Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +64 -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 +294 -0
- trainer_state.json +2094 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -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 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: MATH_training_response_Qwen2.5-32B-Instruct_common_correct_level
|
| 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 |
+
# MATH_training_response_Qwen2.5-32B-Instruct_common_correct_level
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on the MATH_training_response_Qwen2.5-32B-Instruct_common_correct_level dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1674
|
| 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: 4
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- total_train_batch_size: 16
|
| 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 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 0.049 | 1.3699 | 200 | 0.1710 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- Transformers 4.46.1
|
| 62 |
+
- Pytorch 2.5.1+cu124
|
| 63 |
+
- Datasets 3.1.0
|
| 64 |
+
- 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": 0.16735880076885223,
|
| 4 |
+
"eval_runtime": 0.987,
|
| 5 |
+
"eval_samples_per_second": 24.317,
|
| 6 |
+
"eval_steps_per_second": 6.079,
|
| 7 |
+
"total_flos": 3642198589440.0,
|
| 8 |
+
"train_loss": 0.09577030846721506,
|
| 9 |
+
"train_runtime": 252.2381,
|
| 10 |
+
"train_samples_per_second": 18.467,
|
| 11 |
+
"train_steps_per_second": 1.158
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-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": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 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": 0.16735880076885223,
|
| 4 |
+
"eval_runtime": 0.987,
|
| 5 |
+
"eval_samples_per_second": 24.317,
|
| 6 |
+
"eval_steps_per_second": 6.079
|
| 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:ccde7eb851adda41170dcedf2336039349aaf69276b496b75a2597e29ce3833d
|
| 3 |
+
size 3087467144
|
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 tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 32768,
|
| 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": 3642198589440.0,
|
| 4 |
+
"train_loss": 0.09577030846721506,
|
| 5 |
+
"train_runtime": 252.2381,
|
| 6 |
+
"train_samples_per_second": 18.467,
|
| 7 |
+
"train_steps_per_second": 1.158
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,294 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 292, "loss": 0.1611, "lr": 9.999710619100732e-06, "epoch": 0.00684931506849315, "percentage": 0.34, "elapsed_time": "0:00:02", "remaining_time": "0:09:48"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 292, "loss": 0.2252, "lr": 9.998842509899456e-06, "epoch": 0.0136986301369863, "percentage": 0.68, "elapsed_time": "0:00:04", "remaining_time": "0:11:58"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 292, "loss": 0.1579, "lr": 9.997395772881853e-06, "epoch": 0.02054794520547945, "percentage": 1.03, "elapsed_time": "0:00:05", "remaining_time": "0:09:15"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 292, "loss": 0.1773, "lr": 9.995370575511151e-06, "epoch": 0.0273972602739726, "percentage": 1.37, "elapsed_time": "0:00:06", "remaining_time": "0:07:52"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 292, "loss": 0.1473, "lr": 9.992767152208724e-06, "epoch": 0.03424657534246575, "percentage": 1.71, "elapsed_time": "0:00:07", "remaining_time": "0:07:05"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 292, "loss": 0.1334, "lr": 9.989585804326963e-06, "epoch": 0.0410958904109589, "percentage": 2.05, "elapsed_time": "0:00:08", "remaining_time": "0:06:31"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 292, "loss": 0.142, "lr": 9.985826900114391e-06, "epoch": 0.04794520547945205, "percentage": 2.4, "elapsed_time": "0:00:08", "remaining_time": "0:06:06"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 292, "loss": 0.1277, "lr": 9.98149087467304e-06, "epoch": 0.0547945205479452, "percentage": 2.74, "elapsed_time": "0:00:09", "remaining_time": "0:05:47"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 292, "loss": 0.1551, "lr": 9.97657822990809e-06, "epoch": 0.06164383561643835, "percentage": 3.08, "elapsed_time": "0:00:10", "remaining_time": "0:05:32"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 292, "loss": 0.1297, "lr": 9.97108953446976e-06, "epoch": 0.0684931506849315, "percentage": 3.42, "elapsed_time": "0:00:11", "remaining_time": "0:05:20"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 292, "loss": 0.1555, "lr": 9.965025423687505e-06, "epoch": 0.07534246575342465, "percentage": 3.77, "elapsed_time": "0:00:12", "remaining_time": "0:05:10"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 292, "loss": 0.1291, "lr": 9.95838659949645e-06, "epoch": 0.0821917808219178, "percentage": 4.11, "elapsed_time": "0:00:12", "remaining_time": "0:05:02"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 292, "loss": 0.1326, "lr": 9.951173830356168e-06, "epoch": 0.08904109589041095, "percentage": 4.45, "elapsed_time": "0:00:13", "remaining_time": "0:04:55"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 292, "loss": 0.1708, "lr": 9.943387951161702e-06, "epoch": 0.0958904109589041, "percentage": 4.79, "elapsed_time": "0:00:14", "remaining_time": "0:04:48"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 292, "loss": 0.1323, "lr": 9.935029863146946e-06, "epoch": 0.10273972602739725, "percentage": 5.14, "elapsed_time": "0:00:15", "remaining_time": "0:04:43"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 292, "loss": 0.1127, "lr": 9.926100533780304e-06, "epoch": 0.1095890410958904, "percentage": 5.48, "elapsed_time": "0:00:16", "remaining_time": "0:04:39"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 292, "loss": 0.143, "lr": 9.916600996652726e-06, "epoch": 0.11643835616438356, "percentage": 5.82, "elapsed_time": "0:00:16", "remaining_time": "0:04:34"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 292, "loss": 0.1605, "lr": 9.906532351358047e-06, "epoch": 0.1232876712328767, "percentage": 6.16, "elapsed_time": "0:00:17", "remaining_time": "0:04:30"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 292, "loss": 0.1399, "lr": 9.895895763365722e-06, "epoch": 0.13013698630136986, "percentage": 6.51, "elapsed_time": "0:00:18", "remaining_time": "0:04:26"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 292, "loss": 0.1593, "lr": 9.88469246388591e-06, "epoch": 0.136986301369863, "percentage": 6.85, "elapsed_time": "0:00:19", "remaining_time": "0:04:23"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 292, "loss": 0.1503, "lr": 9.872923749726959e-06, "epoch": 0.14383561643835616, "percentage": 7.19, "elapsed_time": "0:00:20", "remaining_time": "0:04:20"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 292, "loss": 0.1267, "lr": 9.860590983145307e-06, "epoch": 0.1506849315068493, "percentage": 7.53, "elapsed_time": "0:00:20", "remaining_time": "0:04:17"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 292, "loss": 0.173, "lr": 9.847695591687788e-06, "epoch": 0.15753424657534246, "percentage": 7.88, "elapsed_time": "0:00:21", "remaining_time": "0:04:14"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 292, "loss": 0.1471, "lr": 9.834239068026388e-06, "epoch": 0.1643835616438356, "percentage": 8.22, "elapsed_time": "0:00:22", "remaining_time": "0:04:12"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 292, "loss": 0.1275, "lr": 9.82022296978548e-06, "epoch": 0.17123287671232876, "percentage": 8.56, "elapsed_time": "0:00:23", "remaining_time": "0:04:09"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 292, "loss": 0.1218, "lr": 9.805648919361505e-06, "epoch": 0.1780821917808219, "percentage": 8.9, "elapsed_time": "0:00:24", "remaining_time": "0:04:07"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 292, "loss": 0.1465, "lr": 9.790518603735191e-06, "epoch": 0.18493150684931506, "percentage": 9.25, "elapsed_time": "0:00:24", "remaining_time": "0:04:04"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 292, "loss": 0.1447, "lr": 9.774833774276278e-06, "epoch": 0.1917808219178082, "percentage": 9.59, "elapsed_time": "0:00:25", "remaining_time": "0:04:02"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 292, "loss": 0.176, "lr": 9.758596246540782e-06, "epoch": 0.19863013698630136, "percentage": 9.93, "elapsed_time": "0:00:26", "remaining_time": "0:04:00"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 292, "loss": 0.1257, "lr": 9.741807900060858e-06, "epoch": 0.2054794520547945, "percentage": 10.27, "elapsed_time": "0:00:27", "remaining_time": "0:03:58"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 292, "loss": 0.1676, "lr": 9.724470678127226e-06, "epoch": 0.21232876712328766, "percentage": 10.62, "elapsed_time": "0:00:28", "remaining_time": "0:03:56"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 292, "loss": 0.159, "lr": 9.706586587564236e-06, "epoch": 0.2191780821917808, "percentage": 10.96, "elapsed_time": "0:00:28", "remaining_time": "0:03:54"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 292, "loss": 0.149, "lr": 9.68815769849757e-06, "epoch": 0.22602739726027396, "percentage": 11.3, "elapsed_time": "0:00:29", "remaining_time": "0:03:52"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 292, "loss": 0.1567, "lr": 9.669186144114627e-06, "epoch": 0.2328767123287671, "percentage": 11.64, "elapsed_time": "0:00:30", "remaining_time": "0:03:51"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 292, "loss": 0.149, "lr": 9.649674120417591e-06, "epoch": 0.23972602739726026, "percentage": 11.99, "elapsed_time": "0:00:31", "remaining_time": "0:03:49"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 292, "loss": 0.1526, "lr": 9.62962388596925e-06, "epoch": 0.2465753424657534, "percentage": 12.33, "elapsed_time": "0:00:32", "remaining_time": "0:03:47"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 292, "loss": 0.1705, "lr": 9.609037761631552e-06, "epoch": 0.2534246575342466, "percentage": 12.67, "elapsed_time": "0:00:32", "remaining_time": "0:03:46"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 292, "loss": 0.1581, "lr": 9.587918130296969e-06, "epoch": 0.2602739726027397, "percentage": 13.01, "elapsed_time": "0:00:33", "remaining_time": "0:03:44"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 292, "loss": 0.1432, "lr": 9.566267436612662e-06, "epoch": 0.2671232876712329, "percentage": 13.36, "elapsed_time": "0:00:34", "remaining_time": "0:03:43"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 292, "loss": 0.1391, "lr": 9.544088186697515e-06, "epoch": 0.273972602739726, "percentage": 13.7, "elapsed_time": "0:00:35", "remaining_time": "0:03:42"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 292, "loss": 0.1003, "lr": 9.521382947852042e-06, "epoch": 0.2808219178082192, "percentage": 14.04, "elapsed_time": "0:00:36", "remaining_time": "0:03:40"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 292, "loss": 0.1436, "lr": 9.498154348261217e-06, "epoch": 0.2876712328767123, "percentage": 14.38, "elapsed_time": "0:00:36", "remaining_time": "0:03:39"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 292, "loss": 0.1481, "lr": 9.474405076690257e-06, "epoch": 0.2945205479452055, "percentage": 14.73, "elapsed_time": "0:00:37", "remaining_time": "0:03:38"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 292, "loss": 0.134, "lr": 9.450137882173385e-06, "epoch": 0.3013698630136986, "percentage": 15.07, "elapsed_time": "0:00:38", "remaining_time": "0:03:37"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 292, "loss": 0.1253, "lr": 9.425355573695628e-06, "epoch": 0.3082191780821918, "percentage": 15.41, "elapsed_time": "0:00:39", "remaining_time": "0:03:35"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 292, "loss": 0.1539, "lr": 9.40006101986768e-06, "epoch": 0.3150684931506849, "percentage": 15.75, "elapsed_time": "0:00:40", "remaining_time": "0:03:34"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 292, "loss": 0.139, "lr": 9.374257148593824e-06, "epoch": 0.3219178082191781, "percentage": 16.1, "elapsed_time": "0:00:40", "remaining_time": "0:03:33"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 292, "loss": 0.1601, "lr": 9.347946946733055e-06, "epoch": 0.3287671232876712, "percentage": 16.44, "elapsed_time": "0:00:41", "remaining_time": "0:03:32"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 292, "loss": 0.1539, "lr": 9.321133459753322e-06, "epoch": 0.3356164383561644, "percentage": 16.78, "elapsed_time": "0:00:42", "remaining_time": "0:03:31"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 292, "loss": 0.1634, "lr": 9.293819791379016e-06, "epoch": 0.3424657534246575, "percentage": 17.12, "elapsed_time": "0:00:43", "remaining_time": "0:03:29"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 292, "loss": 0.1349, "lr": 9.266009103231702e-06, "epoch": 0.3493150684931507, "percentage": 17.47, "elapsed_time": "0:00:44", "remaining_time": "0:03:28"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 292, "loss": 0.1507, "lr": 9.237704614464157e-06, "epoch": 0.3561643835616438, "percentage": 17.81, "elapsed_time": "0:00:44", "remaining_time": "0:03:27"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 292, "loss": 0.1458, "lr": 9.208909601387748e-06, "epoch": 0.363013698630137, "percentage": 18.15, "elapsed_time": "0:00:45", "remaining_time": "0:03:26"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 292, "loss": 0.1353, "lr": 9.179627397093184e-06, "epoch": 0.3698630136986301, "percentage": 18.49, "elapsed_time": "0:00:46", "remaining_time": "0:03:24"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 292, "loss": 0.1463, "lr": 9.149861391064714e-06, "epoch": 0.3767123287671233, "percentage": 18.84, "elapsed_time": "0:00:47", "remaining_time": "0:03:23"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 292, "loss": 0.1469, "lr": 9.119615028787771e-06, "epoch": 0.3835616438356164, "percentage": 19.18, "elapsed_time": "0:00:48", "remaining_time": "0:03:22"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 292, "loss": 0.1473, "lr": 9.088891811350164e-06, "epoch": 0.3904109589041096, "percentage": 19.52, "elapsed_time": "0:00:48", "remaining_time": "0:03:21"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 292, "loss": 0.1419, "lr": 9.057695295036806e-06, "epoch": 0.3972602739726027, "percentage": 19.86, "elapsed_time": "0:00:49", "remaining_time": "0:03:20"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 292, "loss": 0.1257, "lr": 9.026029090918076e-06, "epoch": 0.4041095890410959, "percentage": 20.21, "elapsed_time": "0:00:50", "remaining_time": "0:03:19"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 292, "loss": 0.1533, "lr": 8.993896864431825e-06, "epoch": 0.410958904109589, "percentage": 20.55, "elapsed_time": "0:00:51", "remaining_time": "0:03:18"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 292, "loss": 0.125, "lr": 8.96130233495909e-06, "epoch": 0.4178082191780822, "percentage": 20.89, "elapsed_time": "0:00:52", "remaining_time": "0:03:17"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 292, "loss": 0.1472, "lr": 8.928249275393572e-06, "epoch": 0.4246575342465753, "percentage": 21.23, "elapsed_time": "0:00:52", "remaining_time": "0:03:16"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 292, "loss": 0.1205, "lr": 8.894741511704911e-06, "epoch": 0.4315068493150685, "percentage": 21.58, "elapsed_time": "0:00:53", "remaining_time": "0:03:15"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 292, "loss": 0.155, "lr": 8.860782922495821e-06, "epoch": 0.4383561643835616, "percentage": 21.92, "elapsed_time": "0:00:54", "remaining_time": "0:03:14"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 292, "loss": 0.1621, "lr": 8.826377438553138e-06, "epoch": 0.4452054794520548, "percentage": 22.26, "elapsed_time": "0:00:55", "remaining_time": "0:03:13"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 292, "loss": 0.1345, "lr": 8.791529042392813e-06, "epoch": 0.4520547945205479, "percentage": 22.6, "elapsed_time": "0:00:56", "remaining_time": "0:03:12"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 292, "loss": 0.1288, "lr": 8.756241767798934e-06, "epoch": 0.4589041095890411, "percentage": 22.95, "elapsed_time": "0:00:56", "remaining_time": "0:03:11"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 292, "loss": 0.1576, "lr": 8.720519699356804e-06, "epoch": 0.4657534246575342, "percentage": 23.29, "elapsed_time": "0:00:57", "remaining_time": "0:03:10"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 292, "loss": 0.1528, "lr": 8.684366971980139e-06, "epoch": 0.4726027397260274, "percentage": 23.63, "elapsed_time": "0:00:58", "remaining_time": "0:03:09"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 292, "loss": 0.1481, "lr": 8.647787770432439e-06, "epoch": 0.4794520547945205, "percentage": 23.97, "elapsed_time": "0:00:59", "remaining_time": "0:03:08"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 292, "loss": 0.1165, "lr": 8.610786328842602e-06, "epoch": 0.4863013698630137, "percentage": 24.32, "elapsed_time": "0:01:00", "remaining_time": "0:03:07"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 292, "loss": 0.1379, "lr": 8.573366930214807e-06, "epoch": 0.4931506849315068, "percentage": 24.66, "elapsed_time": "0:01:00", "remaining_time": "0:03:06"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 292, "loss": 0.1397, "lr": 8.535533905932739e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:01:01", "remaining_time": "0:03:05"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 292, "loss": 0.1385, "lr": 8.497291635258235e-06, "epoch": 0.5068493150684932, "percentage": 25.34, "elapsed_time": "0:01:02", "remaining_time": "0:03:04"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 292, "loss": 0.144, "lr": 8.458644544824371e-06, "epoch": 0.5136986301369864, "percentage": 25.68, "elapsed_time": "0:01:03", "remaining_time": "0:03:03"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 292, "loss": 0.1064, "lr": 8.419597108123054e-06, "epoch": 0.5205479452054794, "percentage": 26.03, "elapsed_time": "0:01:04", "remaining_time": "0:03:02"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 292, "loss": 0.1317, "lr": 8.380153844987225e-06, "epoch": 0.5273972602739726, "percentage": 26.37, "elapsed_time": "0:01:04", "remaining_time": "0:03:01"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 292, "loss": 0.1091, "lr": 8.340319321067668e-06, "epoch": 0.5342465753424658, "percentage": 26.71, "elapsed_time": "0:01:05", "remaining_time": "0:03:00"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 292, "loss": 0.1514, "lr": 8.300098147304523e-06, "epoch": 0.541095890410959, "percentage": 27.05, "elapsed_time": "0:01:06", "remaining_time": "0:02:59"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 292, "loss": 0.1736, "lr": 8.259494979393563e-06, "epoch": 0.547945205479452, "percentage": 27.4, "elapsed_time": "0:01:07", "remaining_time": "0:02:58"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 292, "loss": 0.1475, "lr": 8.218514517247287e-06, "epoch": 0.5547945205479452, "percentage": 27.74, "elapsed_time": "0:01:08", "remaining_time": "0:02:57"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 292, "loss": 0.1314, "lr": 8.177161504450887e-06, "epoch": 0.5616438356164384, "percentage": 28.08, "elapsed_time": "0:01:08", "remaining_time": "0:02:56"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 292, "loss": 0.1407, "lr": 8.135440727713179e-06, "epoch": 0.5684931506849316, "percentage": 28.42, "elapsed_time": "0:01:09", "remaining_time": "0:02:55"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 292, "loss": 0.1854, "lr": 8.093357016312518e-06, "epoch": 0.5753424657534246, "percentage": 28.77, "elapsed_time": "0:01:10", "remaining_time": "0:02:54"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 292, "loss": 0.1523, "lr": 8.050915241537802e-06, "epoch": 0.5821917808219178, "percentage": 29.11, "elapsed_time": "0:01:11", "remaining_time": "0:02:53"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 292, "loss": 0.1348, "lr": 8.008120316124612e-06, "epoch": 0.589041095890411, "percentage": 29.45, "elapsed_time": "0:01:12", "remaining_time": "0:02:52"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 292, "loss": 0.1281, "lr": 7.964977193686551e-06, "epoch": 0.5958904109589042, "percentage": 29.79, "elapsed_time": "0:01:12", "remaining_time": "0:02:51"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 292, "loss": 0.1463, "lr": 7.921490868141843e-06, "epoch": 0.6027397260273972, "percentage": 30.14, "elapsed_time": "0:01:13", "remaining_time": "0:02:50"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 292, "loss": 0.1192, "lr": 7.877666373135287e-06, "epoch": 0.6095890410958904, "percentage": 30.48, "elapsed_time": "0:01:14", "remaining_time": "0:02:49"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 292, "loss": 0.1344, "lr": 7.83350878145559e-06, "epoch": 0.6164383561643836, "percentage": 30.82, "elapsed_time": "0:01:15", "remaining_time": "0:02:48"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 292, "loss": 0.1046, "lr": 7.789023204448189e-06, "epoch": 0.6232876712328768, "percentage": 31.16, "elapsed_time": "0:01:16", "remaining_time": "0:02:48"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 292, "loss": 0.1256, "lr": 7.744214791423597e-06, "epoch": 0.6301369863013698, "percentage": 31.51, "elapsed_time": "0:01:17", "remaining_time": "0:02:48"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 292, "loss": 0.1704, "lr": 7.699088729061355e-06, "epoch": 0.636986301369863, "percentage": 31.85, "elapsed_time": "0:01:18", "remaining_time": "0:02:47"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 292, "loss": 0.1284, "lr": 7.653650240809667e-06, "epoch": 0.6438356164383562, "percentage": 32.19, "elapsed_time": "0:01:18", "remaining_time": "0:02:46"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 292, "loss": 0.1386, "lr": 7.60790458628077e-06, "epoch": 0.6506849315068494, "percentage": 32.53, "elapsed_time": "0:01:19", "remaining_time": "0:02:45"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 292, "loss": 0.1425, "lr": 7.56185706064212e-06, "epoch": 0.6575342465753424, "percentage": 32.88, "elapsed_time": "0:01:20", "remaining_time": "0:02:44"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 292, "loss": 0.1266, "lr": 7.5155129940034675e-06, "epoch": 0.6643835616438356, "percentage": 33.22, "elapsed_time": "0:01:21", "remaining_time": "0:02:43"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 292, "loss": 0.1447, "lr": 7.468877750799887e-06, "epoch": 0.6712328767123288, "percentage": 33.56, "elapsed_time": "0:01:22", "remaining_time": "0:02:42"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 292, "loss": 0.1121, "lr": 7.421956729170823e-06, "epoch": 0.678082191780822, "percentage": 33.9, "elapsed_time": "0:01:23", "remaining_time": "0:02:41"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 292, "loss": 0.1257, "lr": 7.374755360335253e-06, "epoch": 0.684931506849315, "percentage": 34.25, "elapsed_time": "0:01:23", "remaining_time": "0:02:40"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 292, "loss": 0.1357, "lr": 7.327279107962995e-06, "epoch": 0.6917808219178082, "percentage": 34.59, "elapsed_time": "0:01:24", "remaining_time": "0:02:40"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 292, "loss": 0.1585, "lr": 7.279533467542295e-06, "epoch": 0.6986301369863014, "percentage": 34.93, "elapsed_time": "0:01:25", "remaining_time": "0:02:39"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 292, "loss": 0.1391, "lr": 7.2315239657436955e-06, "epoch": 0.7054794520547946, "percentage": 35.27, "elapsed_time": "0:01:26", "remaining_time": "0:02:38"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 292, "loss": 0.1332, "lr": 7.183256159780321e-06, "epoch": 0.7123287671232876, "percentage": 35.62, "elapsed_time": "0:01:26", "remaining_time": "0:02:37"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 292, "loss": 0.1408, "lr": 7.134735636764606e-06, "epoch": 0.7191780821917808, "percentage": 35.96, "elapsed_time": "0:01:27", "remaining_time": "0:02:36"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 292, "loss": 0.1636, "lr": 7.085968013061585e-06, "epoch": 0.726027397260274, "percentage": 36.3, "elapsed_time": "0:01:28", "remaining_time": "0:02:35"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 292, "loss": 0.1088, "lr": 7.036958933638779e-06, "epoch": 0.7328767123287672, "percentage": 36.64, "elapsed_time": "0:01:29", "remaining_time": "0:02:34"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 292, "loss": 0.1488, "lr": 6.987714071412781e-06, "epoch": 0.7397260273972602, "percentage": 36.99, "elapsed_time": "0:01:30", "remaining_time": "0:02:33"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 292, "loss": 0.1477, "lr": 6.938239126592592e-06, "epoch": 0.7465753424657534, "percentage": 37.33, "elapsed_time": "0:01:31", "remaining_time": "0:02:32"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 292, "loss": 0.1305, "lr": 6.888539826019824e-06, "epoch": 0.7534246575342466, "percentage": 37.67, "elapsed_time": "0:01:31", "remaining_time": "0:02:32"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 292, "loss": 0.1312, "lr": 6.8386219225057945e-06, "epoch": 0.7602739726027398, "percentage": 38.01, "elapsed_time": "0:01:32", "remaining_time": "0:02:31"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 292, "loss": 0.1292, "lr": 6.788491194165629e-06, "epoch": 0.7671232876712328, "percentage": 38.36, "elapsed_time": "0:01:33", "remaining_time": "0:02:30"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 292, "loss": 0.1482, "lr": 6.738153443749421e-06, "epoch": 0.773972602739726, "percentage": 38.7, "elapsed_time": "0:01:34", "remaining_time": "0:02:29"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 292, "loss": 0.1279, "lr": 6.687614497970567e-06, "epoch": 0.7808219178082192, "percentage": 39.04, "elapsed_time": "0:01:35", "remaining_time": "0:02:28"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 292, "loss": 0.1639, "lr": 6.636880206831298e-06, "epoch": 0.7876712328767124, "percentage": 39.38, "elapsed_time": "0:01:35", "remaining_time": "0:02:27"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 292, "loss": 0.1194, "lr": 6.585956442945531e-06, "epoch": 0.7945205479452054, "percentage": 39.73, "elapsed_time": "0:01:36", "remaining_time": "0:02:26"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 292, "loss": 0.114, "lr": 6.534849100859101e-06, "epoch": 0.8013698630136986, "percentage": 40.07, "elapsed_time": "0:01:37", "remaining_time": "0:02:25"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 292, "loss": 0.1606, "lr": 6.483564096367452e-06, "epoch": 0.8082191780821918, "percentage": 40.41, "elapsed_time": "0:01:38", "remaining_time": "0:02:25"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 292, "loss": 0.1573, "lr": 6.432107365830872e-06, "epoch": 0.815068493150685, "percentage": 40.75, "elapsed_time": "0:01:39", "remaining_time": "0:02:24"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 292, "loss": 0.1624, "lr": 6.380484865487346e-06, "epoch": 0.821917808219178, "percentage": 41.1, "elapsed_time": "0:01:39", "remaining_time": "0:02:23"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 292, "loss": 0.1474, "lr": 6.328702570763098e-06, "epoch": 0.8287671232876712, "percentage": 41.44, "elapsed_time": "0:01:40", "remaining_time": "0:02:22"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 292, "loss": 0.1298, "lr": 6.276766475580935e-06, "epoch": 0.8356164383561644, "percentage": 41.78, "elapsed_time": "0:01:41", "remaining_time": "0:02:21"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 292, "loss": 0.1597, "lr": 6.224682591666431e-06, "epoch": 0.8424657534246576, "percentage": 42.12, "elapsed_time": "0:01:42", "remaining_time": "0:02:20"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 292, "loss": 0.1084, "lr": 6.1724569478520495e-06, "epoch": 0.8493150684931506, "percentage": 42.47, "elapsed_time": "0:01:43", "remaining_time": "0:02:19"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 292, "loss": 0.1508, "lr": 6.120095589379299e-06, "epoch": 0.8561643835616438, "percentage": 42.81, "elapsed_time": "0:01:44", "remaining_time": "0:02:18"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 292, "loss": 0.1365, "lr": 6.067604577198981e-06, "epoch": 0.863013698630137, "percentage": 43.15, "elapsed_time": "0:01:44", "remaining_time": "0:02:18"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 292, "loss": 0.1753, "lr": 6.014989987269617e-06, "epoch": 0.8698630136986302, "percentage": 43.49, "elapsed_time": "0:01:45", "remaining_time": "0:02:17"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 292, "loss": 0.1221, "lr": 5.96225790985415e-06, "epoch": 0.8767123287671232, "percentage": 43.84, "elapsed_time": "0:01:46", "remaining_time": "0:02:16"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 292, "loss": 0.1053, "lr": 5.909414448814971e-06, "epoch": 0.8835616438356164, "percentage": 44.18, "elapsed_time": "0:01:47", "remaining_time": "0:02:15"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 292, "loss": 0.1655, "lr": 5.856465720907388e-06, "epoch": 0.8904109589041096, "percentage": 44.52, "elapsed_time": "0:01:48", "remaining_time": "0:02:14"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 292, "loss": 0.1425, "lr": 5.803417855071603e-06, "epoch": 0.8972602739726028, "percentage": 44.86, "elapsed_time": "0:01:48", "remaining_time": "0:02:13"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 292, "loss": 0.1408, "lr": 5.7502769917232635e-06, "epoch": 0.9041095890410958, "percentage": 45.21, "elapsed_time": "0:01:49", "remaining_time": "0:02:12"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 292, "loss": 0.136, "lr": 5.6970492820426994e-06, "epoch": 0.910958904109589, "percentage": 45.55, "elapsed_time": "0:01:50", "remaining_time": "0:02:12"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 292, "loss": 0.1209, "lr": 5.643740887262905e-06, "epoch": 0.9178082191780822, "percentage": 45.89, "elapsed_time": "0:01:51", "remaining_time": "0:02:11"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 292, "loss": 0.1446, "lr": 5.59035797795637e-06, "epoch": 0.9246575342465754, "percentage": 46.23, "elapsed_time": "0:01:52", "remaining_time": "0:02:10"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 292, "loss": 0.1311, "lr": 5.536906733320816e-06, "epoch": 0.9315068493150684, "percentage": 46.58, "elapsed_time": "0:01:52", "remaining_time": "0:02:09"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 292, "loss": 0.1292, "lr": 5.483393340463938e-06, "epoch": 0.9383561643835616, "percentage": 46.92, "elapsed_time": "0:01:53", "remaining_time": "0:02:08"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 292, "loss": 0.1338, "lr": 5.429823993687234e-06, "epoch": 0.9452054794520548, "percentage": 47.26, "elapsed_time": "0:01:54", "remaining_time": "0:02:07"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 292, "loss": 0.1211, "lr": 5.376204893769e-06, "epoch": 0.952054794520548, "percentage": 47.6, "elapsed_time": "0:01:55", "remaining_time": "0:02:06"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 292, "loss": 0.1258, "lr": 5.322542247246583e-06, "epoch": 0.958904109589041, "percentage": 47.95, "elapsed_time": "0:01:56", "remaining_time": "0:02:05"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 292, "loss": 0.1219, "lr": 5.26884226569794e-06, "epoch": 0.9657534246575342, "percentage": 48.29, "elapsed_time": "0:01:56", "remaining_time": "0:02:05"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 292, "loss": 0.1345, "lr": 5.215111165022653e-06, "epoch": 0.9726027397260274, "percentage": 48.63, "elapsed_time": "0:01:57", "remaining_time": "0:02:04"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 292, "loss": 0.1465, "lr": 5.161355164722416e-06, "epoch": 0.9794520547945206, "percentage": 48.97, "elapsed_time": "0:01:58", "remaining_time": "0:02:03"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 292, "loss": 0.1168, "lr": 5.107580487181112e-06, "epoch": 0.9863013698630136, "percentage": 49.32, "elapsed_time": "0:01:59", "remaining_time": "0:02:03"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 292, "loss": 0.1156, "lr": 5.0537933569445585e-06, "epoch": 0.9931506849315068, "percentage": 49.66, "elapsed_time": "0:02:00", "remaining_time": "0:02:02"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 292, "loss": 0.1138, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:02:01", "remaining_time": "0:02:01"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 292, "loss": 0.0632, "lr": 4.946206643055443e-06, "epoch": 1.0068493150684932, "percentage": 50.34, "elapsed_time": "0:02:02", "remaining_time": "0:02:00"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 292, "loss": 0.04, "lr": 4.89241951281889e-06, "epoch": 1.0136986301369864, "percentage": 50.68, "elapsed_time": "0:02:03", "remaining_time": "0:01:59"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 292, "loss": 0.0616, "lr": 4.838644835277585e-06, "epoch": 1.0205479452054795, "percentage": 51.03, "elapsed_time": "0:02:03", "remaining_time": "0:01:58"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 292, "loss": 0.0485, "lr": 4.784888834977347e-06, "epoch": 1.0273972602739727, "percentage": 51.37, "elapsed_time": "0:02:04", "remaining_time": "0:01:57"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 292, "loss": 0.0641, "lr": 4.731157734302063e-06, "epoch": 1.0342465753424657, "percentage": 51.71, "elapsed_time": "0:02:05", "remaining_time": "0:01:57"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 292, "loss": 0.0497, "lr": 4.6774577527534195e-06, "epoch": 1.0410958904109588, "percentage": 52.05, "elapsed_time": "0:02:06", "remaining_time": "0:01:56"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 292, "loss": 0.06, "lr": 4.623795106231001e-06, "epoch": 1.047945205479452, "percentage": 52.4, "elapsed_time": "0:02:07", "remaining_time": "0:01:55"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 292, "loss": 0.0479, "lr": 4.570176006312769e-06, "epoch": 1.0547945205479452, "percentage": 52.74, "elapsed_time": "0:02:07", "remaining_time": "0:01:54"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 292, "loss": 0.0555, "lr": 4.516606659536063e-06, "epoch": 1.0616438356164384, "percentage": 53.08, "elapsed_time": "0:02:08", "remaining_time": "0:01:53"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 292, "loss": 0.0647, "lr": 4.463093266679185e-06, "epoch": 1.0684931506849316, "percentage": 53.42, "elapsed_time": "0:02:09", "remaining_time": "0:01:52"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 292, "loss": 0.0468, "lr": 4.40964202204363e-06, "epoch": 1.0753424657534247, "percentage": 53.77, "elapsed_time": "0:02:10", "remaining_time": "0:01:52"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 292, "loss": 0.0573, "lr": 4.356259112737096e-06, "epoch": 1.0821917808219177, "percentage": 54.11, "elapsed_time": "0:02:11", "remaining_time": "0:01:51"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 292, "loss": 0.0545, "lr": 4.302950717957304e-06, "epoch": 1.0890410958904109, "percentage": 54.45, "elapsed_time": "0:02:11", "remaining_time": "0:01:50"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 292, "loss": 0.0432, "lr": 4.249723008276737e-06, "epoch": 1.095890410958904, "percentage": 54.79, "elapsed_time": "0:02:12", "remaining_time": "0:01:49"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 292, "loss": 0.058, "lr": 4.196582144928398e-06, "epoch": 1.1027397260273972, "percentage": 55.14, "elapsed_time": "0:02:13", "remaining_time": "0:01:48"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 292, "loss": 0.0578, "lr": 4.143534279092613e-06, "epoch": 1.1095890410958904, "percentage": 55.48, "elapsed_time": "0:02:14", "remaining_time": "0:01:47"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 292, "loss": 0.0552, "lr": 4.090585551185031e-06, "epoch": 1.1164383561643836, "percentage": 55.82, "elapsed_time": "0:02:15", "remaining_time": "0:01:46"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 292, "loss": 0.0473, "lr": 4.037742090145851e-06, "epoch": 1.1232876712328768, "percentage": 56.16, "elapsed_time": "0:02:15", "remaining_time": "0:01:46"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 292, "loss": 0.0461, "lr": 3.985010012730382e-06, "epoch": 1.13013698630137, "percentage": 56.51, "elapsed_time": "0:02:16", "remaining_time": "0:01:45"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 292, "loss": 0.0581, "lr": 3.93239542280102e-06, "epoch": 1.1369863013698631, "percentage": 56.85, "elapsed_time": "0:02:17", "remaining_time": "0:01:44"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 292, "loss": 0.055, "lr": 3.879904410620703e-06, "epoch": 1.143835616438356, "percentage": 57.19, "elapsed_time": "0:02:18", "remaining_time": "0:01:43"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 292, "loss": 0.0762, "lr": 3.827543052147952e-06, "epoch": 1.1506849315068493, "percentage": 57.53, "elapsed_time": "0:02:19", "remaining_time": "0:01:42"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 292, "loss": 0.0589, "lr": 3.775317408333571e-06, "epoch": 1.1575342465753424, "percentage": 57.88, "elapsed_time": "0:02:19", "remaining_time": "0:01:41"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 292, "loss": 0.0615, "lr": 3.7232335244190656e-06, "epoch": 1.1643835616438356, "percentage": 58.22, "elapsed_time": "0:02:20", "remaining_time": "0:01:41"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 292, "loss": 0.0606, "lr": 3.6712974292369035e-06, "epoch": 1.1712328767123288, "percentage": 58.56, "elapsed_time": "0:02:21", "remaining_time": "0:01:40"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 292, "loss": 0.047, "lr": 3.6195151345126556e-06, "epoch": 1.178082191780822, "percentage": 58.9, "elapsed_time": "0:02:22", "remaining_time": "0:01:39"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 292, "loss": 0.068, "lr": 3.5678926341691283e-06, "epoch": 1.1849315068493151, "percentage": 59.25, "elapsed_time": "0:02:23", "remaining_time": "0:01:38"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 292, "loss": 0.0554, "lr": 3.5164359036325483e-06, "epoch": 1.191780821917808, "percentage": 59.59, "elapsed_time": "0:02:23", "remaining_time": "0:01:37"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 292, "loss": 0.049, "lr": 3.4651508991409016e-06, "epoch": 1.1986301369863013, "percentage": 59.93, "elapsed_time": "0:02:24", "remaining_time": "0:01:36"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 292, "loss": 0.0525, "lr": 3.4140435570544708e-06, "epoch": 1.2054794520547945, "percentage": 60.27, "elapsed_time": "0:02:25", "remaining_time": "0:01:35"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 292, "loss": 0.0491, "lr": 3.363119793168704e-06, "epoch": 1.2123287671232876, "percentage": 60.62, "elapsed_time": "0:02:26", "remaining_time": "0:01:35"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 292, "loss": 0.0538, "lr": 3.3123855020294344e-06, "epoch": 1.2191780821917808, "percentage": 60.96, "elapsed_time": "0:02:27", "remaining_time": "0:01:34"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 292, "loss": 0.0485, "lr": 3.26184655625058e-06, "epoch": 1.226027397260274, "percentage": 61.3, "elapsed_time": "0:02:28", "remaining_time": "0:01:33"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 292, "loss": 0.0382, "lr": 3.2115088058343725e-06, "epoch": 1.2328767123287672, "percentage": 61.64, "elapsed_time": "0:02:28", "remaining_time": "0:01:32"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 292, "loss": 0.0434, "lr": 3.161378077494205e-06, "epoch": 1.2397260273972603, "percentage": 61.99, "elapsed_time": "0:02:29", "remaining_time": "0:01:31"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 292, "loss": 0.056, "lr": 3.111460173980175e-06, "epoch": 1.2465753424657535, "percentage": 62.33, "elapsed_time": "0:02:30", "remaining_time": "0:01:30"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 292, "loss": 0.0388, "lr": 3.06176087340741e-06, "epoch": 1.2534246575342465, "percentage": 62.67, "elapsed_time": "0:02:31", "remaining_time": "0:01:30"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 292, "loss": 0.0445, "lr": 3.0122859285872214e-06, "epoch": 1.2602739726027397, "percentage": 63.01, "elapsed_time": "0:02:32", "remaining_time": "0:01:29"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 292, "loss": 0.0475, "lr": 2.9630410663612226e-06, "epoch": 1.2671232876712328, "percentage": 63.36, "elapsed_time": "0:02:32", "remaining_time": "0:01:28"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 292, "loss": 0.0532, "lr": 2.914031986938417e-06, "epoch": 1.273972602739726, "percentage": 63.7, "elapsed_time": "0:02:33", "remaining_time": "0:01:27"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 292, "loss": 0.0579, "lr": 2.865264363235396e-06, "epoch": 1.2808219178082192, "percentage": 64.04, "elapsed_time": "0:02:34", "remaining_time": "0:01:26"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 292, "loss": 0.0491, "lr": 2.816743840219681e-06, "epoch": 1.2876712328767124, "percentage": 64.38, "elapsed_time": "0:02:35", "remaining_time": "0:01:25"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 292, "loss": 0.0473, "lr": 2.7684760342563045e-06, "epoch": 1.2945205479452055, "percentage": 64.73, "elapsed_time": "0:02:36", "remaining_time": "0:01:25"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 292, "loss": 0.0419, "lr": 2.720466532457707e-06, "epoch": 1.3013698630136985, "percentage": 65.07, "elapsed_time": "0:02:36", "remaining_time": "0:01:24"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 292, "loss": 0.0518, "lr": 2.6727208920370063e-06, "epoch": 1.308219178082192, "percentage": 65.41, "elapsed_time": "0:02:37", "remaining_time": "0:01:23"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 292, "loss": 0.0511, "lr": 2.6252446396647503e-06, "epoch": 1.3150684931506849, "percentage": 65.75, "elapsed_time": "0:02:38", "remaining_time": "0:01:22"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 292, "loss": 0.0455, "lr": 2.578043270829178e-06, "epoch": 1.321917808219178, "percentage": 66.1, "elapsed_time": "0:02:39", "remaining_time": "0:01:21"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 292, "loss": 0.0578, "lr": 2.531122249200114e-06, "epoch": 1.3287671232876712, "percentage": 66.44, "elapsed_time": "0:02:39", "remaining_time": "0:01:20"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 292, "loss": 0.0537, "lr": 2.4844870059965337e-06, "epoch": 1.3356164383561644, "percentage": 66.78, "elapsed_time": "0:02:40", "remaining_time": "0:01:19"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 292, "loss": 0.06, "lr": 2.438142939357882e-06, "epoch": 1.3424657534246576, "percentage": 67.12, "elapsed_time": "0:02:41", "remaining_time": "0:01:19"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 292, "loss": 0.0666, "lr": 2.392095413719231e-06, "epoch": 1.3493150684931507, "percentage": 67.47, "elapsed_time": "0:02:42", "remaining_time": "0:01:18"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 292, "loss": 0.0641, "lr": 2.346349759190332e-06, "epoch": 1.356164383561644, "percentage": 67.81, "elapsed_time": "0:02:43", "remaining_time": "0:01:17"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 292, "loss": 0.0485, "lr": 2.3009112709386454e-06, "epoch": 1.3630136986301369, "percentage": 68.15, "elapsed_time": "0:02:43", "remaining_time": "0:01:16"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 292, "loss": 0.049, "lr": 2.2557852085764053e-06, "epoch": 1.36986301369863, "percentage": 68.49, "elapsed_time": "0:02:44", "remaining_time": "0:01:15"}
|
| 201 |
+
{"current_steps": 200, "total_steps": 292, "eval_loss": 0.17095182836055756, "epoch": 1.36986301369863, "percentage": 68.49, "elapsed_time": "0:02:45", "remaining_time": "0:01:16"}
|
| 202 |
+
{"current_steps": 201, "total_steps": 292, "loss": 0.0398, "lr": 2.2109767955518135e-06, "epoch": 1.3767123287671232, "percentage": 68.84, "elapsed_time": "0:02:46", "remaining_time": "0:01:15"}
|
| 203 |
+
{"current_steps": 202, "total_steps": 292, "loss": 0.05, "lr": 2.1664912185444127e-06, "epoch": 1.3835616438356164, "percentage": 69.18, "elapsed_time": "0:02:47", "remaining_time": "0:01:14"}
|
| 204 |
+
{"current_steps": 203, "total_steps": 292, "loss": 0.041, "lr": 2.1223336268647154e-06, "epoch": 1.3904109589041096, "percentage": 69.52, "elapsed_time": "0:02:48", "remaining_time": "0:01:13"}
|
| 205 |
+
{"current_steps": 204, "total_steps": 292, "loss": 0.0476, "lr": 2.0785091318581577e-06, "epoch": 1.3972602739726028, "percentage": 69.86, "elapsed_time": "0:02:48", "remaining_time": "0:01:12"}
|
| 206 |
+
{"current_steps": 205, "total_steps": 292, "loss": 0.0477, "lr": 2.035022806313449e-06, "epoch": 1.404109589041096, "percentage": 70.21, "elapsed_time": "0:02:49", "remaining_time": "0:01:12"}
|
| 207 |
+
{"current_steps": 206, "total_steps": 292, "loss": 0.057, "lr": 1.991879683875386e-06, "epoch": 1.410958904109589, "percentage": 70.55, "elapsed_time": "0:02:50", "remaining_time": "0:01:11"}
|
| 208 |
+
{"current_steps": 207, "total_steps": 292, "loss": 0.0447, "lr": 1.9490847584621993e-06, "epoch": 1.4178082191780823, "percentage": 70.89, "elapsed_time": "0:02:51", "remaining_time": "0:01:10"}
|
| 209 |
+
{"current_steps": 208, "total_steps": 292, "loss": 0.0455, "lr": 1.9066429836874844e-06, "epoch": 1.4246575342465753, "percentage": 71.23, "elapsed_time": "0:02:52", "remaining_time": "0:01:09"}
|
| 210 |
+
{"current_steps": 209, "total_steps": 292, "loss": 0.0572, "lr": 1.8645592722868223e-06, "epoch": 1.4315068493150684, "percentage": 71.58, "elapsed_time": "0:02:52", "remaining_time": "0:01:08"}
|
| 211 |
+
{"current_steps": 210, "total_steps": 292, "loss": 0.0403, "lr": 1.8228384955491136e-06, "epoch": 1.4383561643835616, "percentage": 71.92, "elapsed_time": "0:02:53", "remaining_time": "0:01:07"}
|
| 212 |
+
{"current_steps": 211, "total_steps": 292, "loss": 0.0463, "lr": 1.7814854827527144e-06, "epoch": 1.4452054794520548, "percentage": 72.26, "elapsed_time": "0:02:54", "remaining_time": "0:01:06"}
|
| 213 |
+
{"current_steps": 212, "total_steps": 292, "loss": 0.0618, "lr": 1.7405050206064372e-06, "epoch": 1.452054794520548, "percentage": 72.6, "elapsed_time": "0:02:55", "remaining_time": "0:01:06"}
|
| 214 |
+
{"current_steps": 213, "total_steps": 292, "loss": 0.0496, "lr": 1.6999018526954775e-06, "epoch": 1.4589041095890412, "percentage": 72.95, "elapsed_time": "0:02:56", "remaining_time": "0:01:05"}
|
| 215 |
+
{"current_steps": 214, "total_steps": 292, "loss": 0.045, "lr": 1.6596806789323317e-06, "epoch": 1.4657534246575343, "percentage": 73.29, "elapsed_time": "0:02:56", "remaining_time": "0:01:04"}
|
| 216 |
+
{"current_steps": 215, "total_steps": 292, "loss": 0.0522, "lr": 1.6198461550127758e-06, "epoch": 1.4726027397260273, "percentage": 73.63, "elapsed_time": "0:02:57", "remaining_time": "0:01:03"}
|
| 217 |
+
{"current_steps": 216, "total_steps": 292, "loss": 0.0447, "lr": 1.5804028918769488e-06, "epoch": 1.4794520547945205, "percentage": 73.97, "elapsed_time": "0:02:58", "remaining_time": "0:01:02"}
|
| 218 |
+
{"current_steps": 217, "total_steps": 292, "loss": 0.0467, "lr": 1.5413554551756321e-06, "epoch": 1.4863013698630136, "percentage": 74.32, "elapsed_time": "0:02:59", "remaining_time": "0:01:02"}
|
| 219 |
+
{"current_steps": 218, "total_steps": 292, "loss": 0.0495, "lr": 1.5027083647417657e-06, "epoch": 1.4931506849315068, "percentage": 74.66, "elapsed_time": "0:03:00", "remaining_time": "0:01:01"}
|
| 220 |
+
{"current_steps": 219, "total_steps": 292, "loss": 0.056, "lr": 1.4644660940672628e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:03:00", "remaining_time": "0:01:00"}
|
| 221 |
+
{"current_steps": 220, "total_steps": 292, "loss": 0.0413, "lr": 1.4266330697851955e-06, "epoch": 1.5068493150684932, "percentage": 75.34, "elapsed_time": "0:03:01", "remaining_time": "0:00:59"}
|
| 222 |
+
{"current_steps": 221, "total_steps": 292, "loss": 0.0387, "lr": 1.3892136711573983e-06, "epoch": 1.5136986301369864, "percentage": 75.68, "elapsed_time": "0:03:02", "remaining_time": "0:00:58"}
|
| 223 |
+
{"current_steps": 222, "total_steps": 292, "loss": 0.0467, "lr": 1.3522122295675616e-06, "epoch": 1.5205479452054793, "percentage": 76.03, "elapsed_time": "0:03:03", "remaining_time": "0:00:57"}
|
| 224 |
+
{"current_steps": 223, "total_steps": 292, "loss": 0.054, "lr": 1.3156330280198637e-06, "epoch": 1.5273972602739727, "percentage": 76.37, "elapsed_time": "0:03:04", "remaining_time": "0:00:56"}
|
| 225 |
+
{"current_steps": 224, "total_steps": 292, "loss": 0.0422, "lr": 1.2794803006431984e-06, "epoch": 1.5342465753424657, "percentage": 76.71, "elapsed_time": "0:03:04", "remaining_time": "0:00:56"}
|
| 226 |
+
{"current_steps": 225, "total_steps": 292, "loss": 0.0452, "lr": 1.2437582322010672e-06, "epoch": 1.541095890410959, "percentage": 77.05, "elapsed_time": "0:03:05", "remaining_time": "0:00:55"}
|
| 227 |
+
{"current_steps": 226, "total_steps": 292, "loss": 0.0444, "lr": 1.2084709576071885e-06, "epoch": 1.547945205479452, "percentage": 77.4, "elapsed_time": "0:03:06", "remaining_time": "0:00:54"}
|
| 228 |
+
{"current_steps": 227, "total_steps": 292, "loss": 0.0454, "lr": 1.1736225614468627e-06, "epoch": 1.5547945205479452, "percentage": 77.74, "elapsed_time": "0:03:07", "remaining_time": "0:00:53"}
|
| 229 |
+
{"current_steps": 228, "total_steps": 292, "loss": 0.0552, "lr": 1.1392170775041788e-06, "epoch": 1.5616438356164384, "percentage": 78.08, "elapsed_time": "0:03:08", "remaining_time": "0:00:52"}
|
| 230 |
+
{"current_steps": 229, "total_steps": 292, "loss": 0.0453, "lr": 1.1052584882950896e-06, "epoch": 1.5684931506849316, "percentage": 78.42, "elapsed_time": "0:03:08", "remaining_time": "0:00:51"}
|
| 231 |
+
{"current_steps": 230, "total_steps": 292, "loss": 0.0524, "lr": 1.0717507246064273e-06, "epoch": 1.5753424657534247, "percentage": 78.77, "elapsed_time": "0:03:09", "remaining_time": "0:00:51"}
|
| 232 |
+
{"current_steps": 231, "total_steps": 292, "loss": 0.0385, "lr": 1.0386976650409102e-06, "epoch": 1.5821917808219177, "percentage": 79.11, "elapsed_time": "0:03:10", "remaining_time": "0:00:50"}
|
| 233 |
+
{"current_steps": 232, "total_steps": 292, "loss": 0.0509, "lr": 1.0061031355681766e-06, "epoch": 1.589041095890411, "percentage": 79.45, "elapsed_time": "0:03:11", "remaining_time": "0:00:49"}
|
| 234 |
+
{"current_steps": 233, "total_steps": 292, "loss": 0.0541, "lr": 9.739709090819254e-07, "epoch": 1.595890410958904, "percentage": 79.79, "elapsed_time": "0:03:12", "remaining_time": "0:00:48"}
|
| 235 |
+
{"current_steps": 234, "total_steps": 292, "loss": 0.0415, "lr": 9.423047049631956e-07, "epoch": 1.6027397260273972, "percentage": 80.14, "elapsed_time": "0:03:13", "remaining_time": "0:00:47"}
|
| 236 |
+
{"current_steps": 235, "total_steps": 292, "loss": 0.0559, "lr": 9.111081886498374e-07, "epoch": 1.6095890410958904, "percentage": 80.48, "elapsed_time": "0:03:13", "remaining_time": "0:00:47"}
|
| 237 |
+
{"current_steps": 236, "total_steps": 292, "loss": 0.0483, "lr": 8.803849712122292e-07, "epoch": 1.6164383561643836, "percentage": 80.82, "elapsed_time": "0:03:14", "remaining_time": "0:00:46"}
|
| 238 |
+
{"current_steps": 237, "total_steps": 292, "loss": 0.0538, "lr": 8.501386089352858e-07, "epoch": 1.6232876712328768, "percentage": 81.16, "elapsed_time": "0:03:15", "remaining_time": "0:00:45"}
|
| 239 |
+
{"current_steps": 238, "total_steps": 292, "loss": 0.052, "lr": 8.203726029068149e-07, "epoch": 1.6301369863013697, "percentage": 81.51, "elapsed_time": "0:03:16", "remaining_time": "0:00:44"}
|
| 240 |
+
{"current_steps": 239, "total_steps": 292, "loss": 0.0466, "lr": 7.910903986122537e-07, "epoch": 1.6369863013698631, "percentage": 81.85, "elapsed_time": "0:03:17", "remaining_time": "0:00:43"}
|
| 241 |
+
{"current_steps": 240, "total_steps": 292, "loss": 0.0554, "lr": 7.622953855358456e-07, "epoch": 1.643835616438356, "percentage": 82.19, "elapsed_time": "0:03:17", "remaining_time": "0:00:42"}
|
| 242 |
+
{"current_steps": 241, "total_steps": 292, "loss": 0.0567, "lr": 7.339908967683007e-07, "epoch": 1.6506849315068495, "percentage": 82.53, "elapsed_time": "0:03:18", "remaining_time": "0:00:42"}
|
| 243 |
+
{"current_steps": 242, "total_steps": 292, "loss": 0.0481, "lr": 7.061802086209857e-07, "epoch": 1.6575342465753424, "percentage": 82.88, "elapsed_time": "0:03:19", "remaining_time": "0:00:41"}
|
| 244 |
+
{"current_steps": 243, "total_steps": 292, "loss": 0.0424, "lr": 6.788665402466782e-07, "epoch": 1.6643835616438356, "percentage": 83.22, "elapsed_time": "0:03:20", "remaining_time": "0:00:40"}
|
| 245 |
+
{"current_steps": 244, "total_steps": 292, "loss": 0.0438, "lr": 6.52053053266945e-07, "epoch": 1.6712328767123288, "percentage": 83.56, "elapsed_time": "0:03:21", "remaining_time": "0:00:39"}
|
| 246 |
+
{"current_steps": 245, "total_steps": 292, "loss": 0.0383, "lr": 6.257428514061764e-07, "epoch": 1.678082191780822, "percentage": 83.9, "elapsed_time": "0:03:21", "remaining_time": "0:00:38"}
|
| 247 |
+
{"current_steps": 246, "total_steps": 292, "loss": 0.0469, "lr": 5.999389801323219e-07, "epoch": 1.6849315068493151, "percentage": 84.25, "elapsed_time": "0:03:22", "remaining_time": "0:00:37"}
|
| 248 |
+
{"current_steps": 247, "total_steps": 292, "loss": 0.0587, "lr": 5.746444263043715e-07, "epoch": 1.691780821917808, "percentage": 84.59, "elapsed_time": "0:03:23", "remaining_time": "0:00:37"}
|
| 249 |
+
{"current_steps": 248, "total_steps": 292, "loss": 0.0421, "lr": 5.498621178266167e-07, "epoch": 1.6986301369863015, "percentage": 84.93, "elapsed_time": "0:03:24", "remaining_time": "0:00:36"}
|
| 250 |
+
{"current_steps": 249, "total_steps": 292, "loss": 0.0514, "lr": 5.255949233097451e-07, "epoch": 1.7054794520547945, "percentage": 85.27, "elapsed_time": "0:03:25", "remaining_time": "0:00:35"}
|
| 251 |
+
{"current_steps": 250, "total_steps": 292, "loss": 0.0643, "lr": 5.018456517387837e-07, "epoch": 1.7123287671232876, "percentage": 85.62, "elapsed_time": "0:03:25", "remaining_time": "0:00:34"}
|
| 252 |
+
{"current_steps": 251, "total_steps": 292, "loss": 0.0404, "lr": 4.786170521479588e-07, "epoch": 1.7191780821917808, "percentage": 85.96, "elapsed_time": "0:03:26", "remaining_time": "0:00:33"}
|
| 253 |
+
{"current_steps": 252, "total_steps": 292, "loss": 0.0445, "lr": 4.5591181330248534e-07, "epoch": 1.726027397260274, "percentage": 86.3, "elapsed_time": "0:03:27", "remaining_time": "0:00:32"}
|
| 254 |
+
{"current_steps": 253, "total_steps": 292, "loss": 0.0493, "lr": 4.3373256338733847e-07, "epoch": 1.7328767123287672, "percentage": 86.64, "elapsed_time": "0:03:28", "remaining_time": "0:00:32"}
|
| 255 |
+
{"current_steps": 254, "total_steps": 292, "loss": 0.0611, "lr": 4.1208186970303097e-07, "epoch": 1.7397260273972601, "percentage": 86.99, "elapsed_time": "0:03:29", "remaining_time": "0:00:31"}
|
| 256 |
+
{"current_steps": 255, "total_steps": 292, "loss": 0.0432, "lr": 3.90962238368448e-07, "epoch": 1.7465753424657535, "percentage": 87.33, "elapsed_time": "0:03:29", "remaining_time": "0:00:30"}
|
| 257 |
+
{"current_steps": 256, "total_steps": 292, "loss": 0.0321, "lr": 3.70376114030751e-07, "epoch": 1.7534246575342465, "percentage": 87.67, "elapsed_time": "0:03:30", "remaining_time": "0:00:29"}
|
| 258 |
+
{"current_steps": 257, "total_steps": 292, "loss": 0.0428, "lr": 3.503258795824105e-07, "epoch": 1.7602739726027399, "percentage": 88.01, "elapsed_time": "0:03:31", "remaining_time": "0:00:28"}
|
| 259 |
+
{"current_steps": 258, "total_steps": 292, "loss": 0.0527, "lr": 3.308138558853746e-07, "epoch": 1.7671232876712328, "percentage": 88.36, "elapsed_time": "0:03:32", "remaining_time": "0:00:27"}
|
| 260 |
+
{"current_steps": 259, "total_steps": 292, "loss": 0.0416, "lr": 3.1184230150243025e-07, "epoch": 1.773972602739726, "percentage": 88.7, "elapsed_time": "0:03:33", "remaining_time": "0:00:27"}
|
| 261 |
+
{"current_steps": 260, "total_steps": 292, "loss": 0.0492, "lr": 2.934134124357646e-07, "epoch": 1.7808219178082192, "percentage": 89.04, "elapsed_time": "0:03:33", "remaining_time": "0:00:26"}
|
| 262 |
+
{"current_steps": 261, "total_steps": 292, "loss": 0.0514, "lr": 2.755293218727739e-07, "epoch": 1.7876712328767124, "percentage": 89.38, "elapsed_time": "0:03:34", "remaining_time": "0:00:25"}
|
| 263 |
+
{"current_steps": 262, "total_steps": 292, "loss": 0.0436, "lr": 2.5819209993914185e-07, "epoch": 1.7945205479452055, "percentage": 89.73, "elapsed_time": "0:03:35", "remaining_time": "0:00:24"}
|
| 264 |
+
{"current_steps": 263, "total_steps": 292, "loss": 0.0429, "lr": 2.4140375345921895e-07, "epoch": 1.8013698630136985, "percentage": 90.07, "elapsed_time": "0:03:36", "remaining_time": "0:00:23"}
|
| 265 |
+
{"current_steps": 264, "total_steps": 292, "loss": 0.0387, "lr": 2.2516622572372416e-07, "epoch": 1.808219178082192, "percentage": 90.41, "elapsed_time": "0:03:36", "remaining_time": "0:00:23"}
|
| 266 |
+
{"current_steps": 265, "total_steps": 292, "loss": 0.0526, "lr": 2.094813962648101e-07, "epoch": 1.8150684931506849, "percentage": 90.75, "elapsed_time": "0:03:37", "remaining_time": "0:00:22"}
|
| 267 |
+
{"current_steps": 266, "total_steps": 292, "loss": 0.0451, "lr": 1.9435108063849684e-07, "epoch": 1.821917808219178, "percentage": 91.1, "elapsed_time": "0:03:38", "remaining_time": "0:00:21"}
|
| 268 |
+
{"current_steps": 267, "total_steps": 292, "loss": 0.0607, "lr": 1.7977703021452185e-07, "epoch": 1.8287671232876712, "percentage": 91.44, "elapsed_time": "0:03:39", "remaining_time": "0:00:20"}
|
| 269 |
+
{"current_steps": 268, "total_steps": 292, "loss": 0.0548, "lr": 1.6576093197361253e-07, "epoch": 1.8356164383561644, "percentage": 91.78, "elapsed_time": "0:03:40", "remaining_time": "0:00:19"}
|
| 270 |
+
{"current_steps": 269, "total_steps": 292, "loss": 0.051, "lr": 1.523044083122138e-07, "epoch": 1.8424657534246576, "percentage": 92.12, "elapsed_time": "0:03:40", "remaining_time": "0:00:18"}
|
| 271 |
+
{"current_steps": 270, "total_steps": 292, "loss": 0.0531, "lr": 1.39409016854693e-07, "epoch": 1.8493150684931505, "percentage": 92.47, "elapsed_time": "0:03:41", "remaining_time": "0:00:18"}
|
| 272 |
+
{"current_steps": 271, "total_steps": 292, "loss": 0.0466, "lr": 1.2707625027304104e-07, "epoch": 1.856164383561644, "percentage": 92.81, "elapsed_time": "0:03:42", "remaining_time": "0:00:17"}
|
| 273 |
+
{"current_steps": 272, "total_steps": 292, "loss": 0.049, "lr": 1.1530753611409151e-07, "epoch": 1.8630136986301369, "percentage": 93.15, "elapsed_time": "0:03:43", "remaining_time": "0:00:16"}
|
| 274 |
+
{"current_steps": 273, "total_steps": 292, "loss": 0.0572, "lr": 1.041042366342787e-07, "epoch": 1.8698630136986303, "percentage": 93.49, "elapsed_time": "0:03:44", "remaining_time": "0:00:15"}
|
| 275 |
+
{"current_steps": 274, "total_steps": 292, "loss": 0.0437, "lr": 9.346764864195335e-08, "epoch": 1.8767123287671232, "percentage": 93.84, "elapsed_time": "0:03:44", "remaining_time": "0:00:14"}
|
| 276 |
+
{"current_steps": 275, "total_steps": 292, "loss": 0.0529, "lr": 8.339900334727536e-08, "epoch": 1.8835616438356164, "percentage": 94.18, "elapsed_time": "0:03:45", "remaining_time": "0:00:13"}
|
| 277 |
+
{"current_steps": 276, "total_steps": 292, "loss": 0.0468, "lr": 7.389946621969679e-08, "epoch": 1.8904109589041096, "percentage": 94.52, "elapsed_time": "0:03:46", "remaining_time": "0:00:13"}
|
| 278 |
+
{"current_steps": 277, "total_steps": 292, "loss": 0.0377, "lr": 6.497013685305586e-08, "epoch": 1.8972602739726028, "percentage": 94.86, "elapsed_time": "0:03:47", "remaining_time": "0:00:12"}
|
| 279 |
+
{"current_steps": 278, "total_steps": 292, "loss": 0.0571, "lr": 5.661204883829763e-08, "epoch": 1.904109589041096, "percentage": 95.21, "elapsed_time": "0:03:48", "remaining_time": "0:00:11"}
|
| 280 |
+
{"current_steps": 279, "total_steps": 292, "loss": 0.0564, "lr": 4.8826169643832464e-08, "epoch": 1.910958904109589, "percentage": 95.55, "elapsed_time": "0:03:48", "remaining_time": "0:00:10"}
|
| 281 |
+
{"current_steps": 280, "total_steps": 292, "loss": 0.0455, "lr": 4.1613400503550114e-08, "epoch": 1.9178082191780823, "percentage": 95.89, "elapsed_time": "0:03:49", "remaining_time": "0:00:09"}
|
| 282 |
+
{"current_steps": 281, "total_steps": 292, "loss": 0.0531, "lr": 3.4974576312497564e-08, "epoch": 1.9246575342465753, "percentage": 96.23, "elapsed_time": "0:03:50", "remaining_time": "0:00:09"}
|
| 283 |
+
{"current_steps": 282, "total_steps": 292, "loss": 0.0384, "lr": 2.8910465530240793e-08, "epoch": 1.9315068493150684, "percentage": 96.58, "elapsed_time": "0:03:51", "remaining_time": "0:00:08"}
|
| 284 |
+
{"current_steps": 283, "total_steps": 292, "loss": 0.0596, "lr": 2.3421770091912044e-08, "epoch": 1.9383561643835616, "percentage": 96.92, "elapsed_time": "0:03:52", "remaining_time": "0:00:07"}
|
| 285 |
+
{"current_steps": 284, "total_steps": 292, "loss": 0.0558, "lr": 1.850912532696092e-08, "epoch": 1.9452054794520548, "percentage": 97.26, "elapsed_time": "0:03:53", "remaining_time": "0:00:06"}
|
| 286 |
+
{"current_steps": 285, "total_steps": 292, "loss": 0.0484, "lr": 1.4173099885610997e-08, "epoch": 1.952054794520548, "percentage": 97.6, "elapsed_time": "0:03:53", "remaining_time": "0:00:05"}
|
| 287 |
+
{"current_steps": 286, "total_steps": 292, "loss": 0.0514, "lr": 1.041419567303914e-08, "epoch": 1.958904109589041, "percentage": 97.95, "elapsed_time": "0:03:54", "remaining_time": "0:00:04"}
|
| 288 |
+
{"current_steps": 287, "total_steps": 292, "loss": 0.0439, "lr": 7.2328477912769756e-09, "epoch": 1.9657534246575343, "percentage": 98.29, "elapsed_time": "0:03:55", "remaining_time": "0:00:04"}
|
| 289 |
+
{"current_steps": 288, "total_steps": 292, "loss": 0.0437, "lr": 4.629424488850065e-09, "epoch": 1.9726027397260273, "percentage": 98.63, "elapsed_time": "0:03:56", "remaining_time": "0:00:03"}
|
| 290 |
+
{"current_steps": 289, "total_steps": 292, "loss": 0.0461, "lr": 2.604227118148117e-09, "epoch": 1.9794520547945207, "percentage": 98.97, "elapsed_time": "0:03:57", "remaining_time": "0:00:02"}
|
| 291 |
+
{"current_steps": 290, "total_steps": 292, "loss": 0.0463, "lr": 1.1574901005456662e-09, "epoch": 1.9863013698630136, "percentage": 99.32, "elapsed_time": "0:03:57", "remaining_time": "0:00:01"}
|
| 292 |
+
{"current_steps": 291, "total_steps": 292, "loss": 0.0527, "lr": 2.89380899267111e-10, "epoch": 1.9931506849315068, "percentage": 99.66, "elapsed_time": "0:03:58", "remaining_time": "0:00:00"}
|
| 293 |
+
{"current_steps": 292, "total_steps": 292, "loss": 0.0355, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:03:59", "remaining_time": "0:00:00"}
|
| 294 |
+
{"current_steps": 292, "total_steps": 292, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:12", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2094 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 292,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00684931506849315,
|
| 13 |
+
"grad_norm": 1.681326122254487,
|
| 14 |
+
"learning_rate": 9.999710619100732e-06,
|
| 15 |
+
"loss": 0.1611,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0136986301369863,
|
| 20 |
+
"grad_norm": 1.885174927262565,
|
| 21 |
+
"learning_rate": 9.998842509899456e-06,
|
| 22 |
+
"loss": 0.2252,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02054794520547945,
|
| 27 |
+
"grad_norm": 1.179602376110374,
|
| 28 |
+
"learning_rate": 9.997395772881853e-06,
|
| 29 |
+
"loss": 0.1579,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0273972602739726,
|
| 34 |
+
"grad_norm": 1.3212718738011484,
|
| 35 |
+
"learning_rate": 9.995370575511151e-06,
|
| 36 |
+
"loss": 0.1773,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03424657534246575,
|
| 41 |
+
"grad_norm": 1.2694099278803193,
|
| 42 |
+
"learning_rate": 9.992767152208724e-06,
|
| 43 |
+
"loss": 0.1473,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0410958904109589,
|
| 48 |
+
"grad_norm": 1.0978592118937816,
|
| 49 |
+
"learning_rate": 9.989585804326963e-06,
|
| 50 |
+
"loss": 0.1334,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04794520547945205,
|
| 55 |
+
"grad_norm": 1.3566448131161286,
|
| 56 |
+
"learning_rate": 9.985826900114391e-06,
|
| 57 |
+
"loss": 0.142,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0547945205479452,
|
| 62 |
+
"grad_norm": 1.284850640729133,
|
| 63 |
+
"learning_rate": 9.98149087467304e-06,
|
| 64 |
+
"loss": 0.1277,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06164383561643835,
|
| 69 |
+
"grad_norm": 1.2901956009935414,
|
| 70 |
+
"learning_rate": 9.97657822990809e-06,
|
| 71 |
+
"loss": 0.1551,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0684931506849315,
|
| 76 |
+
"grad_norm": 1.2427576389089712,
|
| 77 |
+
"learning_rate": 9.97108953446976e-06,
|
| 78 |
+
"loss": 0.1297,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07534246575342465,
|
| 83 |
+
"grad_norm": 1.5194810959051008,
|
| 84 |
+
"learning_rate": 9.965025423687505e-06,
|
| 85 |
+
"loss": 0.1555,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0821917808219178,
|
| 90 |
+
"grad_norm": 1.3243390902374774,
|
| 91 |
+
"learning_rate": 9.95838659949645e-06,
|
| 92 |
+
"loss": 0.1291,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08904109589041095,
|
| 97 |
+
"grad_norm": 1.4585506874626977,
|
| 98 |
+
"learning_rate": 9.951173830356168e-06,
|
| 99 |
+
"loss": 0.1326,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0958904109589041,
|
| 104 |
+
"grad_norm": 1.6276497265420493,
|
| 105 |
+
"learning_rate": 9.943387951161702e-06,
|
| 106 |
+
"loss": 0.1708,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.10273972602739725,
|
| 111 |
+
"grad_norm": 1.2741860443203552,
|
| 112 |
+
"learning_rate": 9.935029863146946e-06,
|
| 113 |
+
"loss": 0.1323,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1095890410958904,
|
| 118 |
+
"grad_norm": 1.220031414671926,
|
| 119 |
+
"learning_rate": 9.926100533780304e-06,
|
| 120 |
+
"loss": 0.1127,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.11643835616438356,
|
| 125 |
+
"grad_norm": 1.4702203721515053,
|
| 126 |
+
"learning_rate": 9.916600996652726e-06,
|
| 127 |
+
"loss": 0.143,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1232876712328767,
|
| 132 |
+
"grad_norm": 1.5239518421451066,
|
| 133 |
+
"learning_rate": 9.906532351358047e-06,
|
| 134 |
+
"loss": 0.1605,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13013698630136986,
|
| 139 |
+
"grad_norm": 1.3919880221564283,
|
| 140 |
+
"learning_rate": 9.895895763365722e-06,
|
| 141 |
+
"loss": 0.1399,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.136986301369863,
|
| 146 |
+
"grad_norm": 1.3716828836791362,
|
| 147 |
+
"learning_rate": 9.88469246388591e-06,
|
| 148 |
+
"loss": 0.1593,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14383561643835616,
|
| 153 |
+
"grad_norm": 1.3819895166348615,
|
| 154 |
+
"learning_rate": 9.872923749726959e-06,
|
| 155 |
+
"loss": 0.1503,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.1506849315068493,
|
| 160 |
+
"grad_norm": 1.2303338462493663,
|
| 161 |
+
"learning_rate": 9.860590983145307e-06,
|
| 162 |
+
"loss": 0.1267,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15753424657534246,
|
| 167 |
+
"grad_norm": 1.5135324094168527,
|
| 168 |
+
"learning_rate": 9.847695591687788e-06,
|
| 169 |
+
"loss": 0.173,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1643835616438356,
|
| 174 |
+
"grad_norm": 1.3421926292400204,
|
| 175 |
+
"learning_rate": 9.834239068026388e-06,
|
| 176 |
+
"loss": 0.1471,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17123287671232876,
|
| 181 |
+
"grad_norm": 1.2346572511285872,
|
| 182 |
+
"learning_rate": 9.82022296978548e-06,
|
| 183 |
+
"loss": 0.1275,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1780821917808219,
|
| 188 |
+
"grad_norm": 1.2396976103208144,
|
| 189 |
+
"learning_rate": 9.805648919361505e-06,
|
| 190 |
+
"loss": 0.1218,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18493150684931506,
|
| 195 |
+
"grad_norm": 1.3844170900094526,
|
| 196 |
+
"learning_rate": 9.790518603735191e-06,
|
| 197 |
+
"loss": 0.1465,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1917808219178082,
|
| 202 |
+
"grad_norm": 1.424145723431035,
|
| 203 |
+
"learning_rate": 9.774833774276278e-06,
|
| 204 |
+
"loss": 0.1447,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19863013698630136,
|
| 209 |
+
"grad_norm": 1.4725460541915585,
|
| 210 |
+
"learning_rate": 9.758596246540782e-06,
|
| 211 |
+
"loss": 0.176,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2054794520547945,
|
| 216 |
+
"grad_norm": 1.3278710551771418,
|
| 217 |
+
"learning_rate": 9.741807900060858e-06,
|
| 218 |
+
"loss": 0.1257,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21232876712328766,
|
| 223 |
+
"grad_norm": 1.5068094579436004,
|
| 224 |
+
"learning_rate": 9.724470678127226e-06,
|
| 225 |
+
"loss": 0.1676,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2191780821917808,
|
| 230 |
+
"grad_norm": 1.3895289229659755,
|
| 231 |
+
"learning_rate": 9.706586587564236e-06,
|
| 232 |
+
"loss": 0.159,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22602739726027396,
|
| 237 |
+
"grad_norm": 1.2976004166683957,
|
| 238 |
+
"learning_rate": 9.68815769849757e-06,
|
| 239 |
+
"loss": 0.149,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.2328767123287671,
|
| 244 |
+
"grad_norm": 1.4966687843901014,
|
| 245 |
+
"learning_rate": 9.669186144114627e-06,
|
| 246 |
+
"loss": 0.1567,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.23972602739726026,
|
| 251 |
+
"grad_norm": 1.3932254437475051,
|
| 252 |
+
"learning_rate": 9.649674120417591e-06,
|
| 253 |
+
"loss": 0.149,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.2465753424657534,
|
| 258 |
+
"grad_norm": 1.467531588632254,
|
| 259 |
+
"learning_rate": 9.62962388596925e-06,
|
| 260 |
+
"loss": 0.1526,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2534246575342466,
|
| 265 |
+
"grad_norm": 1.501698446219021,
|
| 266 |
+
"learning_rate": 9.609037761631552e-06,
|
| 267 |
+
"loss": 0.1705,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2602739726027397,
|
| 272 |
+
"grad_norm": 1.4152904201677108,
|
| 273 |
+
"learning_rate": 9.587918130296969e-06,
|
| 274 |
+
"loss": 0.1581,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2671232876712329,
|
| 279 |
+
"grad_norm": 1.4446872759238176,
|
| 280 |
+
"learning_rate": 9.566267436612662e-06,
|
| 281 |
+
"loss": 0.1432,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.273972602739726,
|
| 286 |
+
"grad_norm": 1.1804940453405255,
|
| 287 |
+
"learning_rate": 9.544088186697515e-06,
|
| 288 |
+
"loss": 0.1391,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2808219178082192,
|
| 293 |
+
"grad_norm": 1.144704853459006,
|
| 294 |
+
"learning_rate": 9.521382947852042e-06,
|
| 295 |
+
"loss": 0.1003,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2876712328767123,
|
| 300 |
+
"grad_norm": 1.351871436844165,
|
| 301 |
+
"learning_rate": 9.498154348261217e-06,
|
| 302 |
+
"loss": 0.1436,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2945205479452055,
|
| 307 |
+
"grad_norm": 1.3349758336974982,
|
| 308 |
+
"learning_rate": 9.474405076690257e-06,
|
| 309 |
+
"loss": 0.1481,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3013698630136986,
|
| 314 |
+
"grad_norm": 1.2477087916865037,
|
| 315 |
+
"learning_rate": 9.450137882173385e-06,
|
| 316 |
+
"loss": 0.134,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.3082191780821918,
|
| 321 |
+
"grad_norm": 1.1782092302507017,
|
| 322 |
+
"learning_rate": 9.425355573695628e-06,
|
| 323 |
+
"loss": 0.1253,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3150684931506849,
|
| 328 |
+
"grad_norm": 1.5204864248374035,
|
| 329 |
+
"learning_rate": 9.40006101986768e-06,
|
| 330 |
+
"loss": 0.1539,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3219178082191781,
|
| 335 |
+
"grad_norm": 1.1981915399905478,
|
| 336 |
+
"learning_rate": 9.374257148593824e-06,
|
| 337 |
+
"loss": 0.139,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.3287671232876712,
|
| 342 |
+
"grad_norm": 1.3887135298273199,
|
| 343 |
+
"learning_rate": 9.347946946733055e-06,
|
| 344 |
+
"loss": 0.1601,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3356164383561644,
|
| 349 |
+
"grad_norm": 1.2968095874294396,
|
| 350 |
+
"learning_rate": 9.321133459753322e-06,
|
| 351 |
+
"loss": 0.1539,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.3424657534246575,
|
| 356 |
+
"grad_norm": 1.4364868786802811,
|
| 357 |
+
"learning_rate": 9.293819791379016e-06,
|
| 358 |
+
"loss": 0.1634,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3493150684931507,
|
| 363 |
+
"grad_norm": 1.3540955184420536,
|
| 364 |
+
"learning_rate": 9.266009103231702e-06,
|
| 365 |
+
"loss": 0.1349,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.3561643835616438,
|
| 370 |
+
"grad_norm": 1.5237168671650452,
|
| 371 |
+
"learning_rate": 9.237704614464157e-06,
|
| 372 |
+
"loss": 0.1507,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.363013698630137,
|
| 377 |
+
"grad_norm": 1.5917345987329778,
|
| 378 |
+
"learning_rate": 9.208909601387748e-06,
|
| 379 |
+
"loss": 0.1458,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3698630136986301,
|
| 384 |
+
"grad_norm": 1.3156459420192685,
|
| 385 |
+
"learning_rate": 9.179627397093184e-06,
|
| 386 |
+
"loss": 0.1353,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3767123287671233,
|
| 391 |
+
"grad_norm": 1.325555508213008,
|
| 392 |
+
"learning_rate": 9.149861391064714e-06,
|
| 393 |
+
"loss": 0.1463,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3835616438356164,
|
| 398 |
+
"grad_norm": 1.3427034481236366,
|
| 399 |
+
"learning_rate": 9.119615028787771e-06,
|
| 400 |
+
"loss": 0.1469,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3904109589041096,
|
| 405 |
+
"grad_norm": 1.5027298401132316,
|
| 406 |
+
"learning_rate": 9.088891811350164e-06,
|
| 407 |
+
"loss": 0.1473,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3972602739726027,
|
| 412 |
+
"grad_norm": 1.3610506372704276,
|
| 413 |
+
"learning_rate": 9.057695295036806e-06,
|
| 414 |
+
"loss": 0.1419,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.4041095890410959,
|
| 419 |
+
"grad_norm": 1.2642265258066954,
|
| 420 |
+
"learning_rate": 9.026029090918076e-06,
|
| 421 |
+
"loss": 0.1257,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.410958904109589,
|
| 426 |
+
"grad_norm": 1.440991569152398,
|
| 427 |
+
"learning_rate": 8.993896864431825e-06,
|
| 428 |
+
"loss": 0.1533,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4178082191780822,
|
| 433 |
+
"grad_norm": 1.2813377733063473,
|
| 434 |
+
"learning_rate": 8.96130233495909e-06,
|
| 435 |
+
"loss": 0.125,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.4246575342465753,
|
| 440 |
+
"grad_norm": 1.3659169198349856,
|
| 441 |
+
"learning_rate": 8.928249275393572e-06,
|
| 442 |
+
"loss": 0.1472,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.4315068493150685,
|
| 447 |
+
"grad_norm": 1.2268590043988192,
|
| 448 |
+
"learning_rate": 8.894741511704911e-06,
|
| 449 |
+
"loss": 0.1205,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.4383561643835616,
|
| 454 |
+
"grad_norm": 1.3651988261826855,
|
| 455 |
+
"learning_rate": 8.860782922495821e-06,
|
| 456 |
+
"loss": 0.155,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.4452054794520548,
|
| 461 |
+
"grad_norm": 1.4870467841335842,
|
| 462 |
+
"learning_rate": 8.826377438553138e-06,
|
| 463 |
+
"loss": 0.1621,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4520547945205479,
|
| 468 |
+
"grad_norm": 1.4206840025436027,
|
| 469 |
+
"learning_rate": 8.791529042392813e-06,
|
| 470 |
+
"loss": 0.1345,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4589041095890411,
|
| 475 |
+
"grad_norm": 1.2039693664592048,
|
| 476 |
+
"learning_rate": 8.756241767798934e-06,
|
| 477 |
+
"loss": 0.1288,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.4657534246575342,
|
| 482 |
+
"grad_norm": 1.4229631805774499,
|
| 483 |
+
"learning_rate": 8.720519699356804e-06,
|
| 484 |
+
"loss": 0.1576,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.4726027397260274,
|
| 489 |
+
"grad_norm": 1.3422084011124138,
|
| 490 |
+
"learning_rate": 8.684366971980139e-06,
|
| 491 |
+
"loss": 0.1528,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.4794520547945205,
|
| 496 |
+
"grad_norm": 1.3588373354816943,
|
| 497 |
+
"learning_rate": 8.647787770432439e-06,
|
| 498 |
+
"loss": 0.1481,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.4863013698630137,
|
| 503 |
+
"grad_norm": 1.212585714583905,
|
| 504 |
+
"learning_rate": 8.610786328842602e-06,
|
| 505 |
+
"loss": 0.1165,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4931506849315068,
|
| 510 |
+
"grad_norm": 1.4063398493513959,
|
| 511 |
+
"learning_rate": 8.573366930214807e-06,
|
| 512 |
+
"loss": 0.1379,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.5,
|
| 517 |
+
"grad_norm": 1.355186771065564,
|
| 518 |
+
"learning_rate": 8.535533905932739e-06,
|
| 519 |
+
"loss": 0.1397,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.5068493150684932,
|
| 524 |
+
"grad_norm": 1.2478672834854156,
|
| 525 |
+
"learning_rate": 8.497291635258235e-06,
|
| 526 |
+
"loss": 0.1385,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.5136986301369864,
|
| 531 |
+
"grad_norm": 1.4534155589861801,
|
| 532 |
+
"learning_rate": 8.458644544824371e-06,
|
| 533 |
+
"loss": 0.144,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.5205479452054794,
|
| 538 |
+
"grad_norm": 1.04722797325612,
|
| 539 |
+
"learning_rate": 8.419597108123054e-06,
|
| 540 |
+
"loss": 0.1064,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5273972602739726,
|
| 545 |
+
"grad_norm": 1.3033203620715152,
|
| 546 |
+
"learning_rate": 8.380153844987225e-06,
|
| 547 |
+
"loss": 0.1317,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.5342465753424658,
|
| 552 |
+
"grad_norm": 1.2813679536683218,
|
| 553 |
+
"learning_rate": 8.340319321067668e-06,
|
| 554 |
+
"loss": 0.1091,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.541095890410959,
|
| 559 |
+
"grad_norm": 1.357419635870511,
|
| 560 |
+
"learning_rate": 8.300098147304523e-06,
|
| 561 |
+
"loss": 0.1514,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.547945205479452,
|
| 566 |
+
"grad_norm": 1.616321997313015,
|
| 567 |
+
"learning_rate": 8.259494979393563e-06,
|
| 568 |
+
"loss": 0.1736,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5547945205479452,
|
| 573 |
+
"grad_norm": 1.2556566795057675,
|
| 574 |
+
"learning_rate": 8.218514517247287e-06,
|
| 575 |
+
"loss": 0.1475,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5616438356164384,
|
| 580 |
+
"grad_norm": 1.5339692041811004,
|
| 581 |
+
"learning_rate": 8.177161504450887e-06,
|
| 582 |
+
"loss": 0.1314,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5684931506849316,
|
| 587 |
+
"grad_norm": 1.3594337341398315,
|
| 588 |
+
"learning_rate": 8.135440727713179e-06,
|
| 589 |
+
"loss": 0.1407,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5753424657534246,
|
| 594 |
+
"grad_norm": 1.6068961546835263,
|
| 595 |
+
"learning_rate": 8.093357016312518e-06,
|
| 596 |
+
"loss": 0.1854,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5821917808219178,
|
| 601 |
+
"grad_norm": 1.5306036516044554,
|
| 602 |
+
"learning_rate": 8.050915241537802e-06,
|
| 603 |
+
"loss": 0.1523,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.589041095890411,
|
| 608 |
+
"grad_norm": 1.2927891632747877,
|
| 609 |
+
"learning_rate": 8.008120316124612e-06,
|
| 610 |
+
"loss": 0.1348,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5958904109589042,
|
| 615 |
+
"grad_norm": 1.3176965732619508,
|
| 616 |
+
"learning_rate": 7.964977193686551e-06,
|
| 617 |
+
"loss": 0.1281,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.6027397260273972,
|
| 622 |
+
"grad_norm": 1.5465899452811223,
|
| 623 |
+
"learning_rate": 7.921490868141843e-06,
|
| 624 |
+
"loss": 0.1463,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.6095890410958904,
|
| 629 |
+
"grad_norm": 1.2375746843660715,
|
| 630 |
+
"learning_rate": 7.877666373135287e-06,
|
| 631 |
+
"loss": 0.1192,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.6164383561643836,
|
| 636 |
+
"grad_norm": 1.4677533194054369,
|
| 637 |
+
"learning_rate": 7.83350878145559e-06,
|
| 638 |
+
"loss": 0.1344,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.6232876712328768,
|
| 643 |
+
"grad_norm": 1.0567413642855223,
|
| 644 |
+
"learning_rate": 7.789023204448189e-06,
|
| 645 |
+
"loss": 0.1046,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.6301369863013698,
|
| 650 |
+
"grad_norm": 1.5916021905053273,
|
| 651 |
+
"learning_rate": 7.744214791423597e-06,
|
| 652 |
+
"loss": 0.1256,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.636986301369863,
|
| 657 |
+
"grad_norm": 1.5485965320906747,
|
| 658 |
+
"learning_rate": 7.699088729061355e-06,
|
| 659 |
+
"loss": 0.1704,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6438356164383562,
|
| 664 |
+
"grad_norm": 1.276476574995875,
|
| 665 |
+
"learning_rate": 7.653650240809667e-06,
|
| 666 |
+
"loss": 0.1284,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6506849315068494,
|
| 671 |
+
"grad_norm": 1.4508513839280315,
|
| 672 |
+
"learning_rate": 7.60790458628077e-06,
|
| 673 |
+
"loss": 0.1386,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6575342465753424,
|
| 678 |
+
"grad_norm": 1.362673656578717,
|
| 679 |
+
"learning_rate": 7.56185706064212e-06,
|
| 680 |
+
"loss": 0.1425,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6643835616438356,
|
| 685 |
+
"grad_norm": 1.1942244971415934,
|
| 686 |
+
"learning_rate": 7.5155129940034675e-06,
|
| 687 |
+
"loss": 0.1266,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6712328767123288,
|
| 692 |
+
"grad_norm": 1.4509447461224823,
|
| 693 |
+
"learning_rate": 7.468877750799887e-06,
|
| 694 |
+
"loss": 0.1447,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.678082191780822,
|
| 699 |
+
"grad_norm": 1.1958773982210433,
|
| 700 |
+
"learning_rate": 7.421956729170823e-06,
|
| 701 |
+
"loss": 0.1121,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.684931506849315,
|
| 706 |
+
"grad_norm": 1.3228337980715248,
|
| 707 |
+
"learning_rate": 7.374755360335253e-06,
|
| 708 |
+
"loss": 0.1257,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.6917808219178082,
|
| 713 |
+
"grad_norm": 1.3414764504690957,
|
| 714 |
+
"learning_rate": 7.327279107962995e-06,
|
| 715 |
+
"loss": 0.1357,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6986301369863014,
|
| 720 |
+
"grad_norm": 1.371994777223703,
|
| 721 |
+
"learning_rate": 7.279533467542295e-06,
|
| 722 |
+
"loss": 0.1585,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.7054794520547946,
|
| 727 |
+
"grad_norm": 1.4822871233303652,
|
| 728 |
+
"learning_rate": 7.2315239657436955e-06,
|
| 729 |
+
"loss": 0.1391,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.7123287671232876,
|
| 734 |
+
"grad_norm": 1.4385370443802574,
|
| 735 |
+
"learning_rate": 7.183256159780321e-06,
|
| 736 |
+
"loss": 0.1332,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.7191780821917808,
|
| 741 |
+
"grad_norm": 1.3952690951469036,
|
| 742 |
+
"learning_rate": 7.134735636764606e-06,
|
| 743 |
+
"loss": 0.1408,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.726027397260274,
|
| 748 |
+
"grad_norm": 1.399569696295691,
|
| 749 |
+
"learning_rate": 7.085968013061585e-06,
|
| 750 |
+
"loss": 0.1636,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.7328767123287672,
|
| 755 |
+
"grad_norm": 1.2655956227875966,
|
| 756 |
+
"learning_rate": 7.036958933638779e-06,
|
| 757 |
+
"loss": 0.1088,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.7397260273972602,
|
| 762 |
+
"grad_norm": 1.4045720425704544,
|
| 763 |
+
"learning_rate": 6.987714071412781e-06,
|
| 764 |
+
"loss": 0.1488,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.7465753424657534,
|
| 769 |
+
"grad_norm": 1.3873121633063503,
|
| 770 |
+
"learning_rate": 6.938239126592592e-06,
|
| 771 |
+
"loss": 0.1477,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.7534246575342466,
|
| 776 |
+
"grad_norm": 1.5087315862930963,
|
| 777 |
+
"learning_rate": 6.888539826019824e-06,
|
| 778 |
+
"loss": 0.1305,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7602739726027398,
|
| 783 |
+
"grad_norm": 1.312527435911279,
|
| 784 |
+
"learning_rate": 6.8386219225057945e-06,
|
| 785 |
+
"loss": 0.1312,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7671232876712328,
|
| 790 |
+
"grad_norm": 1.3494179538878939,
|
| 791 |
+
"learning_rate": 6.788491194165629e-06,
|
| 792 |
+
"loss": 0.1292,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.773972602739726,
|
| 797 |
+
"grad_norm": 1.242973511227221,
|
| 798 |
+
"learning_rate": 6.738153443749421e-06,
|
| 799 |
+
"loss": 0.1482,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.7808219178082192,
|
| 804 |
+
"grad_norm": 1.3896383294127825,
|
| 805 |
+
"learning_rate": 6.687614497970567e-06,
|
| 806 |
+
"loss": 0.1279,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.7876712328767124,
|
| 811 |
+
"grad_norm": 1.4932528045047573,
|
| 812 |
+
"learning_rate": 6.636880206831298e-06,
|
| 813 |
+
"loss": 0.1639,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.7945205479452054,
|
| 818 |
+
"grad_norm": 1.2620847315404062,
|
| 819 |
+
"learning_rate": 6.585956442945531e-06,
|
| 820 |
+
"loss": 0.1194,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.8013698630136986,
|
| 825 |
+
"grad_norm": 1.2276285818052897,
|
| 826 |
+
"learning_rate": 6.534849100859101e-06,
|
| 827 |
+
"loss": 0.114,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.8082191780821918,
|
| 832 |
+
"grad_norm": 1.3969636430912677,
|
| 833 |
+
"learning_rate": 6.483564096367452e-06,
|
| 834 |
+
"loss": 0.1606,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.815068493150685,
|
| 839 |
+
"grad_norm": 1.2695129268729821,
|
| 840 |
+
"learning_rate": 6.432107365830872e-06,
|
| 841 |
+
"loss": 0.1573,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.821917808219178,
|
| 846 |
+
"grad_norm": 1.3814796537444807,
|
| 847 |
+
"learning_rate": 6.380484865487346e-06,
|
| 848 |
+
"loss": 0.1624,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.8287671232876712,
|
| 853 |
+
"grad_norm": 1.3569843098289172,
|
| 854 |
+
"learning_rate": 6.328702570763098e-06,
|
| 855 |
+
"loss": 0.1474,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.8356164383561644,
|
| 860 |
+
"grad_norm": 1.3272524820679883,
|
| 861 |
+
"learning_rate": 6.276766475580935e-06,
|
| 862 |
+
"loss": 0.1298,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.8424657534246576,
|
| 867 |
+
"grad_norm": 1.4930150913696454,
|
| 868 |
+
"learning_rate": 6.224682591666431e-06,
|
| 869 |
+
"loss": 0.1597,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.8493150684931506,
|
| 874 |
+
"grad_norm": 1.1679807292300126,
|
| 875 |
+
"learning_rate": 6.1724569478520495e-06,
|
| 876 |
+
"loss": 0.1084,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.8561643835616438,
|
| 881 |
+
"grad_norm": 1.4509793836729856,
|
| 882 |
+
"learning_rate": 6.120095589379299e-06,
|
| 883 |
+
"loss": 0.1508,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.863013698630137,
|
| 888 |
+
"grad_norm": 1.3047264122844966,
|
| 889 |
+
"learning_rate": 6.067604577198981e-06,
|
| 890 |
+
"loss": 0.1365,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8698630136986302,
|
| 895 |
+
"grad_norm": 1.5322588491580615,
|
| 896 |
+
"learning_rate": 6.014989987269617e-06,
|
| 897 |
+
"loss": 0.1753,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8767123287671232,
|
| 902 |
+
"grad_norm": 1.2593436906353077,
|
| 903 |
+
"learning_rate": 5.96225790985415e-06,
|
| 904 |
+
"loss": 0.1221,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.8835616438356164,
|
| 909 |
+
"grad_norm": 1.1309025409587363,
|
| 910 |
+
"learning_rate": 5.909414448814971e-06,
|
| 911 |
+
"loss": 0.1053,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.8904109589041096,
|
| 916 |
+
"grad_norm": 1.5505281779641227,
|
| 917 |
+
"learning_rate": 5.856465720907388e-06,
|
| 918 |
+
"loss": 0.1655,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.8972602739726028,
|
| 923 |
+
"grad_norm": 1.407860114753361,
|
| 924 |
+
"learning_rate": 5.803417855071603e-06,
|
| 925 |
+
"loss": 0.1425,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.9041095890410958,
|
| 930 |
+
"grad_norm": 1.2323872762835282,
|
| 931 |
+
"learning_rate": 5.7502769917232635e-06,
|
| 932 |
+
"loss": 0.1408,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.910958904109589,
|
| 937 |
+
"grad_norm": 1.3421989948581072,
|
| 938 |
+
"learning_rate": 5.6970492820426994e-06,
|
| 939 |
+
"loss": 0.136,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.9178082191780822,
|
| 944 |
+
"grad_norm": 1.298316984662014,
|
| 945 |
+
"learning_rate": 5.643740887262905e-06,
|
| 946 |
+
"loss": 0.1209,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9246575342465754,
|
| 951 |
+
"grad_norm": 1.4328664698203022,
|
| 952 |
+
"learning_rate": 5.59035797795637e-06,
|
| 953 |
+
"loss": 0.1446,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.9315068493150684,
|
| 958 |
+
"grad_norm": 1.4421607530522575,
|
| 959 |
+
"learning_rate": 5.536906733320816e-06,
|
| 960 |
+
"loss": 0.1311,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.9383561643835616,
|
| 965 |
+
"grad_norm": 1.2101761643845483,
|
| 966 |
+
"learning_rate": 5.483393340463938e-06,
|
| 967 |
+
"loss": 0.1292,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.9452054794520548,
|
| 972 |
+
"grad_norm": 1.4264617265723734,
|
| 973 |
+
"learning_rate": 5.429823993687234e-06,
|
| 974 |
+
"loss": 0.1338,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.952054794520548,
|
| 979 |
+
"grad_norm": 1.245060053460186,
|
| 980 |
+
"learning_rate": 5.376204893769e-06,
|
| 981 |
+
"loss": 0.1211,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.958904109589041,
|
| 986 |
+
"grad_norm": 1.2443527818472415,
|
| 987 |
+
"learning_rate": 5.322542247246583e-06,
|
| 988 |
+
"loss": 0.1258,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.9657534246575342,
|
| 993 |
+
"grad_norm": 1.2017083185214588,
|
| 994 |
+
"learning_rate": 5.26884226569794e-06,
|
| 995 |
+
"loss": 0.1219,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.9726027397260274,
|
| 1000 |
+
"grad_norm": 1.3962140753424785,
|
| 1001 |
+
"learning_rate": 5.215111165022653e-06,
|
| 1002 |
+
"loss": 0.1345,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.9794520547945206,
|
| 1007 |
+
"grad_norm": 1.3196832738264022,
|
| 1008 |
+
"learning_rate": 5.161355164722416e-06,
|
| 1009 |
+
"loss": 0.1465,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.9863013698630136,
|
| 1014 |
+
"grad_norm": 1.355289493679882,
|
| 1015 |
+
"learning_rate": 5.107580487181112e-06,
|
| 1016 |
+
"loss": 0.1168,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.9931506849315068,
|
| 1021 |
+
"grad_norm": 1.104989144687109,
|
| 1022 |
+
"learning_rate": 5.0537933569445585e-06,
|
| 1023 |
+
"loss": 0.1156,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.0,
|
| 1028 |
+
"grad_norm": 1.279051072918835,
|
| 1029 |
+
"learning_rate": 5e-06,
|
| 1030 |
+
"loss": 0.1138,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.0068493150684932,
|
| 1035 |
+
"grad_norm": 0.8586515026588978,
|
| 1036 |
+
"learning_rate": 4.946206643055443e-06,
|
| 1037 |
+
"loss": 0.0632,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.0136986301369864,
|
| 1042 |
+
"grad_norm": 0.8425305140453805,
|
| 1043 |
+
"learning_rate": 4.89241951281889e-06,
|
| 1044 |
+
"loss": 0.04,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.0205479452054795,
|
| 1049 |
+
"grad_norm": 1.0168009580381887,
|
| 1050 |
+
"learning_rate": 4.838644835277585e-06,
|
| 1051 |
+
"loss": 0.0616,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.0273972602739727,
|
| 1056 |
+
"grad_norm": 0.8762024239173903,
|
| 1057 |
+
"learning_rate": 4.784888834977347e-06,
|
| 1058 |
+
"loss": 0.0485,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.0342465753424657,
|
| 1063 |
+
"grad_norm": 1.1160497678521428,
|
| 1064 |
+
"learning_rate": 4.731157734302063e-06,
|
| 1065 |
+
"loss": 0.0641,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.0410958904109588,
|
| 1070 |
+
"grad_norm": 0.8520250381620433,
|
| 1071 |
+
"learning_rate": 4.6774577527534195e-06,
|
| 1072 |
+
"loss": 0.0497,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.047945205479452,
|
| 1077 |
+
"grad_norm": 1.1045565105093977,
|
| 1078 |
+
"learning_rate": 4.623795106231001e-06,
|
| 1079 |
+
"loss": 0.06,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.0547945205479452,
|
| 1084 |
+
"grad_norm": 1.062312295012558,
|
| 1085 |
+
"learning_rate": 4.570176006312769e-06,
|
| 1086 |
+
"loss": 0.0479,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.0616438356164384,
|
| 1091 |
+
"grad_norm": 1.0739762922457419,
|
| 1092 |
+
"learning_rate": 4.516606659536063e-06,
|
| 1093 |
+
"loss": 0.0555,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.0684931506849316,
|
| 1098 |
+
"grad_norm": 1.2636651092806135,
|
| 1099 |
+
"learning_rate": 4.463093266679185e-06,
|
| 1100 |
+
"loss": 0.0647,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.0753424657534247,
|
| 1105 |
+
"grad_norm": 1.0721529657415103,
|
| 1106 |
+
"learning_rate": 4.40964202204363e-06,
|
| 1107 |
+
"loss": 0.0468,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.0821917808219177,
|
| 1112 |
+
"grad_norm": 1.231384399528468,
|
| 1113 |
+
"learning_rate": 4.356259112737096e-06,
|
| 1114 |
+
"loss": 0.0573,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.0890410958904109,
|
| 1119 |
+
"grad_norm": 1.275400189295023,
|
| 1120 |
+
"learning_rate": 4.302950717957304e-06,
|
| 1121 |
+
"loss": 0.0545,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.095890410958904,
|
| 1126 |
+
"grad_norm": 1.2570105134615532,
|
| 1127 |
+
"learning_rate": 4.249723008276737e-06,
|
| 1128 |
+
"loss": 0.0432,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.1027397260273972,
|
| 1133 |
+
"grad_norm": 1.7384583593326175,
|
| 1134 |
+
"learning_rate": 4.196582144928398e-06,
|
| 1135 |
+
"loss": 0.058,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.1095890410958904,
|
| 1140 |
+
"grad_norm": 1.6646996010877795,
|
| 1141 |
+
"learning_rate": 4.143534279092613e-06,
|
| 1142 |
+
"loss": 0.0578,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.1164383561643836,
|
| 1147 |
+
"grad_norm": 1.7368998293007798,
|
| 1148 |
+
"learning_rate": 4.090585551185031e-06,
|
| 1149 |
+
"loss": 0.0552,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.1232876712328768,
|
| 1154 |
+
"grad_norm": 1.3999971047454893,
|
| 1155 |
+
"learning_rate": 4.037742090145851e-06,
|
| 1156 |
+
"loss": 0.0473,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.13013698630137,
|
| 1161 |
+
"grad_norm": 1.3519516119795982,
|
| 1162 |
+
"learning_rate": 3.985010012730382e-06,
|
| 1163 |
+
"loss": 0.0461,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.1369863013698631,
|
| 1168 |
+
"grad_norm": 1.3441810471024978,
|
| 1169 |
+
"learning_rate": 3.93239542280102e-06,
|
| 1170 |
+
"loss": 0.0581,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.143835616438356,
|
| 1175 |
+
"grad_norm": 1.2434793247071403,
|
| 1176 |
+
"learning_rate": 3.879904410620703e-06,
|
| 1177 |
+
"loss": 0.055,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.1506849315068493,
|
| 1182 |
+
"grad_norm": 1.5638455529307607,
|
| 1183 |
+
"learning_rate": 3.827543052147952e-06,
|
| 1184 |
+
"loss": 0.0762,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.1575342465753424,
|
| 1189 |
+
"grad_norm": 1.443979029792356,
|
| 1190 |
+
"learning_rate": 3.775317408333571e-06,
|
| 1191 |
+
"loss": 0.0589,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.1643835616438356,
|
| 1196 |
+
"grad_norm": 1.3336601726659003,
|
| 1197 |
+
"learning_rate": 3.7232335244190656e-06,
|
| 1198 |
+
"loss": 0.0615,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.1712328767123288,
|
| 1203 |
+
"grad_norm": 1.5692599399327827,
|
| 1204 |
+
"learning_rate": 3.6712974292369035e-06,
|
| 1205 |
+
"loss": 0.0606,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.178082191780822,
|
| 1210 |
+
"grad_norm": 1.2762741127185413,
|
| 1211 |
+
"learning_rate": 3.6195151345126556e-06,
|
| 1212 |
+
"loss": 0.047,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.1849315068493151,
|
| 1217 |
+
"grad_norm": 1.303744739468211,
|
| 1218 |
+
"learning_rate": 3.5678926341691283e-06,
|
| 1219 |
+
"loss": 0.068,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.191780821917808,
|
| 1224 |
+
"grad_norm": 1.2540325544449227,
|
| 1225 |
+
"learning_rate": 3.5164359036325483e-06,
|
| 1226 |
+
"loss": 0.0554,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.1986301369863013,
|
| 1231 |
+
"grad_norm": 1.2658597598753545,
|
| 1232 |
+
"learning_rate": 3.4651508991409016e-06,
|
| 1233 |
+
"loss": 0.049,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.2054794520547945,
|
| 1238 |
+
"grad_norm": 1.348974065214196,
|
| 1239 |
+
"learning_rate": 3.4140435570544708e-06,
|
| 1240 |
+
"loss": 0.0525,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.2123287671232876,
|
| 1245 |
+
"grad_norm": 1.0308925199314465,
|
| 1246 |
+
"learning_rate": 3.363119793168704e-06,
|
| 1247 |
+
"loss": 0.0491,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.2191780821917808,
|
| 1252 |
+
"grad_norm": 1.28666663527575,
|
| 1253 |
+
"learning_rate": 3.3123855020294344e-06,
|
| 1254 |
+
"loss": 0.0538,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.226027397260274,
|
| 1259 |
+
"grad_norm": 1.1858734364568144,
|
| 1260 |
+
"learning_rate": 3.26184655625058e-06,
|
| 1261 |
+
"loss": 0.0485,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.2328767123287672,
|
| 1266 |
+
"grad_norm": 1.0621342326878584,
|
| 1267 |
+
"learning_rate": 3.2115088058343725e-06,
|
| 1268 |
+
"loss": 0.0382,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.2397260273972603,
|
| 1273 |
+
"grad_norm": 1.1779906602484476,
|
| 1274 |
+
"learning_rate": 3.161378077494205e-06,
|
| 1275 |
+
"loss": 0.0434,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.2465753424657535,
|
| 1280 |
+
"grad_norm": 1.2324381742409494,
|
| 1281 |
+
"learning_rate": 3.111460173980175e-06,
|
| 1282 |
+
"loss": 0.056,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.2534246575342465,
|
| 1287 |
+
"grad_norm": 1.016063229925584,
|
| 1288 |
+
"learning_rate": 3.06176087340741e-06,
|
| 1289 |
+
"loss": 0.0388,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.2602739726027397,
|
| 1294 |
+
"grad_norm": 1.0840691627496952,
|
| 1295 |
+
"learning_rate": 3.0122859285872214e-06,
|
| 1296 |
+
"loss": 0.0445,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.2671232876712328,
|
| 1301 |
+
"grad_norm": 1.1800022011324331,
|
| 1302 |
+
"learning_rate": 2.9630410663612226e-06,
|
| 1303 |
+
"loss": 0.0475,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.273972602739726,
|
| 1308 |
+
"grad_norm": 1.1502081584079749,
|
| 1309 |
+
"learning_rate": 2.914031986938417e-06,
|
| 1310 |
+
"loss": 0.0532,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.2808219178082192,
|
| 1315 |
+
"grad_norm": 1.1419379346372434,
|
| 1316 |
+
"learning_rate": 2.865264363235396e-06,
|
| 1317 |
+
"loss": 0.0579,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.2876712328767124,
|
| 1322 |
+
"grad_norm": 1.0957031139769768,
|
| 1323 |
+
"learning_rate": 2.816743840219681e-06,
|
| 1324 |
+
"loss": 0.0491,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.2945205479452055,
|
| 1329 |
+
"grad_norm": 1.0901187608784015,
|
| 1330 |
+
"learning_rate": 2.7684760342563045e-06,
|
| 1331 |
+
"loss": 0.0473,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.3013698630136985,
|
| 1336 |
+
"grad_norm": 1.0575483725072405,
|
| 1337 |
+
"learning_rate": 2.720466532457707e-06,
|
| 1338 |
+
"loss": 0.0419,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.308219178082192,
|
| 1343 |
+
"grad_norm": 1.135668561172309,
|
| 1344 |
+
"learning_rate": 2.6727208920370063e-06,
|
| 1345 |
+
"loss": 0.0518,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.3150684931506849,
|
| 1350 |
+
"grad_norm": 1.1680719294193762,
|
| 1351 |
+
"learning_rate": 2.6252446396647503e-06,
|
| 1352 |
+
"loss": 0.0511,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.321917808219178,
|
| 1357 |
+
"grad_norm": 1.1580638553895997,
|
| 1358 |
+
"learning_rate": 2.578043270829178e-06,
|
| 1359 |
+
"loss": 0.0455,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.3287671232876712,
|
| 1364 |
+
"grad_norm": 1.2471826242333424,
|
| 1365 |
+
"learning_rate": 2.531122249200114e-06,
|
| 1366 |
+
"loss": 0.0578,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.3356164383561644,
|
| 1371 |
+
"grad_norm": 1.3079303850475892,
|
| 1372 |
+
"learning_rate": 2.4844870059965337e-06,
|
| 1373 |
+
"loss": 0.0537,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.3424657534246576,
|
| 1378 |
+
"grad_norm": 1.3041132194078697,
|
| 1379 |
+
"learning_rate": 2.438142939357882e-06,
|
| 1380 |
+
"loss": 0.06,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.3493150684931507,
|
| 1385 |
+
"grad_norm": 1.2944993563381708,
|
| 1386 |
+
"learning_rate": 2.392095413719231e-06,
|
| 1387 |
+
"loss": 0.0666,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.356164383561644,
|
| 1392 |
+
"grad_norm": 1.3244575964243106,
|
| 1393 |
+
"learning_rate": 2.346349759190332e-06,
|
| 1394 |
+
"loss": 0.0641,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.3630136986301369,
|
| 1399 |
+
"grad_norm": 1.0913065870690115,
|
| 1400 |
+
"learning_rate": 2.3009112709386454e-06,
|
| 1401 |
+
"loss": 0.0485,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.36986301369863,
|
| 1406 |
+
"grad_norm": 1.3347948349150438,
|
| 1407 |
+
"learning_rate": 2.2557852085764053e-06,
|
| 1408 |
+
"loss": 0.049,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.36986301369863,
|
| 1413 |
+
"eval_loss": 0.17095182836055756,
|
| 1414 |
+
"eval_runtime": 0.9858,
|
| 1415 |
+
"eval_samples_per_second": 24.345,
|
| 1416 |
+
"eval_steps_per_second": 6.086,
|
| 1417 |
+
"step": 200
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.3767123287671232,
|
| 1421 |
+
"grad_norm": 1.0572048672090835,
|
| 1422 |
+
"learning_rate": 2.2109767955518135e-06,
|
| 1423 |
+
"loss": 0.0398,
|
| 1424 |
+
"step": 201
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.3835616438356164,
|
| 1428 |
+
"grad_norm": 1.1446986514437294,
|
| 1429 |
+
"learning_rate": 2.1664912185444127e-06,
|
| 1430 |
+
"loss": 0.05,
|
| 1431 |
+
"step": 202
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.3904109589041096,
|
| 1435 |
+
"grad_norm": 0.9532099686577133,
|
| 1436 |
+
"learning_rate": 2.1223336268647154e-06,
|
| 1437 |
+
"loss": 0.041,
|
| 1438 |
+
"step": 203
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.3972602739726028,
|
| 1442 |
+
"grad_norm": 1.0604020244789194,
|
| 1443 |
+
"learning_rate": 2.0785091318581577e-06,
|
| 1444 |
+
"loss": 0.0476,
|
| 1445 |
+
"step": 204
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.404109589041096,
|
| 1449 |
+
"grad_norm": 1.2205404764589123,
|
| 1450 |
+
"learning_rate": 2.035022806313449e-06,
|
| 1451 |
+
"loss": 0.0477,
|
| 1452 |
+
"step": 205
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.410958904109589,
|
| 1456 |
+
"grad_norm": 1.344957091931486,
|
| 1457 |
+
"learning_rate": 1.991879683875386e-06,
|
| 1458 |
+
"loss": 0.057,
|
| 1459 |
+
"step": 206
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.4178082191780823,
|
| 1463 |
+
"grad_norm": 1.2276818967649494,
|
| 1464 |
+
"learning_rate": 1.9490847584621993e-06,
|
| 1465 |
+
"loss": 0.0447,
|
| 1466 |
+
"step": 207
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.4246575342465753,
|
| 1470 |
+
"grad_norm": 1.1060696341477245,
|
| 1471 |
+
"learning_rate": 1.9066429836874844e-06,
|
| 1472 |
+
"loss": 0.0455,
|
| 1473 |
+
"step": 208
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.4315068493150684,
|
| 1477 |
+
"grad_norm": 1.3431910460892778,
|
| 1478 |
+
"learning_rate": 1.8645592722868223e-06,
|
| 1479 |
+
"loss": 0.0572,
|
| 1480 |
+
"step": 209
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.4383561643835616,
|
| 1484 |
+
"grad_norm": 1.0903993698691534,
|
| 1485 |
+
"learning_rate": 1.8228384955491136e-06,
|
| 1486 |
+
"loss": 0.0403,
|
| 1487 |
+
"step": 210
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.4452054794520548,
|
| 1491 |
+
"grad_norm": 1.2367516434543324,
|
| 1492 |
+
"learning_rate": 1.7814854827527144e-06,
|
| 1493 |
+
"loss": 0.0463,
|
| 1494 |
+
"step": 211
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.452054794520548,
|
| 1498 |
+
"grad_norm": 1.2531998615808957,
|
| 1499 |
+
"learning_rate": 1.7405050206064372e-06,
|
| 1500 |
+
"loss": 0.0618,
|
| 1501 |
+
"step": 212
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.4589041095890412,
|
| 1505 |
+
"grad_norm": 1.2985229177513158,
|
| 1506 |
+
"learning_rate": 1.6999018526954775e-06,
|
| 1507 |
+
"loss": 0.0496,
|
| 1508 |
+
"step": 213
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.4657534246575343,
|
| 1512 |
+
"grad_norm": 1.0805156976876642,
|
| 1513 |
+
"learning_rate": 1.6596806789323317e-06,
|
| 1514 |
+
"loss": 0.045,
|
| 1515 |
+
"step": 214
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.4726027397260273,
|
| 1519 |
+
"grad_norm": 1.1465918774198998,
|
| 1520 |
+
"learning_rate": 1.6198461550127758e-06,
|
| 1521 |
+
"loss": 0.0522,
|
| 1522 |
+
"step": 215
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.4794520547945205,
|
| 1526 |
+
"grad_norm": 1.1640328927581092,
|
| 1527 |
+
"learning_rate": 1.5804028918769488e-06,
|
| 1528 |
+
"loss": 0.0447,
|
| 1529 |
+
"step": 216
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.4863013698630136,
|
| 1533 |
+
"grad_norm": 1.2157084710869184,
|
| 1534 |
+
"learning_rate": 1.5413554551756321e-06,
|
| 1535 |
+
"loss": 0.0467,
|
| 1536 |
+
"step": 217
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.4931506849315068,
|
| 1540 |
+
"grad_norm": 1.118472346713982,
|
| 1541 |
+
"learning_rate": 1.5027083647417657e-06,
|
| 1542 |
+
"loss": 0.0495,
|
| 1543 |
+
"step": 218
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.5,
|
| 1547 |
+
"grad_norm": 1.3393005778338531,
|
| 1548 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 1549 |
+
"loss": 0.056,
|
| 1550 |
+
"step": 219
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.5068493150684932,
|
| 1554 |
+
"grad_norm": 1.2183563773799277,
|
| 1555 |
+
"learning_rate": 1.4266330697851955e-06,
|
| 1556 |
+
"loss": 0.0413,
|
| 1557 |
+
"step": 220
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.5136986301369864,
|
| 1561 |
+
"grad_norm": 1.1547102603873718,
|
| 1562 |
+
"learning_rate": 1.3892136711573983e-06,
|
| 1563 |
+
"loss": 0.0387,
|
| 1564 |
+
"step": 221
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.5205479452054793,
|
| 1568 |
+
"grad_norm": 1.0519260190067063,
|
| 1569 |
+
"learning_rate": 1.3522122295675616e-06,
|
| 1570 |
+
"loss": 0.0467,
|
| 1571 |
+
"step": 222
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.5273972602739727,
|
| 1575 |
+
"grad_norm": 1.293820836816745,
|
| 1576 |
+
"learning_rate": 1.3156330280198637e-06,
|
| 1577 |
+
"loss": 0.054,
|
| 1578 |
+
"step": 223
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.5342465753424657,
|
| 1582 |
+
"grad_norm": 1.0290894992949906,
|
| 1583 |
+
"learning_rate": 1.2794803006431984e-06,
|
| 1584 |
+
"loss": 0.0422,
|
| 1585 |
+
"step": 224
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.541095890410959,
|
| 1589 |
+
"grad_norm": 1.306351028186318,
|
| 1590 |
+
"learning_rate": 1.2437582322010672e-06,
|
| 1591 |
+
"loss": 0.0452,
|
| 1592 |
+
"step": 225
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.547945205479452,
|
| 1596 |
+
"grad_norm": 1.1696056423875878,
|
| 1597 |
+
"learning_rate": 1.2084709576071885e-06,
|
| 1598 |
+
"loss": 0.0444,
|
| 1599 |
+
"step": 226
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.5547945205479452,
|
| 1603 |
+
"grad_norm": 1.186236165896346,
|
| 1604 |
+
"learning_rate": 1.1736225614468627e-06,
|
| 1605 |
+
"loss": 0.0454,
|
| 1606 |
+
"step": 227
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.5616438356164384,
|
| 1610 |
+
"grad_norm": 1.2431287375191755,
|
| 1611 |
+
"learning_rate": 1.1392170775041788e-06,
|
| 1612 |
+
"loss": 0.0552,
|
| 1613 |
+
"step": 228
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.5684931506849316,
|
| 1617 |
+
"grad_norm": 1.0066132329773945,
|
| 1618 |
+
"learning_rate": 1.1052584882950896e-06,
|
| 1619 |
+
"loss": 0.0453,
|
| 1620 |
+
"step": 229
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.5753424657534247,
|
| 1624 |
+
"grad_norm": 1.1254717152610825,
|
| 1625 |
+
"learning_rate": 1.0717507246064273e-06,
|
| 1626 |
+
"loss": 0.0524,
|
| 1627 |
+
"step": 230
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.5821917808219177,
|
| 1631 |
+
"grad_norm": 1.2565062571687002,
|
| 1632 |
+
"learning_rate": 1.0386976650409102e-06,
|
| 1633 |
+
"loss": 0.0385,
|
| 1634 |
+
"step": 231
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.589041095890411,
|
| 1638 |
+
"grad_norm": 1.128134951204567,
|
| 1639 |
+
"learning_rate": 1.0061031355681766e-06,
|
| 1640 |
+
"loss": 0.0509,
|
| 1641 |
+
"step": 232
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.595890410958904,
|
| 1645 |
+
"grad_norm": 1.1300603515931058,
|
| 1646 |
+
"learning_rate": 9.739709090819254e-07,
|
| 1647 |
+
"loss": 0.0541,
|
| 1648 |
+
"step": 233
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.6027397260273972,
|
| 1652 |
+
"grad_norm": 1.0049977524206184,
|
| 1653 |
+
"learning_rate": 9.423047049631956e-07,
|
| 1654 |
+
"loss": 0.0415,
|
| 1655 |
+
"step": 234
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.6095890410958904,
|
| 1659 |
+
"grad_norm": 1.3871591183250866,
|
| 1660 |
+
"learning_rate": 9.111081886498374e-07,
|
| 1661 |
+
"loss": 0.0559,
|
| 1662 |
+
"step": 235
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.6164383561643836,
|
| 1666 |
+
"grad_norm": 1.4720951719862536,
|
| 1667 |
+
"learning_rate": 8.803849712122292e-07,
|
| 1668 |
+
"loss": 0.0483,
|
| 1669 |
+
"step": 236
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.6232876712328768,
|
| 1673 |
+
"grad_norm": 1.1581061964095616,
|
| 1674 |
+
"learning_rate": 8.501386089352858e-07,
|
| 1675 |
+
"loss": 0.0538,
|
| 1676 |
+
"step": 237
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.6301369863013697,
|
| 1680 |
+
"grad_norm": 1.2127418181518994,
|
| 1681 |
+
"learning_rate": 8.203726029068149e-07,
|
| 1682 |
+
"loss": 0.052,
|
| 1683 |
+
"step": 238
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.6369863013698631,
|
| 1687 |
+
"grad_norm": 1.1114779496019611,
|
| 1688 |
+
"learning_rate": 7.910903986122537e-07,
|
| 1689 |
+
"loss": 0.0466,
|
| 1690 |
+
"step": 239
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.643835616438356,
|
| 1694 |
+
"grad_norm": 1.2490146133864022,
|
| 1695 |
+
"learning_rate": 7.622953855358456e-07,
|
| 1696 |
+
"loss": 0.0554,
|
| 1697 |
+
"step": 240
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.6506849315068495,
|
| 1701 |
+
"grad_norm": 1.1476071970673816,
|
| 1702 |
+
"learning_rate": 7.339908967683007e-07,
|
| 1703 |
+
"loss": 0.0567,
|
| 1704 |
+
"step": 241
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.6575342465753424,
|
| 1708 |
+
"grad_norm": 1.2755564414681178,
|
| 1709 |
+
"learning_rate": 7.061802086209857e-07,
|
| 1710 |
+
"loss": 0.0481,
|
| 1711 |
+
"step": 242
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.6643835616438356,
|
| 1715 |
+
"grad_norm": 1.09065248699925,
|
| 1716 |
+
"learning_rate": 6.788665402466782e-07,
|
| 1717 |
+
"loss": 0.0424,
|
| 1718 |
+
"step": 243
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.6712328767123288,
|
| 1722 |
+
"grad_norm": 1.0551465512817664,
|
| 1723 |
+
"learning_rate": 6.52053053266945e-07,
|
| 1724 |
+
"loss": 0.0438,
|
| 1725 |
+
"step": 244
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.678082191780822,
|
| 1729 |
+
"grad_norm": 1.0435945791470003,
|
| 1730 |
+
"learning_rate": 6.257428514061764e-07,
|
| 1731 |
+
"loss": 0.0383,
|
| 1732 |
+
"step": 245
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.6849315068493151,
|
| 1736 |
+
"grad_norm": 1.0888214393154396,
|
| 1737 |
+
"learning_rate": 5.999389801323219e-07,
|
| 1738 |
+
"loss": 0.0469,
|
| 1739 |
+
"step": 246
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.691780821917808,
|
| 1743 |
+
"grad_norm": 1.264077054034139,
|
| 1744 |
+
"learning_rate": 5.746444263043715e-07,
|
| 1745 |
+
"loss": 0.0587,
|
| 1746 |
+
"step": 247
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.6986301369863015,
|
| 1750 |
+
"grad_norm": 1.0959411451227186,
|
| 1751 |
+
"learning_rate": 5.498621178266167e-07,
|
| 1752 |
+
"loss": 0.0421,
|
| 1753 |
+
"step": 248
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.7054794520547945,
|
| 1757 |
+
"grad_norm": 1.122284549427763,
|
| 1758 |
+
"learning_rate": 5.255949233097451e-07,
|
| 1759 |
+
"loss": 0.0514,
|
| 1760 |
+
"step": 249
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.7123287671232876,
|
| 1764 |
+
"grad_norm": 1.3012311154131373,
|
| 1765 |
+
"learning_rate": 5.018456517387837e-07,
|
| 1766 |
+
"loss": 0.0643,
|
| 1767 |
+
"step": 250
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.7191780821917808,
|
| 1771 |
+
"grad_norm": 1.0896480435450884,
|
| 1772 |
+
"learning_rate": 4.786170521479588e-07,
|
| 1773 |
+
"loss": 0.0404,
|
| 1774 |
+
"step": 251
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.726027397260274,
|
| 1778 |
+
"grad_norm": 1.0694727357917808,
|
| 1779 |
+
"learning_rate": 4.5591181330248534e-07,
|
| 1780 |
+
"loss": 0.0445,
|
| 1781 |
+
"step": 252
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.7328767123287672,
|
| 1785 |
+
"grad_norm": 1.1279927144437545,
|
| 1786 |
+
"learning_rate": 4.3373256338733847e-07,
|
| 1787 |
+
"loss": 0.0493,
|
| 1788 |
+
"step": 253
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.7397260273972601,
|
| 1792 |
+
"grad_norm": 1.401517163326509,
|
| 1793 |
+
"learning_rate": 4.1208186970303097e-07,
|
| 1794 |
+
"loss": 0.0611,
|
| 1795 |
+
"step": 254
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.7465753424657535,
|
| 1799 |
+
"grad_norm": 1.1287773022742749,
|
| 1800 |
+
"learning_rate": 3.90962238368448e-07,
|
| 1801 |
+
"loss": 0.0432,
|
| 1802 |
+
"step": 255
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.7534246575342465,
|
| 1806 |
+
"grad_norm": 0.9454218081951945,
|
| 1807 |
+
"learning_rate": 3.70376114030751e-07,
|
| 1808 |
+
"loss": 0.0321,
|
| 1809 |
+
"step": 256
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.7602739726027399,
|
| 1813 |
+
"grad_norm": 1.0853026394578211,
|
| 1814 |
+
"learning_rate": 3.503258795824105e-07,
|
| 1815 |
+
"loss": 0.0428,
|
| 1816 |
+
"step": 257
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.7671232876712328,
|
| 1820 |
+
"grad_norm": 1.2657010405292017,
|
| 1821 |
+
"learning_rate": 3.308138558853746e-07,
|
| 1822 |
+
"loss": 0.0527,
|
| 1823 |
+
"step": 258
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.773972602739726,
|
| 1827 |
+
"grad_norm": 1.081601059768871,
|
| 1828 |
+
"learning_rate": 3.1184230150243025e-07,
|
| 1829 |
+
"loss": 0.0416,
|
| 1830 |
+
"step": 259
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.7808219178082192,
|
| 1834 |
+
"grad_norm": 1.2178871055893603,
|
| 1835 |
+
"learning_rate": 2.934134124357646e-07,
|
| 1836 |
+
"loss": 0.0492,
|
| 1837 |
+
"step": 260
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.7876712328767124,
|
| 1841 |
+
"grad_norm": 1.1325261695724949,
|
| 1842 |
+
"learning_rate": 2.755293218727739e-07,
|
| 1843 |
+
"loss": 0.0514,
|
| 1844 |
+
"step": 261
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.7945205479452055,
|
| 1848 |
+
"grad_norm": 1.0896203238686062,
|
| 1849 |
+
"learning_rate": 2.5819209993914185e-07,
|
| 1850 |
+
"loss": 0.0436,
|
| 1851 |
+
"step": 262
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.8013698630136985,
|
| 1855 |
+
"grad_norm": 1.1462955990719499,
|
| 1856 |
+
"learning_rate": 2.4140375345921895e-07,
|
| 1857 |
+
"loss": 0.0429,
|
| 1858 |
+
"step": 263
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.808219178082192,
|
| 1862 |
+
"grad_norm": 0.9609054642547443,
|
| 1863 |
+
"learning_rate": 2.2516622572372416e-07,
|
| 1864 |
+
"loss": 0.0387,
|
| 1865 |
+
"step": 264
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.8150684931506849,
|
| 1869 |
+
"grad_norm": 1.1320165035370875,
|
| 1870 |
+
"learning_rate": 2.094813962648101e-07,
|
| 1871 |
+
"loss": 0.0526,
|
| 1872 |
+
"step": 265
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.821917808219178,
|
| 1876 |
+
"grad_norm": 1.1009898054758995,
|
| 1877 |
+
"learning_rate": 1.9435108063849684e-07,
|
| 1878 |
+
"loss": 0.0451,
|
| 1879 |
+
"step": 266
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.8287671232876712,
|
| 1883 |
+
"grad_norm": 1.1970876946239368,
|
| 1884 |
+
"learning_rate": 1.7977703021452185e-07,
|
| 1885 |
+
"loss": 0.0607,
|
| 1886 |
+
"step": 267
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.8356164383561644,
|
| 1890 |
+
"grad_norm": 1.0789405708685311,
|
| 1891 |
+
"learning_rate": 1.6576093197361253e-07,
|
| 1892 |
+
"loss": 0.0548,
|
| 1893 |
+
"step": 268
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.8424657534246576,
|
| 1897 |
+
"grad_norm": 1.2971908193363033,
|
| 1898 |
+
"learning_rate": 1.523044083122138e-07,
|
| 1899 |
+
"loss": 0.051,
|
| 1900 |
+
"step": 269
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.8493150684931505,
|
| 1904 |
+
"grad_norm": 1.38945249572563,
|
| 1905 |
+
"learning_rate": 1.39409016854693e-07,
|
| 1906 |
+
"loss": 0.0531,
|
| 1907 |
+
"step": 270
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.856164383561644,
|
| 1911 |
+
"grad_norm": 1.1250150055020298,
|
| 1912 |
+
"learning_rate": 1.2707625027304104e-07,
|
| 1913 |
+
"loss": 0.0466,
|
| 1914 |
+
"step": 271
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.8630136986301369,
|
| 1918 |
+
"grad_norm": 1.156415490841873,
|
| 1919 |
+
"learning_rate": 1.1530753611409151e-07,
|
| 1920 |
+
"loss": 0.049,
|
| 1921 |
+
"step": 272
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.8698630136986303,
|
| 1925 |
+
"grad_norm": 1.2599914891881805,
|
| 1926 |
+
"learning_rate": 1.041042366342787e-07,
|
| 1927 |
+
"loss": 0.0572,
|
| 1928 |
+
"step": 273
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.8767123287671232,
|
| 1932 |
+
"grad_norm": 1.1332068911263111,
|
| 1933 |
+
"learning_rate": 9.346764864195335e-08,
|
| 1934 |
+
"loss": 0.0437,
|
| 1935 |
+
"step": 274
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.8835616438356164,
|
| 1939 |
+
"grad_norm": 1.1783460646903443,
|
| 1940 |
+
"learning_rate": 8.339900334727536e-08,
|
| 1941 |
+
"loss": 0.0529,
|
| 1942 |
+
"step": 275
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.8904109589041096,
|
| 1946 |
+
"grad_norm": 1.3799917695012671,
|
| 1947 |
+
"learning_rate": 7.389946621969679e-08,
|
| 1948 |
+
"loss": 0.0468,
|
| 1949 |
+
"step": 276
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.8972602739726028,
|
| 1953 |
+
"grad_norm": 1.1364544186041734,
|
| 1954 |
+
"learning_rate": 6.497013685305586e-08,
|
| 1955 |
+
"loss": 0.0377,
|
| 1956 |
+
"step": 277
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.904109589041096,
|
| 1960 |
+
"grad_norm": 1.3823555107329624,
|
| 1961 |
+
"learning_rate": 5.661204883829763e-08,
|
| 1962 |
+
"loss": 0.0571,
|
| 1963 |
+
"step": 278
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.910958904109589,
|
| 1967 |
+
"grad_norm": 1.2472159662352063,
|
| 1968 |
+
"learning_rate": 4.8826169643832464e-08,
|
| 1969 |
+
"loss": 0.0564,
|
| 1970 |
+
"step": 279
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.9178082191780823,
|
| 1974 |
+
"grad_norm": 0.9979321136419178,
|
| 1975 |
+
"learning_rate": 4.1613400503550114e-08,
|
| 1976 |
+
"loss": 0.0455,
|
| 1977 |
+
"step": 280
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.9246575342465753,
|
| 1981 |
+
"grad_norm": 1.3003917397193072,
|
| 1982 |
+
"learning_rate": 3.4974576312497564e-08,
|
| 1983 |
+
"loss": 0.0531,
|
| 1984 |
+
"step": 281
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.9315068493150684,
|
| 1988 |
+
"grad_norm": 0.891331720320104,
|
| 1989 |
+
"learning_rate": 2.8910465530240793e-08,
|
| 1990 |
+
"loss": 0.0384,
|
| 1991 |
+
"step": 282
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.9383561643835616,
|
| 1995 |
+
"grad_norm": 1.3303789210771468,
|
| 1996 |
+
"learning_rate": 2.3421770091912044e-08,
|
| 1997 |
+
"loss": 0.0596,
|
| 1998 |
+
"step": 283
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.9452054794520548,
|
| 2002 |
+
"grad_norm": 1.3962569857235412,
|
| 2003 |
+
"learning_rate": 1.850912532696092e-08,
|
| 2004 |
+
"loss": 0.0558,
|
| 2005 |
+
"step": 284
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.952054794520548,
|
| 2009 |
+
"grad_norm": 1.1782292809508987,
|
| 2010 |
+
"learning_rate": 1.4173099885610997e-08,
|
| 2011 |
+
"loss": 0.0484,
|
| 2012 |
+
"step": 285
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.958904109589041,
|
| 2016 |
+
"grad_norm": 1.105134750666742,
|
| 2017 |
+
"learning_rate": 1.041419567303914e-08,
|
| 2018 |
+
"loss": 0.0514,
|
| 2019 |
+
"step": 286
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.9657534246575343,
|
| 2023 |
+
"grad_norm": 1.1041260161475412,
|
| 2024 |
+
"learning_rate": 7.2328477912769756e-09,
|
| 2025 |
+
"loss": 0.0439,
|
| 2026 |
+
"step": 287
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.9726027397260273,
|
| 2030 |
+
"grad_norm": 1.386469900945591,
|
| 2031 |
+
"learning_rate": 4.629424488850065e-09,
|
| 2032 |
+
"loss": 0.0437,
|
| 2033 |
+
"step": 288
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.9794520547945207,
|
| 2037 |
+
"grad_norm": 1.3839773628676217,
|
| 2038 |
+
"learning_rate": 2.604227118148117e-09,
|
| 2039 |
+
"loss": 0.0461,
|
| 2040 |
+
"step": 289
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.9863013698630136,
|
| 2044 |
+
"grad_norm": 1.2331483012041884,
|
| 2045 |
+
"learning_rate": 1.1574901005456662e-09,
|
| 2046 |
+
"loss": 0.0463,
|
| 2047 |
+
"step": 290
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.9931506849315068,
|
| 2051 |
+
"grad_norm": 1.2474270116129644,
|
| 2052 |
+
"learning_rate": 2.89380899267111e-10,
|
| 2053 |
+
"loss": 0.0527,
|
| 2054 |
+
"step": 291
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.0,
|
| 2058 |
+
"grad_norm": 0.9389958258991117,
|
| 2059 |
+
"learning_rate": 0.0,
|
| 2060 |
+
"loss": 0.0355,
|
| 2061 |
+
"step": 292
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.0,
|
| 2065 |
+
"step": 292,
|
| 2066 |
+
"total_flos": 3642198589440.0,
|
| 2067 |
+
"train_loss": 0.09577030846721506,
|
| 2068 |
+
"train_runtime": 252.2381,
|
| 2069 |
+
"train_samples_per_second": 18.467,
|
| 2070 |
+
"train_steps_per_second": 1.158
|
| 2071 |
+
}
|
| 2072 |
+
],
|
| 2073 |
+
"logging_steps": 1,
|
| 2074 |
+
"max_steps": 292,
|
| 2075 |
+
"num_input_tokens_seen": 0,
|
| 2076 |
+
"num_train_epochs": 2,
|
| 2077 |
+
"save_steps": 5000,
|
| 2078 |
+
"stateful_callbacks": {
|
| 2079 |
+
"TrainerControl": {
|
| 2080 |
+
"args": {
|
| 2081 |
+
"should_epoch_stop": false,
|
| 2082 |
+
"should_evaluate": false,
|
| 2083 |
+
"should_log": false,
|
| 2084 |
+
"should_save": true,
|
| 2085 |
+
"should_training_stop": true
|
| 2086 |
+
},
|
| 2087 |
+
"attributes": {}
|
| 2088 |
+
}
|
| 2089 |
+
},
|
| 2090 |
+
"total_flos": 3642198589440.0,
|
| 2091 |
+
"train_batch_size": 4,
|
| 2092 |
+
"trial_name": null,
|
| 2093 |
+
"trial_params": null
|
| 2094 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86d9dbe9dd68e81c4ba4e09878d7ef59dfebc72c923384dc9b6211f471110232
|
| 3 |
+
size 7288
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|