |
+
"step": 3580
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.7529362416107382,
|
| 2520 |
+
"grad_norm": 22.479677200317383,
|
| 2521 |
+
"learning_rate": 9.263609159757563e-05,
|
| 2522 |
+
"loss": 684.18955078125,
|
| 2523 |
+
"step": 3590
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.7550335570469798,
|
| 2527 |
+
"grad_norm": 22.954744338989258,
|
| 2528 |
+
"learning_rate": 9.179232319457263e-05,
|
| 2529 |
+
"loss": 686.7052734375,
|
| 2530 |
+
"step": 3600
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.7571308724832215,
|
| 2534 |
+
"grad_norm": 23.088876724243164,
|
| 2535 |
+
"learning_rate": 9.095423452790545e-05,
|
| 2536 |
+
"loss": 685.3046875,
|
| 2537 |
+
"step": 3610
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.7592281879194631,
|
| 2541 |
+
"grad_norm": 24.69822120666504,
|
| 2542 |
+
"learning_rate": 9.012186272579281e-05,
|
| 2543 |
+
"loss": 685.684521484375,
|
| 2544 |
+
"step": 3620
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.7613255033557047,
|
| 2548 |
+
"grad_norm": 25.845073699951172,
|
| 2549 |
+
"learning_rate": 8.929524466319001e-05,
|
| 2550 |
+
"loss": 683.671142578125,
|
| 2551 |
+
"step": 3630
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.7634228187919463,
|
| 2555 |
+
"grad_norm": 23.543195724487305,
|
| 2556 |
+
"learning_rate": 8.84744169601558e-05,
|
| 2557 |
+
"loss": 684.632177734375,
|
| 2558 |
+
"step": 3640
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.7655201342281879,
|
| 2562 |
+
"grad_norm": 22.957509994506836,
|
| 2563 |
+
"learning_rate": 8.765941598022974e-05,
|
| 2564 |
+
"loss": 685.3962890625,
|
| 2565 |
+
"step": 3650
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.7676174496644296,
|
| 2569 |
+
"grad_norm": 22.979705810546875,
|
| 2570 |
+
"learning_rate": 8.685027782882137e-05,
|
| 2571 |
+
"loss": 683.3501953125,
|
| 2572 |
+
"step": 3660
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.7697147651006712,
|
| 2576 |
+
"grad_norm": 22.801042556762695,
|
| 2577 |
+
"learning_rate": 8.604703835161078e-05,
|
| 2578 |
+
"loss": 680.969775390625,
|
| 2579 |
+
"step": 3670
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.7718120805369127,
|
| 2583 |
+
"grad_norm": 23.970422744750977,
|
| 2584 |
+
"learning_rate": 8.524973313296044e-05,
|
| 2585 |
+
"loss": 683.797705078125,
|
| 2586 |
+
"step": 3680
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.7739093959731543,
|
| 2590 |
+
"grad_norm": 23.845319747924805,
|
| 2591 |
+
"learning_rate": 8.445839749433879e-05,
|
| 2592 |
+
"loss": 680.916796875,
|
| 2593 |
+
"step": 3690
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.7760067114093959,
|
| 2597 |
+
"grad_norm": 23.90414047241211,
|
| 2598 |
+
"learning_rate": 8.36730664927557e-05,
|
| 2599 |
+
"loss": 684.574951171875,
|
| 2600 |
+
"step": 3700
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.7781040268456376,
|
| 2604 |
+
"grad_norm": 22.141538619995117,
|
| 2605 |
+
"learning_rate": 8.289377491920906e-05,
|
| 2606 |
+
"loss": 686.685107421875,
|
| 2607 |
+
"step": 3710
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.7802013422818792,
|
| 2611 |
+
"grad_norm": 22.511852264404297,
|
| 2612 |
+
"learning_rate": 8.212055729714395e-05,
|
| 2613 |
+
"loss": 682.07216796875,
|
| 2614 |
+
"step": 3720
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.7822986577181208,
|
| 2618 |
+
"grad_norm": 23.860305786132812,
|
| 2619 |
+
"learning_rate": 8.135344788092268e-05,
|
| 2620 |
+
"loss": 683.2880859375,
|
| 2621 |
+
"step": 3730
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.7843959731543624,
|
| 2625 |
+
"grad_norm": 24.159772872924805,
|
| 2626 |
+
"learning_rate": 8.059248065430754e-05,
|
| 2627 |
+
"loss": 683.333544921875,
|
| 2628 |
+
"step": 3740
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.7864932885906041,
|
| 2632 |
+
"grad_norm": 25.201622009277344,
|
| 2633 |
+
"learning_rate": 7.983768932895552e-05,
|
| 2634 |
+
"loss": 684.48095703125,
|
| 2635 |
+
"step": 3750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.7885906040268457,
|
| 2639 |
+
"grad_norm": 23.27935791015625,
|
| 2640 |
+
"learning_rate": 7.908910734292443e-05,
|
| 2641 |
+
"loss": 682.99365234375,
|
| 2642 |
+
"step": 3760
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.7906879194630873,
|
| 2646 |
+
"grad_norm": 23.803667068481445,
|
| 2647 |
+
"learning_rate": 7.834676785919184e-05,
|
| 2648 |
+
"loss": 683.983349609375,
|
| 2649 |
+
"step": 3770
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.7927852348993288,
|
| 2653 |
+
"grad_norm": 22.286733627319336,
|
| 2654 |
+
"learning_rate": 7.761070376418576e-05,
|
| 2655 |
+
"loss": 683.07724609375,
|
| 2656 |
+
"step": 3780
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.7948825503355704,
|
| 2660 |
+
"grad_norm": 23.109832763671875,
|
| 2661 |
+
"learning_rate": 7.688094766632796e-05,
|
| 2662 |
+
"loss": 683.54560546875,
|
| 2663 |
+
"step": 3790
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.7969798657718121,
|
| 2667 |
+
"grad_norm": 22.52189826965332,
|
| 2668 |
+
"learning_rate": 7.615753189458901e-05,
|
| 2669 |
+
"loss": 680.865185546875,
|
| 2670 |
+
"step": 3800
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.7990771812080537,
|
| 2674 |
+
"grad_norm": 24.4259090423584,
|
| 2675 |
+
"learning_rate": 7.544048849705643e-05,
|
| 2676 |
+
"loss": 681.9951171875,
|
| 2677 |
+
"step": 3810
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.8011744966442953,
|
| 2681 |
+
"grad_norm": 24.631175994873047,
|
| 2682 |
+
"learning_rate": 7.47298492395148e-05,
|
| 2683 |
+
"loss": 682.766259765625,
|
| 2684 |
+
"step": 3820
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.8032718120805369,
|
| 2688 |
+
"grad_norm": 24.409805297851562,
|
| 2689 |
+
"learning_rate": 7.402564560403849e-05,
|
| 2690 |
+
"loss": 680.79716796875,
|
| 2691 |
+
"step": 3830
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.8053691275167785,
|
| 2695 |
+
"grad_norm": 23.451454162597656,
|
| 2696 |
+
"learning_rate": 7.332790878759689e-05,
|
| 2697 |
+
"loss": 682.815185546875,
|
| 2698 |
+
"step": 3840
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.8074664429530202,
|
| 2702 |
+
"grad_norm": 24.23875617980957,
|
| 2703 |
+
"learning_rate": 7.263666970067252e-05,
|
| 2704 |
+
"loss": 682.263330078125,
|
| 2705 |
+
"step": 3850
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.8095637583892618,
|
| 2709 |
+
"grad_norm": 24.88316535949707,
|
| 2710 |
+
"learning_rate": 7.19519589658916e-05,
|
| 2711 |
+
"loss": 680.236279296875,
|
| 2712 |
+
"step": 3860
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.8116610738255033,
|
| 2716 |
+
"grad_norm": 24.26546859741211,
|
| 2717 |
+
"learning_rate": 7.127380691666728e-05,
|
| 2718 |
+
"loss": 682.1150390625,
|
| 2719 |
+
"step": 3870
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.8137583892617449,
|
| 2723 |
+
"grad_norm": 24.102313995361328,
|
| 2724 |
+
"learning_rate": 7.060224359585608e-05,
|
| 2725 |
+
"loss": 680.230615234375,
|
| 2726 |
+
"step": 3880
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.8158557046979866,
|
| 2730 |
+
"grad_norm": 23.298391342163086,
|
| 2731 |
+
"learning_rate": 6.993729875442679e-05,
|
| 2732 |
+
"loss": 683.053955078125,
|
| 2733 |
+
"step": 3890
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.8179530201342282,
|
| 2737 |
+
"grad_norm": 22.2108097076416,
|
| 2738 |
+
"learning_rate": 6.927900185014261e-05,
|
| 2739 |
+
"loss": 679.271044921875,
|
| 2740 |
+
"step": 3900
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.8200503355704698,
|
| 2744 |
+
"grad_norm": 25.65964126586914,
|
| 2745 |
+
"learning_rate": 6.862738204625598e-05,
|
| 2746 |
+
"loss": 681.87509765625,
|
| 2747 |
+
"step": 3910
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.8221476510067114,
|
| 2751 |
+
"grad_norm": 24.050338745117188,
|
| 2752 |
+
"learning_rate": 6.798246821021675e-05,
|
| 2753 |
+
"loss": 679.88876953125,
|
| 2754 |
+
"step": 3920
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.824244966442953,
|
| 2758 |
+
"grad_norm": 24.42888832092285,
|
| 2759 |
+
"learning_rate": 6.734428891239319e-05,
|
| 2760 |
+
"loss": 680.12578125,
|
| 2761 |
+
"step": 3930
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.8263422818791947,
|
| 2765 |
+
"grad_norm": 24.935672760009766,
|
| 2766 |
+
"learning_rate": 6.671287242480648e-05,
|
| 2767 |
+
"loss": 681.04013671875,
|
| 2768 |
+
"step": 3940
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.8284395973154363,
|
| 2772 |
+
"grad_norm": 25.129545211791992,
|
| 2773 |
+
"learning_rate": 6.608824671987803e-05,
|
| 2774 |
+
"loss": 678.59296875,
|
| 2775 |
+
"step": 3950
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.8305369127516778,
|
| 2779 |
+
"grad_norm": 24.83428192138672,
|
| 2780 |
+
"learning_rate": 6.547043946919043e-05,
|
| 2781 |
+
"loss": 682.446533203125,
|
| 2782 |
+
"step": 3960
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.8326342281879194,
|
| 2786 |
+
"grad_norm": 24.628469467163086,
|
| 2787 |
+
"learning_rate": 6.485947804226143e-05,
|
| 2788 |
+
"loss": 677.285546875,
|
| 2789 |
+
"step": 3970
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.834731543624161,
|
| 2793 |
+
"grad_norm": 24.317861557006836,
|
| 2794 |
+
"learning_rate": 6.425538950533153e-05,
|
| 2795 |
+
"loss": 679.77578125,
|
| 2796 |
+
"step": 3980
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.8368288590604027,
|
| 2800 |
+
"grad_norm": 23.234214782714844,
|
| 2801 |
+
"learning_rate": 6.36582006201649e-05,
|
| 2802 |
+
"loss": 680.6521484375,
|
| 2803 |
+
"step": 3990
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.8389261744966443,
|
| 2807 |
+
"grad_norm": 22.52564811706543,
|
| 2808 |
+
"learning_rate": 6.306793784286387e-05,
|
| 2809 |
+
"loss": 677.32109375,
|
| 2810 |
+
"step": 4000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.8410234899328859,
|
| 2814 |
+
"grad_norm": 23.42584800720215,
|
| 2815 |
+
"learning_rate": 6.248462732269678e-05,
|
| 2816 |
+
"loss": 681.26416015625,
|
| 2817 |
+
"step": 4010
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.8431208053691275,
|
| 2821 |
+
"grad_norm": 23.126731872558594,
|
| 2822 |
+
"learning_rate": 6.190829490093956e-05,
|
| 2823 |
+
"loss": 677.49208984375,
|
| 2824 |
+
"step": 4020
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.8452181208053692,
|
| 2828 |
+
"grad_norm": 23.167861938476562,
|
| 2829 |
+
"learning_rate": 6.133896610973102e-05,
|
| 2830 |
+
"loss": 680.8375,
|
| 2831 |
+
"step": 4030
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.8473154362416108,
|
| 2835 |
+
"grad_norm": 22.692258834838867,
|
| 2836 |
+
"learning_rate": 6.0776666170941634e-05,
|
| 2837 |
+
"loss": 679.8037109375,
|
| 2838 |
+
"step": 4040
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.8494127516778524,
|
| 2842 |
+
"grad_norm": 22.7047061920166,
|
| 2843 |
+
"learning_rate": 6.022141999505628e-05,
|
| 2844 |
+
"loss": 681.933935546875,
|
| 2845 |
+
"step": 4050
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.8515100671140939,
|
| 2849 |
+
"grad_norm": 23.45292091369629,
|
| 2850 |
+
"learning_rate": 5.967325218007066e-05,
|
| 2851 |
+
"loss": 680.2009765625,
|
| 2852 |
+
"step": 4060
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.8536073825503355,
|
| 2856 |
+
"grad_norm": 24.43787956237793,
|
| 2857 |
+
"learning_rate": 5.913218701040155e-05,
|
| 2858 |
+
"loss": 676.1564453125,
|
| 2859 |
+
"step": 4070
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.8557046979865772,
|
| 2863 |
+
"grad_norm": 24.374242782592773,
|
| 2864 |
+
"learning_rate": 5.859824845581097e-05,
|
| 2865 |
+
"loss": 678.980322265625,
|
| 2866 |
+
"step": 4080
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.8578020134228188,
|
| 2870 |
+
"grad_norm": 23.4588565826416,
|
| 2871 |
+
"learning_rate": 5.807146017034434e-05,
|
| 2872 |
+
"loss": 678.86953125,
|
| 2873 |
+
"step": 4090
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.8598993288590604,
|
| 2877 |
+
"grad_norm": 23.756441116333008,
|
| 2878 |
+
"learning_rate": 5.755184549128258e-05,
|
| 2879 |
+
"loss": 681.618994140625,
|
| 2880 |
+
"step": 4100
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.861996644295302,
|
| 2884 |
+
"grad_norm": 25.192712783813477,
|
| 2885 |
+
"learning_rate": 5.703942743810811e-05,
|
| 2886 |
+
"loss": 677.488037109375,
|
| 2887 |
+
"step": 4110
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 0.8640939597315436,
|
| 2891 |
+
"grad_norm": 24.152353286743164,
|
| 2892 |
+
"learning_rate": 5.653422871148536e-05,
|
| 2893 |
+
"loss": 679.816748046875,
|
| 2894 |
+
"step": 4120
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.8661912751677853,
|
| 2898 |
+
"grad_norm": 22.807497024536133,
|
| 2899 |
+
"learning_rate": 5.6036271692254784e-05,
|
| 2900 |
+
"loss": 678.42666015625,
|
| 2901 |
+
"step": 4130
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.8682885906040269,
|
| 2905 |
+
"grad_norm": 25.389739990234375,
|
| 2906 |
+
"learning_rate": 5.554557844044157e-05,
|
| 2907 |
+
"loss": 679.6646484375,
|
| 2908 |
+
"step": 4140
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.8703859060402684,
|
| 2912 |
+
"grad_norm": 22.66519546508789,
|
| 2913 |
+
"learning_rate": 5.506217069427819e-05,
|
| 2914 |
+
"loss": 676.6759765625,
|
| 2915 |
+
"step": 4150
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.87248322147651,
|
| 2919 |
+
"grad_norm": 24.590576171875,
|
| 2920 |
+
"learning_rate": 5.458606986924159e-05,
|
| 2921 |
+
"loss": 678.8537109375,
|
| 2922 |
+
"step": 4160
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 0.8745805369127517,
|
| 2926 |
+
"grad_norm": 22.72840118408203,
|
| 2927 |
+
"learning_rate": 5.4117297057104274e-05,
|
| 2928 |
+
"loss": 677.28154296875,
|
| 2929 |
+
"step": 4170
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 0.8766778523489933,
|
| 2933 |
+
"grad_norm": 22.46537208557129,
|
| 2934 |
+
"learning_rate": 5.365587302500005e-05,
|
| 2935 |
+
"loss": 675.40986328125,
|
| 2936 |
+
"step": 4180
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.8787751677852349,
|
| 2940 |
+
"grad_norm": 29.71303939819336,
|
| 2941 |
+
"learning_rate": 5.320181821450388e-05,
|
| 2942 |
+
"loss": 677.40400390625,
|
| 2943 |
+
"step": 4190
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 0.8808724832214765,
|
| 2947 |
+
"grad_norm": 23.0802059173584,
|
| 2948 |
+
"learning_rate": 5.2755152740726445e-05,
|
| 2949 |
+
"loss": 674.81826171875,
|
| 2950 |
+
"step": 4200
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 0.8829697986577181,
|
| 2954 |
+
"grad_norm": 23.870975494384766,
|
| 2955 |
+
"learning_rate": 5.231589639142296e-05,
|
| 2956 |
+
"loss": 675.855322265625,
|
| 2957 |
+
"step": 4210
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.8850671140939598,
|
| 2961 |
+
"grad_norm": 24.489511489868164,
|
| 2962 |
+
"learning_rate": 5.1884068626116434e-05,
|
| 2963 |
+
"loss": 676.7513671875,
|
| 2964 |
+
"step": 4220
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.8871644295302014,
|
| 2968 |
+
"grad_norm": 22.859840393066406,
|
| 2969 |
+
"learning_rate": 5.145968857523584e-05,
|
| 2970 |
+
"loss": 675.190576171875,
|
| 2971 |
+
"step": 4230
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.889261744966443,
|
| 2975 |
+
"grad_norm": 23.360322952270508,
|
| 2976 |
+
"learning_rate": 5.1042775039268465e-05,
|
| 2977 |
+
"loss": 672.90810546875,
|
| 2978 |
+
"step": 4240
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.8913590604026845,
|
| 2982 |
+
"grad_norm": 24.995880126953125,
|
| 2983 |
+
"learning_rate": 5.0633346487926995e-05,
|
| 2984 |
+
"loss": 676.45029296875,
|
| 2985 |
+
"step": 4250
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.8934563758389261,
|
| 2989 |
+
"grad_norm": 23.80856704711914,
|
| 2990 |
+
"learning_rate": 5.0231421059331404e-05,
|
| 2991 |
+
"loss": 673.52822265625,
|
| 2992 |
+
"step": 4260
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.8955536912751678,
|
| 2996 |
+
"grad_norm": 24.263673782348633,
|
| 2997 |
+
"learning_rate": 4.9837016559205346e-05,
|
| 2998 |
+
"loss": 674.06865234375,
|
| 2999 |
+
"step": 4270
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.8976510067114094,
|
| 3003 |
+
"grad_norm": 23.509172439575195,
|
| 3004 |
+
"learning_rate": 4.9450150460087276e-05,
|
| 3005 |
+
"loss": 675.976171875,
|
| 3006 |
+
"step": 4280
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 0.899748322147651,
|
| 3010 |
+
"grad_norm": 24.816654205322266,
|
| 3011 |
+
"learning_rate": 4.907083990055655e-05,
|
| 3012 |
+
"loss": 673.865185546875,
|
| 3013 |
+
"step": 4290
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.9018456375838926,
|
| 3017 |
+
"grad_norm": 23.49567222595215,
|
| 3018 |
+
"learning_rate": 4.8699101684474055e-05,
|
| 3019 |
+
"loss": 676.16005859375,
|
| 3020 |
+
"step": 4300
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.9039429530201343,
|
| 3024 |
+
"grad_norm": 25.57634925842285,
|
| 3025 |
+
"learning_rate": 4.8334952280237875e-05,
|
| 3026 |
+
"loss": 673.1826171875,
|
| 3027 |
+
"step": 4310
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 0.9060402684563759,
|
| 3031 |
+
"grad_norm": 24.98488998413086,
|
| 3032 |
+
"learning_rate": 4.797840782005362e-05,
|
| 3033 |
+
"loss": 676.1115234375,
|
| 3034 |
+
"step": 4320
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.9081375838926175,
|
| 3038 |
+
"grad_norm": 24.250463485717773,
|
| 3039 |
+
"learning_rate": 4.762948409921976e-05,
|
| 3040 |
+
"loss": 674.84365234375,
|
| 3041 |
+
"step": 4330
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.910234899328859,
|
| 3045 |
+
"grad_norm": 25.994915008544922,
|
| 3046 |
+
"learning_rate": 4.7288196575427945e-05,
|
| 3047 |
+
"loss": 674.15810546875,
|
| 3048 |
+
"step": 4340
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 0.9123322147651006,
|
| 3052 |
+
"grad_norm": 22.44687271118164,
|
| 3053 |
+
"learning_rate": 4.69545603680782e-05,
|
| 3054 |
+
"loss": 673.69814453125,
|
| 3055 |
+
"step": 4350
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.9144295302013423,
|
| 3059 |
+
"grad_norm": 24.059288024902344,
|
| 3060 |
+
"learning_rate": 4.6628590257609074e-05,
|
| 3061 |
+
"loss": 675.2294921875,
|
| 3062 |
+
"step": 4360
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.9165268456375839,
|
| 3066 |
+
"grad_norm": 23.866180419921875,
|
| 3067 |
+
"learning_rate": 4.63103006848429e-05,
|
| 3068 |
+
"loss": 674.218896484375,
|
| 3069 |
+
"step": 4370
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.9186241610738255,
|
| 3073 |
+
"grad_norm": 23.916122436523438,
|
| 3074 |
+
"learning_rate": 4.599970575034604e-05,
|
| 3075 |
+
"loss": 674.363037109375,
|
| 3076 |
+
"step": 4380
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.9207214765100671,
|
| 3080 |
+
"grad_norm": 26.1231632232666,
|
| 3081 |
+
"learning_rate": 4.569681921380412e-05,
|
| 3082 |
+
"loss": 675.52900390625,
|
| 3083 |
+
"step": 4390
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.9228187919463087,
|
| 3087 |
+
"grad_norm": 24.31917953491211,
|
| 3088 |
+
"learning_rate": 4.540165449341264e-05,
|
| 3089 |
+
"loss": 671.547607421875,
|
| 3090 |
+
"step": 4400
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.9249161073825504,
|
| 3094 |
+
"grad_norm": 25.087600708007812,
|
| 3095 |
+
"learning_rate": 4.511422466528239e-05,
|
| 3096 |
+
"loss": 673.746875,
|
| 3097 |
+
"step": 4410
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.927013422818792,
|
| 3101 |
+
"grad_norm": 25.387001037597656,
|
| 3102 |
+
"learning_rate": 4.4834542462860253e-05,
|
| 3103 |
+
"loss": 672.59580078125,
|
| 3104 |
+
"step": 4420
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.9291107382550335,
|
| 3108 |
+
"grad_norm": 25.317588806152344,
|
| 3109 |
+
"learning_rate": 4.4562620276364964e-05,
|
| 3110 |
+
"loss": 670.037890625,
|
| 3111 |
+
"step": 4430
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 0.9312080536912751,
|
| 3115 |
+
"grad_norm": 26.259300231933594,
|
| 3116 |
+
"learning_rate": 4.4298470152238445e-05,
|
| 3117 |
+
"loss": 672.92578125,
|
| 3118 |
+
"step": 4440
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 0.9333053691275168,
|
| 3122 |
+
"grad_norm": 26.846012115478516,
|
| 3123 |
+
"learning_rate": 4.404210379261189e-05,
|
| 3124 |
+
"loss": 672.447265625,
|
| 3125 |
+
"step": 4450
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 0.9354026845637584,
|
| 3129 |
+
"grad_norm": 23.90787124633789,
|
| 3130 |
+
"learning_rate": 4.3793532554787466e-05,
|
| 3131 |
+
"loss": 672.944970703125,
|
| 3132 |
+
"step": 4460
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 0.9375,
|
| 3136 |
+
"grad_norm": 28.882965087890625,
|
| 3137 |
+
"learning_rate": 4.355276745073519e-05,
|
| 3138 |
+
"loss": 671.073095703125,
|
| 3139 |
+
"step": 4470
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 0.9395973154362416,
|
| 3143 |
+
"grad_norm": 26.22090721130371,
|
| 3144 |
+
"learning_rate": 4.3319819146605076e-05,
|
| 3145 |
+
"loss": 674.5400390625,
|
| 3146 |
+
"step": 4480
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.9416946308724832,
|
| 3150 |
+
"grad_norm": 24.984975814819336,
|
| 3151 |
+
"learning_rate": 4.309469796225452e-05,
|
| 3152 |
+
"loss": 675.30908203125,
|
| 3153 |
+
"step": 4490
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 0.9437919463087249,
|
| 3157 |
+
"grad_norm": 23.35356903076172,
|
| 3158 |
+
"learning_rate": 4.2877413870791265e-05,
|
| 3159 |
+
"loss": 675.83837890625,
|
| 3160 |
+
"step": 4500
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 0.9458892617449665,
|
| 3164 |
+
"grad_norm": 26.29161834716797,
|
| 3165 |
+
"learning_rate": 4.2667976498131484e-05,
|
| 3166 |
+
"loss": 673.48466796875,
|
| 3167 |
+
"step": 4510
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 0.947986577181208,
|
| 3171 |
+
"grad_norm": 24.633699417114258,
|
| 3172 |
+
"learning_rate": 4.2466395122573355e-05,
|
| 3173 |
+
"loss": 674.9208984375,
|
| 3174 |
+
"step": 4520
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 0.9500838926174496,
|
| 3178 |
+
"grad_norm": 23.10916519165039,
|
| 3179 |
+
"learning_rate": 4.227267867438603e-05,
|
| 3180 |
+
"loss": 676.23984375,
|
| 3181 |
+
"step": 4530
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.9521812080536913,
|
| 3185 |
+
"grad_norm": 26.628690719604492,
|
| 3186 |
+
"learning_rate": 4.208683573541408e-05,
|
| 3187 |
+
"loss": 678.2919921875,
|
| 3188 |
+
"step": 4540
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.9542785234899329,
|
| 3192 |
+
"grad_norm": 25.501096725463867,
|
| 3193 |
+
"learning_rate": 4.1908874538697176e-05,
|
| 3194 |
+
"loss": 674.9896484375,
|
| 3195 |
+
"step": 4550
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 0.9563758389261745,
|
| 3199 |
+
"grad_norm": 26.29096794128418,
|
| 3200 |
+
"learning_rate": 4.1738802968105485e-05,
|
| 3201 |
+
"loss": 675.5177734375,
|
| 3202 |
+
"step": 4560
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 0.9584731543624161,
|
| 3206 |
+
"grad_norm": 25.067407608032227,
|
| 3207 |
+
"learning_rate": 4.1576628557990294e-05,
|
| 3208 |
+
"loss": 674.130517578125,
|
| 3209 |
+
"step": 4570
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 0.9605704697986577,
|
| 3213 |
+
"grad_norm": 25.92313003540039,
|
| 3214 |
+
"learning_rate": 4.142235849285035e-05,
|
| 3215 |
+
"loss": 675.11962890625,
|
| 3216 |
+
"step": 4580
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 0.9626677852348994,
|
| 3220 |
+
"grad_norm": 26.59023666381836,
|
| 3221 |
+
"learning_rate": 4.127599960701349e-05,
|
| 3222 |
+
"loss": 676.64970703125,
|
| 3223 |
+
"step": 4590
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 0.964765100671141,
|
| 3227 |
+
"grad_norm": 25.86935806274414,
|
| 3228 |
+
"learning_rate": 4.113755838433387e-05,
|
| 3229 |
+
"loss": 673.15,
|
| 3230 |
+
"step": 4600
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 0.9668624161073825,
|
| 3234 |
+
"grad_norm": 26.771474838256836,
|
| 3235 |
+
"learning_rate": 4.1007040957904835e-05,
|
| 3236 |
+
"loss": 673.42724609375,
|
| 3237 |
+
"step": 4610
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 0.9689597315436241,
|
| 3241 |
+
"grad_norm": 23.894729614257812,
|
| 3242 |
+
"learning_rate": 4.088445310978703e-05,
|
| 3243 |
+
"loss": 671.387646484375,
|
| 3244 |
+
"step": 4620
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 0.9710570469798657,
|
| 3248 |
+
"grad_norm": 25.638530731201172,
|
| 3249 |
+
"learning_rate": 4.076980027075245e-05,
|
| 3250 |
+
"loss": 670.821240234375,
|
| 3251 |
+
"step": 4630
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 0.9731543624161074,
|
| 3255 |
+
"grad_norm": 29.335660934448242,
|
| 3256 |
+
"learning_rate": 4.066308752004368e-05,
|
| 3257 |
+
"loss": 672.8646484375,
|
| 3258 |
+
"step": 4640
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 0.975251677852349,
|
| 3262 |
+
"grad_norm": 24.27260971069336,
|
| 3263 |
+
"learning_rate": 4.056431958514902e-05,
|
| 3264 |
+
"loss": 672.34208984375,
|
| 3265 |
+
"step": 4650
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 0.9773489932885906,
|
| 3269 |
+
"grad_norm": 25.83704948425293,
|
| 3270 |
+
"learning_rate": 4.047350084159293e-05,
|
| 3271 |
+
"loss": 672.367578125,
|
| 3272 |
+
"step": 4660
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 0.9794463087248322,
|
| 3276 |
+
"grad_norm": 24.82935905456543,
|
| 3277 |
+
"learning_rate": 4.039063531274225e-05,
|
| 3278 |
+
"loss": 671.880322265625,
|
| 3279 |
+
"step": 4670
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 0.9815436241610739,
|
| 3283 |
+
"grad_norm": 25.728792190551758,
|
| 3284 |
+
"learning_rate": 4.0315726669628004e-05,
|
| 3285 |
+
"loss": 671.256298828125,
|
| 3286 |
+
"step": 4680
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.9836409395973155,
|
| 3290 |
+
"grad_norm": 26.020658493041992,
|
| 3291 |
+
"learning_rate": 4.0248778230782685e-05,
|
| 3292 |
+
"loss": 672.35029296875,
|
| 3293 |
+
"step": 4690
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 0.985738255033557,
|
| 3297 |
+
"grad_norm": 26.47356414794922,
|
| 3298 |
+
"learning_rate": 4.018979296209327e-05,
|
| 3299 |
+
"loss": 671.268408203125,
|
| 3300 |
+
"step": 4700
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 0.9878355704697986,
|
| 3304 |
+
"grad_norm": 25.695480346679688,
|
| 3305 |
+
"learning_rate": 4.013877347666988e-05,
|
| 3306 |
+
"loss": 669.023486328125,
|
| 3307 |
+
"step": 4710
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.9899328859060402,
|
| 3311 |
+
"grad_norm": 28.546607971191406,
|
| 3312 |
+
"learning_rate": 4.009572203472991e-05,
|
| 3313 |
+
"loss": 675.0337890625,
|
| 3314 |
+
"step": 4720
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.9920302013422819,
|
| 3318 |
+
"grad_norm": 24.35601043701172,
|
| 3319 |
+
"learning_rate": 4.0060640543498e-05,
|
| 3320 |
+
"loss": 675.898876953125,
|
| 3321 |
+
"step": 4730
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 0.9941275167785235,
|
| 3325 |
+
"grad_norm": 25.573619842529297,
|
| 3326 |
+
"learning_rate": 4.003353055712148e-05,
|
| 3327 |
+
"loss": 674.478271484375,
|
| 3328 |
+
"step": 4740
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 0.9962248322147651,
|
| 3332 |
+
"grad_norm": 24.39256477355957,
|
| 3333 |
+
"learning_rate": 4.0014393276601606e-05,
|
| 3334 |
+
"loss": 675.296240234375,
|
| 3335 |
+
"step": 4750
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 0.9983221476510067,
|
| 3339 |
+
"grad_norm": 25.135915756225586,
|
| 3340 |
+
"learning_rate": 4.000322954974018e-05,
|
| 3341 |
+
"loss": 676.800146484375,
|
| 3342 |
+
"step": 4760
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 1.0,
|
| 3346 |
+
"step": 4768,
|
| 3347 |
+
"total_flos": 2.1166212224737346e+19,
|
| 3348 |
+
"train_loss": 764.8368647018535,
|
| 3349 |
+
"train_runtime": 201110.1372,
|
| 3350 |
+
"train_samples_per_second": 12.139,
|
| 3351 |
+
"train_steps_per_second": 0.024
|
| 3352 |
+
}
|
| 3353 |
+
],
|
| 3354 |
+
"logging_steps": 10,
|
| 3355 |
+
"max_steps": 4768,
|
| 3356 |
+
"num_input_tokens_seen": 0,
|
| 3357 |
+
"num_train_epochs": 9223372036854775807,
|
| 3358 |
+
"save_steps": 500,
|
| 3359 |
+
"stateful_callbacks": {
|
| 3360 |
+
"TrainerControl": {
|
| 3361 |
+
"args": {
|
| 3362 |
+
"should_epoch_stop": false,
|
| 3363 |
+
"should_evaluate": false,
|
| 3364 |
+
"should_log": false,
|
| 3365 |
+
"should_save": true,
|
| 3366 |
+
"should_training_stop": true
|
| 3367 |
+
},
|
| 3368 |
+
"attributes": {}
|
| 3369 |
+
}
|
| 3370 |
+
},
|
| 3371 |
+
"total_flos": 2.1166212224737346e+19,
|
| 3372 |
+
"train_batch_size": 2,
|
| 3373 |
+
"trial_name": null,
|
| 3374 |
+
"trial_params": null
|
| 3375 |
+
}
|