Ben Buddendorff commited on
Commit ·
35bb4b1
1
Parent(s): 9548349
train_residue_list_lr_3e-4_epochs_4
Browse files- README.md +8 -18
- all_results.json +11 -11
- config.json +31 -0
- eval_results.json +6 -6
- generation_config.json +7 -0
- model_eval_results.csv +0 -0
- special_tokens_map.json +7 -1
- tokenizer_config.json +0 -1
- trainer_log.jsonl +185 -184
- trainer_state.json +1100 -740
- training_args.bin +2 -2
- training_eval_loss.png +2 -2
- training_loss.png +2 -2
README.md
CHANGED
|
@@ -7,19 +7,19 @@ tags:
|
|
| 7 |
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
-
- name:
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
-
#
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [GreatCaptainNemo/ProLLaMA_Stage_1](https://huggingface.co/GreatCaptainNemo/ProLLaMA_Stage_1) on the adpr_train dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Num Input Tokens Seen:
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -51,22 +51,12 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 55 |
-
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
|
| 56 |
-
| 0.4689 | 0.4561 | 100 | 0.4738 | 1230464 |
|
| 57 |
-
| 0.4141 | 0.9122 | 200 | 0.4266 | 2455680 |
|
| 58 |
-
| 0.3463 | 1.3649 | 300 | 0.3486 | 3673744 |
|
| 59 |
-
| 0.3069 | 1.8210 | 400 | 0.3009 | 4901648 |
|
| 60 |
-
| 0.2464 | 2.2737 | 500 | 0.2616 | 6120272 |
|
| 61 |
-
| 0.2138 | 2.7298 | 600 | 0.2381 | 7348944 |
|
| 62 |
-
| 0.1573 | 3.1824 | 700 | 0.2320 | 8570128 |
|
| 63 |
-
| 0.1488 | 3.6385 | 800 | 0.2253 | 9801744 |
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
-
- PEFT 0.
|
| 69 |
-
- Transformers 4.
|
| 70 |
-
- Pytorch 2.
|
| 71 |
-
- Datasets 3.
|
| 72 |
- Tokenizers 0.21.1
|
|
|
|
| 7 |
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
+
- name: train_202507141200
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
+
# train_202507141200
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [GreatCaptainNemo/ProLLaMA_Stage_1](https://huggingface.co/GreatCaptainNemo/ProLLaMA_Stage_1) on the adpr_train dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2193
|
| 22 |
+
- Num Input Tokens Seen: 10772736
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
+
- PEFT 0.15.2
|
| 59 |
+
- Transformers 4.52.4
|
| 60 |
+
- Pytorch 2.6.0+cu124
|
| 61 |
+
- Datasets 3.6.0
|
| 62 |
- Tokenizers 0.21.1
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
-
"num_input_tokens_seen":
|
| 8 |
-
"total_flos": 4.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_loss": 0.21931865811347961,
|
| 4 |
+
"eval_runtime": 32.2123,
|
| 5 |
+
"eval_samples_per_second": 96.795,
|
| 6 |
+
"eval_steps_per_second": 6.054,
|
| 7 |
+
"num_input_tokens_seen": 10772736,
|
| 8 |
+
"total_flos": 4.374108802866217e+17,
|
| 9 |
+
"train_loss": 0.3781262902373617,
|
| 10 |
+
"train_runtime": 4269.5185,
|
| 11 |
+
"train_samples_per_second": 26.287,
|
| 12 |
+
"train_steps_per_second": 0.206
|
| 13 |
}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"outputs_attentions": true,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.52.4",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 32000
|
| 31 |
+
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
-
"num_input_tokens_seen":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_loss": 0.21931865811347961,
|
| 4 |
+
"eval_runtime": 32.2123,
|
| 5 |
+
"eval_samples_per_second": 96.795,
|
| 6 |
+
"eval_steps_per_second": 6.054,
|
| 7 |
+
"num_input_tokens_seen": 10772736
|
| 8 |
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.52.4"
|
| 7 |
+
}
|
model_eval_results.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -29,7 +29,6 @@
|
|
| 29 |
}
|
| 30 |
},
|
| 31 |
"bos_token": "<s>",
|
| 32 |
-
"chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + content + '\n\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n\n' }}{% endif %}{% endfor %}",
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"extra_special_tokens": {},
|
|
|
|
| 29 |
}
|
| 30 |
},
|
| 31 |
"bos_token": "<s>",
|
|
|
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"extra_special_tokens": {},
|
trainer_log.jsonl
CHANGED
|
@@ -1,184 +1,185 @@
|
|
| 1 |
-
{"current_steps": 5, "total_steps":
|
| 2 |
-
{"current_steps": 10, "total_steps":
|
| 3 |
-
{"current_steps": 15, "total_steps":
|
| 4 |
-
{"current_steps": 20, "total_steps":
|
| 5 |
-
{"current_steps": 25, "total_steps":
|
| 6 |
-
{"current_steps": 30, "total_steps":
|
| 7 |
-
{"current_steps": 35, "total_steps":
|
| 8 |
-
{"current_steps": 40, "total_steps":
|
| 9 |
-
{"current_steps": 45, "total_steps":
|
| 10 |
-
{"current_steps": 50, "total_steps":
|
| 11 |
-
{"current_steps": 55, "total_steps":
|
| 12 |
-
{"current_steps": 60, "total_steps":
|
| 13 |
-
{"current_steps": 65, "total_steps":
|
| 14 |
-
{"current_steps": 70, "total_steps":
|
| 15 |
-
{"current_steps": 75, "total_steps":
|
| 16 |
-
{"current_steps": 80, "total_steps":
|
| 17 |
-
{"current_steps": 85, "total_steps":
|
| 18 |
-
{"current_steps": 90, "total_steps":
|
| 19 |
-
{"current_steps": 95, "total_steps":
|
| 20 |
-
{"current_steps": 100, "total_steps":
|
| 21 |
-
{"current_steps": 100, "total_steps":
|
| 22 |
-
{"current_steps": 105, "total_steps":
|
| 23 |
-
{"current_steps": 110, "total_steps":
|
| 24 |
-
{"current_steps": 115, "total_steps":
|
| 25 |
-
{"current_steps": 120, "total_steps":
|
| 26 |
-
{"current_steps": 125, "total_steps":
|
| 27 |
-
{"current_steps": 130, "total_steps":
|
| 28 |
-
{"current_steps": 135, "total_steps":
|
| 29 |
-
{"current_steps": 140, "total_steps":
|
| 30 |
-
{"current_steps": 145, "total_steps":
|
| 31 |
-
{"current_steps": 150, "total_steps":
|
| 32 |
-
{"current_steps": 155, "total_steps":
|
| 33 |
-
{"current_steps": 160, "total_steps":
|
| 34 |
-
{"current_steps": 165, "total_steps":
|
| 35 |
-
{"current_steps": 170, "total_steps":
|
| 36 |
-
{"current_steps": 175, "total_steps":
|
| 37 |
-
{"current_steps": 180, "total_steps":
|
| 38 |
-
{"current_steps": 185, "total_steps":
|
| 39 |
-
{"current_steps": 190, "total_steps":
|
| 40 |
-
{"current_steps": 195, "total_steps":
|
| 41 |
-
{"current_steps": 200, "total_steps":
|
| 42 |
-
{"current_steps": 200, "total_steps":
|
| 43 |
-
{"current_steps": 205, "total_steps":
|
| 44 |
-
{"current_steps": 210, "total_steps":
|
| 45 |
-
{"current_steps": 215, "total_steps":
|
| 46 |
-
{"current_steps": 220, "total_steps":
|
| 47 |
-
{"current_steps": 225, "total_steps":
|
| 48 |
-
{"current_steps": 230, "total_steps":
|
| 49 |
-
{"current_steps": 235, "total_steps":
|
| 50 |
-
{"current_steps": 240, "total_steps":
|
| 51 |
-
{"current_steps": 245, "total_steps":
|
| 52 |
-
{"current_steps": 250, "total_steps":
|
| 53 |
-
{"current_steps": 255, "total_steps":
|
| 54 |
-
{"current_steps": 260, "total_steps":
|
| 55 |
-
{"current_steps": 265, "total_steps":
|
| 56 |
-
{"current_steps": 270, "total_steps":
|
| 57 |
-
{"current_steps": 275, "total_steps":
|
| 58 |
-
{"current_steps": 280, "total_steps":
|
| 59 |
-
{"current_steps": 285, "total_steps":
|
| 60 |
-
{"current_steps": 290, "total_steps":
|
| 61 |
-
{"current_steps": 295, "total_steps":
|
| 62 |
-
{"current_steps": 300, "total_steps":
|
| 63 |
-
{"current_steps": 300, "total_steps":
|
| 64 |
-
{"current_steps": 305, "total_steps":
|
| 65 |
-
{"current_steps": 310, "total_steps":
|
| 66 |
-
{"current_steps": 315, "total_steps":
|
| 67 |
-
{"current_steps": 320, "total_steps":
|
| 68 |
-
{"current_steps": 325, "total_steps":
|
| 69 |
-
{"current_steps": 330, "total_steps":
|
| 70 |
-
{"current_steps": 335, "total_steps":
|
| 71 |
-
{"current_steps": 340, "total_steps":
|
| 72 |
-
{"current_steps": 345, "total_steps":
|
| 73 |
-
{"current_steps": 350, "total_steps":
|
| 74 |
-
{"current_steps": 355, "total_steps":
|
| 75 |
-
{"current_steps": 360, "total_steps":
|
| 76 |
-
{"current_steps": 365, "total_steps":
|
| 77 |
-
{"current_steps": 370, "total_steps":
|
| 78 |
-
{"current_steps": 375, "total_steps":
|
| 79 |
-
{"current_steps": 380, "total_steps":
|
| 80 |
-
{"current_steps": 385, "total_steps":
|
| 81 |
-
{"current_steps": 390, "total_steps":
|
| 82 |
-
{"current_steps": 395, "total_steps":
|
| 83 |
-
{"current_steps": 400, "total_steps":
|
| 84 |
-
{"current_steps": 400, "total_steps":
|
| 85 |
-
{"current_steps": 405, "total_steps":
|
| 86 |
-
{"current_steps": 410, "total_steps":
|
| 87 |
-
{"current_steps": 415, "total_steps":
|
| 88 |
-
{"current_steps": 420, "total_steps":
|
| 89 |
-
{"current_steps": 425, "total_steps":
|
| 90 |
-
{"current_steps": 430, "total_steps":
|
| 91 |
-
{"current_steps": 435, "total_steps":
|
| 92 |
-
{"current_steps": 440, "total_steps":
|
| 93 |
-
{"current_steps": 445, "total_steps":
|
| 94 |
-
{"current_steps": 450, "total_steps":
|
| 95 |
-
{"current_steps": 455, "total_steps":
|
| 96 |
-
{"current_steps": 460, "total_steps":
|
| 97 |
-
{"current_steps": 465, "total_steps":
|
| 98 |
-
{"current_steps": 470, "total_steps":
|
| 99 |
-
{"current_steps": 475, "total_steps":
|
| 100 |
-
{"current_steps": 480, "total_steps":
|
| 101 |
-
{"current_steps": 485, "total_steps":
|
| 102 |
-
{"current_steps": 490, "total_steps":
|
| 103 |
-
{"current_steps": 495, "total_steps":
|
| 104 |
-
{"current_steps": 500, "total_steps":
|
| 105 |
-
{"current_steps": 500, "total_steps":
|
| 106 |
-
{"current_steps": 505, "total_steps":
|
| 107 |
-
{"current_steps": 510, "total_steps":
|
| 108 |
-
{"current_steps": 515, "total_steps":
|
| 109 |
-
{"current_steps": 520, "total_steps":
|
| 110 |
-
{"current_steps": 525, "total_steps":
|
| 111 |
-
{"current_steps": 530, "total_steps":
|
| 112 |
-
{"current_steps": 535, "total_steps":
|
| 113 |
-
{"current_steps": 540, "total_steps":
|
| 114 |
-
{"current_steps": 545, "total_steps":
|
| 115 |
-
{"current_steps": 550, "total_steps":
|
| 116 |
-
{"current_steps": 555, "total_steps":
|
| 117 |
-
{"current_steps": 560, "total_steps":
|
| 118 |
-
{"current_steps": 565, "total_steps":
|
| 119 |
-
{"current_steps": 570, "total_steps":
|
| 120 |
-
{"current_steps": 575, "total_steps":
|
| 121 |
-
{"current_steps": 580, "total_steps":
|
| 122 |
-
{"current_steps": 585, "total_steps":
|
| 123 |
-
{"current_steps": 590, "total_steps":
|
| 124 |
-
{"current_steps": 595, "total_steps":
|
| 125 |
-
{"current_steps": 600, "total_steps":
|
| 126 |
-
{"current_steps": 600, "total_steps":
|
| 127 |
-
{"current_steps": 605, "total_steps":
|
| 128 |
-
{"current_steps": 610, "total_steps":
|
| 129 |
-
{"current_steps": 615, "total_steps":
|
| 130 |
-
{"current_steps": 620, "total_steps":
|
| 131 |
-
{"current_steps": 625, "total_steps":
|
| 132 |
-
{"current_steps": 630, "total_steps":
|
| 133 |
-
{"current_steps": 635, "total_steps":
|
| 134 |
-
{"current_steps": 640, "total_steps":
|
| 135 |
-
{"current_steps": 645, "total_steps":
|
| 136 |
-
{"current_steps": 650, "total_steps":
|
| 137 |
-
{"current_steps": 655, "total_steps":
|
| 138 |
-
{"current_steps": 660, "total_steps":
|
| 139 |
-
{"current_steps": 665, "total_steps":
|
| 140 |
-
{"current_steps": 670, "total_steps":
|
| 141 |
-
{"current_steps": 675, "total_steps":
|
| 142 |
-
{"current_steps": 680, "total_steps":
|
| 143 |
-
{"current_steps": 685, "total_steps":
|
| 144 |
-
{"current_steps": 690, "total_steps":
|
| 145 |
-
{"current_steps": 695, "total_steps":
|
| 146 |
-
{"current_steps": 700, "total_steps":
|
| 147 |
-
{"current_steps": 700, "total_steps":
|
| 148 |
-
{"current_steps": 705, "total_steps":
|
| 149 |
-
{"current_steps": 710, "total_steps":
|
| 150 |
-
{"current_steps": 715, "total_steps":
|
| 151 |
-
{"current_steps": 720, "total_steps":
|
| 152 |
-
{"current_steps": 725, "total_steps":
|
| 153 |
-
{"current_steps": 730, "total_steps":
|
| 154 |
-
{"current_steps": 735, "total_steps":
|
| 155 |
-
{"current_steps": 740, "total_steps":
|
| 156 |
-
{"current_steps": 745, "total_steps":
|
| 157 |
-
{"current_steps": 750, "total_steps":
|
| 158 |
-
{"current_steps": 755, "total_steps":
|
| 159 |
-
{"current_steps": 760, "total_steps":
|
| 160 |
-
{"current_steps": 765, "total_steps":
|
| 161 |
-
{"current_steps": 770, "total_steps":
|
| 162 |
-
{"current_steps": 775, "total_steps":
|
| 163 |
-
{"current_steps": 780, "total_steps":
|
| 164 |
-
{"current_steps": 785, "total_steps":
|
| 165 |
-
{"current_steps": 790, "total_steps":
|
| 166 |
-
{"current_steps": 795, "total_steps":
|
| 167 |
-
{"current_steps": 800, "total_steps":
|
| 168 |
-
{"current_steps": 800, "total_steps":
|
| 169 |
-
{"current_steps": 805, "total_steps":
|
| 170 |
-
{"current_steps": 810, "total_steps":
|
| 171 |
-
{"current_steps": 815, "total_steps":
|
| 172 |
-
{"current_steps": 820, "total_steps":
|
| 173 |
-
{"current_steps": 825, "total_steps":
|
| 174 |
-
{"current_steps": 830, "total_steps":
|
| 175 |
-
{"current_steps": 835, "total_steps":
|
| 176 |
-
{"current_steps": 840, "total_steps":
|
| 177 |
-
{"current_steps": 845, "total_steps":
|
| 178 |
-
{"current_steps": 850, "total_steps":
|
| 179 |
-
{"current_steps": 855, "total_steps":
|
| 180 |
-
{"current_steps": 860, "total_steps":
|
| 181 |
-
{"current_steps": 865, "total_steps":
|
| 182 |
-
{"current_steps": 870, "total_steps":
|
| 183 |
-
{"current_steps": 875, "total_steps":
|
| 184 |
-
{"current_steps":
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 880, "loss": 12.6644, "lr": 2.9999999999999997e-05, "epoch": 0.02280501710376283, "percentage": 0.57, "elapsed_time": "0:00:24", "remaining_time": "1:10:49", "throughput": 2540.89, "total_tokens": 61696}
|
| 2 |
+
{"current_steps": 10, "total_steps": 880, "loss": 5.0641, "lr": 6.75e-05, "epoch": 0.04561003420752566, "percentage": 1.14, "elapsed_time": "0:00:47", "remaining_time": "1:08:11", "throughput": 2618.17, "total_tokens": 123136}
|
| 3 |
+
{"current_steps": 15, "total_steps": 880, "loss": 1.5053, "lr": 0.00010499999999999999, "epoch": 0.06841505131128849, "percentage": 1.7, "elapsed_time": "0:01:09", "remaining_time": "1:07:12", "throughput": 2642.91, "total_tokens": 184832}
|
| 4 |
+
{"current_steps": 20, "total_steps": 880, "loss": 0.6917, "lr": 0.0001425, "epoch": 0.09122006841505131, "percentage": 2.27, "elapsed_time": "0:01:33", "remaining_time": "1:06:42", "throughput": 2659.34, "total_tokens": 247552}
|
| 5 |
+
{"current_steps": 25, "total_steps": 880, "loss": 0.5721, "lr": 0.00017999999999999998, "epoch": 0.11402508551881414, "percentage": 2.84, "elapsed_time": "0:01:55", "remaining_time": "1:05:59", "throughput": 2668.83, "total_tokens": 308992}
|
| 6 |
+
{"current_steps": 30, "total_steps": 880, "loss": 0.6254, "lr": 0.00021749999999999997, "epoch": 0.13683010262257697, "percentage": 3.41, "elapsed_time": "0:02:18", "remaining_time": "1:05:24", "throughput": 2672.47, "total_tokens": 370176}
|
| 7 |
+
{"current_steps": 35, "total_steps": 880, "loss": 0.6389, "lr": 0.00025499999999999996, "epoch": 0.15963511972633979, "percentage": 3.98, "elapsed_time": "0:02:41", "remaining_time": "1:04:47", "throughput": 2674.69, "total_tokens": 430720}
|
| 8 |
+
{"current_steps": 40, "total_steps": 880, "loss": 0.5258, "lr": 0.00029249999999999995, "epoch": 0.18244013683010263, "percentage": 4.55, "elapsed_time": "0:03:04", "remaining_time": "1:04:29", "throughput": 2674.34, "total_tokens": 492800}
|
| 9 |
+
{"current_steps": 45, "total_steps": 880, "loss": 0.5039, "lr": 0.00029998321527154097, "epoch": 0.20524515393386544, "percentage": 5.11, "elapsed_time": "0:03:27", "remaining_time": "1:04:01", "throughput": 2675.62, "total_tokens": 553984}
|
| 10 |
+
{"current_steps": 50, "total_steps": 880, "loss": 0.4873, "lr": 0.00029991503375003, "epoch": 0.22805017103762829, "percentage": 5.68, "elapsed_time": "0:03:49", "remaining_time": "1:03:34", "throughput": 2676.78, "total_tokens": 615040}
|
| 11 |
+
{"current_steps": 55, "total_steps": 880, "loss": 0.4971, "lr": 0.000299794430213186, "epoch": 0.2508551881413911, "percentage": 6.25, "elapsed_time": "0:04:12", "remaining_time": "1:03:08", "throughput": 2679.17, "total_tokens": 676736}
|
| 12 |
+
{"current_steps": 60, "total_steps": 880, "loss": 0.4761, "lr": 0.0002996214468334339, "epoch": 0.27366020524515394, "percentage": 6.82, "elapsed_time": "0:04:35", "remaining_time": "1:02:44", "throughput": 2680.2, "total_tokens": 738176}
|
| 13 |
+
{"current_steps": 65, "total_steps": 880, "loss": 0.4849, "lr": 0.00029939614409928584, "epoch": 0.29646522234891676, "percentage": 7.39, "elapsed_time": "0:04:58", "remaining_time": "1:02:18", "throughput": 2681.16, "total_tokens": 799488}
|
| 14 |
+
{"current_steps": 70, "total_steps": 880, "loss": 0.4819, "lr": 0.00029911860079419073, "epoch": 0.31927023945267957, "percentage": 7.95, "elapsed_time": "0:05:21", "remaining_time": "1:01:55", "throughput": 2682.95, "total_tokens": 861568}
|
| 15 |
+
{"current_steps": 75, "total_steps": 880, "loss": 0.4812, "lr": 0.00029878891396898494, "epoch": 0.34207525655644244, "percentage": 8.52, "elapsed_time": "0:05:44", "remaining_time": "1:01:38", "throughput": 2683.42, "total_tokens": 924544}
|
| 16 |
+
{"current_steps": 80, "total_steps": 880, "loss": 0.4691, "lr": 0.00029840719890795547, "epoch": 0.36488027366020526, "percentage": 9.09, "elapsed_time": "0:06:07", "remaining_time": "1:01:11", "throughput": 2684.07, "total_tokens": 985472}
|
| 17 |
+
{"current_steps": 85, "total_steps": 880, "loss": 0.4845, "lr": 0.00029797358908852816, "epoch": 0.38768529076396807, "percentage": 9.66, "elapsed_time": "0:06:30", "remaining_time": "1:00:47", "throughput": 2684.34, "total_tokens": 1046912}
|
| 18 |
+
{"current_steps": 90, "total_steps": 880, "loss": 0.482, "lr": 0.00029748823613459316, "epoch": 0.4104903078677309, "percentage": 10.23, "elapsed_time": "0:06:52", "remaining_time": "1:00:24", "throughput": 2685.47, "total_tokens": 1108992}
|
| 19 |
+
{"current_steps": 95, "total_steps": 880, "loss": 0.4548, "lr": 0.0002969513097634853, "epoch": 0.43329532497149376, "percentage": 10.8, "elapsed_time": "0:07:15", "remaining_time": "1:00:00", "throughput": 2685.51, "total_tokens": 1170048}
|
| 20 |
+
{"current_steps": 100, "total_steps": 880, "loss": 0.4571, "lr": 0.00029636299772663795, "epoch": 0.45610034207525657, "percentage": 11.36, "elapsed_time": "0:07:38", "remaining_time": "0:59:33", "throughput": 2685.69, "total_tokens": 1230464}
|
| 21 |
+
{"current_steps": 100, "total_steps": 880, "eval_loss": 0.462704062461853, "epoch": 0.45610034207525657, "percentage": 11.36, "elapsed_time": "0:08:10", "remaining_time": "1:03:45", "throughput": 2509.15, "total_tokens": 1230464}
|
| 22 |
+
{"current_steps": 105, "total_steps": 880, "loss": 0.4633, "lr": 0.0002957235057439301, "epoch": 0.4789053591790194, "percentage": 11.93, "elapsed_time": "0:08:33", "remaining_time": "1:03:08", "throughput": 2517.6, "total_tokens": 1292288}
|
| 23 |
+
{"current_steps": 110, "total_steps": 880, "loss": 0.474, "lr": 0.0002950330574317509, "epoch": 0.5017103762827823, "percentage": 12.5, "elapsed_time": "0:08:55", "remaining_time": "1:02:31", "throughput": 2525.01, "total_tokens": 1353344}
|
| 24 |
+
{"current_steps": 115, "total_steps": 880, "loss": 0.4709, "lr": 0.0002942918942248059, "epoch": 0.5245153933865451, "percentage": 13.07, "elapsed_time": "0:09:18", "remaining_time": "1:01:56", "throughput": 2532.46, "total_tokens": 1415040}
|
| 25 |
+
{"current_steps": 120, "total_steps": 880, "loss": 0.4581, "lr": 0.0002935002752916921, "epoch": 0.5473204104903079, "percentage": 13.64, "elapsed_time": "0:09:41", "remaining_time": "1:01:23", "throughput": 2538.96, "total_tokens": 1476480}
|
| 26 |
+
{"current_steps": 125, "total_steps": 880, "loss": 0.4428, "lr": 0.00029265847744427303, "epoch": 0.5701254275940707, "percentage": 14.2, "elapsed_time": "0:10:04", "remaining_time": "1:00:50", "throughput": 2544.32, "total_tokens": 1537664}
|
| 27 |
+
{"current_steps": 130, "total_steps": 880, "loss": 0.441, "lr": 0.0002917667950408832, "epoch": 0.5929304446978335, "percentage": 14.77, "elapsed_time": "0:10:27", "remaining_time": "1:00:18", "throughput": 2549.51, "total_tokens": 1598848}
|
| 28 |
+
{"current_steps": 135, "total_steps": 880, "loss": 0.4484, "lr": 0.0002908255398833979, "epoch": 0.6157354618015963, "percentage": 15.34, "elapsed_time": "0:10:49", "remaining_time": "0:59:47", "throughput": 2555.09, "total_tokens": 1660800}
|
| 29 |
+
{"current_steps": 140, "total_steps": 880, "loss": 0.4312, "lr": 0.0002898350411082021, "epoch": 0.6385404789053591, "percentage": 15.91, "elapsed_time": "0:11:12", "remaining_time": "0:59:15", "throughput": 2559.58, "total_tokens": 1721600}
|
| 30 |
+
{"current_steps": 145, "total_steps": 880, "loss": 0.4374, "lr": 0.00028879564507109946, "epoch": 0.661345496009122, "percentage": 16.48, "elapsed_time": "0:11:35", "remaining_time": "0:58:45", "throughput": 2564.01, "total_tokens": 1783168}
|
| 31 |
+
{"current_steps": 150, "total_steps": 880, "loss": 0.4241, "lr": 0.00028770771522619885, "epoch": 0.6841505131128849, "percentage": 17.05, "elapsed_time": "0:11:58", "remaining_time": "0:58:15", "throughput": 2568.43, "total_tokens": 1844992}
|
| 32 |
+
{"current_steps": 155, "total_steps": 880, "loss": 0.4048, "lr": 0.00028657163199882237, "epoch": 0.7069555302166477, "percentage": 17.61, "elapsed_time": "0:12:21", "remaining_time": "0:57:46", "throughput": 2572.06, "total_tokens": 1906048}
|
| 33 |
+
{"current_steps": 160, "total_steps": 880, "loss": 0.4175, "lr": 0.0002853877926524791, "epoch": 0.7297605473204105, "percentage": 18.18, "elapsed_time": "0:12:43", "remaining_time": "0:57:17", "throughput": 2575.87, "total_tokens": 1967744}
|
| 34 |
+
{"current_steps": 165, "total_steps": 880, "loss": 0.405, "lr": 0.0002841566111499505, "epoch": 0.7525655644241733, "percentage": 18.75, "elapsed_time": "0:13:06", "remaining_time": "0:56:47", "throughput": 2578.85, "total_tokens": 2028032}
|
| 35 |
+
{"current_steps": 170, "total_steps": 880, "loss": 0.4023, "lr": 0.00028287851800853697, "epoch": 0.7753705815279361, "percentage": 19.32, "elapsed_time": "0:13:28", "remaining_time": "0:56:18", "throughput": 2581.88, "total_tokens": 2088448}
|
| 36 |
+
{"current_steps": 175, "total_steps": 880, "loss": 0.4013, "lr": 0.00028155396014951494, "epoch": 0.798175598631699, "percentage": 19.89, "elapsed_time": "0:13:51", "remaining_time": "0:55:50", "throughput": 2585.24, "total_tokens": 2150144}
|
| 37 |
+
{"current_steps": 180, "total_steps": 880, "loss": 0.4065, "lr": 0.0002801834007418587, "epoch": 0.8209806157354618, "percentage": 20.45, "elapsed_time": "0:14:14", "remaining_time": "0:55:23", "throughput": 2588.01, "total_tokens": 2211584}
|
| 38 |
+
{"current_steps": 185, "total_steps": 880, "loss": 0.3784, "lr": 0.0002787673190402799, "epoch": 0.8437856328392246, "percentage": 21.02, "elapsed_time": "0:14:37", "remaining_time": "0:54:54", "throughput": 2590.73, "total_tokens": 2272256}
|
| 39 |
+
{"current_steps": 190, "total_steps": 880, "loss": 0.3882, "lr": 0.0002773062102176429, "epoch": 0.8665906499429875, "percentage": 21.59, "elapsed_time": "0:14:59", "remaining_time": "0:54:27", "throughput": 2593.36, "total_tokens": 2333696}
|
| 40 |
+
{"current_steps": 195, "total_steps": 880, "loss": 0.3953, "lr": 0.0002758005851918136, "epoch": 0.8893956670467503, "percentage": 22.16, "elapsed_time": "0:15:22", "remaining_time": "0:54:00", "throughput": 2595.95, "total_tokens": 2394880}
|
| 41 |
+
{"current_steps": 200, "total_steps": 880, "loss": 0.3676, "lr": 0.00027425097044700246, "epoch": 0.9122006841505131, "percentage": 22.73, "elapsed_time": "0:15:45", "remaining_time": "0:53:33", "throughput": 2598.2, "total_tokens": 2455680}
|
| 42 |
+
{"current_steps": 200, "total_steps": 880, "eval_loss": 0.3956287205219269, "epoch": 0.9122006841505131, "percentage": 22.73, "elapsed_time": "0:16:17", "remaining_time": "0:55:23", "throughput": 2512.32, "total_tokens": 2455680}
|
| 43 |
+
{"current_steps": 205, "total_steps": 880, "loss": 0.3821, "lr": 0.0002726579078496647, "epoch": 0.935005701254276, "percentage": 23.3, "elapsed_time": "0:16:40", "remaining_time": "0:54:53", "throughput": 2516.49, "total_tokens": 2517376}
|
| 44 |
+
{"current_steps": 210, "total_steps": 880, "loss": 0.3828, "lr": 0.0002710219544590212, "epoch": 0.9578107183580388, "percentage": 23.86, "elapsed_time": "0:17:03", "remaining_time": "0:54:24", "throughput": 2520.61, "total_tokens": 2578816}
|
| 45 |
+
{"current_steps": 215, "total_steps": 880, "loss": 0.3569, "lr": 0.00026934368233226714, "epoch": 0.9806157354618016, "percentage": 24.43, "elapsed_time": "0:17:25", "remaining_time": "0:53:54", "throughput": 2524.31, "total_tokens": 2640128}
|
| 46 |
+
{"current_steps": 220, "total_steps": 880, "loss": 0.3597, "lr": 0.00026762367832453617, "epoch": 1.0, "percentage": 25.0, "elapsed_time": "0:17:45", "remaining_time": "0:53:15", "throughput": 2527.29, "total_tokens": 2691984}
|
| 47 |
+
{"current_steps": 225, "total_steps": 880, "loss": 0.3621, "lr": 0.0002658625438836899, "epoch": 1.0228050171037628, "percentage": 25.57, "elapsed_time": "0:18:08", "remaining_time": "0:52:47", "throughput": 2530.83, "total_tokens": 2753808}
|
| 48 |
+
{"current_steps": 230, "total_steps": 880, "loss": 0.3623, "lr": 0.00026406089484000466, "epoch": 1.0456100342075256, "percentage": 26.14, "elapsed_time": "0:18:30", "remaining_time": "0:52:19", "throughput": 2534.3, "total_tokens": 2815248}
|
| 49 |
+
{"current_steps": 235, "total_steps": 880, "loss": 0.3866, "lr": 0.00026221936119082904, "epoch": 1.0684150513112884, "percentage": 26.7, "elapsed_time": "0:18:53", "remaining_time": "0:51:52", "throughput": 2537.46, "total_tokens": 2877456}
|
| 50 |
+
{"current_steps": 240, "total_steps": 880, "loss": 0.3598, "lr": 0.00026033858688028784, "epoch": 1.0912200684150513, "percentage": 27.27, "elapsed_time": "0:19:16", "remaining_time": "0:51:25", "throughput": 2540.5, "total_tokens": 2939280}
|
| 51 |
+
{"current_steps": 245, "total_steps": 880, "loss": 0.3488, "lr": 0.0002584192295741087, "epoch": 1.114025085518814, "percentage": 27.84, "elapsed_time": "0:19:39", "remaining_time": "0:50:57", "throughput": 2543.27, "total_tokens": 3000336}
|
| 52 |
+
{"current_steps": 250, "total_steps": 880, "loss": 0.3516, "lr": 0.0002564619604296506, "epoch": 1.1368301026225769, "percentage": 28.41, "elapsed_time": "0:20:02", "remaining_time": "0:50:30", "throughput": 2546.18, "total_tokens": 3062416}
|
| 53 |
+
{"current_steps": 255, "total_steps": 880, "loss": 0.34, "lr": 0.00025446746386121504, "epoch": 1.1596351197263397, "percentage": 28.98, "elapsed_time": "0:20:25", "remaining_time": "0:50:04", "throughput": 2548.93, "total_tokens": 3124368}
|
| 54 |
+
{"current_steps": 260, "total_steps": 880, "loss": 0.3361, "lr": 0.000252436437300721, "epoch": 1.1824401368301025, "percentage": 29.55, "elapsed_time": "0:20:48", "remaining_time": "0:49:37", "throughput": 2551.45, "total_tokens": 3185424}
|
| 55 |
+
{"current_steps": 265, "total_steps": 880, "loss": 0.3172, "lr": 0.0002503695909538287, "epoch": 1.2052451539338653, "percentage": 30.11, "elapsed_time": "0:21:11", "remaining_time": "0:49:09", "throughput": 2553.91, "total_tokens": 3246096}
|
| 56 |
+
{"current_steps": 270, "total_steps": 880, "loss": 0.3387, "lr": 0.00024826764755159566, "epoch": 1.2280501710376284, "percentage": 30.68, "elapsed_time": "0:21:33", "remaining_time": "0:48:43", "throughput": 2556.34, "total_tokens": 3307536}
|
| 57 |
+
{"current_steps": 275, "total_steps": 880, "loss": 0.3112, "lr": 0.0002461313420977536, "epoch": 1.2508551881413912, "percentage": 31.25, "elapsed_time": "0:21:56", "remaining_time": "0:48:16", "throughput": 2558.63, "total_tokens": 3368976}
|
| 58 |
+
{"current_steps": 280, "total_steps": 880, "loss": 0.3223, "lr": 0.0002439614216116939, "epoch": 1.273660205245154, "percentage": 31.82, "elapsed_time": "0:22:19", "remaining_time": "0:47:49", "throughput": 2560.82, "total_tokens": 3429520}
|
| 59 |
+
{"current_steps": 285, "total_steps": 880, "loss": 0.312, "lr": 0.00024175864486725092, "epoch": 1.2964652223489168, "percentage": 32.39, "elapsed_time": "0:22:41", "remaining_time": "0:47:23", "throughput": 2562.88, "total_tokens": 3490448}
|
| 60 |
+
{"current_steps": 290, "total_steps": 880, "loss": 0.3096, "lr": 0.00023952378212737554, "epoch": 1.3192702394526796, "percentage": 32.95, "elapsed_time": "0:23:04", "remaining_time": "0:46:56", "throughput": 2564.82, "total_tokens": 3551120}
|
| 61 |
+
{"current_steps": 295, "total_steps": 880, "loss": 0.3109, "lr": 0.00023725761487479086, "epoch": 1.3420752565564424, "percentage": 33.52, "elapsed_time": "0:23:27", "remaining_time": "0:46:30", "throughput": 2566.78, "total_tokens": 3611920}
|
| 62 |
+
{"current_steps": 300, "total_steps": 880, "loss": 0.3092, "lr": 0.0002349609355387249, "epoch": 1.3648802736602053, "percentage": 34.09, "elapsed_time": "0:23:50", "remaining_time": "0:46:04", "throughput": 2568.98, "total_tokens": 3673744}
|
| 63 |
+
{"current_steps": 300, "total_steps": 880, "eval_loss": 0.31190308928489685, "epoch": 1.3648802736602053, "percentage": 34.09, "elapsed_time": "0:24:22", "remaining_time": "0:47:07", "throughput": 2512.21, "total_tokens": 3673744}
|
| 64 |
+
{"current_steps": 305, "total_steps": 880, "loss": 0.308, "lr": 0.00023263454721781537, "epoch": 1.387685290763968, "percentage": 34.66, "elapsed_time": "0:24:45", "remaining_time": "0:46:40", "throughput": 2515.09, "total_tokens": 3735568}
|
| 65 |
+
{"current_steps": 310, "total_steps": 880, "loss": 0.3089, "lr": 0.0002302792633992835, "epoch": 1.4104903078677309, "percentage": 35.23, "elapsed_time": "0:25:08", "remaining_time": "0:46:13", "throughput": 2517.8, "total_tokens": 3798160}
|
| 66 |
+
{"current_steps": 315, "total_steps": 880, "loss": 0.3028, "lr": 0.00022789590767447533, "epoch": 1.4332953249714937, "percentage": 35.8, "elapsed_time": "0:25:31", "remaining_time": "0:45:46", "throughput": 2520.33, "total_tokens": 3859600}
|
| 67 |
+
{"current_steps": 320, "total_steps": 880, "loss": 0.2925, "lr": 0.00022548531345087, "epoch": 1.4561003420752565, "percentage": 36.36, "elapsed_time": "0:25:53", "remaining_time": "0:45:19", "throughput": 2522.88, "total_tokens": 3920528}
|
| 68 |
+
{"current_steps": 325, "total_steps": 880, "loss": 0.285, "lr": 0.00022304832366065505, "epoch": 1.4789053591790193, "percentage": 36.93, "elapsed_time": "0:26:16", "remaining_time": "0:44:52", "throughput": 2525.37, "total_tokens": 3982096}
|
| 69 |
+
{"current_steps": 330, "total_steps": 880, "loss": 0.304, "lr": 0.0002205857904659717, "epoch": 1.5017103762827824, "percentage": 37.5, "elapsed_time": "0:26:39", "remaining_time": "0:44:26", "throughput": 2527.73, "total_tokens": 4044048}
|
| 70 |
+
{"current_steps": 335, "total_steps": 880, "loss": 0.2892, "lr": 0.00021809857496093199, "epoch": 1.5245153933865452, "percentage": 38.07, "elapsed_time": "0:27:02", "remaining_time": "0:43:59", "throughput": 2530.08, "total_tokens": 4105104}
|
| 71 |
+
{"current_steps": 340, "total_steps": 880, "loss": 0.2849, "lr": 0.00021558754687051344, "epoch": 1.547320410490308, "percentage": 38.64, "elapsed_time": "0:27:25", "remaining_time": "0:43:32", "throughput": 2532.44, "total_tokens": 4165904}
|
| 72 |
+
{"current_steps": 345, "total_steps": 880, "loss": 0.2975, "lr": 0.0002130535842464348, "epoch": 1.5701254275940708, "percentage": 39.2, "elapsed_time": "0:27:47", "remaining_time": "0:43:06", "throughput": 2534.53, "total_tokens": 4226704}
|
| 73 |
+
{"current_steps": 350, "total_steps": 880, "loss": 0.2845, "lr": 0.00021049757316012077, "epoch": 1.5929304446978336, "percentage": 39.77, "elapsed_time": "0:28:10", "remaining_time": "0:42:39", "throughput": 2536.78, "total_tokens": 4288400}
|
| 74 |
+
{"current_steps": 355, "total_steps": 880, "loss": 0.2869, "lr": 0.0002079204073928619, "epoch": 1.6157354618015964, "percentage": 40.34, "elapsed_time": "0:28:33", "remaining_time": "0:42:13", "throughput": 2538.9, "total_tokens": 4349712}
|
| 75 |
+
{"current_steps": 360, "total_steps": 880, "loss": 0.2601, "lr": 0.0002053229881232793, "epoch": 1.6385404789053593, "percentage": 40.91, "elapsed_time": "0:28:55", "remaining_time": "0:41:47", "throughput": 2540.88, "total_tokens": 4410256}
|
| 76 |
+
{"current_steps": 365, "total_steps": 880, "loss": 0.2826, "lr": 0.0002027062236122014, "epoch": 1.661345496009122, "percentage": 41.48, "elapsed_time": "0:29:18", "remaining_time": "0:41:20", "throughput": 2542.97, "total_tokens": 4471440}
|
| 77 |
+
{"current_steps": 370, "total_steps": 880, "loss": 0.2729, "lr": 0.0002000710288850656, "epoch": 1.6841505131128849, "percentage": 42.05, "elapsed_time": "0:29:41", "remaining_time": "0:40:55", "throughput": 2544.98, "total_tokens": 4533008}
|
| 78 |
+
{"current_steps": 375, "total_steps": 880, "loss": 0.2772, "lr": 0.00019741832541195366, "epoch": 1.7069555302166477, "percentage": 42.61, "elapsed_time": "0:30:03", "remaining_time": "0:40:29", "throughput": 2546.98, "total_tokens": 4594320}
|
| 79 |
+
{"current_steps": 380, "total_steps": 880, "loss": 0.2789, "lr": 0.0001947490407853734, "epoch": 1.7297605473204105, "percentage": 43.18, "elapsed_time": "0:30:26", "remaining_time": "0:40:03", "throughput": 2548.91, "total_tokens": 4655760}
|
| 80 |
+
{"current_steps": 385, "total_steps": 880, "loss": 0.2743, "lr": 0.0001920641083959004, "epoch": 1.7525655644241733, "percentage": 43.75, "elapsed_time": "0:30:49", "remaining_time": "0:39:37", "throughput": 2550.81, "total_tokens": 4717328}
|
| 81 |
+
{"current_steps": 390, "total_steps": 880, "loss": 0.2657, "lr": 0.00018936446710579122, "epoch": 1.7753705815279361, "percentage": 44.32, "elapsed_time": "0:31:12", "remaining_time": "0:39:12", "throughput": 2552.74, "total_tokens": 4779152}
|
| 82 |
+
{"current_steps": 395, "total_steps": 880, "loss": 0.2847, "lr": 0.00018665106092068408, "epoch": 1.798175598631699, "percentage": 44.89, "elapsed_time": "0:31:34", "remaining_time": "0:38:46", "throughput": 2554.53, "total_tokens": 4840336}
|
| 83 |
+
{"current_steps": 400, "total_steps": 880, "loss": 0.2796, "lr": 0.00018392483865950046, "epoch": 1.8209806157354618, "percentage": 45.45, "elapsed_time": "0:31:57", "remaining_time": "0:38:20", "throughput": 2556.32, "total_tokens": 4901648}
|
| 84 |
+
{"current_steps": 400, "total_steps": 880, "eval_loss": 0.2729249596595764, "epoch": 1.8209806157354618, "percentage": 45.45, "elapsed_time": "0:32:29", "remaining_time": "0:38:59", "throughput": 2514.03, "total_tokens": 4901648}
|
| 85 |
+
{"current_steps": 405, "total_steps": 880, "loss": 0.2725, "lr": 0.00018118675362266385, "epoch": 1.8437856328392246, "percentage": 46.02, "elapsed_time": "0:32:52", "remaining_time": "0:38:33", "throughput": 2516.19, "total_tokens": 4963216}
|
| 86 |
+
{"current_steps": 410, "total_steps": 880, "loss": 0.2714, "lr": 0.00017843776325875176, "epoch": 1.8665906499429874, "percentage": 46.59, "elapsed_time": "0:33:15", "remaining_time": "0:38:07", "throughput": 2518.33, "total_tokens": 5024912}
|
| 87 |
+
{"current_steps": 415, "total_steps": 880, "loss": 0.2547, "lr": 0.00017567882882969628, "epoch": 1.8893956670467502, "percentage": 47.16, "elapsed_time": "0:33:38", "remaining_time": "0:37:41", "throughput": 2520.24, "total_tokens": 5086224}
|
| 88 |
+
{"current_steps": 420, "total_steps": 880, "loss": 0.2687, "lr": 0.0001729109150746521, "epoch": 1.912200684150513, "percentage": 47.73, "elapsed_time": "0:34:01", "remaining_time": "0:37:15", "throughput": 2522.2, "total_tokens": 5148048}
|
| 89 |
+
{"current_steps": 425, "total_steps": 880, "loss": 0.2644, "lr": 0.00017013498987264832, "epoch": 1.9350057012542758, "percentage": 48.3, "elapsed_time": "0:34:23", "remaining_time": "0:36:49", "throughput": 2524.15, "total_tokens": 5209104}
|
| 90 |
+
{"current_steps": 430, "total_steps": 880, "loss": 0.2696, "lr": 0.00016735202390414215, "epoch": 1.9578107183580387, "percentage": 48.86, "elapsed_time": "0:34:46", "remaining_time": "0:36:23", "throughput": 2526.03, "total_tokens": 5270544}
|
| 91 |
+
{"current_steps": 435, "total_steps": 880, "loss": 0.2694, "lr": 0.00016456299031159322, "epoch": 1.9806157354618015, "percentage": 49.43, "elapsed_time": "0:35:09", "remaining_time": "0:35:57", "throughput": 2527.81, "total_tokens": 5331472}
|
| 92 |
+
{"current_steps": 440, "total_steps": 880, "loss": 0.2495, "lr": 0.00016176886435917675, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "0:35:28", "remaining_time": "0:35:28", "throughput": 2529.09, "total_tokens": 5382864}
|
| 93 |
+
{"current_steps": 445, "total_steps": 880, "loss": 0.2453, "lr": 0.00015897062309175512, "epoch": 2.022805017103763, "percentage": 50.57, "elapsed_time": "0:35:51", "remaining_time": "0:35:02", "throughput": 2530.83, "total_tokens": 5444176}
|
| 94 |
+
{"current_steps": 450, "total_steps": 880, "loss": 0.2299, "lr": 0.0001561692449932266, "epoch": 2.0456100342075256, "percentage": 51.14, "elapsed_time": "0:36:13", "remaining_time": "0:34:37", "throughput": 2532.6, "total_tokens": 5505872}
|
| 95 |
+
{"current_steps": 455, "total_steps": 880, "loss": 0.2301, "lr": 0.00015336570964437075, "epoch": 2.0684150513112884, "percentage": 51.7, "elapsed_time": "0:36:37", "remaining_time": "0:34:12", "throughput": 2534.34, "total_tokens": 5568208}
|
| 96 |
+
{"current_steps": 460, "total_steps": 880, "loss": 0.2376, "lr": 0.0001505609973803105, "epoch": 2.0912200684150513, "percentage": 52.27, "elapsed_time": "0:36:59", "remaining_time": "0:33:46", "throughput": 2535.86, "total_tokens": 5628880}
|
| 97 |
+
{"current_steps": 465, "total_steps": 880, "loss": 0.2199, "lr": 0.00014775608894771047, "epoch": 2.114025085518814, "percentage": 52.84, "elapsed_time": "0:37:22", "remaining_time": "0:33:21", "throughput": 2537.51, "total_tokens": 5690320}
|
| 98 |
+
{"current_steps": 470, "total_steps": 880, "loss": 0.2237, "lr": 0.00014495196516183095, "epoch": 2.136830102622577, "percentage": 53.41, "elapsed_time": "0:37:45", "remaining_time": "0:32:56", "throughput": 2539.15, "total_tokens": 5752912}
|
| 99 |
+
{"current_steps": 475, "total_steps": 880, "loss": 0.2294, "lr": 0.0001421496065635584, "epoch": 2.1596351197263397, "percentage": 53.98, "elapsed_time": "0:38:08", "remaining_time": "0:32:31", "throughput": 2540.66, "total_tokens": 5813968}
|
| 100 |
+
{"current_steps": 480, "total_steps": 880, "loss": 0.231, "lr": 0.00013934999307653193, "epoch": 2.1824401368301025, "percentage": 54.55, "elapsed_time": "0:38:30", "remaining_time": "0:32:05", "throughput": 2542.21, "total_tokens": 5874896}
|
| 101 |
+
{"current_steps": 485, "total_steps": 880, "loss": 0.2252, "lr": 0.00013655410366448498, "epoch": 2.2052451539338653, "percentage": 55.11, "elapsed_time": "0:38:53", "remaining_time": "0:31:40", "throughput": 2543.74, "total_tokens": 5935952}
|
| 102 |
+
{"current_steps": 490, "total_steps": 880, "loss": 0.2151, "lr": 0.0001337629159889232, "epoch": 2.228050171037628, "percentage": 55.68, "elapsed_time": "0:39:16", "remaining_time": "0:31:15", "throughput": 2545.24, "total_tokens": 5997008}
|
| 103 |
+
{"current_steps": 495, "total_steps": 880, "loss": 0.2228, "lr": 0.00013097740606725776, "epoch": 2.250855188141391, "percentage": 56.25, "elapsed_time": "0:39:39", "remaining_time": "0:30:50", "throughput": 2546.67, "total_tokens": 6058704}
|
| 104 |
+
{"current_steps": 500, "total_steps": 880, "loss": 0.2265, "lr": 0.00012819854793151312, "epoch": 2.2736602052451538, "percentage": 56.82, "elapsed_time": "0:40:01", "remaining_time": "0:30:25", "throughput": 2548.01, "total_tokens": 6120272}
|
| 105 |
+
{"current_steps": 500, "total_steps": 880, "eval_loss": 0.24168384075164795, "epoch": 2.2736602052451538, "percentage": 56.82, "elapsed_time": "0:40:34", "remaining_time": "0:30:50", "throughput": 2514.23, "total_tokens": 6120272}
|
| 106 |
+
{"current_steps": 505, "total_steps": 880, "loss": 0.2126, "lr": 0.00012542731328772934, "epoch": 2.2964652223489166, "percentage": 57.39, "elapsed_time": "0:41:02", "remaining_time": "0:30:28", "throughput": 2509.48, "total_tokens": 6180816}
|
| 107 |
+
{"current_steps": 510, "total_steps": 880, "loss": 0.2202, "lr": 0.00012266467117617787, "epoch": 2.3192702394526794, "percentage": 57.95, "elapsed_time": "0:41:25", "remaining_time": "0:30:03", "throughput": 2511.22, "total_tokens": 6242128}
|
| 108 |
+
{"current_steps": 515, "total_steps": 880, "loss": 0.2203, "lr": 0.00011991158763250908, "epoch": 2.342075256556442, "percentage": 58.52, "elapsed_time": "0:41:48", "remaining_time": "0:29:37", "throughput": 2512.89, "total_tokens": 6303312}
|
| 109 |
+
{"current_steps": 520, "total_steps": 880, "loss": 0.223, "lr": 0.00011716902534995079, "epoch": 2.364880273660205, "percentage": 59.09, "elapsed_time": "0:42:11", "remaining_time": "0:29:12", "throughput": 2514.53, "total_tokens": 6364624}
|
| 110 |
+
{"current_steps": 525, "total_steps": 880, "loss": 0.2218, "lr": 0.00011443794334267538, "epoch": 2.387685290763968, "percentage": 59.66, "elapsed_time": "0:42:33", "remaining_time": "0:28:46", "throughput": 2516.13, "total_tokens": 6425040}
|
| 111 |
+
{"current_steps": 530, "total_steps": 880, "loss": 0.2156, "lr": 0.0001117192966104536, "epoch": 2.4104903078677307, "percentage": 60.23, "elapsed_time": "0:42:56", "remaining_time": "0:28:21", "throughput": 2517.81, "total_tokens": 6486736}
|
| 112 |
+
{"current_steps": 535, "total_steps": 880, "loss": 0.2161, "lr": 0.000109014035804712, "epoch": 2.433295324971494, "percentage": 60.8, "elapsed_time": "0:43:19", "remaining_time": "0:27:56", "throughput": 2519.4, "total_tokens": 6548304}
|
| 113 |
+
{"current_steps": 540, "total_steps": 880, "loss": 0.2045, "lr": 0.0001063231068961106, "epoch": 2.4561003420752567, "percentage": 61.36, "elapsed_time": "0:43:42", "remaining_time": "0:27:30", "throughput": 2520.94, "total_tokens": 6610000}
|
| 114 |
+
{"current_steps": 545, "total_steps": 880, "loss": 0.2073, "lr": 0.0001036474508437579, "epoch": 2.4789053591790196, "percentage": 61.93, "elapsed_time": "0:44:04", "remaining_time": "0:27:05", "throughput": 2522.38, "total_tokens": 6670672}
|
| 115 |
+
{"current_steps": 550, "total_steps": 880, "loss": 0.2018, "lr": 0.00010098800326617791, "epoch": 2.5017103762827824, "percentage": 62.5, "elapsed_time": "0:44:27", "remaining_time": "0:26:40", "throughput": 2523.89, "total_tokens": 6732112}
|
| 116 |
+
{"current_steps": 555, "total_steps": 880, "loss": 0.2048, "lr": 9.834569411414471e-05, "epoch": 2.524515393386545, "percentage": 63.07, "elapsed_time": "0:44:50", "remaining_time": "0:26:15", "throughput": 2525.4, "total_tokens": 6793424}
|
| 117 |
+
{"current_steps": 560, "total_steps": 880, "loss": 0.2062, "lr": 9.572144734549919e-05, "epoch": 2.547320410490308, "percentage": 63.64, "elapsed_time": "0:45:13", "remaining_time": "0:25:50", "throughput": 2526.96, "total_tokens": 6855760}
|
| 118 |
+
{"current_steps": 565, "total_steps": 880, "loss": 0.216, "lr": 9.311618060206074e-05, "epoch": 2.570125427594071, "percentage": 64.2, "elapsed_time": "0:45:35", "remaining_time": "0:25:25", "throughput": 2528.28, "total_tokens": 6916688}
|
| 119 |
+
{"current_steps": 570, "total_steps": 880, "loss": 0.1953, "lr": 9.053080488874836e-05, "epoch": 2.5929304446978336, "percentage": 64.77, "elapsed_time": "0:45:58", "remaining_time": "0:25:00", "throughput": 2529.73, "total_tokens": 6978512}
|
| 120 |
+
{"current_steps": 575, "total_steps": 880, "loss": 0.2147, "lr": 8.796622425502192e-05, "epoch": 2.6157354618015964, "percentage": 65.34, "elapsed_time": "0:46:21", "remaining_time": "0:24:35", "throughput": 2531.03, "total_tokens": 7040208}
|
| 121 |
+
{"current_steps": 580, "total_steps": 880, "loss": 0.209, "lr": 8.54233354787557e-05, "epoch": 2.6385404789053593, "percentage": 65.91, "elapsed_time": "0:46:44", "remaining_time": "0:24:10", "throughput": 2532.36, "total_tokens": 7101264}
|
| 122 |
+
{"current_steps": 585, "total_steps": 880, "loss": 0.2077, "lr": 8.290302775265509e-05, "epoch": 2.661345496009122, "percentage": 66.48, "elapsed_time": "0:47:07", "remaining_time": "0:23:45", "throughput": 2533.77, "total_tokens": 7163600}
|
| 123 |
+
{"current_steps": 590, "total_steps": 880, "loss": 0.2058, "lr": 8.04061823733249e-05, "epoch": 2.684150513112885, "percentage": 67.05, "elapsed_time": "0:47:30", "remaining_time": "0:23:20", "throughput": 2535.21, "total_tokens": 7225936}
|
| 124 |
+
{"current_steps": 595, "total_steps": 880, "loss": 0.1961, "lr": 7.79336724330994e-05, "epoch": 2.7069555302166477, "percentage": 67.61, "elapsed_time": "0:47:53", "remaining_time": "0:22:56", "throughput": 2536.44, "total_tokens": 7287760}
|
| 125 |
+
{"current_steps": 600, "total_steps": 880, "loss": 0.2003, "lr": 7.548636251474091e-05, "epoch": 2.7297605473204105, "percentage": 68.18, "elapsed_time": "0:48:15", "remaining_time": "0:22:31", "throughput": 2537.64, "total_tokens": 7348944}
|
| 126 |
+
{"current_steps": 600, "total_steps": 880, "eval_loss": 0.22281652688980103, "epoch": 2.7297605473204105, "percentage": 68.18, "elapsed_time": "0:48:48", "remaining_time": "0:22:46", "throughput": 2509.68, "total_tokens": 7348944}
|
| 127 |
+
{"current_steps": 605, "total_steps": 880, "loss": 0.2058, "lr": 7.30651083891141e-05, "epoch": 2.7525655644241733, "percentage": 68.75, "elapsed_time": "0:49:11", "remaining_time": "0:22:21", "throughput": 2511.21, "total_tokens": 7410640}
|
| 128 |
+
{"current_steps": 610, "total_steps": 880, "loss": 0.1909, "lr": 7.067075671594168e-05, "epoch": 2.775370581527936, "percentage": 69.32, "elapsed_time": "0:49:33", "remaining_time": "0:21:56", "throughput": 2512.59, "total_tokens": 7471184}
|
| 129 |
+
{"current_steps": 615, "total_steps": 880, "loss": 0.2035, "lr": 6.830414474774594e-05, "epoch": 2.798175598631699, "percentage": 69.89, "elapsed_time": "0:49:56", "remaining_time": "0:21:31", "throughput": 2514.06, "total_tokens": 7533392}
|
| 130 |
+
{"current_steps": 620, "total_steps": 880, "loss": 0.1963, "lr": 6.596610003707958e-05, "epoch": 2.8209806157354618, "percentage": 70.45, "elapsed_time": "0:50:19", "remaining_time": "0:21:06", "throughput": 2515.46, "total_tokens": 7594832}
|
| 131 |
+
{"current_steps": 625, "total_steps": 880, "loss": 0.1951, "lr": 6.365744014714898e-05, "epoch": 2.8437856328392246, "percentage": 71.02, "elapsed_time": "0:50:42", "remaining_time": "0:20:41", "throughput": 2516.85, "total_tokens": 7656656}
|
| 132 |
+
{"current_steps": 630, "total_steps": 880, "loss": 0.193, "lr": 6.137897236593002e-05, "epoch": 2.8665906499429874, "percentage": 71.59, "elapsed_time": "0:51:04", "remaining_time": "0:20:16", "throughput": 2518.16, "total_tokens": 7717712}
|
| 133 |
+
{"current_steps": 635, "total_steps": 880, "loss": 0.1925, "lr": 5.913149342387703e-05, "epoch": 2.88939566704675, "percentage": 72.16, "elapsed_time": "0:51:27", "remaining_time": "0:19:51", "throughput": 2519.53, "total_tokens": 7779920}
|
| 134 |
+
{"current_steps": 640, "total_steps": 880, "loss": 0.1995, "lr": 5.6915789215323817e-05, "epoch": 2.912200684150513, "percentage": 72.73, "elapsed_time": "0:51:50", "remaining_time": "0:19:26", "throughput": 2520.84, "total_tokens": 7840976}
|
| 135 |
+
{"current_steps": 645, "total_steps": 880, "loss": 0.1852, "lr": 5.473263452367318e-05, "epoch": 2.935005701254276, "percentage": 73.3, "elapsed_time": "0:52:13", "remaining_time": "0:19:01", "throughput": 2522.07, "total_tokens": 7902160}
|
| 136 |
+
{"current_steps": 650, "total_steps": 880, "loss": 0.1878, "lr": 5.2582792750472464e-05, "epoch": 2.9578107183580387, "percentage": 73.86, "elapsed_time": "0:52:35", "remaining_time": "0:18:36", "throughput": 2523.41, "total_tokens": 7963856}
|
| 137 |
+
{"current_steps": 655, "total_steps": 880, "loss": 0.1945, "lr": 5.046701564846834e-05, "epoch": 2.9806157354618015, "percentage": 74.43, "elapsed_time": "0:52:59", "remaining_time": "0:18:12", "throughput": 2524.69, "total_tokens": 8026448}
|
| 138 |
+
{"current_steps": 660, "total_steps": 880, "loss": 0.1645, "lr": 4.8386043058735465e-05, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "0:53:18", "remaining_time": "0:17:46", "throughput": 2525.72, "total_tokens": 8078224}
|
| 139 |
+
{"current_steps": 665, "total_steps": 880, "loss": 0.1556, "lr": 4.63406026519703e-05, "epoch": 3.022805017103763, "percentage": 75.57, "elapsed_time": "0:53:41", "remaining_time": "0:17:21", "throughput": 2527.0, "total_tokens": 8140176}
|
| 140 |
+
{"current_steps": 670, "total_steps": 880, "loss": 0.1397, "lr": 4.4331409674040324e-05, "epoch": 3.0456100342075256, "percentage": 76.14, "elapsed_time": "0:54:04", "remaining_time": "0:16:56", "throughput": 2528.18, "total_tokens": 8201616}
|
| 141 |
+
{"current_steps": 675, "total_steps": 880, "loss": 0.1478, "lr": 4.23591666958782e-05, "epoch": 3.0684150513112884, "percentage": 76.7, "elapsed_time": "0:54:26", "remaining_time": "0:16:32", "throughput": 2529.34, "total_tokens": 8262928}
|
| 142 |
+
{"current_steps": 680, "total_steps": 880, "loss": 0.1413, "lr": 4.042456336780837e-05, "epoch": 3.0912200684150513, "percentage": 77.27, "elapsed_time": "0:54:49", "remaining_time": "0:16:07", "throughput": 2530.57, "total_tokens": 8324496}
|
| 143 |
+
{"current_steps": 685, "total_steps": 880, "loss": 0.1494, "lr": 3.852827617839084e-05, "epoch": 3.114025085518814, "percentage": 77.84, "elapsed_time": "0:55:12", "remaining_time": "0:15:42", "throughput": 2531.65, "total_tokens": 8385680}
|
| 144 |
+
{"current_steps": 690, "total_steps": 880, "loss": 0.1426, "lr": 3.667096821786847e-05, "epoch": 3.136830102622577, "percentage": 78.41, "elapsed_time": "0:55:35", "remaining_time": "0:15:18", "throughput": 2532.72, "total_tokens": 8447632}
|
| 145 |
+
{"current_steps": 695, "total_steps": 880, "loss": 0.1413, "lr": 3.485328894629833e-05, "epoch": 3.1596351197263397, "percentage": 78.98, "elapsed_time": "0:55:57", "remaining_time": "0:14:53", "throughput": 2533.81, "total_tokens": 8508432}
|
| 146 |
+
{"current_steps": 700, "total_steps": 880, "loss": 0.1439, "lr": 3.307587396644996e-05, "epoch": 3.1824401368301025, "percentage": 79.55, "elapsed_time": "0:56:20", "remaining_time": "0:14:29", "throughput": 2534.97, "total_tokens": 8570128}
|
| 147 |
+
{"current_steps": 700, "total_steps": 880, "eval_loss": 0.23035594820976257, "epoch": 3.1824401368301025, "percentage": 79.55, "elapsed_time": "0:56:53", "remaining_time": "0:14:37", "throughput": 2511.01, "total_tokens": 8570128}
|
| 148 |
+
{"current_steps": 705, "total_steps": 880, "loss": 0.1474, "lr": 3.133934480154885e-05, "epoch": 3.2052451539338653, "percentage": 80.11, "elapsed_time": "0:57:15", "remaining_time": "0:14:12", "throughput": 2512.29, "total_tokens": 8631952}
|
| 149 |
+
{"current_steps": 710, "total_steps": 880, "loss": 0.1453, "lr": 2.9644308677943313e-05, "epoch": 3.228050171037628, "percentage": 80.68, "elapsed_time": "0:57:38", "remaining_time": "0:13:48", "throughput": 2513.6, "total_tokens": 8694032}
|
| 150 |
+
{"current_steps": 715, "total_steps": 880, "loss": 0.1379, "lr": 2.7991358312770805e-05, "epoch": 3.250855188141391, "percentage": 81.25, "elapsed_time": "0:58:01", "remaining_time": "0:13:23", "throughput": 2514.74, "total_tokens": 8754576}
|
| 151 |
+
{"current_steps": 720, "total_steps": 880, "loss": 0.1441, "lr": 2.6381071706697644e-05, "epoch": 3.2736602052451538, "percentage": 81.82, "elapsed_time": "0:58:24", "remaining_time": "0:12:58", "throughput": 2515.91, "total_tokens": 8816528}
|
| 152 |
+
{"current_steps": 725, "total_steps": 880, "loss": 0.1442, "lr": 2.48140119418046e-05, "epoch": 3.2964652223489166, "percentage": 82.39, "elapsed_time": "0:58:46", "remaining_time": "0:12:34", "throughput": 2517.04, "total_tokens": 8877200}
|
| 153 |
+
{"current_steps": 730, "total_steps": 880, "loss": 0.139, "lr": 2.329072698468963e-05, "epoch": 3.3192702394526794, "percentage": 82.95, "elapsed_time": "0:59:09", "remaining_time": "0:12:09", "throughput": 2518.23, "total_tokens": 8938512}
|
| 154 |
+
{"current_steps": 735, "total_steps": 880, "loss": 0.1429, "lr": 2.1811749494855778e-05, "epoch": 3.342075256556442, "percentage": 83.52, "elapsed_time": "0:59:32", "remaining_time": "0:11:44", "throughput": 2519.37, "total_tokens": 9000464}
|
| 155 |
+
{"current_steps": 740, "total_steps": 880, "loss": 0.1452, "lr": 2.037759663845181e-05, "epoch": 3.364880273660205, "percentage": 84.09, "elapsed_time": "0:59:55", "remaining_time": "0:11:20", "throughput": 2520.49, "total_tokens": 9061648}
|
| 156 |
+
{"current_steps": 745, "total_steps": 880, "loss": 0.1392, "lr": 1.8988769907430552e-05, "epoch": 3.387685290763968, "percentage": 84.66, "elapsed_time": "1:00:17", "remaining_time": "0:10:55", "throughput": 2521.6, "total_tokens": 9122704}
|
| 157 |
+
{"current_steps": 750, "total_steps": 880, "loss": 0.1408, "lr": 1.7645754944187983e-05, "epoch": 3.4104903078677307, "percentage": 85.23, "elapsed_time": "1:00:40", "remaining_time": "0:10:30", "throughput": 2522.68, "total_tokens": 9183504}
|
| 158 |
+
{"current_steps": 755, "total_steps": 880, "loss": 0.1406, "lr": 1.634902137174483e-05, "epoch": 3.433295324971494, "percentage": 85.8, "elapsed_time": "1:01:03", "remaining_time": "0:10:06", "throughput": 2523.73, "total_tokens": 9245072}
|
| 159 |
+
{"current_steps": 760, "total_steps": 880, "loss": 0.1395, "lr": 1.5099022629529495e-05, "epoch": 3.4561003420752567, "percentage": 86.36, "elapsed_time": "1:01:26", "remaining_time": "0:09:42", "throughput": 2524.84, "total_tokens": 9307152}
|
| 160 |
+
{"current_steps": 765, "total_steps": 880, "loss": 0.137, "lr": 1.3896195814820266e-05, "epoch": 3.4789053591790196, "percentage": 86.93, "elapsed_time": "1:01:49", "remaining_time": "0:09:17", "throughput": 2526.02, "total_tokens": 9369616}
|
| 161 |
+
{"current_steps": 770, "total_steps": 880, "loss": 0.1337, "lr": 1.2740961529902027e-05, "epoch": 3.5017103762827824, "percentage": 87.5, "elapsed_time": "1:02:12", "remaining_time": "0:08:53", "throughput": 2527.07, "total_tokens": 9431568}
|
| 162 |
+
{"current_steps": 775, "total_steps": 880, "loss": 0.1384, "lr": 1.1633723734990624e-05, "epoch": 3.524515393386545, "percentage": 88.07, "elapsed_time": "1:02:34", "remaining_time": "0:08:28", "throughput": 2528.19, "total_tokens": 9493264}
|
| 163 |
+
{"current_steps": 780, "total_steps": 880, "loss": 0.1345, "lr": 1.0574869606976888e-05, "epoch": 3.547320410490308, "percentage": 88.64, "elapsed_time": "1:02:57", "remaining_time": "0:08:04", "throughput": 2529.21, "total_tokens": 9554448}
|
| 164 |
+
{"current_steps": 785, "total_steps": 880, "loss": 0.1368, "lr": 9.564769404039419e-06, "epoch": 3.570125427594071, "percentage": 89.2, "elapsed_time": "1:03:20", "remaining_time": "0:07:39", "throughput": 2530.21, "total_tokens": 9615760}
|
| 165 |
+
{"current_steps": 790, "total_steps": 880, "loss": 0.1452, "lr": 8.603776336173235e-06, "epoch": 3.5929304446978336, "percentage": 89.77, "elapsed_time": "1:03:43", "remaining_time": "0:07:15", "throughput": 2531.34, "total_tokens": 9678608}
|
| 166 |
+
{"current_steps": 795, "total_steps": 880, "loss": 0.1413, "lr": 7.692226441680038e-06, "epoch": 3.6157354618015964, "percentage": 90.34, "elapsed_time": "1:04:06", "remaining_time": "0:06:51", "throughput": 2532.36, "total_tokens": 9740304}
|
| 167 |
+
{"current_steps": 800, "total_steps": 880, "loss": 0.1356, "lr": 6.830438469662891e-06, "epoch": 3.6385404789053593, "percentage": 90.91, "elapsed_time": "1:04:29", "remaining_time": "0:06:26", "throughput": 2533.37, "total_tokens": 9801744}
|
| 168 |
+
{"current_steps": 800, "total_steps": 880, "eval_loss": 0.22199535369873047, "epoch": 3.6385404789053593, "percentage": 90.91, "elapsed_time": "1:05:01", "remaining_time": "0:06:30", "throughput": 2512.41, "total_tokens": 9801744}
|
| 169 |
+
{"current_steps": 805, "total_steps": 880, "loss": 0.1355, "lr": 6.018713768566658e-06, "epoch": 3.661345496009122, "percentage": 91.48, "elapsed_time": "1:05:24", "remaining_time": "0:06:05", "throughput": 2513.43, "total_tokens": 9862928}
|
| 170 |
+
{"current_steps": 810, "total_steps": 880, "loss": 0.1376, "lr": 5.257336180803029e-06, "epoch": 3.684150513112885, "percentage": 92.05, "elapsed_time": "1:05:46", "remaining_time": "0:05:41", "throughput": 2514.47, "total_tokens": 9924112}
|
| 171 |
+
{"current_steps": 815, "total_steps": 880, "loss": 0.1303, "lr": 4.546571943496968e-06, "epoch": 3.7069555302166477, "percentage": 92.61, "elapsed_time": "1:06:09", "remaining_time": "0:05:16", "throughput": 2515.44, "total_tokens": 9984784}
|
| 172 |
+
{"current_steps": 820, "total_steps": 880, "loss": 0.1405, "lr": 3.88666959538953e-06, "epoch": 3.7297605473204105, "percentage": 93.18, "elapsed_time": "1:06:32", "remaining_time": "0:04:52", "throughput": 2516.55, "total_tokens": 10046736}
|
| 173 |
+
{"current_steps": 825, "total_steps": 880, "loss": 0.132, "lr": 3.2778598899291465e-06, "epoch": 3.7525655644241733, "percentage": 93.75, "elapsed_time": "1:06:55", "remaining_time": "0:04:27", "throughput": 2517.59, "total_tokens": 10108176}
|
| 174 |
+
{"current_steps": 830, "total_steps": 880, "loss": 0.1326, "lr": 2.7203557145822398e-06, "epoch": 3.775370581527936, "percentage": 94.32, "elapsed_time": "1:07:17", "remaining_time": "0:04:03", "throughput": 2518.54, "total_tokens": 10169744}
|
| 175 |
+
{"current_steps": 835, "total_steps": 880, "loss": 0.1268, "lr": 2.2143520163911187e-06, "epoch": 3.798175598631699, "percentage": 94.89, "elapsed_time": "1:07:40", "remaining_time": "0:03:38", "throughput": 2519.61, "total_tokens": 10231696}
|
| 176 |
+
{"current_steps": 840, "total_steps": 880, "loss": 0.1341, "lr": 1.7600257338052593e-06, "epoch": 3.8209806157354618, "percentage": 95.45, "elapsed_time": "1:08:03", "remaining_time": "0:03:14", "throughput": 2520.55, "total_tokens": 10292624}
|
| 177 |
+
{"current_steps": 845, "total_steps": 880, "loss": 0.1366, "lr": 1.3575357348097948e-06, "epoch": 3.8437856328392246, "percentage": 96.02, "elapsed_time": "1:08:25", "remaining_time": "0:02:50", "throughput": 2521.47, "total_tokens": 10353040}
|
| 178 |
+
{"current_steps": 850, "total_steps": 880, "loss": 0.1317, "lr": 1.0070227613728221e-06, "epoch": 3.8665906499429874, "percentage": 96.59, "elapsed_time": "1:08:48", "remaining_time": "0:02:25", "throughput": 2522.44, "total_tokens": 10414480}
|
| 179 |
+
{"current_steps": 855, "total_steps": 880, "loss": 0.1312, "lr": 7.086093802310344e-07, "epoch": 3.88939566704675, "percentage": 97.16, "elapsed_time": "1:09:11", "remaining_time": "0:02:01", "throughput": 2523.32, "total_tokens": 10476432}
|
| 180 |
+
{"current_steps": 860, "total_steps": 880, "loss": 0.1286, "lr": 4.623999400308054e-07, "epoch": 3.912200684150513, "percentage": 97.73, "elapsed_time": "1:09:34", "remaining_time": "0:01:37", "throughput": 2524.29, "total_tokens": 10538128}
|
| 181 |
+
{"current_steps": 865, "total_steps": 880, "loss": 0.1279, "lr": 2.6848053483972677e-07, "epoch": 3.935005701254276, "percentage": 98.3, "elapsed_time": "1:09:57", "remaining_time": "0:01:12", "throughput": 2525.29, "total_tokens": 10600080}
|
| 182 |
+
{"current_steps": 870, "total_steps": 880, "loss": 0.1374, "lr": 1.2691897404140671e-07, "epoch": 3.9578107183580387, "percentage": 98.86, "elapsed_time": "1:10:20", "remaining_time": "0:00:48", "throughput": 2526.16, "total_tokens": 10660752}
|
| 183 |
+
{"current_steps": 875, "total_steps": 880, "loss": 0.1347, "lr": 3.77647586240204e-08, "epoch": 3.9806157354618015, "percentage": 99.43, "elapsed_time": "1:10:42", "remaining_time": "0:00:24", "throughput": 2527.09, "total_tokens": 10721680}
|
| 184 |
+
{"current_steps": 880, "total_steps": 880, "loss": 0.1323, "lr": 1.0490638708393616e-09, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:11:01", "remaining_time": "0:00:00", "throughput": 2527.8, "total_tokens": 10772736}
|
| 185 |
+
{"current_steps": 880, "total_steps": 880, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:11:09", "remaining_time": "0:00:00", "throughput": 2523.18, "total_tokens": 10772736}
|
trainer_state.json
CHANGED
|
@@ -2,1501 +2,1861 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.02280501710376283,
|
| 14 |
-
"grad_norm":
|
| 15 |
"learning_rate": 2.9999999999999997e-05,
|
| 16 |
-
"loss": 12.
|
| 17 |
"num_input_tokens_seen": 61696,
|
| 18 |
-
"step": 5
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 0.04561003420752566,
|
| 22 |
-
"grad_norm":
|
| 23 |
"learning_rate": 6.75e-05,
|
| 24 |
-
"loss": 5.
|
| 25 |
"num_input_tokens_seen": 123136,
|
| 26 |
-
"step": 10
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.06841505131128849,
|
| 30 |
-
"grad_norm":
|
| 31 |
"learning_rate": 0.00010499999999999999,
|
| 32 |
-
"loss": 1.
|
| 33 |
"num_input_tokens_seen": 184832,
|
| 34 |
-
"step": 15
|
|
|
|
|
|
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 0.09122006841505131,
|
| 38 |
-
"grad_norm":
|
| 39 |
"learning_rate": 0.0001425,
|
| 40 |
-
"loss": 0.
|
| 41 |
"num_input_tokens_seen": 247552,
|
| 42 |
-
"step": 20
|
|
|
|
|
|
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 0.11402508551881414,
|
| 46 |
-
"grad_norm":
|
| 47 |
"learning_rate": 0.00017999999999999998,
|
| 48 |
-
"loss": 0.
|
| 49 |
"num_input_tokens_seen": 308992,
|
| 50 |
-
"step": 25
|
|
|
|
|
|
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.13683010262257697,
|
| 54 |
-
"grad_norm":
|
| 55 |
"learning_rate": 0.00021749999999999997,
|
| 56 |
-
"loss": 0.
|
| 57 |
"num_input_tokens_seen": 370176,
|
| 58 |
-
"step": 30
|
|
|
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.15963511972633979,
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
"learning_rate": 0.00025499999999999996,
|
| 64 |
-
"loss": 0.
|
| 65 |
"num_input_tokens_seen": 430720,
|
| 66 |
-
"step": 35
|
|
|
|
|
|
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.18244013683010263,
|
| 70 |
-
"grad_norm":
|
| 71 |
"learning_rate": 0.00029249999999999995,
|
| 72 |
-
"loss": 0.
|
| 73 |
"num_input_tokens_seen": 492800,
|
| 74 |
-
"step": 40
|
|
|
|
|
|
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.20524515393386544,
|
| 78 |
-
"grad_norm":
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 0.
|
| 81 |
"num_input_tokens_seen": 553984,
|
| 82 |
-
"step": 45
|
|
|
|
|
|
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 0.22805017103762829,
|
| 86 |
-
"grad_norm":
|
| 87 |
-
"learning_rate": 0.
|
| 88 |
-
"loss": 0.
|
| 89 |
"num_input_tokens_seen": 615040,
|
| 90 |
-
"step": 50
|
|
|
|
|
|
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.2508551881413911,
|
| 94 |
-
"grad_norm": 0.
|
| 95 |
-
"learning_rate": 0.
|
| 96 |
-
"loss": 0.
|
| 97 |
"num_input_tokens_seen": 676736,
|
| 98 |
-
"step": 55
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.27366020524515394,
|
| 102 |
-
"grad_norm":
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 0.
|
| 105 |
"num_input_tokens_seen": 738176,
|
| 106 |
-
"step": 60
|
|
|
|
|
|
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 0.29646522234891676,
|
| 110 |
-
"grad_norm": 0.
|
| 111 |
-
"learning_rate": 0.
|
| 112 |
-
"loss": 0.
|
| 113 |
"num_input_tokens_seen": 799488,
|
| 114 |
-
"step": 65
|
|
|
|
|
|
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.31927023945267957,
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"num_input_tokens_seen": 861568,
|
| 122 |
-
"step": 70
|
|
|
|
|
|
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.34207525655644244,
|
| 126 |
-
"grad_norm": 0.
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss": 0.
|
| 129 |
"num_input_tokens_seen": 924544,
|
| 130 |
-
"step": 75
|
|
|
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.36488027366020526,
|
| 134 |
-
"grad_norm": 0.
|
| 135 |
-
"learning_rate": 0.
|
| 136 |
-
"loss": 0.
|
| 137 |
"num_input_tokens_seen": 985472,
|
| 138 |
-
"step": 80
|
|
|
|
|
|
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.38768529076396807,
|
| 142 |
-
"grad_norm": 0.
|
| 143 |
-
"learning_rate": 0.
|
| 144 |
-
"loss": 0.
|
| 145 |
"num_input_tokens_seen": 1046912,
|
| 146 |
-
"step": 85
|
|
|
|
|
|
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.4104903078677309,
|
| 150 |
-
"grad_norm": 0.
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 0.
|
| 153 |
"num_input_tokens_seen": 1108992,
|
| 154 |
-
"step": 90
|
|
|
|
|
|
|
| 155 |
},
|
| 156 |
{
|
| 157 |
"epoch": 0.43329532497149376,
|
| 158 |
-
"grad_norm": 0.
|
| 159 |
-
"learning_rate": 0.
|
| 160 |
-
"loss": 0.
|
| 161 |
"num_input_tokens_seen": 1170048,
|
| 162 |
-
"step": 95
|
|
|
|
|
|
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 0.45610034207525657,
|
| 166 |
-
"grad_norm": 0.
|
| 167 |
-
"learning_rate": 0.
|
| 168 |
-
"loss": 0.
|
| 169 |
"num_input_tokens_seen": 1230464,
|
| 170 |
-
"step": 100
|
|
|
|
|
|
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.45610034207525657,
|
| 174 |
-
"eval_loss": 0.
|
| 175 |
-
"eval_runtime":
|
| 176 |
-
"eval_samples_per_second":
|
| 177 |
-
"eval_steps_per_second":
|
| 178 |
"num_input_tokens_seen": 1230464,
|
| 179 |
"step": 100
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.4789053591790194,
|
| 183 |
-
"grad_norm": 0.
|
| 184 |
-
"learning_rate": 0.
|
| 185 |
-
"loss": 0.
|
| 186 |
"num_input_tokens_seen": 1292288,
|
| 187 |
-
"step": 105
|
|
|
|
|
|
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 0.5017103762827823,
|
| 191 |
-
"grad_norm": 0.
|
| 192 |
-
"learning_rate": 0.
|
| 193 |
-
"loss": 0.
|
| 194 |
"num_input_tokens_seen": 1353344,
|
| 195 |
-
"step": 110
|
|
|
|
|
|
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.5245153933865451,
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
-
"learning_rate": 0.
|
| 201 |
-
"loss": 0.
|
| 202 |
"num_input_tokens_seen": 1415040,
|
| 203 |
-
"step": 115
|
|
|
|
|
|
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 0.5473204104903079,
|
| 207 |
-
"grad_norm": 0.
|
| 208 |
-
"learning_rate": 0.
|
| 209 |
-
"loss": 0.
|
| 210 |
"num_input_tokens_seen": 1476480,
|
| 211 |
-
"step": 120
|
|
|
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"epoch": 0.5701254275940707,
|
| 215 |
-
"grad_norm": 0.
|
| 216 |
-
"learning_rate": 0.
|
| 217 |
-
"loss": 0.
|
| 218 |
"num_input_tokens_seen": 1537664,
|
| 219 |
-
"step": 125
|
|
|
|
|
|
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.5929304446978335,
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate": 0.
|
| 225 |
-
"loss": 0.
|
| 226 |
"num_input_tokens_seen": 1598848,
|
| 227 |
-
"step": 130
|
|
|
|
|
|
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.6157354618015963,
|
| 231 |
-
"grad_norm": 0.
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 0.
|
| 234 |
"num_input_tokens_seen": 1660800,
|
| 235 |
-
"step": 135
|
|
|
|
|
|
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.6385404789053591,
|
| 239 |
-
"grad_norm": 0.
|
| 240 |
-
"learning_rate": 0.
|
| 241 |
-
"loss": 0.
|
| 242 |
"num_input_tokens_seen": 1721600,
|
| 243 |
-
"step": 140
|
|
|
|
|
|
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.661345496009122,
|
| 247 |
-
"grad_norm": 0.
|
| 248 |
-
"learning_rate": 0.
|
| 249 |
-
"loss": 0.
|
| 250 |
"num_input_tokens_seen": 1783168,
|
| 251 |
-
"step": 145
|
|
|
|
|
|
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 0.6841505131128849,
|
| 255 |
-
"grad_norm": 0.
|
| 256 |
-
"learning_rate": 0.
|
| 257 |
-
"loss": 0.
|
| 258 |
"num_input_tokens_seen": 1844992,
|
| 259 |
-
"step": 150
|
|
|
|
|
|
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.7069555302166477,
|
| 263 |
-
"grad_norm": 0.
|
| 264 |
-
"learning_rate": 0.
|
| 265 |
-
"loss": 0.
|
| 266 |
"num_input_tokens_seen": 1906048,
|
| 267 |
-
"step": 155
|
|
|
|
|
|
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.7297605473204105,
|
| 271 |
-
"grad_norm": 0.
|
| 272 |
-
"learning_rate": 0.
|
| 273 |
-
"loss": 0.
|
| 274 |
"num_input_tokens_seen": 1967744,
|
| 275 |
-
"step": 160
|
|
|
|
|
|
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 0.7525655644241733,
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate": 0.
|
| 281 |
-
"loss": 0.
|
| 282 |
"num_input_tokens_seen": 2028032,
|
| 283 |
-
"step": 165
|
|
|
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 0.7753705815279361,
|
| 287 |
-
"grad_norm": 0.
|
| 288 |
-
"learning_rate": 0.
|
| 289 |
-
"loss": 0.
|
| 290 |
"num_input_tokens_seen": 2088448,
|
| 291 |
-
"step": 170
|
|
|
|
|
|
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.798175598631699,
|
| 295 |
-
"grad_norm": 0.
|
| 296 |
-
"learning_rate": 0.
|
| 297 |
-
"loss": 0.
|
| 298 |
"num_input_tokens_seen": 2150144,
|
| 299 |
-
"step": 175
|
|
|
|
|
|
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.8209806157354618,
|
| 303 |
-
"grad_norm": 0.
|
| 304 |
-
"learning_rate": 0.
|
| 305 |
-
"loss": 0.
|
| 306 |
"num_input_tokens_seen": 2211584,
|
| 307 |
-
"step": 180
|
|
|
|
|
|
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 0.8437856328392246,
|
| 311 |
-
"grad_norm": 0.
|
| 312 |
-
"learning_rate": 0.
|
| 313 |
-
"loss": 0.
|
| 314 |
"num_input_tokens_seen": 2272256,
|
| 315 |
-
"step": 185
|
|
|
|
|
|
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.8665906499429875,
|
| 319 |
-
"grad_norm": 0.
|
| 320 |
-
"learning_rate": 0.
|
| 321 |
-
"loss": 0.
|
| 322 |
"num_input_tokens_seen": 2333696,
|
| 323 |
-
"step": 190
|
|
|
|
|
|
|
| 324 |
},
|
| 325 |
{
|
| 326 |
"epoch": 0.8893956670467503,
|
| 327 |
-
"grad_norm": 0.
|
| 328 |
-
"learning_rate": 0.
|
| 329 |
-
"loss": 0.
|
| 330 |
"num_input_tokens_seen": 2394880,
|
| 331 |
-
"step": 195
|
|
|
|
|
|
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.9122006841505131,
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate": 0.
|
| 337 |
-
"loss": 0.
|
| 338 |
"num_input_tokens_seen": 2455680,
|
| 339 |
-
"step": 200
|
|
|
|
|
|
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.9122006841505131,
|
| 343 |
-
"eval_loss": 0.
|
| 344 |
-
"eval_runtime":
|
| 345 |
-
"eval_samples_per_second":
|
| 346 |
-
"eval_steps_per_second":
|
| 347 |
"num_input_tokens_seen": 2455680,
|
| 348 |
"step": 200
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 0.935005701254276,
|
| 352 |
-
"grad_norm": 0.
|
| 353 |
-
"learning_rate": 0.
|
| 354 |
-
"loss": 0.
|
| 355 |
"num_input_tokens_seen": 2517376,
|
| 356 |
-
"step": 205
|
|
|
|
|
|
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.9578107183580388,
|
| 360 |
-
"grad_norm": 0.
|
| 361 |
-
"learning_rate": 0.
|
| 362 |
-
"loss": 0.
|
| 363 |
"num_input_tokens_seen": 2578816,
|
| 364 |
-
"step": 210
|
|
|
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 0.9806157354618016,
|
| 368 |
-
"grad_norm": 0.
|
| 369 |
-
"learning_rate": 0.
|
| 370 |
-
"loss": 0.
|
| 371 |
"num_input_tokens_seen": 2640128,
|
| 372 |
-
"step": 215
|
|
|
|
|
|
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 1.0,
|
| 376 |
-
"grad_norm": 0.
|
| 377 |
-
"learning_rate": 0.
|
| 378 |
-
"loss": 0.
|
| 379 |
"num_input_tokens_seen": 2691984,
|
| 380 |
-
"step": 220
|
|
|
|
|
|
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 1.0228050171037628,
|
| 384 |
-
"grad_norm": 0.
|
| 385 |
-
"learning_rate": 0.
|
| 386 |
-
"loss": 0.
|
| 387 |
"num_input_tokens_seen": 2753808,
|
| 388 |
-
"step": 225
|
|
|
|
|
|
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.0456100342075256,
|
| 392 |
-
"grad_norm": 0.
|
| 393 |
-
"learning_rate": 0.
|
| 394 |
-
"loss": 0.
|
| 395 |
"num_input_tokens_seen": 2815248,
|
| 396 |
-
"step": 230
|
|
|
|
|
|
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 1.0684150513112884,
|
| 400 |
-
"grad_norm": 0.
|
| 401 |
-
"learning_rate": 0.
|
| 402 |
-
"loss": 0.
|
| 403 |
"num_input_tokens_seen": 2877456,
|
| 404 |
-
"step": 235
|
|
|
|
|
|
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 1.0912200684150513,
|
| 408 |
-
"grad_norm": 0.
|
| 409 |
-
"learning_rate": 0.
|
| 410 |
-
"loss": 0.
|
| 411 |
"num_input_tokens_seen": 2939280,
|
| 412 |
-
"step": 240
|
|
|
|
|
|
|
| 413 |
},
|
| 414 |
{
|
| 415 |
"epoch": 1.114025085518814,
|
| 416 |
-
"grad_norm": 0.
|
| 417 |
-
"learning_rate": 0.
|
| 418 |
-
"loss": 0.
|
| 419 |
"num_input_tokens_seen": 3000336,
|
| 420 |
-
"step": 245
|
|
|
|
|
|
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 1.1368301026225769,
|
| 424 |
-
"grad_norm": 0.
|
| 425 |
-
"learning_rate": 0.
|
| 426 |
-
"loss": 0.
|
| 427 |
"num_input_tokens_seen": 3062416,
|
| 428 |
-
"step": 250
|
|
|
|
|
|
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 1.1596351197263397,
|
| 432 |
-
"grad_norm": 0.
|
| 433 |
-
"learning_rate": 0.
|
| 434 |
-
"loss": 0.
|
| 435 |
"num_input_tokens_seen": 3124368,
|
| 436 |
-
"step": 255
|
|
|
|
|
|
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 1.1824401368301025,
|
| 440 |
-
"grad_norm": 0.
|
| 441 |
-
"learning_rate": 0.
|
| 442 |
-
"loss": 0.
|
| 443 |
"num_input_tokens_seen": 3185424,
|
| 444 |
-
"step": 260
|
|
|
|
|
|
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.2052451539338653,
|
| 448 |
-
"grad_norm": 0.
|
| 449 |
-
"learning_rate": 0.
|
| 450 |
-
"loss": 0.
|
| 451 |
"num_input_tokens_seen": 3246096,
|
| 452 |
-
"step": 265
|
|
|
|
|
|
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 1.2280501710376284,
|
| 456 |
-
"grad_norm": 0.
|
| 457 |
-
"learning_rate": 0.
|
| 458 |
-
"loss": 0.
|
| 459 |
"num_input_tokens_seen": 3307536,
|
| 460 |
-
"step": 270
|
|
|
|
|
|
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 1.2508551881413912,
|
| 464 |
-
"grad_norm": 0.
|
| 465 |
-
"learning_rate": 0.
|
| 466 |
-
"loss": 0.
|
| 467 |
"num_input_tokens_seen": 3368976,
|
| 468 |
-
"step": 275
|
|
|
|
|
|
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 1.273660205245154,
|
| 472 |
-
"grad_norm": 0.
|
| 473 |
-
"learning_rate": 0.
|
| 474 |
-
"loss": 0.
|
| 475 |
"num_input_tokens_seen": 3429520,
|
| 476 |
-
"step": 280
|
|
|
|
|
|
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 1.2964652223489168,
|
| 480 |
-
"grad_norm": 0.
|
| 481 |
-
"learning_rate": 0.
|
| 482 |
-
"loss": 0.
|
| 483 |
"num_input_tokens_seen": 3490448,
|
| 484 |
-
"step": 285
|
|
|
|
|
|
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 1.3192702394526796,
|
| 488 |
-
"grad_norm": 0.
|
| 489 |
-
"learning_rate": 0.
|
| 490 |
-
"loss": 0.
|
| 491 |
"num_input_tokens_seen": 3551120,
|
| 492 |
-
"step": 290
|
|
|
|
|
|
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 1.3420752565564424,
|
| 496 |
-
"grad_norm": 0.
|
| 497 |
-
"learning_rate": 0.
|
| 498 |
-
"loss": 0.
|
| 499 |
"num_input_tokens_seen": 3611920,
|
| 500 |
-
"step": 295
|
|
|
|
|
|
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 1.3648802736602053,
|
| 504 |
-
"grad_norm": 0.
|
| 505 |
-
"learning_rate": 0.
|
| 506 |
-
"loss": 0.
|
| 507 |
"num_input_tokens_seen": 3673744,
|
| 508 |
-
"step": 300
|
|
|
|
|
|
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 1.3648802736602053,
|
| 512 |
-
"eval_loss": 0.
|
| 513 |
-
"eval_runtime":
|
| 514 |
-
"eval_samples_per_second":
|
| 515 |
-
"eval_steps_per_second":
|
| 516 |
"num_input_tokens_seen": 3673744,
|
| 517 |
"step": 300
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 1.387685290763968,
|
| 521 |
-
"grad_norm": 0.
|
| 522 |
-
"learning_rate": 0.
|
| 523 |
-
"loss": 0.
|
| 524 |
"num_input_tokens_seen": 3735568,
|
| 525 |
-
"step": 305
|
|
|
|
|
|
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 1.4104903078677309,
|
| 529 |
-
"grad_norm": 0.
|
| 530 |
-
"learning_rate": 0.
|
| 531 |
-
"loss": 0.
|
| 532 |
"num_input_tokens_seen": 3798160,
|
| 533 |
-
"step": 310
|
|
|
|
|
|
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 1.4332953249714937,
|
| 537 |
-
"grad_norm": 0.
|
| 538 |
-
"learning_rate": 0.
|
| 539 |
-
"loss": 0.
|
| 540 |
"num_input_tokens_seen": 3859600,
|
| 541 |
-
"step": 315
|
|
|
|
|
|
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 1.4561003420752565,
|
| 545 |
-
"grad_norm": 0.
|
| 546 |
-
"learning_rate": 0.
|
| 547 |
-
"loss": 0.
|
| 548 |
"num_input_tokens_seen": 3920528,
|
| 549 |
-
"step": 320
|
|
|
|
|
|
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 1.4789053591790193,
|
| 553 |
-
"grad_norm": 0.
|
| 554 |
-
"learning_rate": 0.
|
| 555 |
-
"loss": 0.
|
| 556 |
"num_input_tokens_seen": 3982096,
|
| 557 |
-
"step": 325
|
|
|
|
|
|
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 1.5017103762827824,
|
| 561 |
-
"grad_norm": 0.
|
| 562 |
-
"learning_rate": 0.
|
| 563 |
-
"loss": 0.
|
| 564 |
"num_input_tokens_seen": 4044048,
|
| 565 |
-
"step": 330
|
|
|
|
|
|
|
| 566 |
},
|
| 567 |
{
|
| 568 |
"epoch": 1.5245153933865452,
|
| 569 |
-
"grad_norm": 0.
|
| 570 |
-
"learning_rate": 0.
|
| 571 |
-
"loss": 0.
|
| 572 |
"num_input_tokens_seen": 4105104,
|
| 573 |
-
"step": 335
|
|
|
|
|
|
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 1.547320410490308,
|
| 577 |
-
"grad_norm": 0.
|
| 578 |
-
"learning_rate": 0.
|
| 579 |
-
"loss": 0.
|
| 580 |
"num_input_tokens_seen": 4165904,
|
| 581 |
-
"step": 340
|
|
|
|
|
|
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 1.5701254275940708,
|
| 585 |
-
"grad_norm": 0.
|
| 586 |
-
"learning_rate": 0.
|
| 587 |
-
"loss": 0.
|
| 588 |
"num_input_tokens_seen": 4226704,
|
| 589 |
-
"step": 345
|
|
|
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 1.5929304446978336,
|
| 593 |
-
"grad_norm": 0.
|
| 594 |
-
"learning_rate": 0.
|
| 595 |
-
"loss": 0.
|
| 596 |
"num_input_tokens_seen": 4288400,
|
| 597 |
-
"step": 350
|
|
|
|
|
|
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 1.6157354618015964,
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
-
"learning_rate": 0.
|
| 603 |
-
"loss": 0.
|
| 604 |
"num_input_tokens_seen": 4349712,
|
| 605 |
-
"step": 355
|
|
|
|
|
|
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 1.6385404789053593,
|
| 609 |
-
"grad_norm": 0.
|
| 610 |
-
"learning_rate": 0.
|
| 611 |
-
"loss": 0.
|
| 612 |
"num_input_tokens_seen": 4410256,
|
| 613 |
-
"step": 360
|
|
|
|
|
|
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 1.661345496009122,
|
| 617 |
-
"grad_norm":
|
| 618 |
-
"learning_rate": 0.
|
| 619 |
-
"loss": 0.
|
| 620 |
"num_input_tokens_seen": 4471440,
|
| 621 |
-
"step": 365
|
|
|
|
|
|
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 1.6841505131128849,
|
| 625 |
-
"grad_norm": 0.
|
| 626 |
-
"learning_rate": 0.
|
| 627 |
-
"loss": 0.
|
| 628 |
"num_input_tokens_seen": 4533008,
|
| 629 |
-
"step": 370
|
|
|
|
|
|
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 1.7069555302166477,
|
| 633 |
-
"grad_norm": 0.
|
| 634 |
-
"learning_rate": 0.
|
| 635 |
-
"loss": 0.
|
| 636 |
"num_input_tokens_seen": 4594320,
|
| 637 |
-
"step": 375
|
|
|
|
|
|
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 1.7297605473204105,
|
| 641 |
-
"grad_norm": 0.
|
| 642 |
-
"learning_rate": 0.
|
| 643 |
-
"loss": 0.
|
| 644 |
"num_input_tokens_seen": 4655760,
|
| 645 |
-
"step": 380
|
|
|
|
|
|
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 1.7525655644241733,
|
| 649 |
-
"grad_norm": 0.
|
| 650 |
-
"learning_rate": 0.
|
| 651 |
-
"loss": 0.
|
| 652 |
"num_input_tokens_seen": 4717328,
|
| 653 |
-
"step": 385
|
|
|
|
|
|
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 1.7753705815279361,
|
| 657 |
-
"grad_norm": 0.
|
| 658 |
-
"learning_rate": 0.
|
| 659 |
-
"loss": 0.
|
| 660 |
"num_input_tokens_seen": 4779152,
|
| 661 |
-
"step": 390
|
|
|
|
|
|
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 1.798175598631699,
|
| 665 |
-
"grad_norm": 0.
|
| 666 |
-
"learning_rate": 0.
|
| 667 |
-
"loss": 0.
|
| 668 |
"num_input_tokens_seen": 4840336,
|
| 669 |
-
"step": 395
|
|
|
|
|
|
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 1.8209806157354618,
|
| 673 |
-
"grad_norm": 0.
|
| 674 |
-
"learning_rate": 0.
|
| 675 |
-
"loss": 0.
|
| 676 |
"num_input_tokens_seen": 4901648,
|
| 677 |
-
"step": 400
|
|
|
|
|
|
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 1.8209806157354618,
|
| 681 |
-
"eval_loss": 0.
|
| 682 |
-
"eval_runtime":
|
| 683 |
-
"eval_samples_per_second":
|
| 684 |
-
"eval_steps_per_second":
|
| 685 |
"num_input_tokens_seen": 4901648,
|
| 686 |
"step": 400
|
| 687 |
},
|
| 688 |
{
|
| 689 |
"epoch": 1.8437856328392246,
|
| 690 |
-
"grad_norm": 0.
|
| 691 |
-
"learning_rate": 0.
|
| 692 |
-
"loss": 0.
|
| 693 |
"num_input_tokens_seen": 4963216,
|
| 694 |
-
"step": 405
|
|
|
|
|
|
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 1.8665906499429874,
|
| 698 |
-
"grad_norm": 0.
|
| 699 |
-
"learning_rate": 0.
|
| 700 |
-
"loss": 0.
|
| 701 |
"num_input_tokens_seen": 5024912,
|
| 702 |
-
"step": 410
|
|
|
|
|
|
|
| 703 |
},
|
| 704 |
{
|
| 705 |
"epoch": 1.8893956670467502,
|
| 706 |
-
"grad_norm": 0.
|
| 707 |
-
"learning_rate": 0.
|
| 708 |
-
"loss": 0.
|
| 709 |
"num_input_tokens_seen": 5086224,
|
| 710 |
-
"step": 415
|
|
|
|
|
|
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 1.912200684150513,
|
| 714 |
-
"grad_norm": 0.
|
| 715 |
-
"learning_rate": 0.
|
| 716 |
-
"loss": 0.
|
| 717 |
"num_input_tokens_seen": 5148048,
|
| 718 |
-
"step": 420
|
|
|
|
|
|
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 1.9350057012542758,
|
| 722 |
-
"grad_norm": 0.
|
| 723 |
-
"learning_rate": 0.
|
| 724 |
-
"loss": 0.
|
| 725 |
"num_input_tokens_seen": 5209104,
|
| 726 |
-
"step": 425
|
|
|
|
|
|
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 1.9578107183580387,
|
| 730 |
-
"grad_norm": 0.
|
| 731 |
-
"learning_rate": 0.
|
| 732 |
-
"loss": 0.
|
| 733 |
"num_input_tokens_seen": 5270544,
|
| 734 |
-
"step": 430
|
|
|
|
|
|
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 1.9806157354618015,
|
| 738 |
-
"grad_norm": 0.
|
| 739 |
-
"learning_rate": 0.
|
| 740 |
-
"loss": 0.
|
| 741 |
"num_input_tokens_seen": 5331472,
|
| 742 |
-
"step": 435
|
|
|
|
|
|
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"epoch": 2.0,
|
| 746 |
-
"grad_norm": 0.
|
| 747 |
-
"learning_rate": 0.
|
| 748 |
-
"loss": 0.
|
| 749 |
"num_input_tokens_seen": 5382864,
|
| 750 |
-
"step": 440
|
|
|
|
|
|
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 2.022805017103763,
|
| 754 |
-
"grad_norm": 0.
|
| 755 |
-
"learning_rate": 0.
|
| 756 |
-
"loss": 0.
|
| 757 |
"num_input_tokens_seen": 5444176,
|
| 758 |
-
"step": 445
|
|
|
|
|
|
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 2.0456100342075256,
|
| 762 |
-
"grad_norm": 0.
|
| 763 |
-
"learning_rate": 0.
|
| 764 |
-
"loss": 0.
|
| 765 |
"num_input_tokens_seen": 5505872,
|
| 766 |
-
"step": 450
|
|
|
|
|
|
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 2.0684150513112884,
|
| 770 |
-
"grad_norm": 0.
|
| 771 |
-
"learning_rate": 0.
|
| 772 |
-
"loss": 0.
|
| 773 |
"num_input_tokens_seen": 5568208,
|
| 774 |
-
"step": 455
|
|
|
|
|
|
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 2.0912200684150513,
|
| 778 |
-
"grad_norm": 0.
|
| 779 |
-
"learning_rate": 0.
|
| 780 |
-
"loss": 0.
|
| 781 |
"num_input_tokens_seen": 5628880,
|
| 782 |
-
"step": 460
|
|
|
|
|
|
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 2.114025085518814,
|
| 786 |
-
"grad_norm": 0.
|
| 787 |
-
"learning_rate": 0.
|
| 788 |
-
"loss": 0.
|
| 789 |
"num_input_tokens_seen": 5690320,
|
| 790 |
-
"step": 465
|
|
|
|
|
|
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 2.136830102622577,
|
| 794 |
-
"grad_norm": 0.
|
| 795 |
-
"learning_rate": 0.
|
| 796 |
-
"loss": 0.
|
| 797 |
"num_input_tokens_seen": 5752912,
|
| 798 |
-
"step": 470
|
|
|
|
|
|
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 2.1596351197263397,
|
| 802 |
-
"grad_norm": 0.
|
| 803 |
-
"learning_rate": 0.
|
| 804 |
-
"loss": 0.
|
| 805 |
"num_input_tokens_seen": 5813968,
|
| 806 |
-
"step": 475
|
|
|
|
|
|
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 2.1824401368301025,
|
| 810 |
-
"grad_norm": 0.
|
| 811 |
-
"learning_rate": 0.
|
| 812 |
-
"loss": 0.
|
| 813 |
"num_input_tokens_seen": 5874896,
|
| 814 |
-
"step": 480
|
|
|
|
|
|
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"epoch": 2.2052451539338653,
|
| 818 |
-
"grad_norm": 0.
|
| 819 |
-
"learning_rate": 0.
|
| 820 |
-
"loss": 0.
|
| 821 |
"num_input_tokens_seen": 5935952,
|
| 822 |
-
"step": 485
|
|
|
|
|
|
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 2.228050171037628,
|
| 826 |
-
"grad_norm": 0.
|
| 827 |
-
"learning_rate": 0.
|
| 828 |
-
"loss": 0.
|
| 829 |
"num_input_tokens_seen": 5997008,
|
| 830 |
-
"step": 490
|
|
|
|
|
|
|
| 831 |
},
|
| 832 |
{
|
| 833 |
"epoch": 2.250855188141391,
|
| 834 |
-
"grad_norm":
|
| 835 |
-
"learning_rate": 0.
|
| 836 |
-
"loss": 0.
|
| 837 |
"num_input_tokens_seen": 6058704,
|
| 838 |
-
"step": 495
|
|
|
|
|
|
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 2.2736602052451538,
|
| 842 |
-
"grad_norm": 0.
|
| 843 |
-
"learning_rate": 0.
|
| 844 |
-
"loss": 0.
|
| 845 |
"num_input_tokens_seen": 6120272,
|
| 846 |
-
"step": 500
|
|
|
|
|
|
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"epoch": 2.2736602052451538,
|
| 850 |
-
"eval_loss": 0.
|
| 851 |
-
"eval_runtime":
|
| 852 |
-
"eval_samples_per_second":
|
| 853 |
-
"eval_steps_per_second":
|
| 854 |
"num_input_tokens_seen": 6120272,
|
| 855 |
"step": 500
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 2.2964652223489166,
|
| 859 |
-
"grad_norm": 0.
|
| 860 |
-
"learning_rate": 0.
|
| 861 |
-
"loss": 0.
|
| 862 |
"num_input_tokens_seen": 6180816,
|
| 863 |
-
"step": 505
|
|
|
|
|
|
|
| 864 |
},
|
| 865 |
{
|
| 866 |
"epoch": 2.3192702394526794,
|
| 867 |
-
"grad_norm": 0.
|
| 868 |
-
"learning_rate": 0.
|
| 869 |
-
"loss": 0.
|
| 870 |
"num_input_tokens_seen": 6242128,
|
| 871 |
-
"step": 510
|
|
|
|
|
|
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 2.342075256556442,
|
| 875 |
-
"grad_norm": 0.
|
| 876 |
-
"learning_rate": 0.
|
| 877 |
-
"loss": 0.
|
| 878 |
"num_input_tokens_seen": 6303312,
|
| 879 |
-
"step": 515
|
|
|
|
|
|
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 2.364880273660205,
|
| 883 |
-
"grad_norm": 0.
|
| 884 |
-
"learning_rate": 0.
|
| 885 |
-
"loss": 0.
|
| 886 |
"num_input_tokens_seen": 6364624,
|
| 887 |
-
"step": 520
|
|
|
|
|
|
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 2.387685290763968,
|
| 891 |
-
"grad_norm": 0.
|
| 892 |
-
"learning_rate": 0.
|
| 893 |
-
"loss": 0.
|
| 894 |
"num_input_tokens_seen": 6425040,
|
| 895 |
-
"step": 525
|
|
|
|
|
|
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 2.4104903078677307,
|
| 899 |
-
"grad_norm": 0.
|
| 900 |
-
"learning_rate": 0.
|
| 901 |
-
"loss": 0.
|
| 902 |
"num_input_tokens_seen": 6486736,
|
| 903 |
-
"step": 530
|
|
|
|
|
|
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 2.433295324971494,
|
| 907 |
-
"grad_norm": 0.
|
| 908 |
-
"learning_rate": 0.
|
| 909 |
-
"loss": 0.
|
| 910 |
"num_input_tokens_seen": 6548304,
|
| 911 |
-
"step": 535
|
|
|
|
|
|
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 2.4561003420752567,
|
| 915 |
-
"grad_norm": 0.
|
| 916 |
-
"learning_rate": 0.
|
| 917 |
-
"loss": 0.
|
| 918 |
"num_input_tokens_seen": 6610000,
|
| 919 |
-
"step": 540
|
|
|
|
|
|
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 2.4789053591790196,
|
| 923 |
-
"grad_norm": 0.
|
| 924 |
-
"learning_rate": 0.
|
| 925 |
-
"loss": 0.
|
| 926 |
"num_input_tokens_seen": 6670672,
|
| 927 |
-
"step": 545
|
|
|
|
|
|
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 2.5017103762827824,
|
| 931 |
-
"grad_norm": 0.
|
| 932 |
-
"learning_rate":
|
| 933 |
-
"loss": 0.
|
| 934 |
"num_input_tokens_seen": 6732112,
|
| 935 |
-
"step": 550
|
|
|
|
|
|
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 2.524515393386545,
|
| 939 |
-
"grad_norm": 0.
|
| 940 |
-
"learning_rate": 9.
|
| 941 |
-
"loss": 0.
|
| 942 |
"num_input_tokens_seen": 6793424,
|
| 943 |
-
"step": 555
|
|
|
|
|
|
|
| 944 |
},
|
| 945 |
{
|
| 946 |
"epoch": 2.547320410490308,
|
| 947 |
-
"grad_norm": 0.
|
| 948 |
-
"learning_rate": 9.
|
| 949 |
-
"loss": 0.
|
| 950 |
"num_input_tokens_seen": 6855760,
|
| 951 |
-
"step": 560
|
|
|
|
|
|
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 2.570125427594071,
|
| 955 |
-
"grad_norm": 0.
|
| 956 |
-
"learning_rate": 9.
|
| 957 |
-
"loss": 0.
|
| 958 |
"num_input_tokens_seen": 6916688,
|
| 959 |
-
"step": 565
|
|
|
|
|
|
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 2.5929304446978336,
|
| 963 |
-
"grad_norm": 0.
|
| 964 |
-
"learning_rate":
|
| 965 |
-
"loss": 0.
|
| 966 |
"num_input_tokens_seen": 6978512,
|
| 967 |
-
"step": 570
|
|
|
|
|
|
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 2.6157354618015964,
|
| 971 |
-
"grad_norm": 0.
|
| 972 |
-
"learning_rate": 8.
|
| 973 |
-
"loss": 0.
|
| 974 |
"num_input_tokens_seen": 7040208,
|
| 975 |
-
"step": 575
|
|
|
|
|
|
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 2.6385404789053593,
|
| 979 |
-
"grad_norm": 0.
|
| 980 |
-
"learning_rate": 8.
|
| 981 |
-
"loss": 0.
|
| 982 |
"num_input_tokens_seen": 7101264,
|
| 983 |
-
"step": 580
|
|
|
|
|
|
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 2.661345496009122,
|
| 987 |
-
"grad_norm": 0.
|
| 988 |
-
"learning_rate": 8.
|
| 989 |
-
"loss": 0.
|
| 990 |
"num_input_tokens_seen": 7163600,
|
| 991 |
-
"step": 585
|
|
|
|
|
|
|
| 992 |
},
|
| 993 |
{
|
| 994 |
"epoch": 2.684150513112885,
|
| 995 |
-
"grad_norm": 0.
|
| 996 |
-
"learning_rate":
|
| 997 |
-
"loss": 0.
|
| 998 |
"num_input_tokens_seen": 7225936,
|
| 999 |
-
"step": 590
|
|
|
|
|
|
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 2.7069555302166477,
|
| 1003 |
-
"grad_norm": 0.
|
| 1004 |
-
"learning_rate": 7.
|
| 1005 |
-
"loss": 0.
|
| 1006 |
"num_input_tokens_seen": 7287760,
|
| 1007 |
-
"step": 595
|
|
|
|
|
|
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 2.7297605473204105,
|
| 1011 |
-
"grad_norm": 0.
|
| 1012 |
-
"learning_rate": 7.
|
| 1013 |
-
"loss": 0.
|
| 1014 |
"num_input_tokens_seen": 7348944,
|
| 1015 |
-
"step": 600
|
|
|
|
|
|
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 2.7297605473204105,
|
| 1019 |
-
"eval_loss": 0.
|
| 1020 |
-
"eval_runtime":
|
| 1021 |
-
"eval_samples_per_second":
|
| 1022 |
-
"eval_steps_per_second":
|
| 1023 |
"num_input_tokens_seen": 7348944,
|
| 1024 |
"step": 600
|
| 1025 |
},
|
| 1026 |
{
|
| 1027 |
"epoch": 2.7525655644241733,
|
| 1028 |
-
"grad_norm": 0.
|
| 1029 |
-
"learning_rate": 7.
|
| 1030 |
-
"loss": 0.
|
| 1031 |
"num_input_tokens_seen": 7410640,
|
| 1032 |
-
"step": 605
|
|
|
|
|
|
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
"epoch": 2.775370581527936,
|
| 1036 |
-
"grad_norm": 0.
|
| 1037 |
-
"learning_rate":
|
| 1038 |
-
"loss": 0.
|
| 1039 |
"num_input_tokens_seen": 7471184,
|
| 1040 |
-
"step": 610
|
|
|
|
|
|
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 2.798175598631699,
|
| 1044 |
-
"grad_norm": 0.
|
| 1045 |
-
"learning_rate": 6.
|
| 1046 |
-
"loss": 0.
|
| 1047 |
"num_input_tokens_seen": 7533392,
|
| 1048 |
-
"step": 615
|
|
|
|
|
|
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 2.8209806157354618,
|
| 1052 |
-
"grad_norm": 0.
|
| 1053 |
-
"learning_rate": 6.
|
| 1054 |
-
"loss": 0.
|
| 1055 |
"num_input_tokens_seen": 7594832,
|
| 1056 |
-
"step": 620
|
|
|
|
|
|
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 2.8437856328392246,
|
| 1060 |
-
"grad_norm": 0.
|
| 1061 |
-
"learning_rate": 6.
|
| 1062 |
-
"loss": 0.
|
| 1063 |
"num_input_tokens_seen": 7656656,
|
| 1064 |
-
"step": 625
|
|
|
|
|
|
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 2.8665906499429874,
|
| 1068 |
-
"grad_norm": 0.
|
| 1069 |
-
"learning_rate": 6.
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"num_input_tokens_seen": 7717712,
|
| 1072 |
-
"step": 630
|
|
|
|
|
|
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
"epoch": 2.88939566704675,
|
| 1076 |
-
"grad_norm": 0.
|
| 1077 |
-
"learning_rate": 5.
|
| 1078 |
-
"loss": 0.
|
| 1079 |
"num_input_tokens_seen": 7779920,
|
| 1080 |
-
"step": 635
|
|
|
|
|
|
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 2.912200684150513,
|
| 1084 |
-
"grad_norm": 0.
|
| 1085 |
-
"learning_rate": 5.
|
| 1086 |
-
"loss": 0.
|
| 1087 |
"num_input_tokens_seen": 7840976,
|
| 1088 |
-
"step": 640
|
|
|
|
|
|
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
"epoch": 2.935005701254276,
|
| 1092 |
-
"grad_norm": 0.
|
| 1093 |
-
"learning_rate": 5.
|
| 1094 |
-
"loss": 0.
|
| 1095 |
"num_input_tokens_seen": 7902160,
|
| 1096 |
-
"step": 645
|
|
|
|
|
|
|
| 1097 |
},
|
| 1098 |
{
|
| 1099 |
"epoch": 2.9578107183580387,
|
| 1100 |
-
"grad_norm": 0.
|
| 1101 |
-
"learning_rate": 5.
|
| 1102 |
-
"loss": 0.
|
| 1103 |
"num_input_tokens_seen": 7963856,
|
| 1104 |
-
"step": 650
|
|
|
|
|
|
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 2.9806157354618015,
|
| 1108 |
-
"grad_norm": 0.
|
| 1109 |
-
"learning_rate":
|
| 1110 |
-
"loss": 0.
|
| 1111 |
"num_input_tokens_seen": 8026448,
|
| 1112 |
-
"step": 655
|
|
|
|
|
|
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 3.0,
|
| 1116 |
-
"grad_norm": 0.
|
| 1117 |
-
"learning_rate": 4.
|
| 1118 |
-
"loss": 0.
|
| 1119 |
"num_input_tokens_seen": 8078224,
|
| 1120 |
-
"step": 660
|
|
|
|
|
|
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 3.022805017103763,
|
| 1124 |
-
"grad_norm": 0.
|
| 1125 |
-
"learning_rate": 4.
|
| 1126 |
-
"loss": 0.
|
| 1127 |
"num_input_tokens_seen": 8140176,
|
| 1128 |
-
"step": 665
|
|
|
|
|
|
|
| 1129 |
},
|
| 1130 |
{
|
| 1131 |
"epoch": 3.0456100342075256,
|
| 1132 |
-
"grad_norm": 0.
|
| 1133 |
-
"learning_rate": 4.
|
| 1134 |
-
"loss": 0.
|
| 1135 |
"num_input_tokens_seen": 8201616,
|
| 1136 |
-
"step": 670
|
|
|
|
|
|
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 3.0684150513112884,
|
| 1140 |
-
"grad_norm": 0.
|
| 1141 |
-
"learning_rate": 4.
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"num_input_tokens_seen": 8262928,
|
| 1144 |
-
"step": 675
|
|
|
|
|
|
|
| 1145 |
},
|
| 1146 |
{
|
| 1147 |
"epoch": 3.0912200684150513,
|
| 1148 |
-
"grad_norm": 0.
|
| 1149 |
-
"learning_rate":
|
| 1150 |
-
"loss": 0.
|
| 1151 |
"num_input_tokens_seen": 8324496,
|
| 1152 |
-
"step": 680
|
|
|
|
|
|
|
| 1153 |
},
|
| 1154 |
{
|
| 1155 |
"epoch": 3.114025085518814,
|
| 1156 |
-
"grad_norm": 0.
|
| 1157 |
-
"learning_rate": 3.
|
| 1158 |
-
"loss": 0.
|
| 1159 |
"num_input_tokens_seen": 8385680,
|
| 1160 |
-
"step": 685
|
|
|
|
|
|
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 3.136830102622577,
|
| 1164 |
-
"grad_norm": 0.
|
| 1165 |
-
"learning_rate": 3.
|
| 1166 |
-
"loss": 0.
|
| 1167 |
"num_input_tokens_seen": 8447632,
|
| 1168 |
-
"step": 690
|
|
|
|
|
|
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
"epoch": 3.1596351197263397,
|
| 1172 |
-
"grad_norm": 0.
|
| 1173 |
-
"learning_rate": 3.
|
| 1174 |
-
"loss": 0.
|
| 1175 |
"num_input_tokens_seen": 8508432,
|
| 1176 |
-
"step": 695
|
|
|
|
|
|
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 3.1824401368301025,
|
| 1180 |
-
"grad_norm": 0.
|
| 1181 |
-
"learning_rate": 3.
|
| 1182 |
-
"loss": 0.
|
| 1183 |
"num_input_tokens_seen": 8570128,
|
| 1184 |
-
"step": 700
|
|
|
|
|
|
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 3.1824401368301025,
|
| 1188 |
-
"eval_loss": 0.
|
| 1189 |
-
"eval_runtime":
|
| 1190 |
-
"eval_samples_per_second":
|
| 1191 |
-
"eval_steps_per_second":
|
| 1192 |
"num_input_tokens_seen": 8570128,
|
| 1193 |
"step": 700
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 3.2052451539338653,
|
| 1197 |
-
"grad_norm": 0.
|
| 1198 |
-
"learning_rate": 3.
|
| 1199 |
-
"loss": 0.
|
| 1200 |
"num_input_tokens_seen": 8631952,
|
| 1201 |
-
"step": 705
|
|
|
|
|
|
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
"epoch": 3.228050171037628,
|
| 1205 |
-
"grad_norm": 0.
|
| 1206 |
-
"learning_rate": 2.
|
| 1207 |
-
"loss": 0.
|
| 1208 |
"num_input_tokens_seen": 8694032,
|
| 1209 |
-
"step": 710
|
|
|
|
|
|
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 3.250855188141391,
|
| 1213 |
-
"grad_norm": 0.
|
| 1214 |
-
"learning_rate": 2.
|
| 1215 |
-
"loss": 0.
|
| 1216 |
"num_input_tokens_seen": 8754576,
|
| 1217 |
-
"step": 715
|
|
|
|
|
|
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 3.2736602052451538,
|
| 1221 |
-
"grad_norm": 0.
|
| 1222 |
-
"learning_rate": 2.
|
| 1223 |
-
"loss": 0.
|
| 1224 |
"num_input_tokens_seen": 8816528,
|
| 1225 |
-
"step": 720
|
|
|
|
|
|
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 3.2964652223489166,
|
| 1229 |
-
"grad_norm": 0.
|
| 1230 |
-
"learning_rate": 2.
|
| 1231 |
-
"loss": 0.
|
| 1232 |
"num_input_tokens_seen": 8877200,
|
| 1233 |
-
"step": 725
|
|
|
|
|
|
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 3.3192702394526794,
|
| 1237 |
-
"grad_norm": 0.
|
| 1238 |
-
"learning_rate": 2.
|
| 1239 |
-
"loss": 0.
|
| 1240 |
"num_input_tokens_seen": 8938512,
|
| 1241 |
-
"step": 730
|
|
|
|
|
|
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 3.342075256556442,
|
| 1245 |
-
"grad_norm": 0.
|
| 1246 |
-
"learning_rate": 2.
|
| 1247 |
-
"loss": 0.
|
| 1248 |
"num_input_tokens_seen": 9000464,
|
| 1249 |
-
"step": 735
|
|
|
|
|
|
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
"epoch": 3.364880273660205,
|
| 1253 |
-
"grad_norm": 0.
|
| 1254 |
-
"learning_rate":
|
| 1255 |
-
"loss": 0.
|
| 1256 |
"num_input_tokens_seen": 9061648,
|
| 1257 |
-
"step": 740
|
|
|
|
|
|
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 3.387685290763968,
|
| 1261 |
-
"grad_norm": 0.
|
| 1262 |
-
"learning_rate": 1.
|
| 1263 |
-
"loss": 0.
|
| 1264 |
"num_input_tokens_seen": 9122704,
|
| 1265 |
-
"step": 745
|
|
|
|
|
|
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
"epoch": 3.4104903078677307,
|
| 1269 |
-
"grad_norm": 0.
|
| 1270 |
-
"learning_rate": 1.
|
| 1271 |
-
"loss": 0.
|
| 1272 |
"num_input_tokens_seen": 9183504,
|
| 1273 |
-
"step": 750
|
|
|
|
|
|
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 3.433295324971494,
|
| 1277 |
-
"grad_norm": 0.
|
| 1278 |
-
"learning_rate": 1.
|
| 1279 |
-
"loss": 0.
|
| 1280 |
"num_input_tokens_seen": 9245072,
|
| 1281 |
-
"step": 755
|
|
|
|
|
|
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 3.4561003420752567,
|
| 1285 |
-
"grad_norm": 0.
|
| 1286 |
-
"learning_rate": 1.
|
| 1287 |
-
"loss": 0.
|
| 1288 |
"num_input_tokens_seen": 9307152,
|
| 1289 |
-
"step": 760
|
|
|
|
|
|
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 3.4789053591790196,
|
| 1293 |
-
"grad_norm": 0.
|
| 1294 |
-
"learning_rate": 1.
|
| 1295 |
-
"loss": 0.
|
| 1296 |
"num_input_tokens_seen": 9369616,
|
| 1297 |
-
"step": 765
|
|
|
|
|
|
|
| 1298 |
},
|
| 1299 |
{
|
| 1300 |
"epoch": 3.5017103762827824,
|
| 1301 |
-
"grad_norm": 0.
|
| 1302 |
-
"learning_rate": 1.
|
| 1303 |
-
"loss": 0.
|
| 1304 |
"num_input_tokens_seen": 9431568,
|
| 1305 |
-
"step": 770
|
|
|
|
|
|
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
"epoch": 3.524515393386545,
|
| 1309 |
-
"grad_norm": 0.
|
| 1310 |
-
"learning_rate": 1.
|
| 1311 |
-
"loss": 0.
|
| 1312 |
"num_input_tokens_seen": 9493264,
|
| 1313 |
-
"step": 775
|
|
|
|
|
|
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 3.547320410490308,
|
| 1317 |
-
"grad_norm": 0.
|
| 1318 |
-
"learning_rate":
|
| 1319 |
-
"loss": 0.
|
| 1320 |
"num_input_tokens_seen": 9554448,
|
| 1321 |
-
"step": 780
|
|
|
|
|
|
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"epoch": 3.570125427594071,
|
| 1325 |
-
"grad_norm": 0.
|
| 1326 |
-
"learning_rate":
|
| 1327 |
-
"loss": 0.
|
| 1328 |
"num_input_tokens_seen": 9615760,
|
| 1329 |
-
"step": 785
|
|
|
|
|
|
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 3.5929304446978336,
|
| 1333 |
-
"grad_norm": 0.
|
| 1334 |
-
"learning_rate":
|
| 1335 |
-
"loss": 0.
|
| 1336 |
"num_input_tokens_seen": 9678608,
|
| 1337 |
-
"step": 790
|
|
|
|
|
|
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 3.6157354618015964,
|
| 1341 |
-
"grad_norm": 0.
|
| 1342 |
-
"learning_rate": 7.
|
| 1343 |
-
"loss": 0.
|
| 1344 |
"num_input_tokens_seen": 9740304,
|
| 1345 |
-
"step": 795
|
|
|
|
|
|
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
"epoch": 3.6385404789053593,
|
| 1349 |
-
"grad_norm": 0.
|
| 1350 |
-
"learning_rate": 6.
|
| 1351 |
-
"loss": 0.
|
| 1352 |
"num_input_tokens_seen": 9801744,
|
| 1353 |
-
"step": 800
|
|
|
|
|
|
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 3.6385404789053593,
|
| 1357 |
-
"eval_loss": 0.
|
| 1358 |
-
"eval_runtime":
|
| 1359 |
-
"eval_samples_per_second":
|
| 1360 |
-
"eval_steps_per_second":
|
| 1361 |
"num_input_tokens_seen": 9801744,
|
| 1362 |
"step": 800
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 3.661345496009122,
|
| 1366 |
-
"grad_norm": 0.
|
| 1367 |
-
"learning_rate":
|
| 1368 |
-
"loss": 0.
|
| 1369 |
"num_input_tokens_seen": 9862928,
|
| 1370 |
-
"step": 805
|
|
|
|
|
|
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 3.684150513112885,
|
| 1374 |
-
"grad_norm": 0.
|
| 1375 |
-
"learning_rate":
|
| 1376 |
-
"loss": 0.
|
| 1377 |
"num_input_tokens_seen": 9924112,
|
| 1378 |
-
"step": 810
|
|
|
|
|
|
|
| 1379 |
},
|
| 1380 |
{
|
| 1381 |
"epoch": 3.7069555302166477,
|
| 1382 |
-
"grad_norm": 0.
|
| 1383 |
-
"learning_rate": 4.
|
| 1384 |
-
"loss": 0.
|
| 1385 |
"num_input_tokens_seen": 9984784,
|
| 1386 |
-
"step": 815
|
|
|
|
|
|
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 3.7297605473204105,
|
| 1390 |
-
"grad_norm": 0.
|
| 1391 |
-
"learning_rate": 3.
|
| 1392 |
-
"loss": 0.
|
| 1393 |
"num_input_tokens_seen": 10046736,
|
| 1394 |
-
"step": 820
|
|
|
|
|
|
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 3.7525655644241733,
|
| 1398 |
-
"grad_norm": 0.
|
| 1399 |
-
"learning_rate":
|
| 1400 |
-
"loss": 0.
|
| 1401 |
"num_input_tokens_seen": 10108176,
|
| 1402 |
-
"step": 825
|
|
|
|
|
|
|
| 1403 |
},
|
| 1404 |
{
|
| 1405 |
"epoch": 3.775370581527936,
|
| 1406 |
-
"grad_norm": 0.
|
| 1407 |
-
"learning_rate": 2.
|
| 1408 |
-
"loss": 0.
|
| 1409 |
"num_input_tokens_seen": 10169744,
|
| 1410 |
-
"step": 830
|
|
|
|
|
|
|
| 1411 |
},
|
| 1412 |
{
|
| 1413 |
"epoch": 3.798175598631699,
|
| 1414 |
-
"grad_norm": 0.
|
| 1415 |
-
"learning_rate":
|
| 1416 |
-
"loss": 0.
|
| 1417 |
"num_input_tokens_seen": 10231696,
|
| 1418 |
-
"step": 835
|
|
|
|
|
|
|
| 1419 |
},
|
| 1420 |
{
|
| 1421 |
"epoch": 3.8209806157354618,
|
| 1422 |
-
"grad_norm": 0.
|
| 1423 |
-
"learning_rate": 1.
|
| 1424 |
-
"loss": 0.
|
| 1425 |
"num_input_tokens_seen": 10292624,
|
| 1426 |
-
"step": 840
|
|
|
|
|
|
|
| 1427 |
},
|
| 1428 |
{
|
| 1429 |
"epoch": 3.8437856328392246,
|
| 1430 |
-
"grad_norm": 0.
|
| 1431 |
-
"learning_rate": 1.
|
| 1432 |
-
"loss": 0.
|
| 1433 |
"num_input_tokens_seen": 10353040,
|
| 1434 |
-
"step": 845
|
|
|
|
|
|
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 3.8665906499429874,
|
| 1438 |
-
"grad_norm": 0.
|
| 1439 |
-
"learning_rate":
|
| 1440 |
-
"loss": 0.
|
| 1441 |
"num_input_tokens_seen": 10414480,
|
| 1442 |
-
"step": 850
|
|
|
|
|
|
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 3.88939566704675,
|
| 1446 |
-
"grad_norm": 0.
|
| 1447 |
-
"learning_rate":
|
| 1448 |
-
"loss": 0.
|
| 1449 |
"num_input_tokens_seen": 10476432,
|
| 1450 |
-
"step": 855
|
|
|
|
|
|
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 3.912200684150513,
|
| 1454 |
-
"grad_norm": 0.
|
| 1455 |
-
"learning_rate":
|
| 1456 |
-
"loss": 0.
|
| 1457 |
"num_input_tokens_seen": 10538128,
|
| 1458 |
-
"step": 860
|
|
|
|
|
|
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 3.935005701254276,
|
| 1462 |
-
"grad_norm": 0.
|
| 1463 |
-
"learning_rate":
|
| 1464 |
-
"loss": 0.
|
| 1465 |
"num_input_tokens_seen": 10600080,
|
| 1466 |
-
"step": 865
|
|
|
|
|
|
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 3.9578107183580387,
|
| 1470 |
-
"grad_norm": 0.
|
| 1471 |
-
"learning_rate":
|
| 1472 |
-
"loss": 0.
|
| 1473 |
"num_input_tokens_seen": 10660752,
|
| 1474 |
-
"step": 870
|
|
|
|
|
|
|
| 1475 |
},
|
| 1476 |
{
|
| 1477 |
"epoch": 3.9806157354618015,
|
| 1478 |
-
"grad_norm": 0.
|
| 1479 |
-
"learning_rate":
|
| 1480 |
-
"loss": 0.
|
| 1481 |
"num_input_tokens_seen": 10721680,
|
| 1482 |
-
"step": 875
|
| 1483 |
-
|
| 1484 |
-
|
| 1485 |
-
|
| 1486 |
-
|
| 1487 |
-
"
|
| 1488 |
-
"
|
| 1489 |
-
"
|
| 1490 |
-
"
|
| 1491 |
-
"
|
| 1492 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1493 |
}
|
| 1494 |
],
|
| 1495 |
"logging_steps": 5,
|
| 1496 |
-
"max_steps":
|
| 1497 |
-
"num_input_tokens_seen":
|
| 1498 |
"num_train_epochs": 4,
|
| 1499 |
-
"save_steps":
|
| 1500 |
"stateful_callbacks": {
|
| 1501 |
"TrainerControl": {
|
| 1502 |
"args": {
|
|
@@ -1509,7 +1869,7 @@
|
|
| 1509 |
"attributes": {}
|
| 1510 |
}
|
| 1511 |
},
|
| 1512 |
-
"total_flos": 4.
|
| 1513 |
"train_batch_size": 16,
|
| 1514 |
"trial_name": null,
|
| 1515 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.02280501710376283,
|
| 14 |
+
"grad_norm": 32.61074447631836,
|
| 15 |
"learning_rate": 2.9999999999999997e-05,
|
| 16 |
+
"loss": 12.6644,
|
| 17 |
"num_input_tokens_seen": 61696,
|
| 18 |
+
"step": 5,
|
| 19 |
+
"train_runtime": 24.2855,
|
| 20 |
+
"train_tokens_per_second": 2540.442
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.04561003420752566,
|
| 24 |
+
"grad_norm": 18.813081741333008,
|
| 25 |
"learning_rate": 6.75e-05,
|
| 26 |
+
"loss": 5.0641,
|
| 27 |
"num_input_tokens_seen": 123136,
|
| 28 |
+
"step": 10,
|
| 29 |
+
"train_runtime": 47.0357,
|
| 30 |
+
"train_tokens_per_second": 2617.929
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.06841505131128849,
|
| 34 |
+
"grad_norm": 6.64304256439209,
|
| 35 |
"learning_rate": 0.00010499999999999999,
|
| 36 |
+
"loss": 1.5053,
|
| 37 |
"num_input_tokens_seen": 184832,
|
| 38 |
+
"step": 15,
|
| 39 |
+
"train_runtime": 69.9392,
|
| 40 |
+
"train_tokens_per_second": 2642.751
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 0.09122006841505131,
|
| 44 |
+
"grad_norm": 1.0877084732055664,
|
| 45 |
"learning_rate": 0.0001425,
|
| 46 |
+
"loss": 0.6917,
|
| 47 |
"num_input_tokens_seen": 247552,
|
| 48 |
+
"step": 20,
|
| 49 |
+
"train_runtime": 93.0922,
|
| 50 |
+
"train_tokens_per_second": 2659.212
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.11402508551881414,
|
| 54 |
+
"grad_norm": 2.6032357215881348,
|
| 55 |
"learning_rate": 0.00017999999999999998,
|
| 56 |
+
"loss": 0.5721,
|
| 57 |
"num_input_tokens_seen": 308992,
|
| 58 |
+
"step": 25,
|
| 59 |
+
"train_runtime": 115.7825,
|
| 60 |
+
"train_tokens_per_second": 2668.728
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 0.13683010262257697,
|
| 64 |
+
"grad_norm": 3.105325698852539,
|
| 65 |
"learning_rate": 0.00021749999999999997,
|
| 66 |
+
"loss": 0.6254,
|
| 67 |
"num_input_tokens_seen": 370176,
|
| 68 |
+
"step": 30,
|
| 69 |
+
"train_runtime": 138.519,
|
| 70 |
+
"train_tokens_per_second": 2672.384
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 0.15963511972633979,
|
| 74 |
+
"grad_norm": 0.9677203297615051,
|
| 75 |
"learning_rate": 0.00025499999999999996,
|
| 76 |
+
"loss": 0.6389,
|
| 77 |
"num_input_tokens_seen": 430720,
|
| 78 |
+
"step": 35,
|
| 79 |
+
"train_runtime": 161.0396,
|
| 80 |
+
"train_tokens_per_second": 2674.622
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.18244013683010263,
|
| 84 |
+
"grad_norm": 1.2506942749023438,
|
| 85 |
"learning_rate": 0.00029249999999999995,
|
| 86 |
+
"loss": 0.5258,
|
| 87 |
"num_input_tokens_seen": 492800,
|
| 88 |
+
"step": 40,
|
| 89 |
+
"train_runtime": 184.2743,
|
| 90 |
+
"train_tokens_per_second": 2674.275
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.20524515393386544,
|
| 94 |
+
"grad_norm": 4.25206184387207,
|
| 95 |
+
"learning_rate": 0.00029998321527154097,
|
| 96 |
+
"loss": 0.5039,
|
| 97 |
"num_input_tokens_seen": 553984,
|
| 98 |
+
"step": 45,
|
| 99 |
+
"train_runtime": 207.0534,
|
| 100 |
+
"train_tokens_per_second": 2675.562
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.22805017103762829,
|
| 104 |
+
"grad_norm": 0.5203157663345337,
|
| 105 |
+
"learning_rate": 0.00029991503375003,
|
| 106 |
+
"loss": 0.4873,
|
| 107 |
"num_input_tokens_seen": 615040,
|
| 108 |
+
"step": 50,
|
| 109 |
+
"train_runtime": 229.7726,
|
| 110 |
+
"train_tokens_per_second": 2676.734
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.2508551881413911,
|
| 114 |
+
"grad_norm": 0.31907328963279724,
|
| 115 |
+
"learning_rate": 0.000299794430213186,
|
| 116 |
+
"loss": 0.4971,
|
| 117 |
"num_input_tokens_seen": 676736,
|
| 118 |
+
"step": 55,
|
| 119 |
+
"train_runtime": 252.5957,
|
| 120 |
+
"train_tokens_per_second": 2679.127
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 0.27366020524515394,
|
| 124 |
+
"grad_norm": 0.36265772581100464,
|
| 125 |
+
"learning_rate": 0.0002996214468334339,
|
| 126 |
+
"loss": 0.4761,
|
| 127 |
"num_input_tokens_seen": 738176,
|
| 128 |
+
"step": 60,
|
| 129 |
+
"train_runtime": 275.4227,
|
| 130 |
+
"train_tokens_per_second": 2680.157
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.29646522234891676,
|
| 134 |
+
"grad_norm": 0.2299686223268509,
|
| 135 |
+
"learning_rate": 0.00029939614409928584,
|
| 136 |
+
"loss": 0.4849,
|
| 137 |
"num_input_tokens_seen": 799488,
|
| 138 |
+
"step": 65,
|
| 139 |
+
"train_runtime": 298.1913,
|
| 140 |
+
"train_tokens_per_second": 2681.124
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 0.31927023945267957,
|
| 144 |
+
"grad_norm": 0.15398980677127838,
|
| 145 |
+
"learning_rate": 0.00029911860079419073,
|
| 146 |
+
"loss": 0.4819,
|
| 147 |
"num_input_tokens_seen": 861568,
|
| 148 |
+
"step": 70,
|
| 149 |
+
"train_runtime": 321.1312,
|
| 150 |
+
"train_tokens_per_second": 2682.916
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.34207525655644244,
|
| 154 |
+
"grad_norm": 0.21743282675743103,
|
| 155 |
+
"learning_rate": 0.00029878891396898494,
|
| 156 |
+
"loss": 0.4812,
|
| 157 |
"num_input_tokens_seen": 924544,
|
| 158 |
+
"step": 75,
|
| 159 |
+
"train_runtime": 344.5442,
|
| 160 |
+
"train_tokens_per_second": 2683.383
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 0.36488027366020526,
|
| 164 |
+
"grad_norm": 0.18951573967933655,
|
| 165 |
+
"learning_rate": 0.00029840719890795547,
|
| 166 |
+
"loss": 0.4691,
|
| 167 |
"num_input_tokens_seen": 985472,
|
| 168 |
+
"step": 80,
|
| 169 |
+
"train_runtime": 367.16,
|
| 170 |
+
"train_tokens_per_second": 2684.04
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.38768529076396807,
|
| 174 |
+
"grad_norm": 0.4572216272354126,
|
| 175 |
+
"learning_rate": 0.00029797358908852816,
|
| 176 |
+
"loss": 0.4845,
|
| 177 |
"num_input_tokens_seen": 1046912,
|
| 178 |
+
"step": 85,
|
| 179 |
+
"train_runtime": 390.0118,
|
| 180 |
+
"train_tokens_per_second": 2684.308
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 0.4104903078677309,
|
| 184 |
+
"grad_norm": 0.3125233054161072,
|
| 185 |
+
"learning_rate": 0.00029748823613459316,
|
| 186 |
+
"loss": 0.482,
|
| 187 |
"num_input_tokens_seen": 1108992,
|
| 188 |
+
"step": 90,
|
| 189 |
+
"train_runtime": 412.9641,
|
| 190 |
+
"train_tokens_per_second": 2685.444
|
| 191 |
},
|
| 192 |
{
|
| 193 |
"epoch": 0.43329532497149376,
|
| 194 |
+
"grad_norm": 0.2670783996582031,
|
| 195 |
+
"learning_rate": 0.0002969513097634853,
|
| 196 |
+
"loss": 0.4548,
|
| 197 |
"num_input_tokens_seen": 1170048,
|
| 198 |
+
"step": 95,
|
| 199 |
+
"train_runtime": 435.6939,
|
| 200 |
+
"train_tokens_per_second": 2685.482
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.45610034207525657,
|
| 204 |
+
"grad_norm": 0.1218935027718544,
|
| 205 |
+
"learning_rate": 0.00029636299772663795,
|
| 206 |
+
"loss": 0.4571,
|
| 207 |
"num_input_tokens_seen": 1230464,
|
| 208 |
+
"step": 100,
|
| 209 |
+
"train_runtime": 458.1608,
|
| 210 |
+
"train_tokens_per_second": 2685.66
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 0.45610034207525657,
|
| 214 |
+
"eval_loss": 0.462704062461853,
|
| 215 |
+
"eval_runtime": 32.2331,
|
| 216 |
+
"eval_samples_per_second": 96.733,
|
| 217 |
+
"eval_steps_per_second": 6.05,
|
| 218 |
"num_input_tokens_seen": 1230464,
|
| 219 |
"step": 100
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.4789053591790194,
|
| 223 |
+
"grad_norm": 0.16193914413452148,
|
| 224 |
+
"learning_rate": 0.0002957235057439301,
|
| 225 |
+
"loss": 0.4633,
|
| 226 |
"num_input_tokens_seen": 1292288,
|
| 227 |
+
"step": 105,
|
| 228 |
+
"train_runtime": 513.3064,
|
| 229 |
+
"train_tokens_per_second": 2517.576
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 0.5017103762827823,
|
| 233 |
+
"grad_norm": 0.2220025360584259,
|
| 234 |
+
"learning_rate": 0.0002950330574317509,
|
| 235 |
+
"loss": 0.474,
|
| 236 |
"num_input_tokens_seen": 1353344,
|
| 237 |
+
"step": 110,
|
| 238 |
+
"train_runtime": 535.981,
|
| 239 |
+
"train_tokens_per_second": 2524.985
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 0.5245153933865451,
|
| 243 |
+
"grad_norm": 0.25165775418281555,
|
| 244 |
+
"learning_rate": 0.0002942918942248059,
|
| 245 |
+
"loss": 0.4709,
|
| 246 |
"num_input_tokens_seen": 1415040,
|
| 247 |
+
"step": 115,
|
| 248 |
+
"train_runtime": 558.7646,
|
| 249 |
+
"train_tokens_per_second": 2532.444
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.5473204104903079,
|
| 253 |
+
"grad_norm": 0.2007230967283249,
|
| 254 |
+
"learning_rate": 0.0002935002752916921,
|
| 255 |
+
"loss": 0.4581,
|
| 256 |
"num_input_tokens_seen": 1476480,
|
| 257 |
+
"step": 120,
|
| 258 |
+
"train_runtime": 581.5341,
|
| 259 |
+
"train_tokens_per_second": 2538.94
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.5701254275940707,
|
| 263 |
+
"grad_norm": 0.17744658887386322,
|
| 264 |
+
"learning_rate": 0.00029265847744427303,
|
| 265 |
+
"loss": 0.4428,
|
| 266 |
"num_input_tokens_seen": 1537664,
|
| 267 |
+
"step": 125,
|
| 268 |
+
"train_runtime": 604.3564,
|
| 269 |
+
"train_tokens_per_second": 2544.3
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 0.5929304446978335,
|
| 273 |
+
"grad_norm": 0.36229953169822693,
|
| 274 |
+
"learning_rate": 0.0002917667950408832,
|
| 275 |
+
"loss": 0.441,
|
| 276 |
"num_input_tokens_seen": 1598848,
|
| 277 |
+
"step": 130,
|
| 278 |
+
"train_runtime": 627.1244,
|
| 279 |
+
"train_tokens_per_second": 2549.491
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.6157354618015963,
|
| 283 |
+
"grad_norm": 0.20263080298900604,
|
| 284 |
+
"learning_rate": 0.0002908255398833979,
|
| 285 |
+
"loss": 0.4484,
|
| 286 |
"num_input_tokens_seen": 1660800,
|
| 287 |
+
"step": 135,
|
| 288 |
+
"train_runtime": 650.0019,
|
| 289 |
+
"train_tokens_per_second": 2555.069
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 0.6385404789053591,
|
| 293 |
+
"grad_norm": 0.41183140873908997,
|
| 294 |
+
"learning_rate": 0.0002898350411082021,
|
| 295 |
+
"loss": 0.4312,
|
| 296 |
"num_input_tokens_seen": 1721600,
|
| 297 |
+
"step": 140,
|
| 298 |
+
"train_runtime": 672.6152,
|
| 299 |
+
"train_tokens_per_second": 2559.561
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.661345496009122,
|
| 303 |
+
"grad_norm": 0.24306368827819824,
|
| 304 |
+
"learning_rate": 0.00028879564507109946,
|
| 305 |
+
"loss": 0.4374,
|
| 306 |
"num_input_tokens_seen": 1783168,
|
| 307 |
+
"step": 145,
|
| 308 |
+
"train_runtime": 695.4639,
|
| 309 |
+
"train_tokens_per_second": 2563.998
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.6841505131128849,
|
| 313 |
+
"grad_norm": 0.24856272339820862,
|
| 314 |
+
"learning_rate": 0.00028770771522619885,
|
| 315 |
+
"loss": 0.4241,
|
| 316 |
"num_input_tokens_seen": 1844992,
|
| 317 |
+
"step": 150,
|
| 318 |
+
"train_runtime": 718.3395,
|
| 319 |
+
"train_tokens_per_second": 2568.412
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 0.7069555302166477,
|
| 323 |
+
"grad_norm": 0.2576836943626404,
|
| 324 |
+
"learning_rate": 0.00028657163199882237,
|
| 325 |
+
"loss": 0.4048,
|
| 326 |
"num_input_tokens_seen": 1906048,
|
| 327 |
+
"step": 155,
|
| 328 |
+
"train_runtime": 741.0646,
|
| 329 |
+
"train_tokens_per_second": 2572.04
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 0.7297605473204105,
|
| 333 |
+
"grad_norm": 0.28877368569374084,
|
| 334 |
+
"learning_rate": 0.0002853877926524791,
|
| 335 |
+
"loss": 0.4175,
|
| 336 |
"num_input_tokens_seen": 1967744,
|
| 337 |
+
"step": 160,
|
| 338 |
+
"train_runtime": 763.9181,
|
| 339 |
+
"train_tokens_per_second": 2575.857
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.7525655644241733,
|
| 343 |
+
"grad_norm": 0.2601846754550934,
|
| 344 |
+
"learning_rate": 0.0002841566111499505,
|
| 345 |
+
"loss": 0.405,
|
| 346 |
"num_input_tokens_seen": 2028032,
|
| 347 |
+
"step": 165,
|
| 348 |
+
"train_runtime": 786.4134,
|
| 349 |
+
"train_tokens_per_second": 2578.837
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 0.7753705815279361,
|
| 353 |
+
"grad_norm": 0.2702248990535736,
|
| 354 |
+
"learning_rate": 0.00028287851800853697,
|
| 355 |
+
"loss": 0.4023,
|
| 356 |
"num_input_tokens_seen": 2088448,
|
| 357 |
+
"step": 170,
|
| 358 |
+
"train_runtime": 808.8913,
|
| 359 |
+
"train_tokens_per_second": 2581.865
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 0.798175598631699,
|
| 363 |
+
"grad_norm": 0.2885015308856964,
|
| 364 |
+
"learning_rate": 0.00028155396014951494,
|
| 365 |
+
"loss": 0.4013,
|
| 366 |
"num_input_tokens_seen": 2150144,
|
| 367 |
+
"step": 175,
|
| 368 |
+
"train_runtime": 831.7045,
|
| 369 |
+
"train_tokens_per_second": 2585.226
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 0.8209806157354618,
|
| 373 |
+
"grad_norm": 0.4831572473049164,
|
| 374 |
+
"learning_rate": 0.0002801834007418587,
|
| 375 |
+
"loss": 0.4065,
|
| 376 |
"num_input_tokens_seen": 2211584,
|
| 377 |
+
"step": 180,
|
| 378 |
+
"train_runtime": 854.5546,
|
| 379 |
+
"train_tokens_per_second": 2587.996
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 0.8437856328392246,
|
| 383 |
+
"grad_norm": 0.39929574728012085,
|
| 384 |
+
"learning_rate": 0.0002787673190402799,
|
| 385 |
+
"loss": 0.3784,
|
| 386 |
"num_input_tokens_seen": 2272256,
|
| 387 |
+
"step": 185,
|
| 388 |
+
"train_runtime": 877.0766,
|
| 389 |
+
"train_tokens_per_second": 2590.716
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 0.8665906499429875,
|
| 393 |
+
"grad_norm": 0.42691075801849365,
|
| 394 |
+
"learning_rate": 0.0002773062102176429,
|
| 395 |
+
"loss": 0.3882,
|
| 396 |
"num_input_tokens_seen": 2333696,
|
| 397 |
+
"step": 190,
|
| 398 |
+
"train_runtime": 899.8781,
|
| 399 |
+
"train_tokens_per_second": 2593.347
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 0.8893956670467503,
|
| 403 |
+
"grad_norm": 0.4322110116481781,
|
| 404 |
+
"learning_rate": 0.0002758005851918136,
|
| 405 |
+
"loss": 0.3953,
|
| 406 |
"num_input_tokens_seen": 2394880,
|
| 407 |
+
"step": 195,
|
| 408 |
+
"train_runtime": 922.5484,
|
| 409 |
+
"train_tokens_per_second": 2595.94
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 0.9122006841505131,
|
| 413 |
+
"grad_norm": 0.27470600605010986,
|
| 414 |
+
"learning_rate": 0.00027425097044700246,
|
| 415 |
+
"loss": 0.3676,
|
| 416 |
"num_input_tokens_seen": 2455680,
|
| 417 |
+
"step": 200,
|
| 418 |
+
"train_runtime": 945.1495,
|
| 419 |
+
"train_tokens_per_second": 2598.192
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 0.9122006841505131,
|
| 423 |
+
"eval_loss": 0.3956287205219269,
|
| 424 |
+
"eval_runtime": 32.3098,
|
| 425 |
+
"eval_samples_per_second": 96.503,
|
| 426 |
+
"eval_steps_per_second": 6.035,
|
| 427 |
"num_input_tokens_seen": 2455680,
|
| 428 |
"step": 200
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 0.935005701254276,
|
| 432 |
+
"grad_norm": 0.350835919380188,
|
| 433 |
+
"learning_rate": 0.0002726579078496647,
|
| 434 |
+
"loss": 0.3821,
|
| 435 |
"num_input_tokens_seen": 2517376,
|
| 436 |
+
"step": 205,
|
| 437 |
+
"train_runtime": 1000.3566,
|
| 438 |
+
"train_tokens_per_second": 2516.479
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 0.9578107183580388,
|
| 442 |
+
"grad_norm": 0.4473128914833069,
|
| 443 |
+
"learning_rate": 0.0002710219544590212,
|
| 444 |
+
"loss": 0.3828,
|
| 445 |
"num_input_tokens_seen": 2578816,
|
| 446 |
+
"step": 210,
|
| 447 |
+
"train_runtime": 1023.095,
|
| 448 |
+
"train_tokens_per_second": 2520.603
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 0.9806157354618016,
|
| 452 |
+
"grad_norm": 0.3217677175998688,
|
| 453 |
+
"learning_rate": 0.00026934368233226714,
|
| 454 |
+
"loss": 0.3569,
|
| 455 |
"num_input_tokens_seen": 2640128,
|
| 456 |
+
"step": 215,
|
| 457 |
+
"train_runtime": 1045.8834,
|
| 458 |
+
"train_tokens_per_second": 2524.304
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 1.0,
|
| 462 |
+
"grad_norm": 0.5540800094604492,
|
| 463 |
+
"learning_rate": 0.00026762367832453617,
|
| 464 |
+
"loss": 0.3597,
|
| 465 |
"num_input_tokens_seen": 2691984,
|
| 466 |
+
"step": 220,
|
| 467 |
+
"train_runtime": 1065.1708,
|
| 468 |
+
"train_tokens_per_second": 2527.279
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 1.0228050171037628,
|
| 472 |
+
"grad_norm": 0.352602481842041,
|
| 473 |
+
"learning_rate": 0.0002658625438836899,
|
| 474 |
+
"loss": 0.3621,
|
| 475 |
"num_input_tokens_seen": 2753808,
|
| 476 |
+
"step": 225,
|
| 477 |
+
"train_runtime": 1088.108,
|
| 478 |
+
"train_tokens_per_second": 2530.822
|
| 479 |
},
|
| 480 |
{
|
| 481 |
"epoch": 1.0456100342075256,
|
| 482 |
+
"grad_norm": 0.45127010345458984,
|
| 483 |
+
"learning_rate": 0.00026406089484000466,
|
| 484 |
+
"loss": 0.3623,
|
| 485 |
"num_input_tokens_seen": 2815248,
|
| 486 |
+
"step": 230,
|
| 487 |
+
"train_runtime": 1110.8639,
|
| 488 |
+
"train_tokens_per_second": 2534.287
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 1.0684150513112884,
|
| 492 |
+
"grad_norm": 0.34542417526245117,
|
| 493 |
+
"learning_rate": 0.00026221936119082904,
|
| 494 |
+
"loss": 0.3866,
|
| 495 |
"num_input_tokens_seen": 2877456,
|
| 496 |
+
"step": 235,
|
| 497 |
+
"train_runtime": 1133.9972,
|
| 498 |
+
"train_tokens_per_second": 2537.445
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 1.0912200684150513,
|
| 502 |
+
"grad_norm": 0.41213762760162354,
|
| 503 |
+
"learning_rate": 0.00026033858688028784,
|
| 504 |
+
"loss": 0.3598,
|
| 505 |
"num_input_tokens_seen": 2939280,
|
| 506 |
+
"step": 240,
|
| 507 |
+
"train_runtime": 1156.9737,
|
| 508 |
+
"train_tokens_per_second": 2540.49
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 1.114025085518814,
|
| 512 |
+
"grad_norm": 0.34747591614723206,
|
| 513 |
+
"learning_rate": 0.0002584192295741087,
|
| 514 |
+
"loss": 0.3488,
|
| 515 |
"num_input_tokens_seen": 3000336,
|
| 516 |
+
"step": 245,
|
| 517 |
+
"train_runtime": 1179.7195,
|
| 518 |
+
"train_tokens_per_second": 2543.262
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 1.1368301026225769,
|
| 522 |
+
"grad_norm": 0.2995326817035675,
|
| 523 |
+
"learning_rate": 0.0002564619604296506,
|
| 524 |
+
"loss": 0.3516,
|
| 525 |
"num_input_tokens_seen": 3062416,
|
| 526 |
+
"step": 250,
|
| 527 |
+
"train_runtime": 1202.7529,
|
| 528 |
+
"train_tokens_per_second": 2546.172
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 1.1596351197263397,
|
| 532 |
+
"grad_norm": 0.3599797785282135,
|
| 533 |
+
"learning_rate": 0.00025446746386121504,
|
| 534 |
+
"loss": 0.34,
|
| 535 |
"num_input_tokens_seen": 3124368,
|
| 536 |
+
"step": 255,
|
| 537 |
+
"train_runtime": 1225.7586,
|
| 538 |
+
"train_tokens_per_second": 2548.926
|
| 539 |
},
|
| 540 |
{
|
| 541 |
"epoch": 1.1824401368301025,
|
| 542 |
+
"grad_norm": 0.3630430996417999,
|
| 543 |
+
"learning_rate": 0.000252436437300721,
|
| 544 |
+
"loss": 0.3361,
|
| 545 |
"num_input_tokens_seen": 3185424,
|
| 546 |
+
"step": 260,
|
| 547 |
+
"train_runtime": 1248.4807,
|
| 548 |
+
"train_tokens_per_second": 2551.44
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 1.2052451539338653,
|
| 552 |
+
"grad_norm": 0.2464369684457779,
|
| 553 |
+
"learning_rate": 0.0002503695909538287,
|
| 554 |
+
"loss": 0.3172,
|
| 555 |
"num_input_tokens_seen": 3246096,
|
| 556 |
+
"step": 265,
|
| 557 |
+
"train_runtime": 1271.0323,
|
| 558 |
+
"train_tokens_per_second": 2553.905
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 1.2280501710376284,
|
| 562 |
+
"grad_norm": 0.41870465874671936,
|
| 563 |
+
"learning_rate": 0.00024826764755159566,
|
| 564 |
+
"loss": 0.3387,
|
| 565 |
"num_input_tokens_seen": 3307536,
|
| 566 |
+
"step": 270,
|
| 567 |
+
"train_runtime": 1293.8594,
|
| 568 |
+
"train_tokens_per_second": 2556.333
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 1.2508551881413912,
|
| 572 |
+
"grad_norm": 0.6106472611427307,
|
| 573 |
+
"learning_rate": 0.0002461313420977536,
|
| 574 |
+
"loss": 0.3112,
|
| 575 |
"num_input_tokens_seen": 3368976,
|
| 576 |
+
"step": 275,
|
| 577 |
+
"train_runtime": 1316.714,
|
| 578 |
+
"train_tokens_per_second": 2558.624
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 1.273660205245154,
|
| 582 |
+
"grad_norm": 0.5107876658439636,
|
| 583 |
+
"learning_rate": 0.0002439614216116939,
|
| 584 |
+
"loss": 0.3223,
|
| 585 |
"num_input_tokens_seen": 3429520,
|
| 586 |
+
"step": 280,
|
| 587 |
+
"train_runtime": 1339.2313,
|
| 588 |
+
"train_tokens_per_second": 2560.812
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 1.2964652223489168,
|
| 592 |
+
"grad_norm": 0.3615415096282959,
|
| 593 |
+
"learning_rate": 0.00024175864486725092,
|
| 594 |
+
"loss": 0.312,
|
| 595 |
"num_input_tokens_seen": 3490448,
|
| 596 |
+
"step": 285,
|
| 597 |
+
"train_runtime": 1361.9259,
|
| 598 |
+
"train_tokens_per_second": 2562.877
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 1.3192702394526796,
|
| 602 |
+
"grad_norm": 0.3464173674583435,
|
| 603 |
+
"learning_rate": 0.00023952378212737554,
|
| 604 |
+
"loss": 0.3096,
|
| 605 |
"num_input_tokens_seen": 3551120,
|
| 606 |
+
"step": 290,
|
| 607 |
+
"train_runtime": 1384.5561,
|
| 608 |
+
"train_tokens_per_second": 2564.808
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 1.3420752565564424,
|
| 612 |
+
"grad_norm": 0.24868755042552948,
|
| 613 |
+
"learning_rate": 0.00023725761487479086,
|
| 614 |
+
"loss": 0.3109,
|
| 615 |
"num_input_tokens_seen": 3611920,
|
| 616 |
+
"step": 295,
|
| 617 |
+
"train_runtime": 1407.1864,
|
| 618 |
+
"train_tokens_per_second": 2566.767
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 1.3648802736602053,
|
| 622 |
+
"grad_norm": 0.252758651971817,
|
| 623 |
+
"learning_rate": 0.0002349609355387249,
|
| 624 |
+
"loss": 0.3092,
|
| 625 |
"num_input_tokens_seen": 3673744,
|
| 626 |
+
"step": 300,
|
| 627 |
+
"train_runtime": 1430.0422,
|
| 628 |
+
"train_tokens_per_second": 2568.976
|
| 629 |
},
|
| 630 |
{
|
| 631 |
"epoch": 1.3648802736602053,
|
| 632 |
+
"eval_loss": 0.31190308928489685,
|
| 633 |
+
"eval_runtime": 32.3176,
|
| 634 |
+
"eval_samples_per_second": 96.48,
|
| 635 |
+
"eval_steps_per_second": 6.034,
|
| 636 |
"num_input_tokens_seen": 3673744,
|
| 637 |
"step": 300
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 1.387685290763968,
|
| 641 |
+
"grad_norm": 0.3992477059364319,
|
| 642 |
+
"learning_rate": 0.00023263454721781537,
|
| 643 |
+
"loss": 0.308,
|
| 644 |
"num_input_tokens_seen": 3735568,
|
| 645 |
+
"step": 305,
|
| 646 |
+
"train_runtime": 1485.2691,
|
| 647 |
+
"train_tokens_per_second": 2515.078
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 1.4104903078677309,
|
| 651 |
+
"grad_norm": 0.32043761014938354,
|
| 652 |
+
"learning_rate": 0.0002302792633992835,
|
| 653 |
+
"loss": 0.3089,
|
| 654 |
"num_input_tokens_seen": 3798160,
|
| 655 |
+
"step": 310,
|
| 656 |
+
"train_runtime": 1508.5292,
|
| 657 |
+
"train_tokens_per_second": 2517.79
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 1.4332953249714937,
|
| 661 |
+
"grad_norm": 0.28808364272117615,
|
| 662 |
+
"learning_rate": 0.00022789590767447533,
|
| 663 |
+
"loss": 0.3028,
|
| 664 |
"num_input_tokens_seen": 3859600,
|
| 665 |
+
"step": 315,
|
| 666 |
+
"train_runtime": 1531.393,
|
| 667 |
+
"train_tokens_per_second": 2520.32
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 1.4561003420752565,
|
| 671 |
+
"grad_norm": 0.31557497382164,
|
| 672 |
+
"learning_rate": 0.00022548531345087,
|
| 673 |
+
"loss": 0.2925,
|
| 674 |
"num_input_tokens_seen": 3920528,
|
| 675 |
+
"step": 320,
|
| 676 |
+
"train_runtime": 1553.9921,
|
| 677 |
+
"train_tokens_per_second": 2522.875
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 1.4789053591790193,
|
| 681 |
+
"grad_norm": 0.28433188796043396,
|
| 682 |
+
"learning_rate": 0.00022304832366065505,
|
| 683 |
+
"loss": 0.285,
|
| 684 |
"num_input_tokens_seen": 3982096,
|
| 685 |
+
"step": 325,
|
| 686 |
+
"train_runtime": 1576.8412,
|
| 687 |
+
"train_tokens_per_second": 2525.363
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 1.5017103762827824,
|
| 691 |
+
"grad_norm": 0.2831820547580719,
|
| 692 |
+
"learning_rate": 0.0002205857904659717,
|
| 693 |
+
"loss": 0.304,
|
| 694 |
"num_input_tokens_seen": 4044048,
|
| 695 |
+
"step": 330,
|
| 696 |
+
"train_runtime": 1599.876,
|
| 697 |
+
"train_tokens_per_second": 2527.726
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 1.5245153933865452,
|
| 701 |
+
"grad_norm": 0.5233074426651001,
|
| 702 |
+
"learning_rate": 0.00021809857496093199,
|
| 703 |
+
"loss": 0.2892,
|
| 704 |
"num_input_tokens_seen": 4105104,
|
| 705 |
+
"step": 335,
|
| 706 |
+
"train_runtime": 1622.5215,
|
| 707 |
+
"train_tokens_per_second": 2530.077
|
| 708 |
},
|
| 709 |
{
|
| 710 |
"epoch": 1.547320410490308,
|
| 711 |
+
"grad_norm": 0.326762318611145,
|
| 712 |
+
"learning_rate": 0.00021558754687051344,
|
| 713 |
+
"loss": 0.2849,
|
| 714 |
"num_input_tokens_seen": 4165904,
|
| 715 |
+
"step": 340,
|
| 716 |
+
"train_runtime": 1645.0233,
|
| 717 |
+
"train_tokens_per_second": 2532.429
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 1.5701254275940708,
|
| 721 |
+
"grad_norm": 0.35533398389816284,
|
| 722 |
+
"learning_rate": 0.0002130535842464348,
|
| 723 |
+
"loss": 0.2975,
|
| 724 |
"num_input_tokens_seen": 4226704,
|
| 725 |
+
"step": 345,
|
| 726 |
+
"train_runtime": 1667.6513,
|
| 727 |
+
"train_tokens_per_second": 2534.525
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 1.5929304446978336,
|
| 731 |
+
"grad_norm": 0.2767379879951477,
|
| 732 |
+
"learning_rate": 0.00021049757316012077,
|
| 733 |
+
"loss": 0.2845,
|
| 734 |
"num_input_tokens_seen": 4288400,
|
| 735 |
+
"step": 350,
|
| 736 |
+
"train_runtime": 1690.4931,
|
| 737 |
+
"train_tokens_per_second": 2536.775
|
| 738 |
},
|
| 739 |
{
|
| 740 |
"epoch": 1.6157354618015964,
|
| 741 |
+
"grad_norm": 0.35976049304008484,
|
| 742 |
+
"learning_rate": 0.0002079204073928619,
|
| 743 |
+
"loss": 0.2869,
|
| 744 |
"num_input_tokens_seen": 4349712,
|
| 745 |
+
"step": 355,
|
| 746 |
+
"train_runtime": 1713.2321,
|
| 747 |
+
"train_tokens_per_second": 2538.892
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 1.6385404789053593,
|
| 751 |
+
"grad_norm": 0.23936209082603455,
|
| 752 |
+
"learning_rate": 0.0002053229881232793,
|
| 753 |
+
"loss": 0.2601,
|
| 754 |
"num_input_tokens_seen": 4410256,
|
| 755 |
+
"step": 360,
|
| 756 |
+
"train_runtime": 1735.7264,
|
| 757 |
+
"train_tokens_per_second": 2540.87
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 1.661345496009122,
|
| 761 |
+
"grad_norm": 0.2862788140773773,
|
| 762 |
+
"learning_rate": 0.0002027062236122014,
|
| 763 |
+
"loss": 0.2826,
|
| 764 |
"num_input_tokens_seen": 4471440,
|
| 765 |
+
"step": 365,
|
| 766 |
+
"train_runtime": 1758.3589,
|
| 767 |
+
"train_tokens_per_second": 2542.962
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 1.6841505131128849,
|
| 771 |
+
"grad_norm": 0.3150525391101837,
|
| 772 |
+
"learning_rate": 0.0002000710288850656,
|
| 773 |
+
"loss": 0.2729,
|
| 774 |
"num_input_tokens_seen": 4533008,
|
| 775 |
+
"step": 370,
|
| 776 |
+
"train_runtime": 1781.1643,
|
| 777 |
+
"train_tokens_per_second": 2544.969
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 1.7069555302166477,
|
| 781 |
+
"grad_norm": 0.31325292587280273,
|
| 782 |
+
"learning_rate": 0.00019741832541195366,
|
| 783 |
+
"loss": 0.2772,
|
| 784 |
"num_input_tokens_seen": 4594320,
|
| 785 |
+
"step": 375,
|
| 786 |
+
"train_runtime": 1803.8324,
|
| 787 |
+
"train_tokens_per_second": 2546.977
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 1.7297605473204105,
|
| 791 |
+
"grad_norm": 0.8041843175888062,
|
| 792 |
+
"learning_rate": 0.0001947490407853734,
|
| 793 |
+
"loss": 0.2789,
|
| 794 |
"num_input_tokens_seen": 4655760,
|
| 795 |
+
"step": 380,
|
| 796 |
+
"train_runtime": 1826.573,
|
| 797 |
+
"train_tokens_per_second": 2548.904
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 1.7525655644241733,
|
| 801 |
+
"grad_norm": 0.23466791212558746,
|
| 802 |
+
"learning_rate": 0.0001920641083959004,
|
| 803 |
+
"loss": 0.2743,
|
| 804 |
"num_input_tokens_seen": 4717328,
|
| 805 |
+
"step": 385,
|
| 806 |
+
"train_runtime": 1849.3505,
|
| 807 |
+
"train_tokens_per_second": 2550.803
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 1.7753705815279361,
|
| 811 |
+
"grad_norm": 0.29242169857025146,
|
| 812 |
+
"learning_rate": 0.00018936446710579122,
|
| 813 |
+
"loss": 0.2657,
|
| 814 |
"num_input_tokens_seen": 4779152,
|
| 815 |
+
"step": 390,
|
| 816 |
+
"train_runtime": 1872.1695,
|
| 817 |
+
"train_tokens_per_second": 2552.735
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 1.798175598631699,
|
| 821 |
+
"grad_norm": 0.3305339217185974,
|
| 822 |
+
"learning_rate": 0.00018665106092068408,
|
| 823 |
+
"loss": 0.2847,
|
| 824 |
"num_input_tokens_seen": 4840336,
|
| 825 |
+
"step": 395,
|
| 826 |
+
"train_runtime": 1894.8106,
|
| 827 |
+
"train_tokens_per_second": 2554.522
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 1.8209806157354618,
|
| 831 |
+
"grad_norm": 0.3732515871524811,
|
| 832 |
+
"learning_rate": 0.00018392483865950046,
|
| 833 |
+
"loss": 0.2796,
|
| 834 |
"num_input_tokens_seen": 4901648,
|
| 835 |
+
"step": 400,
|
| 836 |
+
"train_runtime": 1917.4674,
|
| 837 |
+
"train_tokens_per_second": 2556.314
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 1.8209806157354618,
|
| 841 |
+
"eval_loss": 0.2729249596595764,
|
| 842 |
+
"eval_runtime": 32.2506,
|
| 843 |
+
"eval_samples_per_second": 96.68,
|
| 844 |
+
"eval_steps_per_second": 6.046,
|
| 845 |
"num_input_tokens_seen": 4901648,
|
| 846 |
"step": 400
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"epoch": 1.8437856328392246,
|
| 850 |
+
"grad_norm": 0.30687257647514343,
|
| 851 |
+
"learning_rate": 0.00018118675362266385,
|
| 852 |
+
"loss": 0.2725,
|
| 853 |
"num_input_tokens_seen": 4963216,
|
| 854 |
+
"step": 405,
|
| 855 |
+
"train_runtime": 1972.5152,
|
| 856 |
+
"train_tokens_per_second": 2516.186
|
| 857 |
},
|
| 858 |
{
|
| 859 |
"epoch": 1.8665906499429874,
|
| 860 |
+
"grad_norm": 0.2922170162200928,
|
| 861 |
+
"learning_rate": 0.00017843776325875176,
|
| 862 |
+
"loss": 0.2714,
|
| 863 |
"num_input_tokens_seen": 5024912,
|
| 864 |
+
"step": 410,
|
| 865 |
+
"train_runtime": 1995.3388,
|
| 866 |
+
"train_tokens_per_second": 2518.325
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 1.8893956670467502,
|
| 870 |
+
"grad_norm": 0.3486429452896118,
|
| 871 |
+
"learning_rate": 0.00017567882882969628,
|
| 872 |
+
"loss": 0.2547,
|
| 873 |
"num_input_tokens_seen": 5086224,
|
| 874 |
+
"step": 415,
|
| 875 |
+
"train_runtime": 2018.156,
|
| 876 |
+
"train_tokens_per_second": 2520.233
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 1.912200684150513,
|
| 880 |
+
"grad_norm": 0.4654463827610016,
|
| 881 |
+
"learning_rate": 0.0001729109150746521,
|
| 882 |
+
"loss": 0.2687,
|
| 883 |
"num_input_tokens_seen": 5148048,
|
| 884 |
+
"step": 420,
|
| 885 |
+
"train_runtime": 2041.096,
|
| 886 |
+
"train_tokens_per_second": 2522.198
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"epoch": 1.9350057012542758,
|
| 890 |
+
"grad_norm": 0.3267694413661957,
|
| 891 |
+
"learning_rate": 0.00017013498987264832,
|
| 892 |
+
"loss": 0.2644,
|
| 893 |
"num_input_tokens_seen": 5209104,
|
| 894 |
+
"step": 425,
|
| 895 |
+
"train_runtime": 2063.7125,
|
| 896 |
+
"train_tokens_per_second": 2524.142
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 1.9578107183580387,
|
| 900 |
+
"grad_norm": 0.6316472291946411,
|
| 901 |
+
"learning_rate": 0.00016735202390414215,
|
| 902 |
+
"loss": 0.2696,
|
| 903 |
"num_input_tokens_seen": 5270544,
|
| 904 |
+
"step": 430,
|
| 905 |
+
"train_runtime": 2086.4995,
|
| 906 |
+
"train_tokens_per_second": 2526.022
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 1.9806157354618015,
|
| 910 |
+
"grad_norm": 0.23907926678657532,
|
| 911 |
+
"learning_rate": 0.00016456299031159322,
|
| 912 |
+
"loss": 0.2694,
|
| 913 |
"num_input_tokens_seen": 5331472,
|
| 914 |
+
"step": 435,
|
| 915 |
+
"train_runtime": 2109.1335,
|
| 916 |
+
"train_tokens_per_second": 2527.802
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 2.0,
|
| 920 |
+
"grad_norm": 0.6817493438720703,
|
| 921 |
+
"learning_rate": 0.00016176886435917675,
|
| 922 |
+
"loss": 0.2495,
|
| 923 |
"num_input_tokens_seen": 5382864,
|
| 924 |
+
"step": 440,
|
| 925 |
+
"train_runtime": 2128.3818,
|
| 926 |
+
"train_tokens_per_second": 2529.088
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 2.022805017103763,
|
| 930 |
+
"grad_norm": 0.5987955927848816,
|
| 931 |
+
"learning_rate": 0.00015897062309175512,
|
| 932 |
+
"loss": 0.2453,
|
| 933 |
"num_input_tokens_seen": 5444176,
|
| 934 |
+
"step": 445,
|
| 935 |
+
"train_runtime": 2151.1431,
|
| 936 |
+
"train_tokens_per_second": 2530.829
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 2.0456100342075256,
|
| 940 |
+
"grad_norm": 0.3288906216621399,
|
| 941 |
+
"learning_rate": 0.0001561692449932266,
|
| 942 |
+
"loss": 0.2299,
|
| 943 |
"num_input_tokens_seen": 5505872,
|
| 944 |
+
"step": 450,
|
| 945 |
+
"train_runtime": 2174.0024,
|
| 946 |
+
"train_tokens_per_second": 2532.597
|
| 947 |
},
|
| 948 |
{
|
| 949 |
"epoch": 2.0684150513112884,
|
| 950 |
+
"grad_norm": 0.31571510434150696,
|
| 951 |
+
"learning_rate": 0.00015336570964437075,
|
| 952 |
+
"loss": 0.2301,
|
| 953 |
"num_input_tokens_seen": 5568208,
|
| 954 |
+
"step": 455,
|
| 955 |
+
"train_runtime": 2197.104,
|
| 956 |
+
"train_tokens_per_second": 2534.34
|
| 957 |
},
|
| 958 |
{
|
| 959 |
"epoch": 2.0912200684150513,
|
| 960 |
+
"grad_norm": 0.3670252859592438,
|
| 961 |
+
"learning_rate": 0.0001505609973803105,
|
| 962 |
+
"loss": 0.2376,
|
| 963 |
"num_input_tokens_seen": 5628880,
|
| 964 |
+
"step": 460,
|
| 965 |
+
"train_runtime": 2219.7182,
|
| 966 |
+
"train_tokens_per_second": 2535.853
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 2.114025085518814,
|
| 970 |
+
"grad_norm": 0.27864688634872437,
|
| 971 |
+
"learning_rate": 0.00014775608894771047,
|
| 972 |
+
"loss": 0.2199,
|
| 973 |
"num_input_tokens_seen": 5690320,
|
| 974 |
+
"step": 465,
|
| 975 |
+
"train_runtime": 2242.4827,
|
| 976 |
+
"train_tokens_per_second": 2537.509
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 2.136830102622577,
|
| 980 |
+
"grad_norm": 0.30822446942329407,
|
| 981 |
+
"learning_rate": 0.00014495196516183095,
|
| 982 |
+
"loss": 0.2237,
|
| 983 |
"num_input_tokens_seen": 5752912,
|
| 984 |
+
"step": 470,
|
| 985 |
+
"train_runtime": 2265.6875,
|
| 986 |
+
"train_tokens_per_second": 2539.146
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 2.1596351197263397,
|
| 990 |
+
"grad_norm": 0.34737417101860046,
|
| 991 |
+
"learning_rate": 0.0001421496065635584,
|
| 992 |
+
"loss": 0.2294,
|
| 993 |
"num_input_tokens_seen": 5813968,
|
| 994 |
+
"step": 475,
|
| 995 |
+
"train_runtime": 2288.3705,
|
| 996 |
+
"train_tokens_per_second": 2540.659
|
| 997 |
},
|
| 998 |
{
|
| 999 |
"epoch": 2.1824401368301025,
|
| 1000 |
+
"grad_norm": 0.2497541755437851,
|
| 1001 |
+
"learning_rate": 0.00013934999307653193,
|
| 1002 |
+
"loss": 0.231,
|
| 1003 |
"num_input_tokens_seen": 5874896,
|
| 1004 |
+
"step": 480,
|
| 1005 |
+
"train_runtime": 2310.9431,
|
| 1006 |
+
"train_tokens_per_second": 2542.207
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 2.2052451539338653,
|
| 1010 |
+
"grad_norm": 0.30357566475868225,
|
| 1011 |
+
"learning_rate": 0.00013655410366448498,
|
| 1012 |
+
"loss": 0.2252,
|
| 1013 |
"num_input_tokens_seen": 5935952,
|
| 1014 |
+
"step": 485,
|
| 1015 |
+
"train_runtime": 2333.5618,
|
| 1016 |
+
"train_tokens_per_second": 2543.73
|
| 1017 |
},
|
| 1018 |
{
|
| 1019 |
"epoch": 2.228050171037628,
|
| 1020 |
+
"grad_norm": 0.3196811378002167,
|
| 1021 |
+
"learning_rate": 0.0001337629159889232,
|
| 1022 |
+
"loss": 0.2151,
|
| 1023 |
"num_input_tokens_seen": 5997008,
|
| 1024 |
+
"step": 490,
|
| 1025 |
+
"train_runtime": 2356.1683,
|
| 1026 |
+
"train_tokens_per_second": 2545.237
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 2.250855188141391,
|
| 1030 |
+
"grad_norm": 0.464616984128952,
|
| 1031 |
+
"learning_rate": 0.00013097740606725776,
|
| 1032 |
+
"loss": 0.2228,
|
| 1033 |
"num_input_tokens_seen": 6058704,
|
| 1034 |
+
"step": 495,
|
| 1035 |
+
"train_runtime": 2379.0776,
|
| 1036 |
+
"train_tokens_per_second": 2546.661
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
"epoch": 2.2736602052451538,
|
| 1040 |
+
"grad_norm": 0.31572940945625305,
|
| 1041 |
+
"learning_rate": 0.00012819854793151312,
|
| 1042 |
+
"loss": 0.2265,
|
| 1043 |
"num_input_tokens_seen": 6120272,
|
| 1044 |
+
"step": 500,
|
| 1045 |
+
"train_runtime": 2401.9854,
|
| 1046 |
+
"train_tokens_per_second": 2548.006
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
"epoch": 2.2736602052451538,
|
| 1050 |
+
"eval_loss": 0.24168384075164795,
|
| 1051 |
+
"eval_runtime": 32.2697,
|
| 1052 |
+
"eval_samples_per_second": 96.623,
|
| 1053 |
+
"eval_steps_per_second": 6.043,
|
| 1054 |
"num_input_tokens_seen": 6120272,
|
| 1055 |
"step": 500
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 2.2964652223489166,
|
| 1059 |
+
"grad_norm": 0.3663758933544159,
|
| 1060 |
+
"learning_rate": 0.00012542731328772934,
|
| 1061 |
+
"loss": 0.2126,
|
| 1062 |
"num_input_tokens_seen": 6180816,
|
| 1063 |
+
"step": 505,
|
| 1064 |
+
"train_runtime": 2462.9918,
|
| 1065 |
+
"train_tokens_per_second": 2509.475
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 2.3192702394526794,
|
| 1069 |
+
"grad_norm": 0.4008311629295349,
|
| 1070 |
+
"learning_rate": 0.00012266467117617787,
|
| 1071 |
+
"loss": 0.2202,
|
| 1072 |
"num_input_tokens_seen": 6242128,
|
| 1073 |
+
"step": 510,
|
| 1074 |
+
"train_runtime": 2485.6998,
|
| 1075 |
+
"train_tokens_per_second": 2511.216
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
"epoch": 2.342075256556442,
|
| 1079 |
+
"grad_norm": 0.29326286911964417,
|
| 1080 |
+
"learning_rate": 0.00011991158763250908,
|
| 1081 |
+
"loss": 0.2203,
|
| 1082 |
"num_input_tokens_seen": 6303312,
|
| 1083 |
+
"step": 515,
|
| 1084 |
+
"train_runtime": 2508.4008,
|
| 1085 |
+
"train_tokens_per_second": 2512.881
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 2.364880273660205,
|
| 1089 |
+
"grad_norm": 0.2958817780017853,
|
| 1090 |
+
"learning_rate": 0.00011716902534995079,
|
| 1091 |
+
"loss": 0.223,
|
| 1092 |
"num_input_tokens_seen": 6364624,
|
| 1093 |
+
"step": 520,
|
| 1094 |
+
"train_runtime": 2531.1448,
|
| 1095 |
+
"train_tokens_per_second": 2514.524
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 2.387685290763968,
|
| 1099 |
+
"grad_norm": 0.42678675055503845,
|
| 1100 |
+
"learning_rate": 0.00011443794334267538,
|
| 1101 |
+
"loss": 0.2218,
|
| 1102 |
"num_input_tokens_seen": 6425040,
|
| 1103 |
+
"step": 525,
|
| 1104 |
+
"train_runtime": 2553.5434,
|
| 1105 |
+
"train_tokens_per_second": 2516.127
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
"epoch": 2.4104903078677307,
|
| 1109 |
+
"grad_norm": 0.3538350760936737,
|
| 1110 |
+
"learning_rate": 0.0001117192966104536,
|
| 1111 |
+
"loss": 0.2156,
|
| 1112 |
"num_input_tokens_seen": 6486736,
|
| 1113 |
+
"step": 530,
|
| 1114 |
+
"train_runtime": 2576.3405,
|
| 1115 |
+
"train_tokens_per_second": 2517.81
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 2.433295324971494,
|
| 1119 |
+
"grad_norm": 0.31797412037849426,
|
| 1120 |
+
"learning_rate": 0.000109014035804712,
|
| 1121 |
+
"loss": 0.2161,
|
| 1122 |
"num_input_tokens_seen": 6548304,
|
| 1123 |
+
"step": 535,
|
| 1124 |
+
"train_runtime": 2599.1554,
|
| 1125 |
+
"train_tokens_per_second": 2519.397
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 2.4561003420752567,
|
| 1129 |
+
"grad_norm": 0.3164632320404053,
|
| 1130 |
+
"learning_rate": 0.0001063231068961106,
|
| 1131 |
+
"loss": 0.2045,
|
| 1132 |
"num_input_tokens_seen": 6610000,
|
| 1133 |
+
"step": 540,
|
| 1134 |
+
"train_runtime": 2622.0446,
|
| 1135 |
+
"train_tokens_per_second": 2520.933
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
"epoch": 2.4789053591790196,
|
| 1139 |
+
"grad_norm": 0.2635822296142578,
|
| 1140 |
+
"learning_rate": 0.0001036474508437579,
|
| 1141 |
+
"loss": 0.2073,
|
| 1142 |
"num_input_tokens_seen": 6670672,
|
| 1143 |
+
"step": 545,
|
| 1144 |
+
"train_runtime": 2644.5946,
|
| 1145 |
+
"train_tokens_per_second": 2522.38
|
| 1146 |
},
|
| 1147 |
{
|
| 1148 |
"epoch": 2.5017103762827824,
|
| 1149 |
+
"grad_norm": 0.2644634246826172,
|
| 1150 |
+
"learning_rate": 0.00010098800326617791,
|
| 1151 |
+
"loss": 0.2018,
|
| 1152 |
"num_input_tokens_seen": 6732112,
|
| 1153 |
+
"step": 550,
|
| 1154 |
+
"train_runtime": 2667.3609,
|
| 1155 |
+
"train_tokens_per_second": 2523.885
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 2.524515393386545,
|
| 1159 |
+
"grad_norm": 0.3596520721912384,
|
| 1160 |
+
"learning_rate": 9.834569411414471e-05,
|
| 1161 |
+
"loss": 0.2048,
|
| 1162 |
"num_input_tokens_seen": 6793424,
|
| 1163 |
+
"step": 555,
|
| 1164 |
+
"train_runtime": 2690.0439,
|
| 1165 |
+
"train_tokens_per_second": 2525.395
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
"epoch": 2.547320410490308,
|
| 1169 |
+
"grad_norm": 0.3009176254272461,
|
| 1170 |
+
"learning_rate": 9.572144734549919e-05,
|
| 1171 |
+
"loss": 0.2062,
|
| 1172 |
"num_input_tokens_seen": 6855760,
|
| 1173 |
+
"step": 560,
|
| 1174 |
+
"train_runtime": 2713.0534,
|
| 1175 |
+
"train_tokens_per_second": 2526.954
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
"epoch": 2.570125427594071,
|
| 1179 |
+
"grad_norm": 0.3456870913505554,
|
| 1180 |
+
"learning_rate": 9.311618060206074e-05,
|
| 1181 |
+
"loss": 0.216,
|
| 1182 |
"num_input_tokens_seen": 6916688,
|
| 1183 |
+
"step": 565,
|
| 1184 |
+
"train_runtime": 2735.7383,
|
| 1185 |
+
"train_tokens_per_second": 2528.271
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 2.5929304446978336,
|
| 1189 |
+
"grad_norm": 0.27823150157928467,
|
| 1190 |
+
"learning_rate": 9.053080488874836e-05,
|
| 1191 |
+
"loss": 0.1953,
|
| 1192 |
"num_input_tokens_seen": 6978512,
|
| 1193 |
+
"step": 570,
|
| 1194 |
+
"train_runtime": 2758.6045,
|
| 1195 |
+
"train_tokens_per_second": 2529.725
|
| 1196 |
},
|
| 1197 |
{
|
| 1198 |
"epoch": 2.6157354618015964,
|
| 1199 |
+
"grad_norm": 0.31827694177627563,
|
| 1200 |
+
"learning_rate": 8.796622425502192e-05,
|
| 1201 |
+
"loss": 0.2147,
|
| 1202 |
"num_input_tokens_seen": 7040208,
|
| 1203 |
+
"step": 575,
|
| 1204 |
+
"train_runtime": 2781.5669,
|
| 1205 |
+
"train_tokens_per_second": 2531.022
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 2.6385404789053593,
|
| 1209 |
+
"grad_norm": 0.3293188512325287,
|
| 1210 |
+
"learning_rate": 8.54233354787557e-05,
|
| 1211 |
+
"loss": 0.209,
|
| 1212 |
"num_input_tokens_seen": 7101264,
|
| 1213 |
+
"step": 580,
|
| 1214 |
+
"train_runtime": 2804.2079,
|
| 1215 |
+
"train_tokens_per_second": 2532.36
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 2.661345496009122,
|
| 1219 |
+
"grad_norm": 0.26295793056488037,
|
| 1220 |
+
"learning_rate": 8.290302775265509e-05,
|
| 1221 |
+
"loss": 0.2077,
|
| 1222 |
"num_input_tokens_seen": 7163600,
|
| 1223 |
+
"step": 585,
|
| 1224 |
+
"train_runtime": 2827.2586,
|
| 1225 |
+
"train_tokens_per_second": 2533.762
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 2.684150513112885,
|
| 1229 |
+
"grad_norm": 0.2915421426296234,
|
| 1230 |
+
"learning_rate": 8.04061823733249e-05,
|
| 1231 |
+
"loss": 0.2058,
|
| 1232 |
"num_input_tokens_seen": 7225936,
|
| 1233 |
+
"step": 590,
|
| 1234 |
+
"train_runtime": 2850.236,
|
| 1235 |
+
"train_tokens_per_second": 2535.206
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 2.7069555302166477,
|
| 1239 |
+
"grad_norm": 0.3178254961967468,
|
| 1240 |
+
"learning_rate": 7.79336724330994e-05,
|
| 1241 |
+
"loss": 0.1961,
|
| 1242 |
"num_input_tokens_seen": 7287760,
|
| 1243 |
+
"step": 595,
|
| 1244 |
+
"train_runtime": 2873.2284,
|
| 1245 |
+
"train_tokens_per_second": 2536.436
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
"epoch": 2.7297605473204105,
|
| 1249 |
+
"grad_norm": 0.2937912344932556,
|
| 1250 |
+
"learning_rate": 7.548636251474091e-05,
|
| 1251 |
+
"loss": 0.2003,
|
| 1252 |
"num_input_tokens_seen": 7348944,
|
| 1253 |
+
"step": 600,
|
| 1254 |
+
"train_runtime": 2895.9783,
|
| 1255 |
+
"train_tokens_per_second": 2537.638
|
| 1256 |
},
|
| 1257 |
{
|
| 1258 |
"epoch": 2.7297605473204105,
|
| 1259 |
+
"eval_loss": 0.22281652688980103,
|
| 1260 |
+
"eval_runtime": 32.2665,
|
| 1261 |
+
"eval_samples_per_second": 96.633,
|
| 1262 |
+
"eval_steps_per_second": 6.043,
|
| 1263 |
"num_input_tokens_seen": 7348944,
|
| 1264 |
"step": 600
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 2.7525655644241733,
|
| 1268 |
+
"grad_norm": 0.30021318793296814,
|
| 1269 |
+
"learning_rate": 7.30651083891141e-05,
|
| 1270 |
+
"loss": 0.2058,
|
| 1271 |
"num_input_tokens_seen": 7410640,
|
| 1272 |
+
"step": 605,
|
| 1273 |
+
"train_runtime": 2951.0324,
|
| 1274 |
+
"train_tokens_per_second": 2511.203
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 2.775370581527936,
|
| 1278 |
+
"grad_norm": 0.3852008581161499,
|
| 1279 |
+
"learning_rate": 7.067075671594168e-05,
|
| 1280 |
+
"loss": 0.1909,
|
| 1281 |
"num_input_tokens_seen": 7471184,
|
| 1282 |
+
"step": 610,
|
| 1283 |
+
"train_runtime": 2973.5012,
|
| 1284 |
+
"train_tokens_per_second": 2512.588
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 2.798175598631699,
|
| 1288 |
+
"grad_norm": 0.3185110092163086,
|
| 1289 |
+
"learning_rate": 6.830414474774594e-05,
|
| 1290 |
+
"loss": 0.2035,
|
| 1291 |
"num_input_tokens_seen": 7533392,
|
| 1292 |
+
"step": 615,
|
| 1293 |
+
"train_runtime": 2996.5054,
|
| 1294 |
+
"train_tokens_per_second": 2514.059
|
| 1295 |
},
|
| 1296 |
{
|
| 1297 |
"epoch": 2.8209806157354618,
|
| 1298 |
+
"grad_norm": 0.33980560302734375,
|
| 1299 |
+
"learning_rate": 6.596610003707958e-05,
|
| 1300 |
+
"loss": 0.1963,
|
| 1301 |
"num_input_tokens_seen": 7594832,
|
| 1302 |
+
"step": 620,
|
| 1303 |
+
"train_runtime": 3019.2698,
|
| 1304 |
+
"train_tokens_per_second": 2515.453
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 2.8437856328392246,
|
| 1308 |
+
"grad_norm": 0.26889362931251526,
|
| 1309 |
+
"learning_rate": 6.365744014714898e-05,
|
| 1310 |
+
"loss": 0.1951,
|
| 1311 |
"num_input_tokens_seen": 7656656,
|
| 1312 |
+
"step": 625,
|
| 1313 |
+
"train_runtime": 3042.165,
|
| 1314 |
+
"train_tokens_per_second": 2516.844
|
| 1315 |
},
|
| 1316 |
{
|
| 1317 |
"epoch": 2.8665906499429874,
|
| 1318 |
+
"grad_norm": 0.2750576436519623,
|
| 1319 |
+
"learning_rate": 6.137897236593002e-05,
|
| 1320 |
+
"loss": 0.193,
|
| 1321 |
"num_input_tokens_seen": 7717712,
|
| 1322 |
+
"step": 630,
|
| 1323 |
+
"train_runtime": 3064.8231,
|
| 1324 |
+
"train_tokens_per_second": 2518.159
|
| 1325 |
},
|
| 1326 |
{
|
| 1327 |
"epoch": 2.88939566704675,
|
| 1328 |
+
"grad_norm": 0.32393938302993774,
|
| 1329 |
+
"learning_rate": 5.913149342387703e-05,
|
| 1330 |
+
"loss": 0.1925,
|
| 1331 |
"num_input_tokens_seen": 7779920,
|
| 1332 |
+
"step": 635,
|
| 1333 |
+
"train_runtime": 3087.8496,
|
| 1334 |
+
"train_tokens_per_second": 2519.527
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 2.912200684150513,
|
| 1338 |
+
"grad_norm": 0.33339279890060425,
|
| 1339 |
+
"learning_rate": 5.6915789215323817e-05,
|
| 1340 |
+
"loss": 0.1995,
|
| 1341 |
"num_input_tokens_seen": 7840976,
|
| 1342 |
+
"step": 640,
|
| 1343 |
+
"train_runtime": 3110.4659,
|
| 1344 |
+
"train_tokens_per_second": 2520.836
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 2.935005701254276,
|
| 1348 |
+
"grad_norm": 0.26764461398124695,
|
| 1349 |
+
"learning_rate": 5.473263452367318e-05,
|
| 1350 |
+
"loss": 0.1852,
|
| 1351 |
"num_input_tokens_seen": 7902160,
|
| 1352 |
+
"step": 645,
|
| 1353 |
+
"train_runtime": 3133.2052,
|
| 1354 |
+
"train_tokens_per_second": 2522.069
|
| 1355 |
},
|
| 1356 |
{
|
| 1357 |
"epoch": 2.9578107183580387,
|
| 1358 |
+
"grad_norm": 0.28049248456954956,
|
| 1359 |
+
"learning_rate": 5.2582792750472464e-05,
|
| 1360 |
+
"loss": 0.1878,
|
| 1361 |
"num_input_tokens_seen": 7963856,
|
| 1362 |
+
"step": 650,
|
| 1363 |
+
"train_runtime": 3155.996,
|
| 1364 |
+
"train_tokens_per_second": 2523.405
|
| 1365 |
},
|
| 1366 |
{
|
| 1367 |
"epoch": 2.9806157354618015,
|
| 1368 |
+
"grad_norm": 0.3994698226451874,
|
| 1369 |
+
"learning_rate": 5.046701564846834e-05,
|
| 1370 |
+
"loss": 0.1945,
|
| 1371 |
"num_input_tokens_seen": 8026448,
|
| 1372 |
+
"step": 655,
|
| 1373 |
+
"train_runtime": 3179.1862,
|
| 1374 |
+
"train_tokens_per_second": 2524.686
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 3.0,
|
| 1378 |
+
"grad_norm": 0.43112221360206604,
|
| 1379 |
+
"learning_rate": 4.8386043058735465e-05,
|
| 1380 |
+
"loss": 0.1645,
|
| 1381 |
"num_input_tokens_seen": 8078224,
|
| 1382 |
+
"step": 660,
|
| 1383 |
+
"train_runtime": 3198.3837,
|
| 1384 |
+
"train_tokens_per_second": 2525.721
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 3.022805017103763,
|
| 1388 |
+
"grad_norm": 0.38409358263015747,
|
| 1389 |
+
"learning_rate": 4.63406026519703e-05,
|
| 1390 |
+
"loss": 0.1556,
|
| 1391 |
"num_input_tokens_seen": 8140176,
|
| 1392 |
+
"step": 665,
|
| 1393 |
+
"train_runtime": 3221.2903,
|
| 1394 |
+
"train_tokens_per_second": 2526.992
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 3.0456100342075256,
|
| 1398 |
+
"grad_norm": 0.2992386221885681,
|
| 1399 |
+
"learning_rate": 4.4331409674040324e-05,
|
| 1400 |
+
"loss": 0.1397,
|
| 1401 |
"num_input_tokens_seen": 8201616,
|
| 1402 |
+
"step": 670,
|
| 1403 |
+
"train_runtime": 3244.0794,
|
| 1404 |
+
"train_tokens_per_second": 2528.18
|
| 1405 |
},
|
| 1406 |
{
|
| 1407 |
"epoch": 3.0684150513112884,
|
| 1408 |
+
"grad_norm": 0.37943175435066223,
|
| 1409 |
+
"learning_rate": 4.23591666958782e-05,
|
| 1410 |
+
"loss": 0.1478,
|
| 1411 |
"num_input_tokens_seen": 8262928,
|
| 1412 |
+
"step": 675,
|
| 1413 |
+
"train_runtime": 3266.8349,
|
| 1414 |
+
"train_tokens_per_second": 2529.338
|
| 1415 |
},
|
| 1416 |
{
|
| 1417 |
"epoch": 3.0912200684150513,
|
| 1418 |
+
"grad_norm": 0.31016451120376587,
|
| 1419 |
+
"learning_rate": 4.042456336780837e-05,
|
| 1420 |
+
"loss": 0.1413,
|
| 1421 |
"num_input_tokens_seen": 8324496,
|
| 1422 |
+
"step": 680,
|
| 1423 |
+
"train_runtime": 3289.573,
|
| 1424 |
+
"train_tokens_per_second": 2530.57
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
"epoch": 3.114025085518814,
|
| 1428 |
+
"grad_norm": 0.3854951858520508,
|
| 1429 |
+
"learning_rate": 3.852827617839084e-05,
|
| 1430 |
+
"loss": 0.1494,
|
| 1431 |
"num_input_tokens_seen": 8385680,
|
| 1432 |
+
"step": 685,
|
| 1433 |
+
"train_runtime": 3312.3405,
|
| 1434 |
+
"train_tokens_per_second": 2531.648
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 3.136830102622577,
|
| 1438 |
+
"grad_norm": 0.36697664856910706,
|
| 1439 |
+
"learning_rate": 3.667096821786847e-05,
|
| 1440 |
+
"loss": 0.1426,
|
| 1441 |
"num_input_tokens_seen": 8447632,
|
| 1442 |
+
"step": 690,
|
| 1443 |
+
"train_runtime": 3335.3977,
|
| 1444 |
+
"train_tokens_per_second": 2532.721
|
| 1445 |
},
|
| 1446 |
{
|
| 1447 |
"epoch": 3.1596351197263397,
|
| 1448 |
+
"grad_norm": 0.2914251983165741,
|
| 1449 |
+
"learning_rate": 3.485328894629833e-05,
|
| 1450 |
+
"loss": 0.1413,
|
| 1451 |
"num_input_tokens_seen": 8508432,
|
| 1452 |
+
"step": 695,
|
| 1453 |
+
"train_runtime": 3357.9702,
|
| 1454 |
+
"train_tokens_per_second": 2533.802
|
| 1455 |
},
|
| 1456 |
{
|
| 1457 |
"epoch": 3.1824401368301025,
|
| 1458 |
+
"grad_norm": 0.3913465440273285,
|
| 1459 |
+
"learning_rate": 3.307587396644996e-05,
|
| 1460 |
+
"loss": 0.1439,
|
| 1461 |
"num_input_tokens_seen": 8570128,
|
| 1462 |
+
"step": 700,
|
| 1463 |
+
"train_runtime": 3380.7711,
|
| 1464 |
+
"train_tokens_per_second": 2534.963
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 3.1824401368301025,
|
| 1468 |
+
"eval_loss": 0.23035594820976257,
|
| 1469 |
+
"eval_runtime": 32.2504,
|
| 1470 |
+
"eval_samples_per_second": 96.681,
|
| 1471 |
+
"eval_steps_per_second": 6.046,
|
| 1472 |
"num_input_tokens_seen": 8570128,
|
| 1473 |
"step": 700
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 3.2052451539338653,
|
| 1477 |
+
"grad_norm": 0.3519875705242157,
|
| 1478 |
+
"learning_rate": 3.133934480154885e-05,
|
| 1479 |
+
"loss": 0.1474,
|
| 1480 |
"num_input_tokens_seen": 8631952,
|
| 1481 |
+
"step": 705,
|
| 1482 |
+
"train_runtime": 3435.8884,
|
| 1483 |
+
"train_tokens_per_second": 2512.291
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 3.228050171037628,
|
| 1487 |
+
"grad_norm": 0.2907137870788574,
|
| 1488 |
+
"learning_rate": 2.9644308677943313e-05,
|
| 1489 |
+
"loss": 0.1453,
|
| 1490 |
"num_input_tokens_seen": 8694032,
|
| 1491 |
+
"step": 710,
|
| 1492 |
+
"train_runtime": 3458.7963,
|
| 1493 |
+
"train_tokens_per_second": 2513.6
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
"epoch": 3.250855188141391,
|
| 1497 |
+
"grad_norm": 0.4542185962200165,
|
| 1498 |
+
"learning_rate": 2.7991358312770805e-05,
|
| 1499 |
+
"loss": 0.1379,
|
| 1500 |
"num_input_tokens_seen": 8754576,
|
| 1501 |
+
"step": 715,
|
| 1502 |
+
"train_runtime": 3481.3102,
|
| 1503 |
+
"train_tokens_per_second": 2514.736
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
"epoch": 3.2736602052451538,
|
| 1507 |
+
"grad_norm": 0.3293727934360504,
|
| 1508 |
+
"learning_rate": 2.6381071706697644e-05,
|
| 1509 |
+
"loss": 0.1441,
|
| 1510 |
"num_input_tokens_seen": 8816528,
|
| 1511 |
+
"step": 720,
|
| 1512 |
+
"train_runtime": 3504.3181,
|
| 1513 |
+
"train_tokens_per_second": 2515.904
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 3.2964652223489166,
|
| 1517 |
+
"grad_norm": 0.3290797173976898,
|
| 1518 |
+
"learning_rate": 2.48140119418046e-05,
|
| 1519 |
+
"loss": 0.1442,
|
| 1520 |
"num_input_tokens_seen": 8877200,
|
| 1521 |
+
"step": 725,
|
| 1522 |
+
"train_runtime": 3526.8441,
|
| 1523 |
+
"train_tokens_per_second": 2517.038
|
| 1524 |
},
|
| 1525 |
{
|
| 1526 |
"epoch": 3.3192702394526794,
|
| 1527 |
+
"grad_norm": 0.313092976808548,
|
| 1528 |
+
"learning_rate": 2.329072698468963e-05,
|
| 1529 |
+
"loss": 0.139,
|
| 1530 |
"num_input_tokens_seen": 8938512,
|
| 1531 |
+
"step": 730,
|
| 1532 |
+
"train_runtime": 3549.5232,
|
| 1533 |
+
"train_tokens_per_second": 2518.229
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 3.342075256556442,
|
| 1537 |
+
"grad_norm": 0.28016939759254456,
|
| 1538 |
+
"learning_rate": 2.1811749494855778e-05,
|
| 1539 |
+
"loss": 0.1429,
|
| 1540 |
"num_input_tokens_seen": 9000464,
|
| 1541 |
+
"step": 735,
|
| 1542 |
+
"train_runtime": 3572.5169,
|
| 1543 |
+
"train_tokens_per_second": 2519.362
|
| 1544 |
},
|
| 1545 |
{
|
| 1546 |
"epoch": 3.364880273660205,
|
| 1547 |
+
"grad_norm": 0.3928128480911255,
|
| 1548 |
+
"learning_rate": 2.037759663845181e-05,
|
| 1549 |
+
"loss": 0.1452,
|
| 1550 |
"num_input_tokens_seen": 9061648,
|
| 1551 |
+
"step": 740,
|
| 1552 |
+
"train_runtime": 3595.1996,
|
| 1553 |
+
"train_tokens_per_second": 2520.485
|
| 1554 |
},
|
| 1555 |
{
|
| 1556 |
"epoch": 3.387685290763968,
|
| 1557 |
+
"grad_norm": 0.3684266209602356,
|
| 1558 |
+
"learning_rate": 1.8988769907430552e-05,
|
| 1559 |
+
"loss": 0.1392,
|
| 1560 |
"num_input_tokens_seen": 9122704,
|
| 1561 |
+
"step": 745,
|
| 1562 |
+
"train_runtime": 3617.8228,
|
| 1563 |
+
"train_tokens_per_second": 2521.601
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 3.4104903078677307,
|
| 1567 |
+
"grad_norm": 0.35439157485961914,
|
| 1568 |
+
"learning_rate": 1.7645754944187983e-05,
|
| 1569 |
+
"loss": 0.1408,
|
| 1570 |
"num_input_tokens_seen": 9183504,
|
| 1571 |
+
"step": 750,
|
| 1572 |
+
"train_runtime": 3640.3859,
|
| 1573 |
+
"train_tokens_per_second": 2522.673
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
"epoch": 3.433295324971494,
|
| 1577 |
+
"grad_norm": 0.3279169797897339,
|
| 1578 |
+
"learning_rate": 1.634902137174483e-05,
|
| 1579 |
+
"loss": 0.1406,
|
| 1580 |
"num_input_tokens_seen": 9245072,
|
| 1581 |
+
"step": 755,
|
| 1582 |
+
"train_runtime": 3663.2554,
|
| 1583 |
+
"train_tokens_per_second": 2523.731
|
| 1584 |
},
|
| 1585 |
{
|
| 1586 |
"epoch": 3.4561003420752567,
|
| 1587 |
+
"grad_norm": 0.35586997866630554,
|
| 1588 |
+
"learning_rate": 1.5099022629529495e-05,
|
| 1589 |
+
"loss": 0.1395,
|
| 1590 |
"num_input_tokens_seen": 9307152,
|
| 1591 |
+
"step": 760,
|
| 1592 |
+
"train_runtime": 3686.2342,
|
| 1593 |
+
"train_tokens_per_second": 2524.84
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 3.4789053591790196,
|
| 1597 |
+
"grad_norm": 0.35383179783821106,
|
| 1598 |
+
"learning_rate": 1.3896195814820266e-05,
|
| 1599 |
+
"loss": 0.137,
|
| 1600 |
"num_input_tokens_seen": 9369616,
|
| 1601 |
+
"step": 765,
|
| 1602 |
+
"train_runtime": 3709.241,
|
| 1603 |
+
"train_tokens_per_second": 2526.02
|
| 1604 |
},
|
| 1605 |
{
|
| 1606 |
"epoch": 3.5017103762827824,
|
| 1607 |
+
"grad_norm": 0.32018619775772095,
|
| 1608 |
+
"learning_rate": 1.2740961529902027e-05,
|
| 1609 |
+
"loss": 0.1337,
|
| 1610 |
"num_input_tokens_seen": 9431568,
|
| 1611 |
+
"step": 770,
|
| 1612 |
+
"train_runtime": 3732.2242,
|
| 1613 |
+
"train_tokens_per_second": 2527.064
|
| 1614 |
},
|
| 1615 |
{
|
| 1616 |
"epoch": 3.524515393386545,
|
| 1617 |
+
"grad_norm": 0.3486245274543762,
|
| 1618 |
+
"learning_rate": 1.1633723734990624e-05,
|
| 1619 |
+
"loss": 0.1384,
|
| 1620 |
"num_input_tokens_seen": 9493264,
|
| 1621 |
+
"step": 775,
|
| 1622 |
+
"train_runtime": 3754.9747,
|
| 1623 |
+
"train_tokens_per_second": 2528.183
|
| 1624 |
},
|
| 1625 |
{
|
| 1626 |
"epoch": 3.547320410490308,
|
| 1627 |
+
"grad_norm": 0.3063414394855499,
|
| 1628 |
+
"learning_rate": 1.0574869606976888e-05,
|
| 1629 |
+
"loss": 0.1345,
|
| 1630 |
"num_input_tokens_seen": 9554448,
|
| 1631 |
+
"step": 780,
|
| 1632 |
+
"train_runtime": 3777.6485,
|
| 1633 |
+
"train_tokens_per_second": 2529.205
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
"epoch": 3.570125427594071,
|
| 1637 |
+
"grad_norm": 0.38662609457969666,
|
| 1638 |
+
"learning_rate": 9.564769404039419e-06,
|
| 1639 |
+
"loss": 0.1368,
|
| 1640 |
"num_input_tokens_seen": 9615760,
|
| 1641 |
+
"step": 785,
|
| 1642 |
+
"train_runtime": 3800.381,
|
| 1643 |
+
"train_tokens_per_second": 2530.209
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 3.5929304446978336,
|
| 1647 |
+
"grad_norm": 0.3517778813838959,
|
| 1648 |
+
"learning_rate": 8.603776336173235e-06,
|
| 1649 |
+
"loss": 0.1452,
|
| 1650 |
"num_input_tokens_seen": 9678608,
|
| 1651 |
+
"step": 790,
|
| 1652 |
+
"train_runtime": 3823.5086,
|
| 1653 |
+
"train_tokens_per_second": 2531.342
|
| 1654 |
},
|
| 1655 |
{
|
| 1656 |
"epoch": 3.6157354618015964,
|
| 1657 |
+
"grad_norm": 0.40929150581359863,
|
| 1658 |
+
"learning_rate": 7.692226441680038e-06,
|
| 1659 |
+
"loss": 0.1413,
|
| 1660 |
"num_input_tokens_seen": 9740304,
|
| 1661 |
+
"step": 795,
|
| 1662 |
+
"train_runtime": 3846.3369,
|
| 1663 |
+
"train_tokens_per_second": 2532.359
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
"epoch": 3.6385404789053593,
|
| 1667 |
+
"grad_norm": 0.4051925837993622,
|
| 1668 |
+
"learning_rate": 6.830438469662891e-06,
|
| 1669 |
+
"loss": 0.1356,
|
| 1670 |
"num_input_tokens_seen": 9801744,
|
| 1671 |
+
"step": 800,
|
| 1672 |
+
"train_runtime": 3869.0646,
|
| 1673 |
+
"train_tokens_per_second": 2533.363
|
| 1674 |
},
|
| 1675 |
{
|
| 1676 |
"epoch": 3.6385404789053593,
|
| 1677 |
+
"eval_loss": 0.22199535369873047,
|
| 1678 |
+
"eval_runtime": 32.2759,
|
| 1679 |
+
"eval_samples_per_second": 96.604,
|
| 1680 |
+
"eval_steps_per_second": 6.042,
|
| 1681 |
"num_input_tokens_seen": 9801744,
|
| 1682 |
"step": 800
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 3.661345496009122,
|
| 1686 |
+
"grad_norm": 0.4790637195110321,
|
| 1687 |
+
"learning_rate": 6.018713768566658e-06,
|
| 1688 |
+
"loss": 0.1355,
|
| 1689 |
"num_input_tokens_seen": 9862928,
|
| 1690 |
+
"step": 805,
|
| 1691 |
+
"train_runtime": 3924.1012,
|
| 1692 |
+
"train_tokens_per_second": 2513.423
|
| 1693 |
},
|
| 1694 |
{
|
| 1695 |
"epoch": 3.684150513112885,
|
| 1696 |
+
"grad_norm": 0.3185409903526306,
|
| 1697 |
+
"learning_rate": 5.257336180803029e-06,
|
| 1698 |
+
"loss": 0.1376,
|
| 1699 |
"num_input_tokens_seen": 9924112,
|
| 1700 |
+
"step": 810,
|
| 1701 |
+
"train_runtime": 3946.8024,
|
| 1702 |
+
"train_tokens_per_second": 2514.469
|
| 1703 |
},
|
| 1704 |
{
|
| 1705 |
"epoch": 3.7069555302166477,
|
| 1706 |
+
"grad_norm": 0.36550357937812805,
|
| 1707 |
+
"learning_rate": 4.546571943496968e-06,
|
| 1708 |
+
"loss": 0.1303,
|
| 1709 |
"num_input_tokens_seen": 9984784,
|
| 1710 |
+
"step": 815,
|
| 1711 |
+
"train_runtime": 3969.4002,
|
| 1712 |
+
"train_tokens_per_second": 2515.439
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 3.7297605473204105,
|
| 1716 |
+
"grad_norm": 0.3187613785266876,
|
| 1717 |
+
"learning_rate": 3.88666959538953e-06,
|
| 1718 |
+
"loss": 0.1405,
|
| 1719 |
"num_input_tokens_seen": 10046736,
|
| 1720 |
+
"step": 820,
|
| 1721 |
+
"train_runtime": 3992.2692,
|
| 1722 |
+
"train_tokens_per_second": 2516.548
|
| 1723 |
},
|
| 1724 |
{
|
| 1725 |
"epoch": 3.7525655644241733,
|
| 1726 |
+
"grad_norm": 0.3294983208179474,
|
| 1727 |
+
"learning_rate": 3.2778598899291465e-06,
|
| 1728 |
+
"loss": 0.132,
|
| 1729 |
"num_input_tokens_seen": 10108176,
|
| 1730 |
+
"step": 825,
|
| 1731 |
+
"train_runtime": 4015.0234,
|
| 1732 |
+
"train_tokens_per_second": 2517.588
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 3.775370581527936,
|
| 1736 |
+
"grad_norm": 0.32192060351371765,
|
| 1737 |
+
"learning_rate": 2.7203557145822398e-06,
|
| 1738 |
+
"loss": 0.1326,
|
| 1739 |
"num_input_tokens_seen": 10169744,
|
| 1740 |
+
"step": 830,
|
| 1741 |
+
"train_runtime": 4037.9551,
|
| 1742 |
+
"train_tokens_per_second": 2518.538
|
| 1743 |
},
|
| 1744 |
{
|
| 1745 |
"epoch": 3.798175598631699,
|
| 1746 |
+
"grad_norm": 0.35039815306663513,
|
| 1747 |
+
"learning_rate": 2.2143520163911187e-06,
|
| 1748 |
+
"loss": 0.1268,
|
| 1749 |
"num_input_tokens_seen": 10231696,
|
| 1750 |
+
"step": 835,
|
| 1751 |
+
"train_runtime": 4060.8327,
|
| 1752 |
+
"train_tokens_per_second": 2519.605
|
| 1753 |
},
|
| 1754 |
{
|
| 1755 |
"epoch": 3.8209806157354618,
|
| 1756 |
+
"grad_norm": 0.3158867359161377,
|
| 1757 |
+
"learning_rate": 1.7600257338052593e-06,
|
| 1758 |
+
"loss": 0.1341,
|
| 1759 |
"num_input_tokens_seen": 10292624,
|
| 1760 |
+
"step": 840,
|
| 1761 |
+
"train_runtime": 4083.4905,
|
| 1762 |
+
"train_tokens_per_second": 2520.546
|
| 1763 |
},
|
| 1764 |
{
|
| 1765 |
"epoch": 3.8437856328392246,
|
| 1766 |
+
"grad_norm": 0.3523620367050171,
|
| 1767 |
+
"learning_rate": 1.3575357348097948e-06,
|
| 1768 |
+
"loss": 0.1366,
|
| 1769 |
"num_input_tokens_seen": 10353040,
|
| 1770 |
+
"step": 845,
|
| 1771 |
+
"train_runtime": 4105.9585,
|
| 1772 |
+
"train_tokens_per_second": 2521.467
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 3.8665906499429874,
|
| 1776 |
+
"grad_norm": 0.34996289014816284,
|
| 1777 |
+
"learning_rate": 1.0070227613728221e-06,
|
| 1778 |
+
"loss": 0.1317,
|
| 1779 |
"num_input_tokens_seen": 10414480,
|
| 1780 |
+
"step": 850,
|
| 1781 |
+
"train_runtime": 4128.7438,
|
| 1782 |
+
"train_tokens_per_second": 2522.433
|
| 1783 |
},
|
| 1784 |
{
|
| 1785 |
"epoch": 3.88939566704675,
|
| 1786 |
+
"grad_norm": 0.36095747351646423,
|
| 1787 |
+
"learning_rate": 7.086093802310344e-07,
|
| 1788 |
+
"loss": 0.1312,
|
| 1789 |
"num_input_tokens_seen": 10476432,
|
| 1790 |
+
"step": 855,
|
| 1791 |
+
"train_runtime": 4151.8485,
|
| 1792 |
+
"train_tokens_per_second": 2523.317
|
| 1793 |
},
|
| 1794 |
{
|
| 1795 |
"epoch": 3.912200684150513,
|
| 1796 |
+
"grad_norm": 0.32904523611068726,
|
| 1797 |
+
"learning_rate": 4.623999400308054e-07,
|
| 1798 |
+
"loss": 0.1286,
|
| 1799 |
"num_input_tokens_seen": 10538128,
|
| 1800 |
+
"step": 860,
|
| 1801 |
+
"train_runtime": 4174.6954,
|
| 1802 |
+
"train_tokens_per_second": 2524.287
|
| 1803 |
},
|
| 1804 |
{
|
| 1805 |
"epoch": 3.935005701254276,
|
| 1806 |
+
"grad_norm": 0.31018680334091187,
|
| 1807 |
+
"learning_rate": 2.6848053483972677e-07,
|
| 1808 |
+
"loss": 0.1279,
|
| 1809 |
"num_input_tokens_seen": 10600080,
|
| 1810 |
+
"step": 865,
|
| 1811 |
+
"train_runtime": 4197.5751,
|
| 1812 |
+
"train_tokens_per_second": 2525.287
|
| 1813 |
},
|
| 1814 |
{
|
| 1815 |
"epoch": 3.9578107183580387,
|
| 1816 |
+
"grad_norm": 0.360738605260849,
|
| 1817 |
+
"learning_rate": 1.2691897404140671e-07,
|
| 1818 |
+
"loss": 0.1374,
|
| 1819 |
"num_input_tokens_seen": 10660752,
|
| 1820 |
+
"step": 870,
|
| 1821 |
+
"train_runtime": 4220.1428,
|
| 1822 |
+
"train_tokens_per_second": 2526.159
|
| 1823 |
},
|
| 1824 |
{
|
| 1825 |
"epoch": 3.9806157354618015,
|
| 1826 |
+
"grad_norm": 0.38618308305740356,
|
| 1827 |
+
"learning_rate": 3.77647586240204e-08,
|
| 1828 |
+
"loss": 0.1347,
|
| 1829 |
"num_input_tokens_seen": 10721680,
|
| 1830 |
+
"step": 875,
|
| 1831 |
+
"train_runtime": 4242.7093,
|
| 1832 |
+
"train_tokens_per_second": 2527.083
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 4.0,
|
| 1836 |
+
"grad_norm": 0.6333906650543213,
|
| 1837 |
+
"learning_rate": 1.0490638708393616e-09,
|
| 1838 |
+
"loss": 0.1323,
|
| 1839 |
+
"num_input_tokens_seen": 10772736,
|
| 1840 |
+
"step": 880,
|
| 1841 |
+
"train_runtime": 4261.7116,
|
| 1842 |
+
"train_tokens_per_second": 2527.796
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 4.0,
|
| 1846 |
+
"num_input_tokens_seen": 10772736,
|
| 1847 |
+
"step": 880,
|
| 1848 |
+
"total_flos": 4.374108802866217e+17,
|
| 1849 |
+
"train_loss": 0.3781262902373617,
|
| 1850 |
+
"train_runtime": 4269.5185,
|
| 1851 |
+
"train_samples_per_second": 26.287,
|
| 1852 |
+
"train_steps_per_second": 0.206
|
| 1853 |
}
|
| 1854 |
],
|
| 1855 |
"logging_steps": 5,
|
| 1856 |
+
"max_steps": 880,
|
| 1857 |
+
"num_input_tokens_seen": 10772736,
|
| 1858 |
"num_train_epochs": 4,
|
| 1859 |
+
"save_steps": 500,
|
| 1860 |
"stateful_callbacks": {
|
| 1861 |
"TrainerControl": {
|
| 1862 |
"args": {
|
|
|
|
| 1869 |
"attributes": {}
|
| 1870 |
}
|
| 1871 |
},
|
| 1872 |
+
"total_flos": 4.374108802866217e+17,
|
| 1873 |
"train_batch_size": 16,
|
| 1874 |
"trial_name": null,
|
| 1875 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0425f47b47b9ab105b7c8824afc016e2251bd80d7cab8bc3f99c37fc0ad556d0
|
| 3 |
+
size 5688
|
training_eval_loss.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
training_loss.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|