初始化项目，由ModelHub XC社区提供模型
Model: introtollm/qwen2.5-0.5B-cb-1_1 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: other
|
||||||
|
base_model: Qwen/Qwen2.5-0.5B
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: qwen2.5-0.5B-cb-1_1
|
||||||
|
results: []
|
||||||
|
---
|
||||||
|
|
||||||
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||||
|
should probably proofread and complete it, then remove this comment. -->
|
||||||
|
|
||||||
|
# qwen2.5-0.5B-cb-1_1
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the cb_1_1_50000 dataset.
|
||||||
|
|
||||||
|
## Model description
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Intended uses & limitations
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training and evaluation data
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
### Training hyperparameters
|
||||||
|
|
||||||
|
The following hyperparameters were used during training:
|
||||||
|
- learning_rate: 2e-05
|
||||||
|
- train_batch_size: 1
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- gradient_accumulation_steps: 8
|
||||||
|
- total_train_batch_size: 8
|
||||||
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: cosine
|
||||||
|
- lr_scheduler_warmup_steps: 42
|
||||||
|
- training_steps: 2109
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.57.1
|
||||||
|
- Pytorch 2.10.0+cu128
|
||||||
|
- Datasets 4.0.0
|
||||||
|
- Tokenizers 0.22.2
|
||||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.4536366770079283,
|
||||||
|
"total_flos": 7.41829675403182e+16,
|
||||||
|
"train_loss": 0.9605129250082827,
|
||||||
|
"train_runtime": 2747.171,
|
||||||
|
"train_samples_per_second": 6.142,
|
||||||
|
"train_steps_per_second": 0.768
|
||||||
|
}
|
||||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- messages[0]['content'] }}
|
||||||
|
{%- else %}
|
||||||
|
{{- 'You are a helpful assistant.' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "\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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role }}
|
||||||
|
{%- if message.content %}
|
||||||
|
{{- '\n' + message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if tool_call.function is defined %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- endif %}
|
||||||
55
config.json
Normal file
55
config.json
Normal file
@@ -0,0 +1,55 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "float32",
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 896,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 4864,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 24,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 14,
|
||||||
|
"num_hidden_layers": 24,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "4.57.1",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_mrope": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"eos_token_id": [
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"transformers_version": "4.57.1"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ae19f8bf30bac77adf8b449b4b3bab731d08a49cc5ce5f887b404e29ff223c5e
|
||||||
|
size 1976163472
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.4536366770079283,
|
||||||
|
"total_flos": 7.41829675403182e+16,
|
||||||
|
"train_loss": 0.9605129250082827,
|
||||||
|
"train_runtime": 2747.171,
|
||||||
|
"train_samples_per_second": 6.142,
|
||||||
|
"train_steps_per_second": 0.768
|
||||||
|
}
|
||||||
44
trainer_log.jsonl
Normal file
44
trainer_log.jsonl
Normal file
@@ -0,0 +1,44 @@
|
|||||||
|
{"current_steps": 1, "total_steps": 2109, "loss": 1.6632, "lr": 0.0, "epoch": 0.0006894174422612892, "percentage": 0.05, "elapsed_time": "0:00:02", "remaining_time": "1:24:58"}
|
||||||
|
{"current_steps": 50, "total_steps": 2109, "loss": 1.4496, "lr": 1.9999434046461045e-05, "epoch": 0.03447087211306446, "percentage": 2.37, "elapsed_time": "0:01:03", "remaining_time": "0:43:17"}
|
||||||
|
{"current_steps": 100, "total_steps": 2109, "loss": 1.2491, "lr": 1.996249692618611e-05, "epoch": 0.06894174422612892, "percentage": 4.74, "elapsed_time": "0:02:04", "remaining_time": "0:41:48"}
|
||||||
|
{"current_steps": 150, "total_steps": 2109, "loss": 1.1876, "lr": 1.9868053167196865e-05, "epoch": 0.10341261633919338, "percentage": 7.11, "elapsed_time": "0:03:06", "remaining_time": "0:40:34"}
|
||||||
|
{"current_steps": 200, "total_steps": 2109, "loss": 1.1607, "lr": 1.971664792831919e-05, "epoch": 0.13788348845225784, "percentage": 9.48, "elapsed_time": "0:04:08", "remaining_time": "0:39:29"}
|
||||||
|
{"current_steps": 250, "total_steps": 2109, "loss": 1.1297, "lr": 1.9509155167802316e-05, "epoch": 0.1723543605653223, "percentage": 11.85, "elapsed_time": "0:05:10", "remaining_time": "0:38:26"}
|
||||||
|
{"current_steps": 300, "total_steps": 2109, "loss": 1.1096, "lr": 1.9246772598559302e-05, "epoch": 0.20682523267838676, "percentage": 14.22, "elapsed_time": "0:06:12", "remaining_time": "0:37:25"}
|
||||||
|
{"current_steps": 350, "total_steps": 2109, "loss": 1.1004, "lr": 1.8931014774594656e-05, "epoch": 0.24129610479145122, "percentage": 16.6, "elapsed_time": "0:07:14", "remaining_time": "0:36:22"}
|
||||||
|
{"current_steps": 400, "total_steps": 2109, "loss": 1.0608, "lr": 1.8563704348526337e-05, "epoch": 0.2757669769045157, "percentage": 18.97, "elapsed_time": "0:08:15", "remaining_time": "0:35:18"}
|
||||||
|
{"current_steps": 450, "total_steps": 2109, "loss": 1.0632, "lr": 1.8146961550666525e-05, "epoch": 0.31023784901758017, "percentage": 21.34, "elapsed_time": "0:09:17", "remaining_time": "0:34:14"}
|
||||||
|
{"current_steps": 500, "total_steps": 2109, "loss": 1.0549, "lr": 1.7683191950391142e-05, "epoch": 0.3447087211306446, "percentage": 23.71, "elapsed_time": "0:10:18", "remaining_time": "0:33:11"}
|
||||||
|
{"current_steps": 550, "total_steps": 2109, "loss": 1.0378, "lr": 1.717507257044331e-05, "epoch": 0.3791795932437091, "percentage": 26.08, "elapsed_time": "0:11:48", "remaining_time": "0:33:29"}
|
||||||
|
{"current_steps": 600, "total_steps": 2109, "loss": 1.0359, "lr": 1.6625536434323358e-05, "epoch": 0.4136504653567735, "percentage": 28.45, "elapsed_time": "0:12:51", "remaining_time": "0:32:19"}
|
||||||
|
{"current_steps": 650, "total_steps": 2109, "loss": 1.017, "lr": 1.6037755635962587e-05, "epoch": 0.448121337469838, "percentage": 30.82, "elapsed_time": "0:13:52", "remaining_time": "0:31:09"}
|
||||||
|
{"current_steps": 700, "total_steps": 2109, "loss": 1.0066, "lr": 1.5415123029408046e-05, "epoch": 0.48259220958290244, "percentage": 33.19, "elapsed_time": "0:14:54", "remaining_time": "0:30:01"}
|
||||||
|
{"current_steps": 750, "total_steps": 2109, "loss": 1.0003, "lr": 1.4761232644210963e-05, "epoch": 0.5170630816959669, "percentage": 35.56, "elapsed_time": "0:15:56", "remaining_time": "0:28:53"}
|
||||||
|
{"current_steps": 800, "total_steps": 2109, "loss": 0.9959, "lr": 1.4079858939567557e-05, "epoch": 0.5515339538090314, "percentage": 37.93, "elapsed_time": "0:16:58", "remaining_time": "0:27:47"}
|
||||||
|
{"current_steps": 850, "total_steps": 2109, "loss": 0.9915, "lr": 1.3374935016963595e-05, "epoch": 0.5860048259220958, "percentage": 40.3, "elapsed_time": "0:18:00", "remaining_time": "0:26:40"}
|
||||||
|
{"current_steps": 900, "total_steps": 2109, "loss": 0.9738, "lr": 1.2650529917086232e-05, "epoch": 0.6204756980351603, "percentage": 42.67, "elapsed_time": "0:19:02", "remaining_time": "0:25:35"}
|
||||||
|
{"current_steps": 950, "total_steps": 2109, "loss": 0.9785, "lr": 1.1910825132052356e-05, "epoch": 0.6549465701482248, "percentage": 45.05, "elapsed_time": "0:20:04", "remaining_time": "0:24:29"}
|
||||||
|
{"current_steps": 1000, "total_steps": 2109, "loss": 0.9806, "lr": 1.1160090468532266e-05, "epoch": 0.6894174422612892, "percentage": 47.42, "elapsed_time": "0:21:06", "remaining_time": "0:23:24"}
|
||||||
|
{"current_steps": 1050, "total_steps": 2109, "loss": 0.9568, "lr": 1.0402659401094154e-05, "epoch": 0.7238883143743536, "percentage": 49.79, "elapsed_time": "0:22:35", "remaining_time": "0:22:47"}
|
||||||
|
{"current_steps": 1100, "total_steps": 2109, "loss": 0.9653, "lr": 9.642904058037667e-06, "epoch": 0.7583591864874182, "percentage": 52.16, "elapsed_time": "0:23:38", "remaining_time": "0:21:41"}
|
||||||
|
{"current_steps": 1150, "total_steps": 2109, "loss": 0.9566, "lr": 8.885209984106072e-06, "epoch": 0.7928300586004826, "percentage": 54.53, "elapsed_time": "0:24:40", "remaining_time": "0:20:34"}
|
||||||
|
{"current_steps": 1200, "total_steps": 2109, "loss": 0.9571, "lr": 8.133950825754511e-06, "epoch": 0.827300930713547, "percentage": 56.9, "elapsed_time": "0:25:42", "remaining_time": "0:19:28"}
|
||||||
|
{"current_steps": 1250, "total_steps": 2109, "loss": 0.9485, "lr": 7.393463085098886e-06, "epoch": 0.8617718028266115, "percentage": 59.27, "elapsed_time": "0:26:44", "remaining_time": "0:18:22"}
|
||||||
|
{"current_steps": 1300, "total_steps": 2109, "loss": 0.9471, "lr": 6.6680210882734805e-06, "epoch": 0.896242674939676, "percentage": 61.64, "elapsed_time": "0:27:46", "remaining_time": "0:17:16"}
|
||||||
|
{"current_steps": 1350, "total_steps": 2109, "loss": 0.9349, "lr": 5.961812312687689e-06, "epoch": 0.9307135470527405, "percentage": 64.01, "elapsed_time": "0:28:47", "remaining_time": "0:16:11"}
|
||||||
|
{"current_steps": 1400, "total_steps": 2109, "loss": 0.9344, "lr": 5.278913215600714e-06, "epoch": 0.9651844191658049, "percentage": 66.38, "elapsed_time": "0:29:50", "remaining_time": "0:15:06"}
|
||||||
|
{"current_steps": 1450, "total_steps": 2109, "loss": 0.9174, "lr": 4.623265703539146e-06, "epoch": 0.9996552912788693, "percentage": 68.75, "elapsed_time": "0:30:52", "remaining_time": "0:14:01"}
|
||||||
|
{"current_steps": 1500, "total_steps": 2109, "loss": 0.7982, "lr": 3.998654378383361e-06, "epoch": 1.033781454670803, "percentage": 71.12, "elapsed_time": "0:31:53", "remaining_time": "0:12:56"}
|
||||||
|
{"current_steps": 1550, "total_steps": 2109, "loss": 0.786, "lr": 3.408684691465355e-06, "epoch": 1.0682523267838677, "percentage": 73.49, "elapsed_time": "0:33:23", "remaining_time": "0:12:02"}
|
||||||
|
{"current_steps": 1600, "total_steps": 2109, "loss": 0.7988, "lr": 2.85676213177945e-06, "epoch": 1.1027231988969322, "percentage": 75.87, "elapsed_time": "0:34:25", "remaining_time": "0:10:57"}
|
||||||
|
{"current_steps": 1650, "total_steps": 2109, "loss": 0.7874, "lr": 2.3460725684379002e-06, "epoch": 1.1371940710099966, "percentage": 78.24, "elapsed_time": "0:35:27", "remaining_time": "0:09:51"}
|
||||||
|
{"current_steps": 1700, "total_steps": 2109, "loss": 0.7965, "lr": 1.8795638608410016e-06, "epoch": 1.171664943123061, "percentage": 80.61, "elapsed_time": "0:36:28", "remaining_time": "0:08:46"}
|
||||||
|
{"current_steps": 1750, "total_steps": 2109, "loss": 0.7922, "lr": 1.4599288427134283e-06, "epoch": 1.2061358152361255, "percentage": 82.98, "elapsed_time": "0:37:30", "remaining_time": "0:07:41"}
|
||||||
|
{"current_steps": 1800, "total_steps": 2109, "loss": 0.7915, "lr": 1.0895897782283305e-06, "epoch": 1.2406066873491899, "percentage": 85.35, "elapsed_time": "0:38:32", "remaining_time": "0:06:37"}
|
||||||
|
{"current_steps": 1850, "total_steps": 2109, "loss": 0.7884, "lr": 7.706843799431985e-07, "epoch": 1.2750775594622543, "percentage": 87.72, "elapsed_time": "0:39:34", "remaining_time": "0:05:32"}
|
||||||
|
{"current_steps": 1900, "total_steps": 2109, "loss": 0.786, "lr": 5.050534692564358e-07, "epoch": 1.309548431575319, "percentage": 90.09, "elapsed_time": "0:40:36", "remaining_time": "0:04:28"}
|
||||||
|
{"current_steps": 1950, "total_steps": 2109, "loss": 0.7751, "lr": 2.94230350612239e-07, "epoch": 1.3440193036883832, "percentage": 92.46, "elapsed_time": "0:41:38", "remaining_time": "0:03:23"}
|
||||||
|
{"current_steps": 2000, "total_steps": 2109, "loss": 0.7861, "lr": 1.3943196078924247e-07, "epoch": 1.3784901758014478, "percentage": 94.83, "elapsed_time": "0:42:39", "remaining_time": "0:02:19"}
|
||||||
|
{"current_steps": 2050, "total_steps": 2109, "loss": 0.7872, "lr": 4.155184436196669e-08, "epoch": 1.4129610479145123, "percentage": 97.2, "elapsed_time": "0:44:08", "remaining_time": "0:01:16"}
|
||||||
|
{"current_steps": 2100, "total_steps": 2109, "loss": 0.7975, "lr": 1.154995882924892e-09, "epoch": 1.4474319200275767, "percentage": 99.57, "elapsed_time": "0:45:12", "remaining_time": "0:00:11"}
|
||||||
|
{"current_steps": 2109, "total_steps": 2109, "epoch": 1.4536366770079283, "percentage": 100.0, "elapsed_time": "0:45:47", "remaining_time": "0:00:00"}
|
||||||
344
trainer_state.json
Normal file
344
trainer_state.json
Normal file
@@ -0,0 +1,344 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.4536366770079283,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 2109,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.0006894174422612892,
|
||||||
|
"grad_norm": 6.479256629943848,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 1.6632,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.03447087211306446,
|
||||||
|
"grad_norm": 3.2223708629608154,
|
||||||
|
"learning_rate": 1.9999434046461045e-05,
|
||||||
|
"loss": 1.4496,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06894174422612892,
|
||||||
|
"grad_norm": 3.344071388244629,
|
||||||
|
"learning_rate": 1.996249692618611e-05,
|
||||||
|
"loss": 1.2491,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10341261633919338,
|
||||||
|
"grad_norm": 3.0401906967163086,
|
||||||
|
"learning_rate": 1.9868053167196865e-05,
|
||||||
|
"loss": 1.1876,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.13788348845225784,
|
||||||
|
"grad_norm": 3.164588689804077,
|
||||||
|
"learning_rate": 1.971664792831919e-05,
|
||||||
|
"loss": 1.1607,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1723543605653223,
|
||||||
|
"grad_norm": 2.982455253601074,
|
||||||
|
"learning_rate": 1.9509155167802316e-05,
|
||||||
|
"loss": 1.1297,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20682523267838676,
|
||||||
|
"grad_norm": 3.021336793899536,
|
||||||
|
"learning_rate": 1.9246772598559302e-05,
|
||||||
|
"loss": 1.1096,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24129610479145122,
|
||||||
|
"grad_norm": 2.949462652206421,
|
||||||
|
"learning_rate": 1.8931014774594656e-05,
|
||||||
|
"loss": 1.1004,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2757669769045157,
|
||||||
|
"grad_norm": 2.738522529602051,
|
||||||
|
"learning_rate": 1.8563704348526337e-05,
|
||||||
|
"loss": 1.0608,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.31023784901758017,
|
||||||
|
"grad_norm": 3.002688407897949,
|
||||||
|
"learning_rate": 1.8146961550666525e-05,
|
||||||
|
"loss": 1.0632,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3447087211306446,
|
||||||
|
"grad_norm": 2.8380253314971924,
|
||||||
|
"learning_rate": 1.7683191950391142e-05,
|
||||||
|
"loss": 1.0549,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3791795932437091,
|
||||||
|
"grad_norm": 2.875920295715332,
|
||||||
|
"learning_rate": 1.717507257044331e-05,
|
||||||
|
"loss": 1.0378,
|
||||||
|
"step": 550
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4136504653567735,
|
||||||
|
"grad_norm": 2.8477611541748047,
|
||||||
|
"learning_rate": 1.6625536434323358e-05,
|
||||||
|
"loss": 1.0359,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.448121337469838,
|
||||||
|
"grad_norm": 2.6955602169036865,
|
||||||
|
"learning_rate": 1.6037755635962587e-05,
|
||||||
|
"loss": 1.017,
|
||||||
|
"step": 650
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.48259220958290244,
|
||||||
|
"grad_norm": 2.665055751800537,
|
||||||
|
"learning_rate": 1.5415123029408046e-05,
|
||||||
|
"loss": 1.0066,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5170630816959669,
|
||||||
|
"grad_norm": 2.7886996269226074,
|
||||||
|
"learning_rate": 1.4761232644210963e-05,
|
||||||
|
"loss": 1.0003,
|
||||||
|
"step": 750
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5515339538090314,
|
||||||
|
"grad_norm": 2.561713218688965,
|
||||||
|
"learning_rate": 1.4079858939567557e-05,
|
||||||
|
"loss": 0.9959,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5860048259220958,
|
||||||
|
"grad_norm": 2.623467206954956,
|
||||||
|
"learning_rate": 1.3374935016963595e-05,
|
||||||
|
"loss": 0.9915,
|
||||||
|
"step": 850
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6204756980351603,
|
||||||
|
"grad_norm": 2.6682498455047607,
|
||||||
|
"learning_rate": 1.2650529917086232e-05,
|
||||||
|
"loss": 0.9738,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6549465701482248,
|
||||||
|
"grad_norm": 2.6951420307159424,
|
||||||
|
"learning_rate": 1.1910825132052356e-05,
|
||||||
|
"loss": 0.9785,
|
||||||
|
"step": 950
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6894174422612892,
|
||||||
|
"grad_norm": 2.6426846981048584,
|
||||||
|
"learning_rate": 1.1160090468532266e-05,
|
||||||
|
"loss": 0.9806,
|
||||||
|
"step": 1000
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7238883143743536,
|
||||||
|
"grad_norm": 2.6905856132507324,
|
||||||
|
"learning_rate": 1.0402659401094154e-05,
|
||||||
|
"loss": 0.9568,
|
||||||
|
"step": 1050
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7583591864874182,
|
||||||
|
"grad_norm": 2.618277072906494,
|
||||||
|
"learning_rate": 9.642904058037667e-06,
|
||||||
|
"loss": 0.9653,
|
||||||
|
"step": 1100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7928300586004826,
|
||||||
|
"grad_norm": 2.5803515911102295,
|
||||||
|
"learning_rate": 8.885209984106072e-06,
|
||||||
|
"loss": 0.9566,
|
||||||
|
"step": 1150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.827300930713547,
|
||||||
|
"grad_norm": 2.7561099529266357,
|
||||||
|
"learning_rate": 8.133950825754511e-06,
|
||||||
|
"loss": 0.9571,
|
||||||
|
"step": 1200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8617718028266115,
|
||||||
|
"grad_norm": 2.651911735534668,
|
||||||
|
"learning_rate": 7.393463085098886e-06,
|
||||||
|
"loss": 0.9485,
|
||||||
|
"step": 1250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.896242674939676,
|
||||||
|
"grad_norm": 2.649693250656128,
|
||||||
|
"learning_rate": 6.6680210882734805e-06,
|
||||||
|
"loss": 0.9471,
|
||||||
|
"step": 1300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9307135470527405,
|
||||||
|
"grad_norm": 2.6041650772094727,
|
||||||
|
"learning_rate": 5.961812312687689e-06,
|
||||||
|
"loss": 0.9349,
|
||||||
|
"step": 1350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9651844191658049,
|
||||||
|
"grad_norm": 2.6525392532348633,
|
||||||
|
"learning_rate": 5.278913215600714e-06,
|
||||||
|
"loss": 0.9344,
|
||||||
|
"step": 1400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9996552912788693,
|
||||||
|
"grad_norm": 2.6537036895751953,
|
||||||
|
"learning_rate": 4.623265703539146e-06,
|
||||||
|
"loss": 0.9174,
|
||||||
|
"step": 1450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.033781454670803,
|
||||||
|
"grad_norm": 2.5499179363250732,
|
||||||
|
"learning_rate": 3.998654378383361e-06,
|
||||||
|
"loss": 0.7982,
|
||||||
|
"step": 1500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0682523267838677,
|
||||||
|
"grad_norm": 2.596992254257202,
|
||||||
|
"learning_rate": 3.408684691465355e-06,
|
||||||
|
"loss": 0.786,
|
||||||
|
"step": 1550
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1027231988969322,
|
||||||
|
"grad_norm": 2.550497531890869,
|
||||||
|
"learning_rate": 2.85676213177945e-06,
|
||||||
|
"loss": 0.7988,
|
||||||
|
"step": 1600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1371940710099966,
|
||||||
|
"grad_norm": 2.5404860973358154,
|
||||||
|
"learning_rate": 2.3460725684379002e-06,
|
||||||
|
"loss": 0.7874,
|
||||||
|
"step": 1650
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.171664943123061,
|
||||||
|
"grad_norm": 2.6311583518981934,
|
||||||
|
"learning_rate": 1.8795638608410016e-06,
|
||||||
|
"loss": 0.7965,
|
||||||
|
"step": 1700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2061358152361255,
|
||||||
|
"grad_norm": 2.623417615890503,
|
||||||
|
"learning_rate": 1.4599288427134283e-06,
|
||||||
|
"loss": 0.7922,
|
||||||
|
"step": 1750
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2406066873491899,
|
||||||
|
"grad_norm": 2.5811400413513184,
|
||||||
|
"learning_rate": 1.0895897782283305e-06,
|
||||||
|
"loss": 0.7915,
|
||||||
|
"step": 1800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2750775594622543,
|
||||||
|
"grad_norm": 2.5747768878936768,
|
||||||
|
"learning_rate": 7.706843799431985e-07,
|
||||||
|
"loss": 0.7884,
|
||||||
|
"step": 1850
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.309548431575319,
|
||||||
|
"grad_norm": 2.675109624862671,
|
||||||
|
"learning_rate": 5.050534692564358e-07,
|
||||||
|
"loss": 0.786,
|
||||||
|
"step": 1900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3440193036883832,
|
||||||
|
"grad_norm": 2.594230890274048,
|
||||||
|
"learning_rate": 2.94230350612239e-07,
|
||||||
|
"loss": 0.7751,
|
||||||
|
"step": 1950
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3784901758014478,
|
||||||
|
"grad_norm": 2.5236330032348633,
|
||||||
|
"learning_rate": 1.3943196078924247e-07,
|
||||||
|
"loss": 0.7861,
|
||||||
|
"step": 2000
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4129610479145123,
|
||||||
|
"grad_norm": 2.671135902404785,
|
||||||
|
"learning_rate": 4.155184436196669e-08,
|
||||||
|
"loss": 0.7872,
|
||||||
|
"step": 2050
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4474319200275767,
|
||||||
|
"grad_norm": 2.5242528915405273,
|
||||||
|
"learning_rate": 1.154995882924892e-09,
|
||||||
|
"loss": 0.7975,
|
||||||
|
"step": 2100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4536366770079283,
|
||||||
|
"step": 2109,
|
||||||
|
"total_flos": 7.41829675403182e+16,
|
||||||
|
"train_loss": 0.9605129250082827,
|
||||||
|
"train_runtime": 2747.171,
|
||||||
|
"train_samples_per_second": 6.142,
|
||||||
|
"train_steps_per_second": 0.768
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 50,
|
||||||
|
"max_steps": 2109,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 2,
|
||||||
|
"save_steps": 500,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 7.41829675403182e+16,
|
||||||
|
"train_batch_size": 1,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:085442b152615852915063759eb28df09a0c56b5179ba0fe6a12488d19332585
|
||||||
|
size 6289
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 36 KiB |
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user