Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +61 -0
- added_tokens.json +24 -0
- all_results.json +12 -0
- config.json +29 -0
- eval_results.json +7 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- train_results.json +8 -0
- trainer_log.jsonl +127 -0
- trainer_state.json +924 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Lean_Code_data
|
| 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 |
+
# Lean_Code_data
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the Lean_Code_data dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2902
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- total_eval_batch_size: 4
|
| 48 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- num_epochs: 2
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.46.1
|
| 59 |
+
- Pytorch 2.6.0+cu124
|
| 60 |
+
- Datasets 3.1.0
|
| 61 |
+
- Tokenizers 0.20.3
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.29015305638313293,
|
| 4 |
+
"eval_runtime": 0.3427,
|
| 5 |
+
"eval_samples_per_second": 17.51,
|
| 6 |
+
"eval_steps_per_second": 5.837,
|
| 7 |
+
"total_flos": 1772529647616.0,
|
| 8 |
+
"train_loss": 0.2918981748913962,
|
| 9 |
+
"train_runtime": 115.6265,
|
| 10 |
+
"train_samples_per_second": 8.683,
|
| 11 |
+
"train_steps_per_second": 1.09
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 14,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.46.1",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 151936
|
| 29 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.29015305638313293,
|
| 4 |
+
"eval_runtime": 0.3427,
|
| 5 |
+
"eval_samples_per_second": 17.51,
|
| 6 |
+
"eval_steps_per_second": 5.837
|
| 7 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.46.1"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67b938323820d069bf2cb11b66b531e0b9143fdd86f0e689d1de4c6f21a83e2f
|
| 3 |
+
size 988097824
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{% 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' %}{{ '<｜User｜>' + content + '<｜Assistant｜>' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' }}{% endif %}{% endfor %}",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"padding_side": "right",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1772529647616.0,
|
| 4 |
+
"train_loss": 0.2918981748913962,
|
| 5 |
+
"train_runtime": 115.6265,
|
| 6 |
+
"train_samples_per_second": 8.683,
|
| 7 |
+
"train_steps_per_second": 1.09
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 126, "loss": 1.2293, "lr": 9.998445910004082e-06, "epoch": 0.015873015873015872, "percentage": 0.79, "elapsed_time": "0:00:02", "remaining_time": "0:04:17"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 126, "loss": 0.8742, "lr": 9.993784606094612e-06, "epoch": 0.031746031746031744, "percentage": 1.59, "elapsed_time": "0:00:06", "remaining_time": "0:06:46"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 126, "loss": 0.6603, "lr": 9.986018985905901e-06, "epoch": 0.047619047619047616, "percentage": 2.38, "elapsed_time": "0:00:07", "remaining_time": "0:05:03"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 126, "loss": 0.6402, "lr": 9.975153876827008e-06, "epoch": 0.06349206349206349, "percentage": 3.17, "elapsed_time": "0:00:08", "remaining_time": "0:04:12"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 126, "loss": 0.5669, "lr": 9.961196033000862e-06, "epoch": 0.07936507936507936, "percentage": 3.97, "elapsed_time": "0:00:09", "remaining_time": "0:03:40"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 126, "loss": 0.4859, "lr": 9.944154131125643e-06, "epoch": 0.09523809523809523, "percentage": 4.76, "elapsed_time": "0:00:09", "remaining_time": "0:03:19"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 126, "loss": 0.4665, "lr": 9.924038765061042e-06, "epoch": 0.1111111111111111, "percentage": 5.56, "elapsed_time": "0:00:10", "remaining_time": "0:03:03"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 126, "loss": 0.4592, "lr": 9.900862439242719e-06, "epoch": 0.12698412698412698, "percentage": 6.35, "elapsed_time": "0:00:11", "remaining_time": "0:02:52"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 126, "loss": 0.4289, "lr": 9.874639560909118e-06, "epoch": 0.14285714285714285, "percentage": 7.14, "elapsed_time": "0:00:12", "remaining_time": "0:02:42"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 126, "loss": 0.4375, "lr": 9.84538643114539e-06, "epoch": 0.15873015873015872, "percentage": 7.94, "elapsed_time": "0:00:13", "remaining_time": "0:02:35"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 126, "loss": 0.4332, "lr": 9.81312123475006e-06, "epoch": 0.1746031746031746, "percentage": 8.73, "elapsed_time": "0:00:14", "remaining_time": "0:02:28"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 126, "loss": 0.3862, "lr": 9.777864028930705e-06, "epoch": 0.19047619047619047, "percentage": 9.52, "elapsed_time": "0:00:15", "remaining_time": "0:02:23"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 126, "loss": 0.3375, "lr": 9.73963673083566e-06, "epoch": 0.20634920634920634, "percentage": 10.32, "elapsed_time": "0:00:15", "remaining_time": "0:02:18"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 126, "loss": 0.3209, "lr": 9.698463103929542e-06, "epoch": 0.2222222222222222, "percentage": 11.11, "elapsed_time": "0:00:16", "remaining_time": "0:02:14"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 126, "loss": 0.3352, "lr": 9.654368743221022e-06, "epoch": 0.23809523809523808, "percentage": 11.9, "elapsed_time": "0:00:17", "remaining_time": "0:02:10"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 126, "loss": 0.324, "lr": 9.60738105935204e-06, "epoch": 0.25396825396825395, "percentage": 12.7, "elapsed_time": "0:00:18", "remaining_time": "0:02:06"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 126, "loss": 0.3292, "lr": 9.557529261558367e-06, "epoch": 0.2698412698412698, "percentage": 13.49, "elapsed_time": "0:00:19", "remaining_time": "0:02:03"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 126, "loss": 0.3404, "lr": 9.504844339512096e-06, "epoch": 0.2857142857142857, "percentage": 14.29, "elapsed_time": "0:00:20", "remaining_time": "0:02:00"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 126, "loss": 0.3416, "lr": 9.449359044057344e-06, "epoch": 0.30158730158730157, "percentage": 15.08, "elapsed_time": "0:00:20", "remaining_time": "0:01:58"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 126, "loss": 0.3283, "lr": 9.391107866851143e-06, "epoch": 0.31746031746031744, "percentage": 15.87, "elapsed_time": "0:00:21", "remaining_time": "0:01:55"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 126, "loss": 0.3065, "lr": 9.330127018922195e-06, "epoch": 0.3333333333333333, "percentage": 16.67, "elapsed_time": "0:00:22", "remaining_time": "0:01:53"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 126, "loss": 0.3898, "lr": 9.266454408160779e-06, "epoch": 0.3492063492063492, "percentage": 17.46, "elapsed_time": "0:00:23", "remaining_time": "0:01:51"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 126, "loss": 0.3566, "lr": 9.200129615753858e-06, "epoch": 0.36507936507936506, "percentage": 18.25, "elapsed_time": "0:00:24", "remaining_time": "0:01:49"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 126, "loss": 0.3397, "lr": 9.131193871579975e-06, "epoch": 0.38095238095238093, "percentage": 19.05, "elapsed_time": "0:00:25", "remaining_time": "0:01:47"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 126, "loss": 0.3146, "lr": 9.059690028579285e-06, "epoch": 0.3968253968253968, "percentage": 19.84, "elapsed_time": "0:00:26", "remaining_time": "0:01:45"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 126, "loss": 0.326, "lr": 8.985662536114614e-06, "epoch": 0.4126984126984127, "percentage": 20.63, "elapsed_time": "0:00:26", "remaining_time": "0:01:43"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 126, "loss": 0.3561, "lr": 8.90915741234015e-06, "epoch": 0.42857142857142855, "percentage": 21.43, "elapsed_time": "0:00:27", "remaining_time": "0:01:41"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 126, "loss": 0.2896, "lr": 8.83022221559489e-06, "epoch": 0.4444444444444444, "percentage": 22.22, "elapsed_time": "0:00:28", "remaining_time": "0:01:40"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 126, "loss": 0.3481, "lr": 8.748906014838672e-06, "epoch": 0.4603174603174603, "percentage": 23.02, "elapsed_time": "0:00:29", "remaining_time": "0:01:38"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 126, "loss": 0.3038, "lr": 8.665259359149132e-06, "epoch": 0.47619047619047616, "percentage": 23.81, "elapsed_time": "0:00:30", "remaining_time": "0:01:37"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 126, "loss": 0.2826, "lr": 8.579334246298593e-06, "epoch": 0.49206349206349204, "percentage": 24.6, "elapsed_time": "0:00:31", "remaining_time": "0:01:35"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 126, "loss": 0.2615, "lr": 8.491184090430365e-06, "epoch": 0.5079365079365079, "percentage": 25.4, "elapsed_time": "0:00:32", "remaining_time": "0:01:34"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 126, "loss": 0.2967, "lr": 8.400863688854598e-06, "epoch": 0.5238095238095238, "percentage": 26.19, "elapsed_time": "0:00:32", "remaining_time": "0:01:32"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 126, "loss": 0.2952, "lr": 8.308429187984298e-06, "epoch": 0.5396825396825397, "percentage": 26.98, "elapsed_time": "0:00:33", "remaining_time": "0:01:31"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 126, "loss": 0.3372, "lr": 8.213938048432697e-06, "epoch": 0.5555555555555556, "percentage": 27.78, "elapsed_time": "0:00:34", "remaining_time": "0:01:29"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 126, "loss": 0.3404, "lr": 8.117449009293668e-06, "epoch": 0.5714285714285714, "percentage": 28.57, "elapsed_time": "0:00:35", "remaining_time": "0:01:28"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 126, "loss": 0.2965, "lr": 8.019022051627387e-06, "epoch": 0.5873015873015873, "percentage": 29.37, "elapsed_time": "0:00:36", "remaining_time": "0:01:27"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 126, "loss": 0.3163, "lr": 7.918718361173951e-06, "epoch": 0.6031746031746031, "percentage": 30.16, "elapsed_time": "0:00:37", "remaining_time": "0:01:25"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 126, "loss": 0.3218, "lr": 7.81660029031811e-06, "epoch": 0.6190476190476191, "percentage": 30.95, "elapsed_time": "0:00:37", "remaining_time": "0:01:24"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 126, "loss": 0.2527, "lr": 7.712731319328798e-06, "epoch": 0.6349206349206349, "percentage": 31.75, "elapsed_time": "0:00:38", "remaining_time": "0:01:23"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 126, "loss": 0.3232, "lr": 7.607176016897491e-06, "epoch": 0.6507936507936508, "percentage": 32.54, "elapsed_time": "0:00:39", "remaining_time": "0:01:22"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 126, "loss": 0.367, "lr": 7.500000000000001e-06, "epoch": 0.6666666666666666, "percentage": 33.33, "elapsed_time": "0:00:40", "remaining_time": "0:01:20"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 126, "loss": 0.3094, "lr": 7.391269893106592e-06, "epoch": 0.6825396825396826, "percentage": 34.13, "elapsed_time": "0:00:41", "remaining_time": "0:01:19"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 126, "loss": 0.282, "lr": 7.281053286765816e-06, "epoch": 0.6984126984126984, "percentage": 34.92, "elapsed_time": "0:00:42", "remaining_time": "0:01:18"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 126, "loss": 0.287, "lr": 7.169418695587791e-06, "epoch": 0.7142857142857143, "percentage": 35.71, "elapsed_time": "0:00:43", "remaining_time": "0:01:17"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 126, "loss": 0.3016, "lr": 7.056435515653059e-06, "epoch": 0.7301587301587301, "percentage": 36.51, "elapsed_time": "0:00:43", "remaining_time": "0:01:16"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 126, "loss": 0.2765, "lr": 6.942173981373474e-06, "epoch": 0.746031746031746, "percentage": 37.3, "elapsed_time": "0:00:44", "remaining_time": "0:01:15"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 126, "loss": 0.2532, "lr": 6.8267051218319766e-06, "epoch": 0.7619047619047619, "percentage": 38.1, "elapsed_time": "0:00:45", "remaining_time": "0:01:14"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 126, "loss": 0.2892, "lr": 6.710100716628345e-06, "epoch": 0.7777777777777778, "percentage": 38.89, "elapsed_time": "0:00:46", "remaining_time": "0:01:12"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 126, "loss": 0.3301, "lr": 6.592433251258423e-06, "epoch": 0.7936507936507936, "percentage": 39.68, "elapsed_time": "0:00:47", "remaining_time": "0:01:11"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 126, "loss": 0.2891, "lr": 6.473775872054522e-06, "epoch": 0.8095238095238095, "percentage": 40.48, "elapsed_time": "0:00:48", "remaining_time": "0:01:10"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 126, "loss": 0.2866, "lr": 6.354202340715027e-06, "epoch": 0.8253968253968254, "percentage": 41.27, "elapsed_time": "0:00:48", "remaining_time": "0:01:09"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 126, "loss": 0.2546, "lr": 6.233786988451468e-06, "epoch": 0.8412698412698413, "percentage": 42.06, "elapsed_time": "0:00:49", "remaining_time": "0:01:08"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 126, "loss": 0.263, "lr": 6.112604669781572e-06, "epoch": 0.8571428571428571, "percentage": 42.86, "elapsed_time": "0:00:50", "remaining_time": "0:01:07"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 126, "loss": 0.2519, "lr": 5.990730715996989e-06, "epoch": 0.873015873015873, "percentage": 43.65, "elapsed_time": "0:00:51", "remaining_time": "0:01:06"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 126, "loss": 0.3114, "lr": 5.8682408883346535e-06, "epoch": 0.8888888888888888, "percentage": 44.44, "elapsed_time": "0:00:52", "remaining_time": "0:01:05"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 126, "loss": 0.2611, "lr": 5.745211330880872e-06, "epoch": 0.9047619047619048, "percentage": 45.24, "elapsed_time": "0:00:53", "remaining_time": "0:01:04"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 126, "loss": 0.2749, "lr": 5.621718523237427e-06, "epoch": 0.9206349206349206, "percentage": 46.03, "elapsed_time": "0:00:54", "remaining_time": "0:01:03"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 126, "loss": 0.2395, "lr": 5.497839232979084e-06, "epoch": 0.9365079365079365, "percentage": 46.83, "elapsed_time": "0:00:54", "remaining_time": "0:01:02"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 126, "loss": 0.2893, "lr": 5.373650467932122e-06, "epoch": 0.9523809523809523, "percentage": 47.62, "elapsed_time": "0:00:55", "remaining_time": "0:01:01"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 126, "loss": 0.2465, "lr": 5.249229428303486e-06, "epoch": 0.9682539682539683, "percentage": 48.41, "elapsed_time": "0:00:56", "remaining_time": "0:01:00"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 126, "loss": 0.2895, "lr": 5.1246534586903655e-06, "epoch": 0.9841269841269841, "percentage": 49.21, "elapsed_time": "0:00:57", "remaining_time": "0:00:59"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 126, "loss": 0.2725, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:00:58", "remaining_time": "0:00:58"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 126, "loss": 0.2332, "lr": 4.875346541309637e-06, "epoch": 1.0158730158730158, "percentage": 50.79, "elapsed_time": "0:00:59", "remaining_time": "0:00:57"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 126, "loss": 0.2586, "lr": 4.750770571696514e-06, "epoch": 1.0317460317460316, "percentage": 51.59, "elapsed_time": "0:00:59", "remaining_time": "0:00:56"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 126, "loss": 0.2542, "lr": 4.626349532067879e-06, "epoch": 1.0476190476190477, "percentage": 52.38, "elapsed_time": "0:01:00", "remaining_time": "0:00:55"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 126, "loss": 0.2526, "lr": 4.502160767020918e-06, "epoch": 1.0634920634920635, "percentage": 53.17, "elapsed_time": "0:01:01", "remaining_time": "0:00:54"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 126, "loss": 0.2305, "lr": 4.3782814767625755e-06, "epoch": 1.0793650793650793, "percentage": 53.97, "elapsed_time": "0:01:02", "remaining_time": "0:00:53"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 126, "loss": 0.2713, "lr": 4.254788669119127e-06, "epoch": 1.0952380952380953, "percentage": 54.76, "elapsed_time": "0:01:03", "remaining_time": "0:00:52"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 126, "loss": 0.2382, "lr": 4.131759111665349e-06, "epoch": 1.1111111111111112, "percentage": 55.56, "elapsed_time": "0:01:04", "remaining_time": "0:00:51"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 126, "loss": 0.226, "lr": 4.009269284003014e-06, "epoch": 1.126984126984127, "percentage": 56.35, "elapsed_time": "0:01:05", "remaining_time": "0:00:50"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 126, "loss": 0.2289, "lr": 3.887395330218429e-06, "epoch": 1.1428571428571428, "percentage": 57.14, "elapsed_time": "0:01:05", "remaining_time": "0:00:49"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 126, "loss": 0.2873, "lr": 3.7662130115485317e-06, "epoch": 1.1587301587301586, "percentage": 57.94, "elapsed_time": "0:01:06", "remaining_time": "0:00:48"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 126, "loss": 0.1974, "lr": 3.6457976592849753e-06, "epoch": 1.1746031746031746, "percentage": 58.73, "elapsed_time": "0:01:07", "remaining_time": "0:00:47"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 126, "loss": 0.2013, "lr": 3.526224127945479e-06, "epoch": 1.1904761904761905, "percentage": 59.52, "elapsed_time": "0:01:08", "remaining_time": "0:00:46"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 126, "loss": 0.2257, "lr": 3.4075667487415785e-06, "epoch": 1.2063492063492063, "percentage": 60.32, "elapsed_time": "0:01:09", "remaining_time": "0:00:45"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 126, "loss": 0.2389, "lr": 3.289899283371657e-06, "epoch": 1.2222222222222223, "percentage": 61.11, "elapsed_time": "0:01:10", "remaining_time": "0:00:44"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 126, "loss": 0.2207, "lr": 3.173294878168025e-06, "epoch": 1.2380952380952381, "percentage": 61.9, "elapsed_time": "0:01:10", "remaining_time": "0:00:43"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 126, "loss": 0.2409, "lr": 3.057826018626527e-06, "epoch": 1.253968253968254, "percentage": 62.7, "elapsed_time": "0:01:11", "remaining_time": "0:00:42"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 126, "loss": 0.2361, "lr": 2.9435644843469434e-06, "epoch": 1.2698412698412698, "percentage": 63.49, "elapsed_time": "0:01:12", "remaining_time": "0:00:41"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 126, "loss": 0.2051, "lr": 2.83058130441221e-06, "epoch": 1.2857142857142856, "percentage": 64.29, "elapsed_time": "0:01:13", "remaining_time": "0:00:40"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 126, "loss": 0.2213, "lr": 2.718946713234185e-06, "epoch": 1.3015873015873016, "percentage": 65.08, "elapsed_time": "0:01:14", "remaining_time": "0:00:39"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 126, "loss": 0.2505, "lr": 2.608730106893411e-06, "epoch": 1.3174603174603174, "percentage": 65.87, "elapsed_time": "0:01:15", "remaining_time": "0:00:38"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 126, "loss": 0.2077, "lr": 2.5000000000000015e-06, "epoch": 1.3333333333333333, "percentage": 66.67, "elapsed_time": "0:01:16", "remaining_time": "0:00:38"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 126, "loss": 0.2231, "lr": 2.39282398310251e-06, "epoch": 1.3492063492063493, "percentage": 67.46, "elapsed_time": "0:01:16", "remaining_time": "0:00:37"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 126, "loss": 0.2063, "lr": 2.2872686806712037e-06, "epoch": 1.3650793650793651, "percentage": 68.25, "elapsed_time": "0:01:17", "remaining_time": "0:00:36"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 126, "loss": 0.2275, "lr": 2.1833997096818897e-06, "epoch": 1.380952380952381, "percentage": 69.05, "elapsed_time": "0:01:18", "remaining_time": "0:00:35"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 126, "loss": 0.2304, "lr": 2.081281638826052e-06, "epoch": 1.3968253968253967, "percentage": 69.84, "elapsed_time": "0:01:19", "remaining_time": "0:00:34"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 126, "loss": 0.2284, "lr": 1.980977948372612e-06, "epoch": 1.4126984126984126, "percentage": 70.63, "elapsed_time": "0:01:20", "remaining_time": "0:00:33"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 126, "loss": 0.2133, "lr": 1.8825509907063328e-06, "epoch": 1.4285714285714286, "percentage": 71.43, "elapsed_time": "0:01:21", "remaining_time": "0:00:32"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 126, "loss": 0.2344, "lr": 1.7860619515673034e-06, "epoch": 1.4444444444444444, "percentage": 72.22, "elapsed_time": "0:01:21", "remaining_time": "0:00:31"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 126, "loss": 0.2326, "lr": 1.6915708120157042e-06, "epoch": 1.4603174603174602, "percentage": 73.02, "elapsed_time": "0:01:22", "remaining_time": "0:00:30"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 126, "loss": 0.2376, "lr": 1.5991363111454023e-06, "epoch": 1.4761904761904763, "percentage": 73.81, "elapsed_time": "0:01:23", "remaining_time": "0:00:29"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 126, "loss": 0.225, "lr": 1.5088159095696365e-06, "epoch": 1.492063492063492, "percentage": 74.6, "elapsed_time": "0:01:24", "remaining_time": "0:00:28"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 126, "loss": 0.2305, "lr": 1.4206657537014078e-06, "epoch": 1.507936507936508, "percentage": 75.4, "elapsed_time": "0:01:25", "remaining_time": "0:00:27"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 126, "loss": 0.2288, "lr": 1.3347406408508695e-06, "epoch": 1.5238095238095237, "percentage": 76.19, "elapsed_time": "0:01:26", "remaining_time": "0:00:26"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 126, "loss": 0.2215, "lr": 1.2510939851613285e-06, "epoch": 1.5396825396825395, "percentage": 76.98, "elapsed_time": "0:01:27", "remaining_time": "0:00:26"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 126, "loss": 0.278, "lr": 1.1697777844051105e-06, "epoch": 1.5555555555555556, "percentage": 77.78, "elapsed_time": "0:01:27", "remaining_time": "0:00:25"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 126, "loss": 0.2287, "lr": 1.0908425876598512e-06, "epoch": 1.5714285714285714, "percentage": 78.57, "elapsed_time": "0:01:28", "remaining_time": "0:00:24"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 126, "loss": 0.2402, "lr": 1.0143374638853892e-06, "epoch": 1.5873015873015874, "percentage": 79.37, "elapsed_time": "0:01:29", "remaining_time": "0:00:23"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 126, "loss": 0.2192, "lr": 9.403099714207175e-07, "epoch": 1.6031746031746033, "percentage": 80.16, "elapsed_time": "0:01:30", "remaining_time": "0:00:22"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 126, "loss": 0.2549, "lr": 8.688061284200266e-07, "epoch": 1.619047619047619, "percentage": 80.95, "elapsed_time": "0:01:31", "remaining_time": "0:00:21"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 126, "loss": 0.2111, "lr": 7.99870384246143e-07, "epoch": 1.6349206349206349, "percentage": 81.75, "elapsed_time": "0:01:32", "remaining_time": "0:00:20"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 126, "loss": 0.2376, "lr": 7.33545591839222e-07, "epoch": 1.6507936507936507, "percentage": 82.54, "elapsed_time": "0:01:32", "remaining_time": "0:00:19"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 126, "loss": 0.2243, "lr": 6.698729810778065e-07, "epoch": 1.6666666666666665, "percentage": 83.33, "elapsed_time": "0:01:33", "remaining_time": "0:00:18"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 126, "loss": 0.2356, "lr": 6.088921331488568e-07, "epoch": 1.6825396825396826, "percentage": 84.13, "elapsed_time": "0:01:34", "remaining_time": "0:00:17"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 126, "loss": 0.2192, "lr": 5.506409559426573e-07, "epoch": 1.6984126984126984, "percentage": 84.92, "elapsed_time": "0:01:35", "remaining_time": "0:00:16"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 126, "loss": 0.2011, "lr": 4.951556604879049e-07, "epoch": 1.7142857142857144, "percentage": 85.71, "elapsed_time": "0:01:36", "remaining_time": "0:00:16"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 126, "loss": 0.1919, "lr": 4.4247073844163434e-07, "epoch": 1.7301587301587302, "percentage": 86.51, "elapsed_time": "0:01:37", "remaining_time": "0:00:15"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 126, "loss": 0.2228, "lr": 3.9261894064796136e-07, "epoch": 1.746031746031746, "percentage": 87.3, "elapsed_time": "0:01:38", "remaining_time": "0:00:14"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 126, "loss": 0.2446, "lr": 3.4563125677897936e-07, "epoch": 1.7619047619047619, "percentage": 88.1, "elapsed_time": "0:01:38", "remaining_time": "0:00:13"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 126, "loss": 0.2085, "lr": 3.015368960704584e-07, "epoch": 1.7777777777777777, "percentage": 88.89, "elapsed_time": "0:01:39", "remaining_time": "0:00:12"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 126, "loss": 0.2043, "lr": 2.6036326916434153e-07, "epoch": 1.7936507936507935, "percentage": 89.68, "elapsed_time": "0:01:40", "remaining_time": "0:00:11"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 126, "loss": 0.213, "lr": 2.2213597106929608e-07, "epoch": 1.8095238095238095, "percentage": 90.48, "elapsed_time": "0:01:41", "remaining_time": "0:00:10"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 126, "loss": 0.2136, "lr": 1.8687876524993987e-07, "epoch": 1.8253968253968254, "percentage": 91.27, "elapsed_time": "0:01:42", "remaining_time": "0:00:09"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 126, "loss": 0.2242, "lr": 1.5461356885461077e-07, "epoch": 1.8412698412698414, "percentage": 92.06, "elapsed_time": "0:01:43", "remaining_time": "0:00:08"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 126, "loss": 0.1934, "lr": 1.253604390908819e-07, "epoch": 1.8571428571428572, "percentage": 92.86, "elapsed_time": "0:01:43", "remaining_time": "0:00:07"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 126, "loss": 0.1943, "lr": 9.913756075728088e-08, "epoch": 1.873015873015873, "percentage": 93.65, "elapsed_time": "0:01:44", "remaining_time": "0:00:07"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 126, "loss": 0.2096, "lr": 7.59612349389599e-08, "epoch": 1.8888888888888888, "percentage": 94.44, "elapsed_time": "0:01:45", "remaining_time": "0:00:06"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 126, "loss": 0.207, "lr": 5.584586887435739e-08, "epoch": 1.9047619047619047, "percentage": 95.24, "elapsed_time": "0:01:46", "remaining_time": "0:00:05"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 126, "loss": 0.1845, "lr": 3.8803966999139686e-08, "epoch": 1.9206349206349205, "percentage": 96.03, "elapsed_time": "0:01:47", "remaining_time": "0:00:04"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 126, "loss": 0.2299, "lr": 2.4846123172992953e-08, "epoch": 1.9365079365079365, "percentage": 96.83, "elapsed_time": "0:01:48", "remaining_time": "0:00:03"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 126, "loss": 0.1846, "lr": 1.3981014094099354e-08, "epoch": 1.9523809523809523, "percentage": 97.62, "elapsed_time": "0:01:49", "remaining_time": "0:00:02"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 126, "loss": 0.2492, "lr": 6.215393905388278e-09, "epoch": 1.9682539682539684, "percentage": 98.41, "elapsed_time": "0:01:49", "remaining_time": "0:00:01"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 126, "loss": 0.1846, "lr": 1.5540899959187727e-09, "epoch": 1.9841269841269842, "percentage": 99.21, "elapsed_time": "0:01:50", "remaining_time": "0:00:00"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 126, "loss": 0.1976, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:01:51", "remaining_time": "0:00:00"}
|
| 127 |
+
{"current_steps": 126, "total_steps": 126, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:01:55", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,924 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 126,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015873015873015872,
|
| 13 |
+
"grad_norm": 14.136896419046405,
|
| 14 |
+
"learning_rate": 9.998445910004082e-06,
|
| 15 |
+
"loss": 1.2293,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.031746031746031744,
|
| 20 |
+
"grad_norm": 9.414916379661909,
|
| 21 |
+
"learning_rate": 9.993784606094612e-06,
|
| 22 |
+
"loss": 0.8742,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.047619047619047616,
|
| 27 |
+
"grad_norm": 7.055571354439035,
|
| 28 |
+
"learning_rate": 9.986018985905901e-06,
|
| 29 |
+
"loss": 0.6603,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06349206349206349,
|
| 34 |
+
"grad_norm": 6.0109678713542065,
|
| 35 |
+
"learning_rate": 9.975153876827008e-06,
|
| 36 |
+
"loss": 0.6402,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07936507936507936,
|
| 41 |
+
"grad_norm": 6.286672268332456,
|
| 42 |
+
"learning_rate": 9.961196033000862e-06,
|
| 43 |
+
"loss": 0.5669,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09523809523809523,
|
| 48 |
+
"grad_norm": 3.75907915574848,
|
| 49 |
+
"learning_rate": 9.944154131125643e-06,
|
| 50 |
+
"loss": 0.4859,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1111111111111111,
|
| 55 |
+
"grad_norm": 2.7783434693295717,
|
| 56 |
+
"learning_rate": 9.924038765061042e-06,
|
| 57 |
+
"loss": 0.4665,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12698412698412698,
|
| 62 |
+
"grad_norm": 3.5757346497904514,
|
| 63 |
+
"learning_rate": 9.900862439242719e-06,
|
| 64 |
+
"loss": 0.4592,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14285714285714285,
|
| 69 |
+
"grad_norm": 3.0154588649031027,
|
| 70 |
+
"learning_rate": 9.874639560909118e-06,
|
| 71 |
+
"loss": 0.4289,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.15873015873015872,
|
| 76 |
+
"grad_norm": 2.9640179533460693,
|
| 77 |
+
"learning_rate": 9.84538643114539e-06,
|
| 78 |
+
"loss": 0.4375,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1746031746031746,
|
| 83 |
+
"grad_norm": 2.4616695644526505,
|
| 84 |
+
"learning_rate": 9.81312123475006e-06,
|
| 85 |
+
"loss": 0.4332,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.19047619047619047,
|
| 90 |
+
"grad_norm": 2.2172107727937336,
|
| 91 |
+
"learning_rate": 9.777864028930705e-06,
|
| 92 |
+
"loss": 0.3862,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.20634920634920634,
|
| 97 |
+
"grad_norm": 2.0026334395442253,
|
| 98 |
+
"learning_rate": 9.73963673083566e-06,
|
| 99 |
+
"loss": 0.3375,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2222222222222222,
|
| 104 |
+
"grad_norm": 2.008975524410557,
|
| 105 |
+
"learning_rate": 9.698463103929542e-06,
|
| 106 |
+
"loss": 0.3209,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.23809523809523808,
|
| 111 |
+
"grad_norm": 2.0020308436998615,
|
| 112 |
+
"learning_rate": 9.654368743221022e-06,
|
| 113 |
+
"loss": 0.3352,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.25396825396825395,
|
| 118 |
+
"grad_norm": 1.7951748955191769,
|
| 119 |
+
"learning_rate": 9.60738105935204e-06,
|
| 120 |
+
"loss": 0.324,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2698412698412698,
|
| 125 |
+
"grad_norm": 1.9455517887105027,
|
| 126 |
+
"learning_rate": 9.557529261558367e-06,
|
| 127 |
+
"loss": 0.3292,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2857142857142857,
|
| 132 |
+
"grad_norm": 1.9655040976499933,
|
| 133 |
+
"learning_rate": 9.504844339512096e-06,
|
| 134 |
+
"loss": 0.3404,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.30158730158730157,
|
| 139 |
+
"grad_norm": 2.257691645993752,
|
| 140 |
+
"learning_rate": 9.449359044057344e-06,
|
| 141 |
+
"loss": 0.3416,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.31746031746031744,
|
| 146 |
+
"grad_norm": 1.9178041719883492,
|
| 147 |
+
"learning_rate": 9.391107866851143e-06,
|
| 148 |
+
"loss": 0.3283,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3333333333333333,
|
| 153 |
+
"grad_norm": 1.8376837225343723,
|
| 154 |
+
"learning_rate": 9.330127018922195e-06,
|
| 155 |
+
"loss": 0.3065,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3492063492063492,
|
| 160 |
+
"grad_norm": 2.255376117326017,
|
| 161 |
+
"learning_rate": 9.266454408160779e-06,
|
| 162 |
+
"loss": 0.3898,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.36507936507936506,
|
| 167 |
+
"grad_norm": 2.3147995497368017,
|
| 168 |
+
"learning_rate": 9.200129615753858e-06,
|
| 169 |
+
"loss": 0.3566,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.38095238095238093,
|
| 174 |
+
"grad_norm": 1.9670946821467294,
|
| 175 |
+
"learning_rate": 9.131193871579975e-06,
|
| 176 |
+
"loss": 0.3397,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3968253968253968,
|
| 181 |
+
"grad_norm": 1.9043148573056243,
|
| 182 |
+
"learning_rate": 9.059690028579285e-06,
|
| 183 |
+
"loss": 0.3146,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4126984126984127,
|
| 188 |
+
"grad_norm": 2.0018857432631436,
|
| 189 |
+
"learning_rate": 8.985662536114614e-06,
|
| 190 |
+
"loss": 0.326,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.42857142857142855,
|
| 195 |
+
"grad_norm": 1.9805418049960362,
|
| 196 |
+
"learning_rate": 8.90915741234015e-06,
|
| 197 |
+
"loss": 0.3561,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4444444444444444,
|
| 202 |
+
"grad_norm": 2.002055916467354,
|
| 203 |
+
"learning_rate": 8.83022221559489e-06,
|
| 204 |
+
"loss": 0.2896,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4603174603174603,
|
| 209 |
+
"grad_norm": 1.9173208879793804,
|
| 210 |
+
"learning_rate": 8.748906014838672e-06,
|
| 211 |
+
"loss": 0.3481,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.47619047619047616,
|
| 216 |
+
"grad_norm": 1.7900189098270431,
|
| 217 |
+
"learning_rate": 8.665259359149132e-06,
|
| 218 |
+
"loss": 0.3038,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.49206349206349204,
|
| 223 |
+
"grad_norm": 1.6509929161585246,
|
| 224 |
+
"learning_rate": 8.579334246298593e-06,
|
| 225 |
+
"loss": 0.2826,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5079365079365079,
|
| 230 |
+
"grad_norm": 1.671085946192089,
|
| 231 |
+
"learning_rate": 8.491184090430365e-06,
|
| 232 |
+
"loss": 0.2615,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5238095238095238,
|
| 237 |
+
"grad_norm": 1.8602137091136728,
|
| 238 |
+
"learning_rate": 8.400863688854598e-06,
|
| 239 |
+
"loss": 0.2967,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5396825396825397,
|
| 244 |
+
"grad_norm": 1.7196097127036853,
|
| 245 |
+
"learning_rate": 8.308429187984298e-06,
|
| 246 |
+
"loss": 0.2952,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5555555555555556,
|
| 251 |
+
"grad_norm": 1.931814044902892,
|
| 252 |
+
"learning_rate": 8.213938048432697e-06,
|
| 253 |
+
"loss": 0.3372,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5714285714285714,
|
| 258 |
+
"grad_norm": 2.1049189778926003,
|
| 259 |
+
"learning_rate": 8.117449009293668e-06,
|
| 260 |
+
"loss": 0.3404,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5873015873015873,
|
| 265 |
+
"grad_norm": 1.8220307585532305,
|
| 266 |
+
"learning_rate": 8.019022051627387e-06,
|
| 267 |
+
"loss": 0.2965,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6031746031746031,
|
| 272 |
+
"grad_norm": 2.1357017184024776,
|
| 273 |
+
"learning_rate": 7.918718361173951e-06,
|
| 274 |
+
"loss": 0.3163,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6190476190476191,
|
| 279 |
+
"grad_norm": 1.9302715132373918,
|
| 280 |
+
"learning_rate": 7.81660029031811e-06,
|
| 281 |
+
"loss": 0.3218,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6349206349206349,
|
| 286 |
+
"grad_norm": 1.6349542473923382,
|
| 287 |
+
"learning_rate": 7.712731319328798e-06,
|
| 288 |
+
"loss": 0.2527,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6507936507936508,
|
| 293 |
+
"grad_norm": 2.300579309285893,
|
| 294 |
+
"learning_rate": 7.607176016897491e-06,
|
| 295 |
+
"loss": 0.3232,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6666666666666666,
|
| 300 |
+
"grad_norm": 2.1075973294948263,
|
| 301 |
+
"learning_rate": 7.500000000000001e-06,
|
| 302 |
+
"loss": 0.367,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6825396825396826,
|
| 307 |
+
"grad_norm": 1.8304036968165827,
|
| 308 |
+
"learning_rate": 7.391269893106592e-06,
|
| 309 |
+
"loss": 0.3094,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6984126984126984,
|
| 314 |
+
"grad_norm": 1.9405966550411191,
|
| 315 |
+
"learning_rate": 7.281053286765816e-06,
|
| 316 |
+
"loss": 0.282,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7142857142857143,
|
| 321 |
+
"grad_norm": 1.920794107387291,
|
| 322 |
+
"learning_rate": 7.169418695587791e-06,
|
| 323 |
+
"loss": 0.287,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7301587301587301,
|
| 328 |
+
"grad_norm": 1.8746805079924518,
|
| 329 |
+
"learning_rate": 7.056435515653059e-06,
|
| 330 |
+
"loss": 0.3016,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.746031746031746,
|
| 335 |
+
"grad_norm": 1.6795992682490004,
|
| 336 |
+
"learning_rate": 6.942173981373474e-06,
|
| 337 |
+
"loss": 0.2765,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7619047619047619,
|
| 342 |
+
"grad_norm": 1.5560823579671665,
|
| 343 |
+
"learning_rate": 6.8267051218319766e-06,
|
| 344 |
+
"loss": 0.2532,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7777777777777778,
|
| 349 |
+
"grad_norm": 1.895658785400284,
|
| 350 |
+
"learning_rate": 6.710100716628345e-06,
|
| 351 |
+
"loss": 0.2892,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7936507936507936,
|
| 356 |
+
"grad_norm": 1.8753314593622137,
|
| 357 |
+
"learning_rate": 6.592433251258423e-06,
|
| 358 |
+
"loss": 0.3301,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8095238095238095,
|
| 363 |
+
"grad_norm": 1.829267141246674,
|
| 364 |
+
"learning_rate": 6.473775872054522e-06,
|
| 365 |
+
"loss": 0.2891,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.8253968253968254,
|
| 370 |
+
"grad_norm": 1.7420326737904375,
|
| 371 |
+
"learning_rate": 6.354202340715027e-06,
|
| 372 |
+
"loss": 0.2866,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8412698412698413,
|
| 377 |
+
"grad_norm": 1.6023111714513605,
|
| 378 |
+
"learning_rate": 6.233786988451468e-06,
|
| 379 |
+
"loss": 0.2546,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8571428571428571,
|
| 384 |
+
"grad_norm": 1.6958524220983555,
|
| 385 |
+
"learning_rate": 6.112604669781572e-06,
|
| 386 |
+
"loss": 0.263,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.873015873015873,
|
| 391 |
+
"grad_norm": 1.641293642541498,
|
| 392 |
+
"learning_rate": 5.990730715996989e-06,
|
| 393 |
+
"loss": 0.2519,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8888888888888888,
|
| 398 |
+
"grad_norm": 1.9737668057519353,
|
| 399 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 400 |
+
"loss": 0.3114,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9047619047619048,
|
| 405 |
+
"grad_norm": 1.6222206764245741,
|
| 406 |
+
"learning_rate": 5.745211330880872e-06,
|
| 407 |
+
"loss": 0.2611,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9206349206349206,
|
| 412 |
+
"grad_norm": 1.6779148540502549,
|
| 413 |
+
"learning_rate": 5.621718523237427e-06,
|
| 414 |
+
"loss": 0.2749,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9365079365079365,
|
| 419 |
+
"grad_norm": 1.5069533839875844,
|
| 420 |
+
"learning_rate": 5.497839232979084e-06,
|
| 421 |
+
"loss": 0.2395,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.9523809523809523,
|
| 426 |
+
"grad_norm": 1.8959358860602276,
|
| 427 |
+
"learning_rate": 5.373650467932122e-06,
|
| 428 |
+
"loss": 0.2893,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9682539682539683,
|
| 433 |
+
"grad_norm": 1.523846974950363,
|
| 434 |
+
"learning_rate": 5.249229428303486e-06,
|
| 435 |
+
"loss": 0.2465,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9841269841269841,
|
| 440 |
+
"grad_norm": 1.648360547715999,
|
| 441 |
+
"learning_rate": 5.1246534586903655e-06,
|
| 442 |
+
"loss": 0.2895,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0,
|
| 447 |
+
"grad_norm": 1.7313601334897208,
|
| 448 |
+
"learning_rate": 5e-06,
|
| 449 |
+
"loss": 0.2725,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0158730158730158,
|
| 454 |
+
"grad_norm": 1.5974296941422694,
|
| 455 |
+
"learning_rate": 4.875346541309637e-06,
|
| 456 |
+
"loss": 0.2332,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.0317460317460316,
|
| 461 |
+
"grad_norm": 1.7754313088972902,
|
| 462 |
+
"learning_rate": 4.750770571696514e-06,
|
| 463 |
+
"loss": 0.2586,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.0476190476190477,
|
| 468 |
+
"grad_norm": 1.7376217331972978,
|
| 469 |
+
"learning_rate": 4.626349532067879e-06,
|
| 470 |
+
"loss": 0.2542,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.0634920634920635,
|
| 475 |
+
"grad_norm": 1.6766787084873536,
|
| 476 |
+
"learning_rate": 4.502160767020918e-06,
|
| 477 |
+
"loss": 0.2526,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.0793650793650793,
|
| 482 |
+
"grad_norm": 1.6040607155196303,
|
| 483 |
+
"learning_rate": 4.3782814767625755e-06,
|
| 484 |
+
"loss": 0.2305,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.0952380952380953,
|
| 489 |
+
"grad_norm": 1.76649027588737,
|
| 490 |
+
"learning_rate": 4.254788669119127e-06,
|
| 491 |
+
"loss": 0.2713,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.1111111111111112,
|
| 496 |
+
"grad_norm": 1.689340586990794,
|
| 497 |
+
"learning_rate": 4.131759111665349e-06,
|
| 498 |
+
"loss": 0.2382,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.126984126984127,
|
| 503 |
+
"grad_norm": 1.6502677192393955,
|
| 504 |
+
"learning_rate": 4.009269284003014e-06,
|
| 505 |
+
"loss": 0.226,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.1428571428571428,
|
| 510 |
+
"grad_norm": 1.6333958229898413,
|
| 511 |
+
"learning_rate": 3.887395330218429e-06,
|
| 512 |
+
"loss": 0.2289,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.1587301587301586,
|
| 517 |
+
"grad_norm": 1.7310975785907043,
|
| 518 |
+
"learning_rate": 3.7662130115485317e-06,
|
| 519 |
+
"loss": 0.2873,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.1746031746031746,
|
| 524 |
+
"grad_norm": 1.5468081102672981,
|
| 525 |
+
"learning_rate": 3.6457976592849753e-06,
|
| 526 |
+
"loss": 0.1974,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.1904761904761905,
|
| 531 |
+
"grad_norm": 1.5296817125485362,
|
| 532 |
+
"learning_rate": 3.526224127945479e-06,
|
| 533 |
+
"loss": 0.2013,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.2063492063492063,
|
| 538 |
+
"grad_norm": 1.6513883543662364,
|
| 539 |
+
"learning_rate": 3.4075667487415785e-06,
|
| 540 |
+
"loss": 0.2257,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.2222222222222223,
|
| 545 |
+
"grad_norm": 1.7657149068040885,
|
| 546 |
+
"learning_rate": 3.289899283371657e-06,
|
| 547 |
+
"loss": 0.2389,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.2380952380952381,
|
| 552 |
+
"grad_norm": 1.6542259947868383,
|
| 553 |
+
"learning_rate": 3.173294878168025e-06,
|
| 554 |
+
"loss": 0.2207,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.253968253968254,
|
| 559 |
+
"grad_norm": 1.785500829184994,
|
| 560 |
+
"learning_rate": 3.057826018626527e-06,
|
| 561 |
+
"loss": 0.2409,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.2698412698412698,
|
| 566 |
+
"grad_norm": 1.624145624947224,
|
| 567 |
+
"learning_rate": 2.9435644843469434e-06,
|
| 568 |
+
"loss": 0.2361,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.2857142857142856,
|
| 573 |
+
"grad_norm": 1.552144673465774,
|
| 574 |
+
"learning_rate": 2.83058130441221e-06,
|
| 575 |
+
"loss": 0.2051,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.3015873015873016,
|
| 580 |
+
"grad_norm": 1.6259207954939752,
|
| 581 |
+
"learning_rate": 2.718946713234185e-06,
|
| 582 |
+
"loss": 0.2213,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.3174603174603174,
|
| 587 |
+
"grad_norm": 1.6311364982482741,
|
| 588 |
+
"learning_rate": 2.608730106893411e-06,
|
| 589 |
+
"loss": 0.2505,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.3333333333333333,
|
| 594 |
+
"grad_norm": 1.5946669632314558,
|
| 595 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 596 |
+
"loss": 0.2077,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.3492063492063493,
|
| 601 |
+
"grad_norm": 1.6540736898757478,
|
| 602 |
+
"learning_rate": 2.39282398310251e-06,
|
| 603 |
+
"loss": 0.2231,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.3650793650793651,
|
| 608 |
+
"grad_norm": 1.5631800963608526,
|
| 609 |
+
"learning_rate": 2.2872686806712037e-06,
|
| 610 |
+
"loss": 0.2063,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.380952380952381,
|
| 615 |
+
"grad_norm": 1.6790445903303324,
|
| 616 |
+
"learning_rate": 2.1833997096818897e-06,
|
| 617 |
+
"loss": 0.2275,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.3968253968253967,
|
| 622 |
+
"grad_norm": 1.71594970960584,
|
| 623 |
+
"learning_rate": 2.081281638826052e-06,
|
| 624 |
+
"loss": 0.2304,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.4126984126984126,
|
| 629 |
+
"grad_norm": 1.6467944353789714,
|
| 630 |
+
"learning_rate": 1.980977948372612e-06,
|
| 631 |
+
"loss": 0.2284,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.4285714285714286,
|
| 636 |
+
"grad_norm": 1.508481981490406,
|
| 637 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 638 |
+
"loss": 0.2133,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.4444444444444444,
|
| 643 |
+
"grad_norm": 1.6577136924947176,
|
| 644 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 645 |
+
"loss": 0.2344,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.4603174603174602,
|
| 650 |
+
"grad_norm": 1.6358011219062036,
|
| 651 |
+
"learning_rate": 1.6915708120157042e-06,
|
| 652 |
+
"loss": 0.2326,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.4761904761904763,
|
| 657 |
+
"grad_norm": 1.5343887042100857,
|
| 658 |
+
"learning_rate": 1.5991363111454023e-06,
|
| 659 |
+
"loss": 0.2376,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.492063492063492,
|
| 664 |
+
"grad_norm": 1.660583983348991,
|
| 665 |
+
"learning_rate": 1.5088159095696365e-06,
|
| 666 |
+
"loss": 0.225,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.507936507936508,
|
| 671 |
+
"grad_norm": 1.6005130793524434,
|
| 672 |
+
"learning_rate": 1.4206657537014078e-06,
|
| 673 |
+
"loss": 0.2305,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.5238095238095237,
|
| 678 |
+
"grad_norm": 1.553147977120734,
|
| 679 |
+
"learning_rate": 1.3347406408508695e-06,
|
| 680 |
+
"loss": 0.2288,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.5396825396825395,
|
| 685 |
+
"grad_norm": 1.5908104698304062,
|
| 686 |
+
"learning_rate": 1.2510939851613285e-06,
|
| 687 |
+
"loss": 0.2215,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.5555555555555556,
|
| 692 |
+
"grad_norm": 1.9504543471947708,
|
| 693 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 694 |
+
"loss": 0.278,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.5714285714285714,
|
| 699 |
+
"grad_norm": 1.704011286004108,
|
| 700 |
+
"learning_rate": 1.0908425876598512e-06,
|
| 701 |
+
"loss": 0.2287,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.5873015873015874,
|
| 706 |
+
"grad_norm": 1.618234720661816,
|
| 707 |
+
"learning_rate": 1.0143374638853892e-06,
|
| 708 |
+
"loss": 0.2402,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.6031746031746033,
|
| 713 |
+
"grad_norm": 1.6475638575246008,
|
| 714 |
+
"learning_rate": 9.403099714207175e-07,
|
| 715 |
+
"loss": 0.2192,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.619047619047619,
|
| 720 |
+
"grad_norm": 1.5958099241656356,
|
| 721 |
+
"learning_rate": 8.688061284200266e-07,
|
| 722 |
+
"loss": 0.2549,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.6349206349206349,
|
| 727 |
+
"grad_norm": 1.561819978797271,
|
| 728 |
+
"learning_rate": 7.99870384246143e-07,
|
| 729 |
+
"loss": 0.2111,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.6507936507936507,
|
| 734 |
+
"grad_norm": 1.7949770813372914,
|
| 735 |
+
"learning_rate": 7.33545591839222e-07,
|
| 736 |
+
"loss": 0.2376,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.6666666666666665,
|
| 741 |
+
"grad_norm": 1.698853452351741,
|
| 742 |
+
"learning_rate": 6.698729810778065e-07,
|
| 743 |
+
"loss": 0.2243,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.6825396825396826,
|
| 748 |
+
"grad_norm": 1.7776514869091975,
|
| 749 |
+
"learning_rate": 6.088921331488568e-07,
|
| 750 |
+
"loss": 0.2356,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.6984126984126984,
|
| 755 |
+
"grad_norm": 1.6125533182565601,
|
| 756 |
+
"learning_rate": 5.506409559426573e-07,
|
| 757 |
+
"loss": 0.2192,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.7142857142857144,
|
| 762 |
+
"grad_norm": 1.4580499888991223,
|
| 763 |
+
"learning_rate": 4.951556604879049e-07,
|
| 764 |
+
"loss": 0.2011,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.7301587301587302,
|
| 769 |
+
"grad_norm": 1.44711042249179,
|
| 770 |
+
"learning_rate": 4.4247073844163434e-07,
|
| 771 |
+
"loss": 0.1919,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.746031746031746,
|
| 776 |
+
"grad_norm": 1.5319692607578637,
|
| 777 |
+
"learning_rate": 3.9261894064796136e-07,
|
| 778 |
+
"loss": 0.2228,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.7619047619047619,
|
| 783 |
+
"grad_norm": 1.703198205141255,
|
| 784 |
+
"learning_rate": 3.4563125677897936e-07,
|
| 785 |
+
"loss": 0.2446,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.7777777777777777,
|
| 790 |
+
"grad_norm": 1.4382012783244584,
|
| 791 |
+
"learning_rate": 3.015368960704584e-07,
|
| 792 |
+
"loss": 0.2085,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.7936507936507935,
|
| 797 |
+
"grad_norm": 1.4938131300996766,
|
| 798 |
+
"learning_rate": 2.6036326916434153e-07,
|
| 799 |
+
"loss": 0.2043,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.8095238095238095,
|
| 804 |
+
"grad_norm": 1.5238283598819027,
|
| 805 |
+
"learning_rate": 2.2213597106929608e-07,
|
| 806 |
+
"loss": 0.213,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.8253968253968254,
|
| 811 |
+
"grad_norm": 1.5482037294832478,
|
| 812 |
+
"learning_rate": 1.8687876524993987e-07,
|
| 813 |
+
"loss": 0.2136,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.8412698412698414,
|
| 818 |
+
"grad_norm": 1.480422561570781,
|
| 819 |
+
"learning_rate": 1.5461356885461077e-07,
|
| 820 |
+
"loss": 0.2242,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.8571428571428572,
|
| 825 |
+
"grad_norm": 1.4385375275853922,
|
| 826 |
+
"learning_rate": 1.253604390908819e-07,
|
| 827 |
+
"loss": 0.1934,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.873015873015873,
|
| 832 |
+
"grad_norm": 1.398116868516386,
|
| 833 |
+
"learning_rate": 9.913756075728088e-08,
|
| 834 |
+
"loss": 0.1943,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.8888888888888888,
|
| 839 |
+
"grad_norm": 1.481535586423097,
|
| 840 |
+
"learning_rate": 7.59612349389599e-08,
|
| 841 |
+
"loss": 0.2096,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.9047619047619047,
|
| 846 |
+
"grad_norm": 1.474742617578431,
|
| 847 |
+
"learning_rate": 5.584586887435739e-08,
|
| 848 |
+
"loss": 0.207,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.9206349206349205,
|
| 853 |
+
"grad_norm": 1.3680015424187337,
|
| 854 |
+
"learning_rate": 3.8803966999139686e-08,
|
| 855 |
+
"loss": 0.1845,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.9365079365079365,
|
| 860 |
+
"grad_norm": 1.7090636442828981,
|
| 861 |
+
"learning_rate": 2.4846123172992953e-08,
|
| 862 |
+
"loss": 0.2299,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.9523809523809523,
|
| 867 |
+
"grad_norm": 1.4560355937269758,
|
| 868 |
+
"learning_rate": 1.3981014094099354e-08,
|
| 869 |
+
"loss": 0.1846,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.9682539682539684,
|
| 874 |
+
"grad_norm": 1.6521726152458496,
|
| 875 |
+
"learning_rate": 6.215393905388278e-09,
|
| 876 |
+
"loss": 0.2492,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.9841269841269842,
|
| 881 |
+
"grad_norm": 1.3715437105112576,
|
| 882 |
+
"learning_rate": 1.5540899959187727e-09,
|
| 883 |
+
"loss": 0.1846,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.0,
|
| 888 |
+
"grad_norm": 1.411488207674534,
|
| 889 |
+
"learning_rate": 0.0,
|
| 890 |
+
"loss": 0.1976,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.0,
|
| 895 |
+
"step": 126,
|
| 896 |
+
"total_flos": 1772529647616.0,
|
| 897 |
+
"train_loss": 0.2918981748913962,
|
| 898 |
+
"train_runtime": 115.6265,
|
| 899 |
+
"train_samples_per_second": 8.683,
|
| 900 |
+
"train_steps_per_second": 1.09
|
| 901 |
+
}
|
| 902 |
+
],
|
| 903 |
+
"logging_steps": 1,
|
| 904 |
+
"max_steps": 126,
|
| 905 |
+
"num_input_tokens_seen": 0,
|
| 906 |
+
"num_train_epochs": 2,
|
| 907 |
+
"save_steps": 70000,
|
| 908 |
+
"stateful_callbacks": {
|
| 909 |
+
"TrainerControl": {
|
| 910 |
+
"args": {
|
| 911 |
+
"should_epoch_stop": false,
|
| 912 |
+
"should_evaluate": false,
|
| 913 |
+
"should_log": false,
|
| 914 |
+
"should_save": true,
|
| 915 |
+
"should_training_stop": true
|
| 916 |
+
},
|
| 917 |
+
"attributes": {}
|
| 918 |
+
}
|
| 919 |
+
},
|
| 920 |
+
"total_flos": 1772529647616.0,
|
| 921 |
+
"train_batch_size": 2,
|
| 922 |
+
"trial_name": null,
|
| 923 |
+
"trial_params": null
|
| 924 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a47c97a8dc8cb9c2d9476b9b86d52488c1fbd21f0fab422d6620d201d3b35e9
|
| 3 |
+
size 7160
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|