Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +61 -3
- added_tokens.json +24 -0
- all_results.json +8 -0
- chat_template.jinja +54 -0
- config.json +58 -0
- generation_config.json +13 -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_state.json +1639 -0
- training_args.bin +3 -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
CHANGED
|
@@ -1,3 +1,61 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: TravelPlanner_Instruct_1_5B_1128_1K_6Epoch
|
| 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 |
+
# TravelPlanner_Instruct_1_5B_1128_1K_6Epoch
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the travelplanner_1108_5k_filter_1128_1k dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- total_eval_batch_size: 64
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 6.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.57.1
|
| 59 |
+
- Pytorch 2.9.0+cu128
|
| 60 |
+
- Datasets 4.0.0
|
| 61 |
+
- Tokenizers 0.22.1
|
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 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 65142872268800.0,
|
| 4 |
+
"train_loss": 0.3093715236244494,
|
| 5 |
+
"train_runtime": 3748.6249,
|
| 6 |
+
"train_samples_per_second": 1.918,
|
| 7 |
+
"train_steps_per_second": 0.061
|
| 8 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 1536,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 8960,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention"
|
| 41 |
+
],
|
| 42 |
+
"max_position_embeddings": 32768,
|
| 43 |
+
"max_window_layers": 21,
|
| 44 |
+
"model_type": "qwen2",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_hidden_layers": 28,
|
| 47 |
+
"num_key_value_heads": 2,
|
| 48 |
+
"pad_token_id": 151643,
|
| 49 |
+
"rms_norm_eps": 1e-06,
|
| 50 |
+
"rope_scaling": null,
|
| 51 |
+
"rope_theta": 1000000.0,
|
| 52 |
+
"sliding_window": null,
|
| 53 |
+
"tie_word_embeddings": true,
|
| 54 |
+
"transformers_version": "4.57.1",
|
| 55 |
+
"use_cache": false,
|
| 56 |
+
"use_sliding_window": false,
|
| 57 |
+
"vocab_size": 151936
|
| 58 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"repetition_penalty": 1.1,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.1"
|
| 13 |
+
}
|
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 sha256:37709d9f3bfae296905bb9ce599f88a13cc50c511939f4f6459e38662937a9a0
|
| 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 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"padding_side": "right",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 65142872268800.0,
|
| 4 |
+
"train_loss": 0.3093715236244494,
|
| 5 |
+
"train_runtime": 3748.6249,
|
| 6 |
+
"train_samples_per_second": 1.918,
|
| 7 |
+
"train_steps_per_second": 0.061
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1639 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 228,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02666666666666667,
|
| 14 |
+
"grad_norm": 3.4266889538511824,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.6888,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05333333333333334,
|
| 21 |
+
"grad_norm": 3.4952376472627034,
|
| 22 |
+
"learning_rate": 2.173913043478261e-07,
|
| 23 |
+
"loss": 0.7291,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08,
|
| 28 |
+
"grad_norm": 3.469989508384374,
|
| 29 |
+
"learning_rate": 4.347826086956522e-07,
|
| 30 |
+
"loss": 0.6992,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.10666666666666667,
|
| 35 |
+
"grad_norm": 3.2394130196452524,
|
| 36 |
+
"learning_rate": 6.521739130434783e-07,
|
| 37 |
+
"loss": 0.7404,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.13333333333333333,
|
| 42 |
+
"grad_norm": 3.4424070618478453,
|
| 43 |
+
"learning_rate": 8.695652173913044e-07,
|
| 44 |
+
"loss": 0.709,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"grad_norm": 3.2220252965714,
|
| 50 |
+
"learning_rate": 1.0869565217391306e-06,
|
| 51 |
+
"loss": 0.7039,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.18666666666666668,
|
| 56 |
+
"grad_norm": 3.3351053835033078,
|
| 57 |
+
"learning_rate": 1.3043478260869566e-06,
|
| 58 |
+
"loss": 0.6988,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.21333333333333335,
|
| 63 |
+
"grad_norm": 3.1144216092901047,
|
| 64 |
+
"learning_rate": 1.521739130434783e-06,
|
| 65 |
+
"loss": 0.7072,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.24,
|
| 70 |
+
"grad_norm": 3.0492654173273355,
|
| 71 |
+
"learning_rate": 1.7391304347826088e-06,
|
| 72 |
+
"loss": 0.6926,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.26666666666666666,
|
| 77 |
+
"grad_norm": 2.409344231187956,
|
| 78 |
+
"learning_rate": 1.956521739130435e-06,
|
| 79 |
+
"loss": 0.6615,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.29333333333333333,
|
| 84 |
+
"grad_norm": 2.181542407771538,
|
| 85 |
+
"learning_rate": 2.173913043478261e-06,
|
| 86 |
+
"loss": 0.6811,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.32,
|
| 91 |
+
"grad_norm": 2.032081123281571,
|
| 92 |
+
"learning_rate": 2.391304347826087e-06,
|
| 93 |
+
"loss": 0.6742,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3466666666666667,
|
| 98 |
+
"grad_norm": 1.8876644523686943,
|
| 99 |
+
"learning_rate": 2.6086956521739132e-06,
|
| 100 |
+
"loss": 0.6392,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.37333333333333335,
|
| 105 |
+
"grad_norm": 1.4365268014427495,
|
| 106 |
+
"learning_rate": 2.8260869565217393e-06,
|
| 107 |
+
"loss": 0.617,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.4,
|
| 112 |
+
"grad_norm": 1.370856094380842,
|
| 113 |
+
"learning_rate": 3.043478260869566e-06,
|
| 114 |
+
"loss": 0.6008,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4266666666666667,
|
| 119 |
+
"grad_norm": 1.323470908392988,
|
| 120 |
+
"learning_rate": 3.2608695652173914e-06,
|
| 121 |
+
"loss": 0.5817,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4533333333333333,
|
| 126 |
+
"grad_norm": 1.2561497781936037,
|
| 127 |
+
"learning_rate": 3.4782608695652175e-06,
|
| 128 |
+
"loss": 0.5733,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.48,
|
| 133 |
+
"grad_norm": 1.2413967840650084,
|
| 134 |
+
"learning_rate": 3.6956521739130436e-06,
|
| 135 |
+
"loss": 0.5988,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5066666666666667,
|
| 140 |
+
"grad_norm": 1.3899702940941752,
|
| 141 |
+
"learning_rate": 3.91304347826087e-06,
|
| 142 |
+
"loss": 0.5396,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5333333333333333,
|
| 147 |
+
"grad_norm": 1.4622582214509077,
|
| 148 |
+
"learning_rate": 4.130434782608696e-06,
|
| 149 |
+
"loss": 0.5304,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.56,
|
| 154 |
+
"grad_norm": 1.2899053617951521,
|
| 155 |
+
"learning_rate": 4.347826086956522e-06,
|
| 156 |
+
"loss": 0.5242,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.5866666666666667,
|
| 161 |
+
"grad_norm": 1.1155507554661583,
|
| 162 |
+
"learning_rate": 4.565217391304348e-06,
|
| 163 |
+
"loss": 0.5258,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6133333333333333,
|
| 168 |
+
"grad_norm": 0.9522534050980639,
|
| 169 |
+
"learning_rate": 4.782608695652174e-06,
|
| 170 |
+
"loss": 0.481,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.64,
|
| 175 |
+
"grad_norm": 0.9659394127612826,
|
| 176 |
+
"learning_rate": 5e-06,
|
| 177 |
+
"loss": 0.4878,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.6666666666666666,
|
| 182 |
+
"grad_norm": 0.9053245665906665,
|
| 183 |
+
"learning_rate": 4.999706442259205e-06,
|
| 184 |
+
"loss": 0.461,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.6933333333333334,
|
| 189 |
+
"grad_norm": 1.1509616929217144,
|
| 190 |
+
"learning_rate": 4.9988258379777334e-06,
|
| 191 |
+
"loss": 0.4468,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.72,
|
| 196 |
+
"grad_norm": 1.1604235385459396,
|
| 197 |
+
"learning_rate": 4.99735839396215e-06,
|
| 198 |
+
"loss": 0.4647,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7466666666666667,
|
| 203 |
+
"grad_norm": 0.9895206119014155,
|
| 204 |
+
"learning_rate": 4.995304454836095e-06,
|
| 205 |
+
"loss": 0.4283,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.7733333333333333,
|
| 210 |
+
"grad_norm": 0.9491649541791972,
|
| 211 |
+
"learning_rate": 4.992664502959351e-06,
|
| 212 |
+
"loss": 0.4612,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.8,
|
| 217 |
+
"grad_norm": 0.8324769801957755,
|
| 218 |
+
"learning_rate": 4.989439158314566e-06,
|
| 219 |
+
"loss": 0.4222,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8266666666666667,
|
| 224 |
+
"grad_norm": 0.8749905156023321,
|
| 225 |
+
"learning_rate": 4.98562917836165e-06,
|
| 226 |
+
"loss": 0.4385,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8533333333333334,
|
| 231 |
+
"grad_norm": 0.8330081259993767,
|
| 232 |
+
"learning_rate": 4.9812354578598876e-06,
|
| 233 |
+
"loss": 0.4443,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.88,
|
| 238 |
+
"grad_norm": 0.8090934818921294,
|
| 239 |
+
"learning_rate": 4.976259028657812e-06,
|
| 240 |
+
"loss": 0.4048,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.9066666666666666,
|
| 245 |
+
"grad_norm": 0.7109417202363956,
|
| 246 |
+
"learning_rate": 4.970701059450872e-06,
|
| 247 |
+
"loss": 0.3689,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.9333333333333333,
|
| 252 |
+
"grad_norm": 0.6938543595016867,
|
| 253 |
+
"learning_rate": 4.964562855506976e-06,
|
| 254 |
+
"loss": 0.4065,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.96,
|
| 259 |
+
"grad_norm": 0.6565418890696835,
|
| 260 |
+
"learning_rate": 4.9578458583599495e-06,
|
| 261 |
+
"loss": 0.3898,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.9866666666666667,
|
| 266 |
+
"grad_norm": 0.6904449343799799,
|
| 267 |
+
"learning_rate": 4.950551645470998e-06,
|
| 268 |
+
"loss": 0.3937,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.0,
|
| 273 |
+
"grad_norm": 0.8632386328377553,
|
| 274 |
+
"learning_rate": 4.942681929858249e-06,
|
| 275 |
+
"loss": 0.3929,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.0266666666666666,
|
| 280 |
+
"grad_norm": 0.654323692693301,
|
| 281 |
+
"learning_rate": 4.934238559694448e-06,
|
| 282 |
+
"loss": 0.3685,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.0533333333333332,
|
| 287 |
+
"grad_norm": 0.66014775435246,
|
| 288 |
+
"learning_rate": 4.925223517872934e-06,
|
| 289 |
+
"loss": 0.3524,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.08,
|
| 294 |
+
"grad_norm": 0.6228188500582,
|
| 295 |
+
"learning_rate": 4.915638921541952e-06,
|
| 296 |
+
"loss": 0.3715,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.1066666666666667,
|
| 301 |
+
"grad_norm": 0.608380420203858,
|
| 302 |
+
"learning_rate": 4.905487021607462e-06,
|
| 303 |
+
"loss": 0.3694,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.1333333333333333,
|
| 308 |
+
"grad_norm": 0.6738086120855645,
|
| 309 |
+
"learning_rate": 4.894770202204509e-06,
|
| 310 |
+
"loss": 0.373,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.16,
|
| 315 |
+
"grad_norm": 0.6325886061740625,
|
| 316 |
+
"learning_rate": 4.883490980137327e-06,
|
| 317 |
+
"loss": 0.3517,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1866666666666668,
|
| 322 |
+
"grad_norm": 0.6362102908332291,
|
| 323 |
+
"learning_rate": 4.871652004288275e-06,
|
| 324 |
+
"loss": 0.3462,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.2133333333333334,
|
| 329 |
+
"grad_norm": 0.6459329605587532,
|
| 330 |
+
"learning_rate": 4.859256054995758e-06,
|
| 331 |
+
"loss": 0.3657,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.24,
|
| 336 |
+
"grad_norm": 0.6223955772841994,
|
| 337 |
+
"learning_rate": 4.846306043401268e-06,
|
| 338 |
+
"loss": 0.3549,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.2666666666666666,
|
| 343 |
+
"grad_norm": 0.5728460190556784,
|
| 344 |
+
"learning_rate": 4.832805010765724e-06,
|
| 345 |
+
"loss": 0.3409,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2933333333333334,
|
| 350 |
+
"grad_norm": 0.630118500621544,
|
| 351 |
+
"learning_rate": 4.8187561277552376e-06,
|
| 352 |
+
"loss": 0.3387,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.32,
|
| 357 |
+
"grad_norm": 0.5618777828912326,
|
| 358 |
+
"learning_rate": 4.804162693696494e-06,
|
| 359 |
+
"loss": 0.3246,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.3466666666666667,
|
| 364 |
+
"grad_norm": 0.585412087026401,
|
| 365 |
+
"learning_rate": 4.789028135801919e-06,
|
| 366 |
+
"loss": 0.3368,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3733333333333333,
|
| 371 |
+
"grad_norm": 0.5882761017367808,
|
| 372 |
+
"learning_rate": 4.773356008364812e-06,
|
| 373 |
+
"loss": 0.3344,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.4,
|
| 378 |
+
"grad_norm": 0.6137291248219465,
|
| 379 |
+
"learning_rate": 4.757149991924633e-06,
|
| 380 |
+
"loss": 0.3409,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.4266666666666667,
|
| 385 |
+
"grad_norm": 0.5769447707468955,
|
| 386 |
+
"learning_rate": 4.740413892402639e-06,
|
| 387 |
+
"loss": 0.3092,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.4533333333333334,
|
| 392 |
+
"grad_norm": 0.5685772345789922,
|
| 393 |
+
"learning_rate": 4.723151640208084e-06,
|
| 394 |
+
"loss": 0.3053,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.48,
|
| 399 |
+
"grad_norm": 0.5322004312242621,
|
| 400 |
+
"learning_rate": 4.705367289315172e-06,
|
| 401 |
+
"loss": 0.3029,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.5066666666666668,
|
| 406 |
+
"grad_norm": 0.585579783857172,
|
| 407 |
+
"learning_rate": 4.687065016310996e-06,
|
| 408 |
+
"loss": 0.32,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.5333333333333332,
|
| 413 |
+
"grad_norm": 0.5931576909282172,
|
| 414 |
+
"learning_rate": 4.668249119414692e-06,
|
| 415 |
+
"loss": 0.3403,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.56,
|
| 420 |
+
"grad_norm": 0.5591621205240426,
|
| 421 |
+
"learning_rate": 4.648924017468003e-06,
|
| 422 |
+
"loss": 0.3182,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.5866666666666667,
|
| 427 |
+
"grad_norm": 0.5830909036857576,
|
| 428 |
+
"learning_rate": 4.629094248897546e-06,
|
| 429 |
+
"loss": 0.3167,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.6133333333333333,
|
| 434 |
+
"grad_norm": 0.583649937601888,
|
| 435 |
+
"learning_rate": 4.608764470648971e-06,
|
| 436 |
+
"loss": 0.3118,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.6400000000000001,
|
| 441 |
+
"grad_norm": 0.588396936239003,
|
| 442 |
+
"learning_rate": 4.587939457093296e-06,
|
| 443 |
+
"loss": 0.3159,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.6666666666666665,
|
| 448 |
+
"grad_norm": 0.5613062911804365,
|
| 449 |
+
"learning_rate": 4.566624098905665e-06,
|
| 450 |
+
"loss": 0.2973,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.6933333333333334,
|
| 455 |
+
"grad_norm": 0.5867530961241251,
|
| 456 |
+
"learning_rate": 4.544823401916794e-06,
|
| 457 |
+
"loss": 0.297,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.72,
|
| 462 |
+
"grad_norm": 0.5966849971757487,
|
| 463 |
+
"learning_rate": 4.522542485937369e-06,
|
| 464 |
+
"loss": 0.3132,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.7466666666666666,
|
| 469 |
+
"grad_norm": 0.6042797485683739,
|
| 470 |
+
"learning_rate": 4.499786583555675e-06,
|
| 471 |
+
"loss": 0.3107,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.7733333333333334,
|
| 476 |
+
"grad_norm": 0.5559494399467654,
|
| 477 |
+
"learning_rate": 4.476561038908745e-06,
|
| 478 |
+
"loss": 0.303,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.8,
|
| 483 |
+
"grad_norm": 0.5201852777677712,
|
| 484 |
+
"learning_rate": 4.452871306427314e-06,
|
| 485 |
+
"loss": 0.288,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.8266666666666667,
|
| 490 |
+
"grad_norm": 0.5322395157847554,
|
| 491 |
+
"learning_rate": 4.428722949554858e-06,
|
| 492 |
+
"loss": 0.2913,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.8533333333333335,
|
| 497 |
+
"grad_norm": 0.5763144907527925,
|
| 498 |
+
"learning_rate": 4.404121639441047e-06,
|
| 499 |
+
"loss": 0.2938,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.88,
|
| 504 |
+
"grad_norm": 0.5871164319564681,
|
| 505 |
+
"learning_rate": 4.379073153609896e-06,
|
| 506 |
+
"loss": 0.3221,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.9066666666666667,
|
| 511 |
+
"grad_norm": 0.5828042207622075,
|
| 512 |
+
"learning_rate": 4.3535833746029335e-06,
|
| 513 |
+
"loss": 0.2988,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.9333333333333333,
|
| 518 |
+
"grad_norm": 0.5563592531877184,
|
| 519 |
+
"learning_rate": 4.32765828859771e-06,
|
| 520 |
+
"loss": 0.2898,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.96,
|
| 525 |
+
"grad_norm": 0.5576668322951177,
|
| 526 |
+
"learning_rate": 4.3013039840019675e-06,
|
| 527 |
+
"loss": 0.2909,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.9866666666666668,
|
| 532 |
+
"grad_norm": 0.5555355850959611,
|
| 533 |
+
"learning_rate": 4.274526650023801e-06,
|
| 534 |
+
"loss": 0.2823,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.0,
|
| 539 |
+
"grad_norm": 0.7487461178612541,
|
| 540 |
+
"learning_rate": 4.247332575218144e-06,
|
| 541 |
+
"loss": 0.2888,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.026666666666667,
|
| 546 |
+
"grad_norm": 0.5368556792415182,
|
| 547 |
+
"learning_rate": 4.2197281460099245e-06,
|
| 548 |
+
"loss": 0.278,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.0533333333333332,
|
| 553 |
+
"grad_norm": 0.5466158230872273,
|
| 554 |
+
"learning_rate": 4.191719845194246e-06,
|
| 555 |
+
"loss": 0.2655,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.08,
|
| 560 |
+
"grad_norm": 0.5784714101105528,
|
| 561 |
+
"learning_rate": 4.163314250413913e-06,
|
| 562 |
+
"loss": 0.2686,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.1066666666666665,
|
| 567 |
+
"grad_norm": 0.528830056126996,
|
| 568 |
+
"learning_rate": 4.134518032614713e-06,
|
| 569 |
+
"loss": 0.2639,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.1333333333333333,
|
| 574 |
+
"grad_norm": 0.5853686252107272,
|
| 575 |
+
"learning_rate": 4.105337954478756e-06,
|
| 576 |
+
"loss": 0.2856,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.16,
|
| 581 |
+
"grad_norm": 0.5652880420456027,
|
| 582 |
+
"learning_rate": 4.075780868836296e-06,
|
| 583 |
+
"loss": 0.2658,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.1866666666666665,
|
| 588 |
+
"grad_norm": 0.6138255133996864,
|
| 589 |
+
"learning_rate": 4.045853717056358e-06,
|
| 590 |
+
"loss": 0.2916,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.2133333333333334,
|
| 595 |
+
"grad_norm": 0.5678369174262076,
|
| 596 |
+
"learning_rate": 4.015563527416596e-06,
|
| 597 |
+
"loss": 0.2912,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.24,
|
| 602 |
+
"grad_norm": 0.544428477162963,
|
| 603 |
+
"learning_rate": 3.984917413452721e-06,
|
| 604 |
+
"loss": 0.2666,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.2666666666666666,
|
| 609 |
+
"grad_norm": 0.5197465962007571,
|
| 610 |
+
"learning_rate": 3.953922572287915e-06,
|
| 611 |
+
"loss": 0.2647,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.2933333333333334,
|
| 616 |
+
"grad_norm": 0.5908682015178118,
|
| 617 |
+
"learning_rate": 3.9225862829426184e-06,
|
| 618 |
+
"loss": 0.298,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.32,
|
| 623 |
+
"grad_norm": 0.5327208518214932,
|
| 624 |
+
"learning_rate": 3.890915904625075e-06,
|
| 625 |
+
"loss": 0.2827,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.3466666666666667,
|
| 630 |
+
"grad_norm": 0.5294622474205594,
|
| 631 |
+
"learning_rate": 3.858918875003053e-06,
|
| 632 |
+
"loss": 0.2592,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.3733333333333335,
|
| 637 |
+
"grad_norm": 0.5498281697696911,
|
| 638 |
+
"learning_rate": 3.8266027084571335e-06,
|
| 639 |
+
"loss": 0.2814,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.4,
|
| 644 |
+
"grad_norm": 0.5326415039012816,
|
| 645 |
+
"learning_rate": 3.793974994315991e-06,
|
| 646 |
+
"loss": 0.2764,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.4266666666666667,
|
| 651 |
+
"grad_norm": 0.5914316333042073,
|
| 652 |
+
"learning_rate": 3.7610433950740667e-06,
|
| 653 |
+
"loss": 0.2757,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.453333333333333,
|
| 658 |
+
"grad_norm": 0.5847805254640198,
|
| 659 |
+
"learning_rate": 3.7278156445920584e-06,
|
| 660 |
+
"loss": 0.2743,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.48,
|
| 665 |
+
"grad_norm": 0.5735479746836512,
|
| 666 |
+
"learning_rate": 3.6942995462806574e-06,
|
| 667 |
+
"loss": 0.277,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.506666666666667,
|
| 672 |
+
"grad_norm": 0.5705195168200543,
|
| 673 |
+
"learning_rate": 3.660502971267945e-06,
|
| 674 |
+
"loss": 0.2823,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.533333333333333,
|
| 679 |
+
"grad_norm": 0.5955256188327557,
|
| 680 |
+
"learning_rate": 3.626433856550886e-06,
|
| 681 |
+
"loss": 0.2778,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.56,
|
| 686 |
+
"grad_norm": 0.5542422176222224,
|
| 687 |
+
"learning_rate": 3.5921002031313586e-06,
|
| 688 |
+
"loss": 0.2675,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.586666666666667,
|
| 693 |
+
"grad_norm": 0.5091738620800978,
|
| 694 |
+
"learning_rate": 3.557510074137147e-06,
|
| 695 |
+
"loss": 0.2525,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.6133333333333333,
|
| 700 |
+
"grad_norm": 0.5656654050738699,
|
| 701 |
+
"learning_rate": 3.5226715929283507e-06,
|
| 702 |
+
"loss": 0.2634,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.64,
|
| 707 |
+
"grad_norm": 0.5868335213321295,
|
| 708 |
+
"learning_rate": 3.487592941189636e-06,
|
| 709 |
+
"loss": 0.2839,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.6666666666666665,
|
| 714 |
+
"grad_norm": 0.5595771642656175,
|
| 715 |
+
"learning_rate": 3.4522823570088073e-06,
|
| 716 |
+
"loss": 0.279,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.6933333333333334,
|
| 721 |
+
"grad_norm": 0.5341461864825586,
|
| 722 |
+
"learning_rate": 3.4167481329421204e-06,
|
| 723 |
+
"loss": 0.2635,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.7199999999999998,
|
| 728 |
+
"grad_norm": 0.5521131965135708,
|
| 729 |
+
"learning_rate": 3.380998614066805e-06,
|
| 730 |
+
"loss": 0.2717,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.7466666666666666,
|
| 735 |
+
"grad_norm": 0.5477287625722965,
|
| 736 |
+
"learning_rate": 3.345042196021257e-06,
|
| 737 |
+
"loss": 0.2727,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.7733333333333334,
|
| 742 |
+
"grad_norm": 0.5526588033092442,
|
| 743 |
+
"learning_rate": 3.3088873230333562e-06,
|
| 744 |
+
"loss": 0.2482,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.8,
|
| 749 |
+
"grad_norm": 0.5320678610511551,
|
| 750 |
+
"learning_rate": 3.272542485937369e-06,
|
| 751 |
+
"loss": 0.2591,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.8266666666666667,
|
| 756 |
+
"grad_norm": 0.5499639409354716,
|
| 757 |
+
"learning_rate": 3.2360162201799085e-06,
|
| 758 |
+
"loss": 0.2697,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.8533333333333335,
|
| 763 |
+
"grad_norm": 0.5425334847787104,
|
| 764 |
+
"learning_rate": 3.1993171038154203e-06,
|
| 765 |
+
"loss": 0.2478,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.88,
|
| 770 |
+
"grad_norm": 0.5929173721214359,
|
| 771 |
+
"learning_rate": 3.162453755491655e-06,
|
| 772 |
+
"loss": 0.2765,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.9066666666666667,
|
| 777 |
+
"grad_norm": 0.5939302794520043,
|
| 778 |
+
"learning_rate": 3.125434832425613e-06,
|
| 779 |
+
"loss": 0.2736,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.9333333333333336,
|
| 784 |
+
"grad_norm": 0.5325582815999844,
|
| 785 |
+
"learning_rate": 3.0882690283704355e-06,
|
| 786 |
+
"loss": 0.2612,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.96,
|
| 791 |
+
"grad_norm": 0.5431061052967631,
|
| 792 |
+
"learning_rate": 3.0509650715736977e-06,
|
| 793 |
+
"loss": 0.2556,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.986666666666667,
|
| 798 |
+
"grad_norm": 0.5683614209988255,
|
| 799 |
+
"learning_rate": 3.0135317227276247e-06,
|
| 800 |
+
"loss": 0.267,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.0,
|
| 805 |
+
"grad_norm": 0.7394515169597469,
|
| 806 |
+
"learning_rate": 2.975977772911671e-06,
|
| 807 |
+
"loss": 0.2716,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 3.026666666666667,
|
| 812 |
+
"grad_norm": 0.562308737707464,
|
| 813 |
+
"learning_rate": 2.93831204152797e-06,
|
| 814 |
+
"loss": 0.2329,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 3.0533333333333332,
|
| 819 |
+
"grad_norm": 0.5557860576175887,
|
| 820 |
+
"learning_rate": 2.9005433742301274e-06,
|
| 821 |
+
"loss": 0.2513,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 3.08,
|
| 826 |
+
"grad_norm": 0.5331122528386106,
|
| 827 |
+
"learning_rate": 2.8626806408458626e-06,
|
| 828 |
+
"loss": 0.2497,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 3.1066666666666665,
|
| 833 |
+
"grad_norm": 0.556351762234367,
|
| 834 |
+
"learning_rate": 2.8247327332939512e-06,
|
| 835 |
+
"loss": 0.2564,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.1333333333333333,
|
| 840 |
+
"grad_norm": 0.5559479679696169,
|
| 841 |
+
"learning_rate": 2.786708563496002e-06,
|
| 842 |
+
"loss": 0.2599,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.16,
|
| 847 |
+
"grad_norm": 0.553560188087277,
|
| 848 |
+
"learning_rate": 2.748617061283518e-06,
|
| 849 |
+
"loss": 0.2401,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 3.1866666666666665,
|
| 854 |
+
"grad_norm": 0.569570092950055,
|
| 855 |
+
"learning_rate": 2.710467172300768e-06,
|
| 856 |
+
"loss": 0.2409,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.2133333333333334,
|
| 861 |
+
"grad_norm": 0.5485988644135641,
|
| 862 |
+
"learning_rate": 2.672267855903927e-06,
|
| 863 |
+
"loss": 0.2507,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.24,
|
| 868 |
+
"grad_norm": 0.5236694365918342,
|
| 869 |
+
"learning_rate": 2.6340280830570142e-06,
|
| 870 |
+
"loss": 0.2354,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 3.2666666666666666,
|
| 875 |
+
"grad_norm": 0.5293512330766601,
|
| 876 |
+
"learning_rate": 2.595756834225089e-06,
|
| 877 |
+
"loss": 0.2424,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.2933333333333334,
|
| 882 |
+
"grad_norm": 0.5895763068526813,
|
| 883 |
+
"learning_rate": 2.5574630972652263e-06,
|
| 884 |
+
"loss": 0.2633,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.32,
|
| 889 |
+
"grad_norm": 0.5581361429014458,
|
| 890 |
+
"learning_rate": 2.5191558653157542e-06,
|
| 891 |
+
"loss": 0.2555,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.3466666666666667,
|
| 896 |
+
"grad_norm": 0.5569677522170305,
|
| 897 |
+
"learning_rate": 2.480844134684246e-06,
|
| 898 |
+
"loss": 0.2432,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.3733333333333335,
|
| 903 |
+
"grad_norm": 0.5377910861845262,
|
| 904 |
+
"learning_rate": 2.4425369027347746e-06,
|
| 905 |
+
"loss": 0.2434,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 3.4,
|
| 910 |
+
"grad_norm": 0.5755778341332671,
|
| 911 |
+
"learning_rate": 2.404243165774912e-06,
|
| 912 |
+
"loss": 0.2508,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.4266666666666667,
|
| 917 |
+
"grad_norm": 0.5542853490279926,
|
| 918 |
+
"learning_rate": 2.3659719169429866e-06,
|
| 919 |
+
"loss": 0.2512,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.453333333333333,
|
| 924 |
+
"grad_norm": 0.52798609473814,
|
| 925 |
+
"learning_rate": 2.3277321440960733e-06,
|
| 926 |
+
"loss": 0.2368,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.48,
|
| 931 |
+
"grad_norm": 0.5418899505614901,
|
| 932 |
+
"learning_rate": 2.2895328276992325e-06,
|
| 933 |
+
"loss": 0.2366,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.506666666666667,
|
| 938 |
+
"grad_norm": 0.5449785885107898,
|
| 939 |
+
"learning_rate": 2.251382938716482e-06,
|
| 940 |
+
"loss": 0.2542,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.533333333333333,
|
| 945 |
+
"grad_norm": 0.5274330454478506,
|
| 946 |
+
"learning_rate": 2.2132914365039993e-06,
|
| 947 |
+
"loss": 0.2329,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.56,
|
| 952 |
+
"grad_norm": 0.5371062578510242,
|
| 953 |
+
"learning_rate": 2.1752672667060488e-06,
|
| 954 |
+
"loss": 0.2396,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 3.586666666666667,
|
| 959 |
+
"grad_norm": 0.5468149466175712,
|
| 960 |
+
"learning_rate": 2.137319359154138e-06,
|
| 961 |
+
"loss": 0.2552,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 3.6133333333333333,
|
| 966 |
+
"grad_norm": 0.5641819586448543,
|
| 967 |
+
"learning_rate": 2.099456625769872e-06,
|
| 968 |
+
"loss": 0.2597,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.64,
|
| 973 |
+
"grad_norm": 0.5482564337935207,
|
| 974 |
+
"learning_rate": 2.0616879584720305e-06,
|
| 975 |
+
"loss": 0.2512,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.6666666666666665,
|
| 980 |
+
"grad_norm": 0.5425718066129126,
|
| 981 |
+
"learning_rate": 2.024022227088329e-06,
|
| 982 |
+
"loss": 0.2484,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.6933333333333334,
|
| 987 |
+
"grad_norm": 0.5458109129538277,
|
| 988 |
+
"learning_rate": 1.9864682772723757e-06,
|
| 989 |
+
"loss": 0.246,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 3.7199999999999998,
|
| 994 |
+
"grad_norm": 0.5272951796005869,
|
| 995 |
+
"learning_rate": 1.9490349284263036e-06,
|
| 996 |
+
"loss": 0.2384,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 3.7466666666666666,
|
| 1001 |
+
"grad_norm": 0.5746355047789706,
|
| 1002 |
+
"learning_rate": 1.9117309716295658e-06,
|
| 1003 |
+
"loss": 0.2674,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.7733333333333334,
|
| 1008 |
+
"grad_norm": 0.5630989463400743,
|
| 1009 |
+
"learning_rate": 1.8745651675743876e-06,
|
| 1010 |
+
"loss": 0.2429,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 3.8,
|
| 1015 |
+
"grad_norm": 0.535806014308918,
|
| 1016 |
+
"learning_rate": 1.8375462445083464e-06,
|
| 1017 |
+
"loss": 0.2458,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 3.8266666666666667,
|
| 1022 |
+
"grad_norm": 0.5447306623865108,
|
| 1023 |
+
"learning_rate": 1.8006828961845807e-06,
|
| 1024 |
+
"loss": 0.2549,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.8533333333333335,
|
| 1029 |
+
"grad_norm": 0.5417645592439112,
|
| 1030 |
+
"learning_rate": 1.7639837798200923e-06,
|
| 1031 |
+
"loss": 0.2546,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 3.88,
|
| 1036 |
+
"grad_norm": 0.5326099442271579,
|
| 1037 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 1038 |
+
"loss": 0.2413,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 3.9066666666666667,
|
| 1043 |
+
"grad_norm": 0.5664176851996381,
|
| 1044 |
+
"learning_rate": 1.6911126769666442e-06,
|
| 1045 |
+
"loss": 0.2548,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.9333333333333336,
|
| 1050 |
+
"grad_norm": 0.5179500788048627,
|
| 1051 |
+
"learning_rate": 1.6549578039787436e-06,
|
| 1052 |
+
"loss": 0.2284,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 3.96,
|
| 1057 |
+
"grad_norm": 0.559888271044599,
|
| 1058 |
+
"learning_rate": 1.6190013859331958e-06,
|
| 1059 |
+
"loss": 0.2444,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 3.986666666666667,
|
| 1064 |
+
"grad_norm": 0.5595404291449413,
|
| 1065 |
+
"learning_rate": 1.5832518670578802e-06,
|
| 1066 |
+
"loss": 0.2473,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 4.0,
|
| 1071 |
+
"grad_norm": 0.7148708586527189,
|
| 1072 |
+
"learning_rate": 1.5477176429911934e-06,
|
| 1073 |
+
"loss": 0.2197,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 4.026666666666666,
|
| 1078 |
+
"grad_norm": 0.5112538739785468,
|
| 1079 |
+
"learning_rate": 1.5124070588103648e-06,
|
| 1080 |
+
"loss": 0.2293,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.053333333333334,
|
| 1085 |
+
"grad_norm": 0.5304245657575032,
|
| 1086 |
+
"learning_rate": 1.4773284070716504e-06,
|
| 1087 |
+
"loss": 0.2339,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.08,
|
| 1092 |
+
"grad_norm": 0.5068141109789993,
|
| 1093 |
+
"learning_rate": 1.4424899258628533e-06,
|
| 1094 |
+
"loss": 0.2231,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 4.1066666666666665,
|
| 1099 |
+
"grad_norm": 0.5380134592068022,
|
| 1100 |
+
"learning_rate": 1.4078997968686425e-06,
|
| 1101 |
+
"loss": 0.2384,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 4.133333333333334,
|
| 1106 |
+
"grad_norm": 0.5031815941088315,
|
| 1107 |
+
"learning_rate": 1.373566143449115e-06,
|
| 1108 |
+
"loss": 0.228,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.16,
|
| 1113 |
+
"grad_norm": 0.5565003784589194,
|
| 1114 |
+
"learning_rate": 1.3394970287320553e-06,
|
| 1115 |
+
"loss": 0.2235,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.1866666666666665,
|
| 1120 |
+
"grad_norm": 0.5554342604721864,
|
| 1121 |
+
"learning_rate": 1.3057004537193424e-06,
|
| 1122 |
+
"loss": 0.2336,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 4.213333333333333,
|
| 1127 |
+
"grad_norm": 0.5692473035057618,
|
| 1128 |
+
"learning_rate": 1.2721843554079418e-06,
|
| 1129 |
+
"loss": 0.2276,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.24,
|
| 1134 |
+
"grad_norm": 0.5476348666959899,
|
| 1135 |
+
"learning_rate": 1.238956604925934e-06,
|
| 1136 |
+
"loss": 0.242,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 4.266666666666667,
|
| 1141 |
+
"grad_norm": 0.5479898757665639,
|
| 1142 |
+
"learning_rate": 1.206025005684009e-06,
|
| 1143 |
+
"loss": 0.2395,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 4.293333333333333,
|
| 1148 |
+
"grad_norm": 0.5449797930389495,
|
| 1149 |
+
"learning_rate": 1.1733972915428665e-06,
|
| 1150 |
+
"loss": 0.2319,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 4.32,
|
| 1155 |
+
"grad_norm": 0.5597316352681958,
|
| 1156 |
+
"learning_rate": 1.1410811249969475e-06,
|
| 1157 |
+
"loss": 0.2451,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 4.346666666666667,
|
| 1162 |
+
"grad_norm": 0.5661582025899617,
|
| 1163 |
+
"learning_rate": 1.1090840953749253e-06,
|
| 1164 |
+
"loss": 0.2402,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 4.373333333333333,
|
| 1169 |
+
"grad_norm": 0.5616482407372545,
|
| 1170 |
+
"learning_rate": 1.0774137170573826e-06,
|
| 1171 |
+
"loss": 0.2369,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 4.4,
|
| 1176 |
+
"grad_norm": 0.5506782168905767,
|
| 1177 |
+
"learning_rate": 1.0460774277120866e-06,
|
| 1178 |
+
"loss": 0.2389,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 4.426666666666667,
|
| 1183 |
+
"grad_norm": 0.5548343238691738,
|
| 1184 |
+
"learning_rate": 1.0150825865472813e-06,
|
| 1185 |
+
"loss": 0.2413,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 4.453333333333333,
|
| 1190 |
+
"grad_norm": 0.513274671756937,
|
| 1191 |
+
"learning_rate": 9.844364725834058e-07,
|
| 1192 |
+
"loss": 0.2331,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.48,
|
| 1197 |
+
"grad_norm": 0.5289069396029727,
|
| 1198 |
+
"learning_rate": 9.541462829436426e-07,
|
| 1199 |
+
"loss": 0.2238,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.506666666666667,
|
| 1204 |
+
"grad_norm": 0.5487013257080448,
|
| 1205 |
+
"learning_rate": 9.24219131163705e-07,
|
| 1206 |
+
"loss": 0.2396,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 4.533333333333333,
|
| 1211 |
+
"grad_norm": 0.558375632390674,
|
| 1212 |
+
"learning_rate": 8.946620455212438e-07,
|
| 1213 |
+
"loss": 0.2417,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 4.5600000000000005,
|
| 1218 |
+
"grad_norm": 0.5160143794268199,
|
| 1219 |
+
"learning_rate": 8.654819673852874e-07,
|
| 1220 |
+
"loss": 0.222,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 4.586666666666667,
|
| 1225 |
+
"grad_norm": 0.5179225596985534,
|
| 1226 |
+
"learning_rate": 8.366857495860869e-07,
|
| 1227 |
+
"loss": 0.234,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 4.613333333333333,
|
| 1232 |
+
"grad_norm": 0.5727602850553298,
|
| 1233 |
+
"learning_rate": 8.082801548057553e-07,
|
| 1234 |
+
"loss": 0.2418,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 4.64,
|
| 1239 |
+
"grad_norm": 0.5287293002213694,
|
| 1240 |
+
"learning_rate": 7.802718539900761e-07,
|
| 1241 |
+
"loss": 0.2316,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 4.666666666666667,
|
| 1246 |
+
"grad_norm": 0.5259358138855481,
|
| 1247 |
+
"learning_rate": 7.526674247818569e-07,
|
| 1248 |
+
"loss": 0.2188,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 4.693333333333333,
|
| 1253 |
+
"grad_norm": 0.5770307284965632,
|
| 1254 |
+
"learning_rate": 7.254733499761993e-07,
|
| 1255 |
+
"loss": 0.2316,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 4.72,
|
| 1260 |
+
"grad_norm": 0.5213040066811029,
|
| 1261 |
+
"learning_rate": 6.986960159980327e-07,
|
| 1262 |
+
"loss": 0.2369,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 4.746666666666667,
|
| 1267 |
+
"grad_norm": 0.5506331269523678,
|
| 1268 |
+
"learning_rate": 6.723417114022907e-07,
|
| 1269 |
+
"loss": 0.2432,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 4.773333333333333,
|
| 1274 |
+
"grad_norm": 0.5198809246291632,
|
| 1275 |
+
"learning_rate": 6.464166253970672e-07,
|
| 1276 |
+
"loss": 0.2274,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 4.8,
|
| 1281 |
+
"grad_norm": 0.5295779016641822,
|
| 1282 |
+
"learning_rate": 6.209268463901047e-07,
|
| 1283 |
+
"loss": 0.2316,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 4.826666666666666,
|
| 1288 |
+
"grad_norm": 0.5006111047008874,
|
| 1289 |
+
"learning_rate": 5.95878360558953e-07,
|
| 1290 |
+
"loss": 0.2133,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 4.8533333333333335,
|
| 1295 |
+
"grad_norm": 0.5619720892589251,
|
| 1296 |
+
"learning_rate": 5.712770504451426e-07,
|
| 1297 |
+
"loss": 0.2375,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 4.88,
|
| 1302 |
+
"grad_norm": 0.547960059803409,
|
| 1303 |
+
"learning_rate": 5.471286935726866e-07,
|
| 1304 |
+
"loss": 0.2358,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 4.906666666666666,
|
| 1309 |
+
"grad_norm": 0.5437751841577767,
|
| 1310 |
+
"learning_rate": 5.234389610912552e-07,
|
| 1311 |
+
"loss": 0.2413,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 4.933333333333334,
|
| 1316 |
+
"grad_norm": 0.5561071692145099,
|
| 1317 |
+
"learning_rate": 5.002134164443262e-07,
|
| 1318 |
+
"loss": 0.2511,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 4.96,
|
| 1323 |
+
"grad_norm": 0.5524808610758712,
|
| 1324 |
+
"learning_rate": 4.774575140626317e-07,
|
| 1325 |
+
"loss": 0.2451,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 4.986666666666666,
|
| 1330 |
+
"grad_norm": 0.5117245503308239,
|
| 1331 |
+
"learning_rate": 4.55176598083206e-07,
|
| 1332 |
+
"loss": 0.2267,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 5.0,
|
| 1337 |
+
"grad_norm": 0.6989862729853452,
|
| 1338 |
+
"learning_rate": 4.3337590109433505e-07,
|
| 1339 |
+
"loss": 0.2207,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 5.026666666666666,
|
| 1344 |
+
"grad_norm": 0.4995135091869768,
|
| 1345 |
+
"learning_rate": 4.1206054290670537e-07,
|
| 1346 |
+
"loss": 0.2247,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 5.053333333333334,
|
| 1351 |
+
"grad_norm": 0.5047065509806464,
|
| 1352 |
+
"learning_rate": 3.9123552935102976e-07,
|
| 1353 |
+
"loss": 0.2306,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 5.08,
|
| 1358 |
+
"grad_norm": 0.4945674141599629,
|
| 1359 |
+
"learning_rate": 3.709057511024541e-07,
|
| 1360 |
+
"loss": 0.2125,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 5.1066666666666665,
|
| 1365 |
+
"grad_norm": 0.5086174474514864,
|
| 1366 |
+
"learning_rate": 3.510759825319976e-07,
|
| 1367 |
+
"loss": 0.2277,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 5.133333333333334,
|
| 1372 |
+
"grad_norm": 0.5159682671301383,
|
| 1373 |
+
"learning_rate": 3.3175088058530925e-07,
|
| 1374 |
+
"loss": 0.2204,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 5.16,
|
| 1379 |
+
"grad_norm": 0.5441763048956033,
|
| 1380 |
+
"learning_rate": 3.1293498368900414e-07,
|
| 1381 |
+
"loss": 0.2434,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 5.1866666666666665,
|
| 1386 |
+
"grad_norm": 0.5159740064519461,
|
| 1387 |
+
"learning_rate": 2.9463271068482955e-07,
|
| 1388 |
+
"loss": 0.2237,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 5.213333333333333,
|
| 1393 |
+
"grad_norm": 0.5298980322954936,
|
| 1394 |
+
"learning_rate": 2.7684835979191664e-07,
|
| 1395 |
+
"loss": 0.2257,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 5.24,
|
| 1400 |
+
"grad_norm": 0.5328075597416619,
|
| 1401 |
+
"learning_rate": 2.5958610759736133e-07,
|
| 1402 |
+
"loss": 0.2427,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 5.266666666666667,
|
| 1407 |
+
"grad_norm": 0.4994362860549418,
|
| 1408 |
+
"learning_rate": 2.428500080753676e-07,
|
| 1409 |
+
"loss": 0.2182,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 5.293333333333333,
|
| 1414 |
+
"grad_norm": 0.5230334389057023,
|
| 1415 |
+
"learning_rate": 2.2664399163518786e-07,
|
| 1416 |
+
"loss": 0.221,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 5.32,
|
| 1421 |
+
"grad_norm": 0.5096051854427429,
|
| 1422 |
+
"learning_rate": 2.1097186419808151e-07,
|
| 1423 |
+
"loss": 0.2265,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 5.346666666666667,
|
| 1428 |
+
"grad_norm": 0.5250652723997868,
|
| 1429 |
+
"learning_rate": 1.958373063035071e-07,
|
| 1430 |
+
"loss": 0.2277,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 5.373333333333333,
|
| 1435 |
+
"grad_norm": 0.4950111600534919,
|
| 1436 |
+
"learning_rate": 1.8124387224476347e-07,
|
| 1437 |
+
"loss": 0.227,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 5.4,
|
| 1442 |
+
"grad_norm": 0.5132601678972979,
|
| 1443 |
+
"learning_rate": 1.6719498923427697e-07,
|
| 1444 |
+
"loss": 0.2142,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 5.426666666666667,
|
| 1449 |
+
"grad_norm": 0.48056843571558366,
|
| 1450 |
+
"learning_rate": 1.5369395659873305e-07,
|
| 1451 |
+
"loss": 0.204,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 5.453333333333333,
|
| 1456 |
+
"grad_norm": 0.532886587918369,
|
| 1457 |
+
"learning_rate": 1.407439450042433e-07,
|
| 1458 |
+
"loss": 0.2423,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 5.48,
|
| 1463 |
+
"grad_norm": 0.5225976942947688,
|
| 1464 |
+
"learning_rate": 1.283479957117248e-07,
|
| 1465 |
+
"loss": 0.2377,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 5.506666666666667,
|
| 1470 |
+
"grad_norm": 0.508633375236256,
|
| 1471 |
+
"learning_rate": 1.1650901986267365e-07,
|
| 1472 |
+
"loss": 0.2217,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 5.533333333333333,
|
| 1477 |
+
"grad_norm": 0.5127917510790955,
|
| 1478 |
+
"learning_rate": 1.052297977954922e-07,
|
| 1479 |
+
"loss": 0.2232,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 5.5600000000000005,
|
| 1484 |
+
"grad_norm": 0.5320971506257629,
|
| 1485 |
+
"learning_rate": 9.451297839253915e-08,
|
| 1486 |
+
"loss": 0.2371,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 5.586666666666667,
|
| 1491 |
+
"grad_norm": 0.6273981411174898,
|
| 1492 |
+
"learning_rate": 8.436107845804842e-08,
|
| 1493 |
+
"loss": 0.2635,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 5.613333333333333,
|
| 1498 |
+
"grad_norm": 0.5492297122057844,
|
| 1499 |
+
"learning_rate": 7.477648212706746e-08,
|
| 1500 |
+
"loss": 0.2349,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 5.64,
|
| 1505 |
+
"grad_norm": 0.560030885133181,
|
| 1506 |
+
"learning_rate": 6.576144030555259e-08,
|
| 1507 |
+
"loss": 0.2553,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 5.666666666666667,
|
| 1512 |
+
"grad_norm": 0.5742398439602496,
|
| 1513 |
+
"learning_rate": 5.731807014175195e-08,
|
| 1514 |
+
"loss": 0.245,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 5.693333333333333,
|
| 1519 |
+
"grad_norm": 0.5002053600146591,
|
| 1520 |
+
"learning_rate": 4.944835452900199e-08,
|
| 1521 |
+
"loss": 0.2253,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 5.72,
|
| 1526 |
+
"grad_norm": 0.48954052536113946,
|
| 1527 |
+
"learning_rate": 4.215414164005116e-08,
|
| 1528 |
+
"loss": 0.2258,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 5.746666666666667,
|
| 1533 |
+
"grad_norm": 0.5457009600529575,
|
| 1534 |
+
"learning_rate": 3.543714449302488e-08,
|
| 1535 |
+
"loss": 0.2344,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 5.773333333333333,
|
| 1540 |
+
"grad_norm": 0.5078551660449542,
|
| 1541 |
+
"learning_rate": 2.9298940549128962e-08,
|
| 1542 |
+
"loss": 0.2261,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 5.8,
|
| 1547 |
+
"grad_norm": 0.5200299965723768,
|
| 1548 |
+
"learning_rate": 2.3740971342189056e-08,
|
| 1549 |
+
"loss": 0.2191,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 5.826666666666666,
|
| 1554 |
+
"grad_norm": 0.5189853503442351,
|
| 1555 |
+
"learning_rate": 1.876454214011253e-08,
|
| 1556 |
+
"loss": 0.2237,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 5.8533333333333335,
|
| 1561 |
+
"grad_norm": 0.5127221813695705,
|
| 1562 |
+
"learning_rate": 1.4370821638350353e-08,
|
| 1563 |
+
"loss": 0.226,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 5.88,
|
| 1568 |
+
"grad_norm": 0.5225377139661572,
|
| 1569 |
+
"learning_rate": 1.0560841685433864e-08,
|
| 1570 |
+
"loss": 0.2311,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 5.906666666666666,
|
| 1575 |
+
"grad_norm": 0.4799049180814793,
|
| 1576 |
+
"learning_rate": 7.335497040648898e-09,
|
| 1577 |
+
"loss": 0.2143,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 5.933333333333334,
|
| 1582 |
+
"grad_norm": 0.5673931458904186,
|
| 1583 |
+
"learning_rate": 4.695545163905524e-09,
|
| 1584 |
+
"loss": 0.232,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 5.96,
|
| 1589 |
+
"grad_norm": 0.5235754968185998,
|
| 1590 |
+
"learning_rate": 2.641606037850353e-09,
|
| 1591 |
+
"loss": 0.2343,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 5.986666666666666,
|
| 1596 |
+
"grad_norm": 0.5097446707022503,
|
| 1597 |
+
"learning_rate": 1.1741620222671667e-09,
|
| 1598 |
+
"loss": 0.2274,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 6.0,
|
| 1603 |
+
"grad_norm": 0.7503717904419861,
|
| 1604 |
+
"learning_rate": 2.9355774079614653e-10,
|
| 1605 |
+
"loss": 0.2205,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 6.0,
|
| 1610 |
+
"step": 228,
|
| 1611 |
+
"total_flos": 65142872268800.0,
|
| 1612 |
+
"train_loss": 0.3093715236244494,
|
| 1613 |
+
"train_runtime": 3748.6249,
|
| 1614 |
+
"train_samples_per_second": 1.918,
|
| 1615 |
+
"train_steps_per_second": 0.061
|
| 1616 |
+
}
|
| 1617 |
+
],
|
| 1618 |
+
"logging_steps": 1,
|
| 1619 |
+
"max_steps": 228,
|
| 1620 |
+
"num_input_tokens_seen": 0,
|
| 1621 |
+
"num_train_epochs": 6,
|
| 1622 |
+
"save_steps": 200,
|
| 1623 |
+
"stateful_callbacks": {
|
| 1624 |
+
"TrainerControl": {
|
| 1625 |
+
"args": {
|
| 1626 |
+
"should_epoch_stop": false,
|
| 1627 |
+
"should_evaluate": false,
|
| 1628 |
+
"should_log": false,
|
| 1629 |
+
"should_save": true,
|
| 1630 |
+
"should_training_stop": true
|
| 1631 |
+
},
|
| 1632 |
+
"attributes": {}
|
| 1633 |
+
}
|
| 1634 |
+
},
|
| 1635 |
+
"total_flos": 65142872268800.0,
|
| 1636 |
+
"train_batch_size": 1,
|
| 1637 |
+
"trial_name": null,
|
| 1638 |
+
"trial_params": null
|
| 1639 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:193d6187e4a03b10b6b5d5ec6f187c7e29009c0150f3a422357c7c8511de3baa
|
| 3 |
+
size 8209
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|