初始化项目，由ModelHub XC社区提供模型
Model: codingmonster1234/Qwen3-4B-Instruct-2507-Chess-Reasoning-SFT-v2 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 @@
|
|||||||
|
---
|
||||||
|
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||||||
|
library_name: transformers
|
||||||
|
model_name: output-Qwen3-4B-Instruct-2507
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
- trl
|
||||||
|
- sft
|
||||||
|
licence: license
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for output-Qwen3-4B-Instruct-2507
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
|
||||||
|
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||||
|
|
||||||
|
## Quick start
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import pipeline
|
||||||
|
|
||||||
|
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||||
|
generator = pipeline("text-generation", model="None", device="cuda")
|
||||||
|
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||||
|
print(output["generated_text"])
|
||||||
|
```
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/easwar-chess-none/huggingface/runs/y90urtlc)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
This model was trained with SFT.
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- TRL: 1.5.1
|
||||||
|
- Transformers: 4.57.6
|
||||||
|
- Pytorch: 2.10.0
|
||||||
|
- Datasets: 5.0.0
|
||||||
|
- Tokenizers: 0.22.2
|
||||||
|
|
||||||
|
## Citations
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Cite TRL as:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@software{vonwerra2020trl,
|
||||||
|
title = {{TRL: Transformers Reinforcement Learning}},
|
||||||
|
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||||
|
license = {Apache-2.0},
|
||||||
|
url = {https://github.com/huggingface/trl},
|
||||||
|
year = {2020}
|
||||||
|
}
|
||||||
|
```
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|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
|
||||||
|
}
|
||||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# 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' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- 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 %}
|
||||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2560,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9728,
|
||||||
|
"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",
|
||||||
|
"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": 262144,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 5000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "4.57.6",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
18
eval_results.txt
Normal file
18
eval_results.txt
Normal file
@@ -0,0 +1,18 @@
|
|||||||
|
Evaluation Summary for
|
||||||
|
codingmonster1234/Qwen3-4B-Instruct-2507-Chess-Reasonin
|
||||||
|
g-SFT-v2
|
||||||
|
╔══════════╤══════════════════════════════╤═══════════╗
|
||||||
|
║ Category │ Metric │ Value ║
|
||||||
|
╟──────────┼──────────────────────────────┼───────────╢
|
||||||
|
║ eval │ format_accuracy │ 0.9510 ║
|
||||||
|
║ eval │ legal_move_accuracy │ 0.9080 ║
|
||||||
|
║ eval │ valid_move_notation_accuracy │ 0.9080 ║
|
||||||
|
║ eval │ perfect_move_accuracy │ 0.2710 ║
|
||||||
|
║ eval │ avg_eval_diff │ 1746.4540 ║
|
||||||
|
║ eval │ avg_length_penalty │ 0.0106 ║
|
||||||
|
║ eval │ avg_final_reward │ 0.1882 ║
|
||||||
|
║ eval │ avg_eval_reward │ 0.1983 ║
|
||||||
|
║ eval │ avg_elo_solved │ 1167.1661 ║
|
||||||
|
╟──────────┼──────────────────────────────┼───────────╢
|
||||||
|
║ │ │ ║
|
||||||
|
╚══════════╧══════════════════════════════╧═══════════╝
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.7,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.8,
|
||||||
|
"transformers_version": "4.57.6"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:947fffbc478f817b35144b43423b38133e0b228cdc310e0828a362aaf14e749f
|
||||||
|
size 4967215360
|
||||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:68a4fe21a522ca5111dc3c1afb987497c603fc4137d2016159d4400d25eb836b
|
||||||
|
size 3077766632
|
||||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 4022468096,
|
||||||
|
"total_size": 8044936192
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
3
optimizer.pt
Normal file
3
optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f7c38cde9e37edcb5fc2c302b85ffcf998ed16d20742816658f249cc326a286f
|
||||||
|
size 16090225449
|
||||||
3
rng_state.pth
Normal file
3
rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
|
||||||
|
size 14645
|
||||||
3
scheduler.pt
Normal file
3
scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:69da190c9ffb471de386838030f5db7ecba7753d98fde1ddc34a98df017ac804
|
||||||
|
size 1465
|
||||||
25
special_tokens_map.json
Normal file
25
special_tokens_map.json
Normal file
@@ -0,0 +1,25 @@
|
|||||||
|
{
|
||||||
|
"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": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
|||||||
|
{
|
||||||
|
"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
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"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": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 1010000,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
885
trainer_state.json
Normal file
885
trainer_state.json
Normal file
@@ -0,0 +1,885 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 84,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"entropy": 1.0289964377880096,
|
||||||
|
"epoch": 0.011904761904761904,
|
||||||
|
"grad_norm": 27.125,
|
||||||
|
"learning_rate": 2e-05,
|
||||||
|
"loss": 2.2931,
|
||||||
|
"mean_token_accuracy": 0.5738132819533348,
|
||||||
|
"num_tokens": 29832.0,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.44026979804039,
|
||||||
|
"epoch": 0.023809523809523808,
|
||||||
|
"grad_norm": 6.3125,
|
||||||
|
"learning_rate": 1.999922292480975e-05,
|
||||||
|
"loss": 1.5703,
|
||||||
|
"mean_token_accuracy": 0.6421284079551697,
|
||||||
|
"num_tokens": 58835.0,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.6413304507732391,
|
||||||
|
"epoch": 0.03571428571428571,
|
||||||
|
"grad_norm": 4.0625,
|
||||||
|
"learning_rate": 1.9996891820008165e-05,
|
||||||
|
"loss": 1.5037,
|
||||||
|
"mean_token_accuracy": 0.6544012948870659,
|
||||||
|
"num_tokens": 88089.0,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.4298747032880783,
|
||||||
|
"epoch": 0.047619047619047616,
|
||||||
|
"grad_norm": 3.171875,
|
||||||
|
"learning_rate": 1.9993007047883988e-05,
|
||||||
|
"loss": 1.3305,
|
||||||
|
"mean_token_accuracy": 0.6857858076691628,
|
||||||
|
"num_tokens": 116996.0,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.266538918018341,
|
||||||
|
"epoch": 0.05952380952380952,
|
||||||
|
"grad_norm": 2.53125,
|
||||||
|
"learning_rate": 1.9987569212189224e-05,
|
||||||
|
"loss": 1.2618,
|
||||||
|
"mean_token_accuracy": 0.6996989399194717,
|
||||||
|
"num_tokens": 146502.0,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.1705086678266525,
|
||||||
|
"epoch": 0.07142857142857142,
|
||||||
|
"grad_norm": 2.515625,
|
||||||
|
"learning_rate": 1.9980579158045322e-05,
|
||||||
|
"loss": 1.2323,
|
||||||
|
"mean_token_accuracy": 0.6959410309791565,
|
||||||
|
"num_tokens": 175000.0,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.1460798904299736,
|
||||||
|
"epoch": 0.08333333333333333,
|
||||||
|
"grad_norm": 2.546875,
|
||||||
|
"learning_rate": 1.9972037971811802e-05,
|
||||||
|
"loss": 1.2006,
|
||||||
|
"mean_token_accuracy": 0.7042278572916985,
|
||||||
|
"num_tokens": 203581.0,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.086261309683323,
|
||||||
|
"epoch": 0.09523809523809523,
|
||||||
|
"grad_norm": 2.28125,
|
||||||
|
"learning_rate": 1.9961946980917457e-05,
|
||||||
|
"loss": 1.1341,
|
||||||
|
"mean_token_accuracy": 0.7203333824872971,
|
||||||
|
"num_tokens": 233225.0,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.1471993625164032,
|
||||||
|
"epoch": 0.10714285714285714,
|
||||||
|
"grad_norm": 2.25,
|
||||||
|
"learning_rate": 1.9950307753654016e-05,
|
||||||
|
"loss": 1.1864,
|
||||||
|
"mean_token_accuracy": 0.7060119584202766,
|
||||||
|
"num_tokens": 261557.0,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.1250567734241486,
|
||||||
|
"epoch": 0.11904761904761904,
|
||||||
|
"grad_norm": 2.125,
|
||||||
|
"learning_rate": 1.9937122098932428e-05,
|
||||||
|
"loss": 1.1066,
|
||||||
|
"mean_token_accuracy": 0.717756524682045,
|
||||||
|
"num_tokens": 290843.0,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0941710397601128,
|
||||||
|
"epoch": 0.13095238095238096,
|
||||||
|
"grad_norm": 1.921875,
|
||||||
|
"learning_rate": 1.9922392066001724e-05,
|
||||||
|
"loss": 1.0633,
|
||||||
|
"mean_token_accuracy": 0.7308941036462784,
|
||||||
|
"num_tokens": 320963.0,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0973558276891708,
|
||||||
|
"epoch": 0.14285714285714285,
|
||||||
|
"grad_norm": 2.03125,
|
||||||
|
"learning_rate": 1.9906119944130527e-05,
|
||||||
|
"loss": 1.0542,
|
||||||
|
"mean_token_accuracy": 0.7335255369544029,
|
||||||
|
"num_tokens": 350648.0,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0850690826773643,
|
||||||
|
"epoch": 0.15476190476190477,
|
||||||
|
"grad_norm": 2.0625,
|
||||||
|
"learning_rate": 1.9888308262251286e-05,
|
||||||
|
"loss": 1.0634,
|
||||||
|
"mean_token_accuracy": 0.7266389280557632,
|
||||||
|
"num_tokens": 380096.0,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0478279069066048,
|
||||||
|
"epoch": 0.16666666666666666,
|
||||||
|
"grad_norm": 2.171875,
|
||||||
|
"learning_rate": 1.9868959788567213e-05,
|
||||||
|
"loss": 1.057,
|
||||||
|
"mean_token_accuracy": 0.7326076179742813,
|
||||||
|
"num_tokens": 407435.0,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0213893577456474,
|
||||||
|
"epoch": 0.17857142857142858,
|
||||||
|
"grad_norm": 2.0,
|
||||||
|
"learning_rate": 1.9848077530122083e-05,
|
||||||
|
"loss": 1.012,
|
||||||
|
"mean_token_accuracy": 0.7387356385588646,
|
||||||
|
"num_tokens": 435734.0,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.07327102124691,
|
||||||
|
"epoch": 0.19047619047619047,
|
||||||
|
"grad_norm": 2.03125,
|
||||||
|
"learning_rate": 1.9825664732332886e-05,
|
||||||
|
"loss": 1.0868,
|
||||||
|
"mean_token_accuracy": 0.7211552038788795,
|
||||||
|
"num_tokens": 464973.0,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0235116630792618,
|
||||||
|
"epoch": 0.20238095238095238,
|
||||||
|
"grad_norm": 1.984375,
|
||||||
|
"learning_rate": 1.9801724878485438e-05,
|
||||||
|
"loss": 1.0377,
|
||||||
|
"mean_token_accuracy": 0.7334162965416908,
|
||||||
|
"num_tokens": 493135.0,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9607449993491173,
|
||||||
|
"epoch": 0.21428571428571427,
|
||||||
|
"grad_norm": 1.8984375,
|
||||||
|
"learning_rate": 1.977626168919305e-05,
|
||||||
|
"loss": 0.9745,
|
||||||
|
"mean_token_accuracy": 0.7495110481977463,
|
||||||
|
"num_tokens": 522656.0,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0044650733470917,
|
||||||
|
"epoch": 0.2261904761904762,
|
||||||
|
"grad_norm": 1.8984375,
|
||||||
|
"learning_rate": 1.9749279121818235e-05,
|
||||||
|
"loss": 1.0128,
|
||||||
|
"mean_token_accuracy": 0.7394910976290703,
|
||||||
|
"num_tokens": 551875.0,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.009770929813385,
|
||||||
|
"epoch": 0.23809523809523808,
|
||||||
|
"grad_norm": 1.921875,
|
||||||
|
"learning_rate": 1.9720781369857747e-05,
|
||||||
|
"loss": 1.0019,
|
||||||
|
"mean_token_accuracy": 0.7396527603268623,
|
||||||
|
"num_tokens": 580523.0,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 1.0536553114652634,
|
||||||
|
"epoch": 0.25,
|
||||||
|
"grad_norm": 1.9140625,
|
||||||
|
"learning_rate": 1.969077286229078e-05,
|
||||||
|
"loss": 1.0288,
|
||||||
|
"mean_token_accuracy": 0.7323001325130463,
|
||||||
|
"num_tokens": 609771.0,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.964533656835556,
|
||||||
|
"epoch": 0.2619047619047619,
|
||||||
|
"grad_norm": 1.828125,
|
||||||
|
"learning_rate": 1.9659258262890683e-05,
|
||||||
|
"loss": 0.9512,
|
||||||
|
"mean_token_accuracy": 0.7494053766131401,
|
||||||
|
"num_tokens": 639104.0,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9821470007300377,
|
||||||
|
"epoch": 0.27380952380952384,
|
||||||
|
"grad_norm": 1.890625,
|
||||||
|
"learning_rate": 1.962624246950012e-05,
|
||||||
|
"loss": 0.9739,
|
||||||
|
"mean_token_accuracy": 0.7434249892830849,
|
||||||
|
"num_tokens": 667792.0,
|
||||||
|
"step": 23
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9782575219869614,
|
||||||
|
"epoch": 0.2857142857142857,
|
||||||
|
"grad_norm": 1.796875,
|
||||||
|
"learning_rate": 1.9591730613269878e-05,
|
||||||
|
"loss": 0.9898,
|
||||||
|
"mean_token_accuracy": 0.7400899454951286,
|
||||||
|
"num_tokens": 696742.0,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.942177914083004,
|
||||||
|
"epoch": 0.2976190476190476,
|
||||||
|
"grad_norm": 1.859375,
|
||||||
|
"learning_rate": 1.955572805786141e-05,
|
||||||
|
"loss": 0.9489,
|
||||||
|
"mean_token_accuracy": 0.7481768950819969,
|
||||||
|
"num_tokens": 725968.0,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9274484664201736,
|
||||||
|
"epoch": 0.30952380952380953,
|
||||||
|
"grad_norm": 1.921875,
|
||||||
|
"learning_rate": 1.9518240398613226e-05,
|
||||||
|
"loss": 0.9505,
|
||||||
|
"mean_token_accuracy": 0.7481107041239738,
|
||||||
|
"num_tokens": 755689.0,
|
||||||
|
"step": 26
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9720096439123154,
|
||||||
|
"epoch": 0.32142857142857145,
|
||||||
|
"grad_norm": 1.8828125,
|
||||||
|
"learning_rate": 1.947927346167132e-05,
|
||||||
|
"loss": 0.9928,
|
||||||
|
"mean_token_accuracy": 0.7357244342565536,
|
||||||
|
"num_tokens": 784977.0,
|
||||||
|
"step": 27
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9152235984802246,
|
||||||
|
"epoch": 0.3333333333333333,
|
||||||
|
"grad_norm": 1.8046875,
|
||||||
|
"learning_rate": 1.9438833303083677e-05,
|
||||||
|
"loss": 0.9064,
|
||||||
|
"mean_token_accuracy": 0.7547181248664856,
|
||||||
|
"num_tokens": 814048.0,
|
||||||
|
"step": 28
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9777852222323418,
|
||||||
|
"epoch": 0.34523809523809523,
|
||||||
|
"grad_norm": 1.8359375,
|
||||||
|
"learning_rate": 1.9396926207859085e-05,
|
||||||
|
"loss": 0.9833,
|
||||||
|
"mean_token_accuracy": 0.7389796674251556,
|
||||||
|
"num_tokens": 843602.0,
|
||||||
|
"step": 29
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9311033263802528,
|
||||||
|
"epoch": 0.35714285714285715,
|
||||||
|
"grad_norm": 2.875,
|
||||||
|
"learning_rate": 1.935355868899034e-05,
|
||||||
|
"loss": 0.9277,
|
||||||
|
"mean_token_accuracy": 0.7512769624590874,
|
||||||
|
"num_tokens": 871915.0,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.97285395860672,
|
||||||
|
"epoch": 0.36904761904761907,
|
||||||
|
"grad_norm": 1.8984375,
|
||||||
|
"learning_rate": 1.9308737486442045e-05,
|
||||||
|
"loss": 0.9626,
|
||||||
|
"mean_token_accuracy": 0.7445296198129654,
|
||||||
|
"num_tokens": 900851.0,
|
||||||
|
"step": 31
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8841484859585762,
|
||||||
|
"epoch": 0.38095238095238093,
|
||||||
|
"grad_norm": 1.7421875,
|
||||||
|
"learning_rate": 1.926246956610309e-05,
|
||||||
|
"loss": 0.8828,
|
||||||
|
"mean_token_accuracy": 0.7655422911047935,
|
||||||
|
"num_tokens": 929498.0,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9625014588236809,
|
||||||
|
"epoch": 0.39285714285714285,
|
||||||
|
"grad_norm": 1.7890625,
|
||||||
|
"learning_rate": 1.921476211870408e-05,
|
||||||
|
"loss": 0.9449,
|
||||||
|
"mean_token_accuracy": 0.7469100803136826,
|
||||||
|
"num_tokens": 958933.0,
|
||||||
|
"step": 33
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9233517870306969,
|
||||||
|
"epoch": 0.40476190476190477,
|
||||||
|
"grad_norm": 1.765625,
|
||||||
|
"learning_rate": 1.9165622558699763e-05,
|
||||||
|
"loss": 0.9282,
|
||||||
|
"mean_token_accuracy": 0.7555889263749123,
|
||||||
|
"num_tokens": 987731.0,
|
||||||
|
"step": 34
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9165640994906425,
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 1.7265625,
|
||||||
|
"learning_rate": 1.9115058523116734e-05,
|
||||||
|
"loss": 0.8923,
|
||||||
|
"mean_token_accuracy": 0.761642724275589,
|
||||||
|
"num_tokens": 1017002.0,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9459593519568443,
|
||||||
|
"epoch": 0.42857142857142855,
|
||||||
|
"grad_norm": 1.6953125,
|
||||||
|
"learning_rate": 1.9063077870366504e-05,
|
||||||
|
"loss": 0.9472,
|
||||||
|
"mean_token_accuracy": 0.7494409009814262,
|
||||||
|
"num_tokens": 1046678.0,
|
||||||
|
"step": 36
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9148919209837914,
|
||||||
|
"epoch": 0.44047619047619047,
|
||||||
|
"grad_norm": 1.8046875,
|
||||||
|
"learning_rate": 1.900968867902419e-05,
|
||||||
|
"loss": 0.9092,
|
||||||
|
"mean_token_accuracy": 0.7560340315103531,
|
||||||
|
"num_tokens": 1074445.0,
|
||||||
|
"step": 37
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8793367967009544,
|
||||||
|
"epoch": 0.4523809523809524,
|
||||||
|
"grad_norm": 1.875,
|
||||||
|
"learning_rate": 1.895489924657301e-05,
|
||||||
|
"loss": 0.864,
|
||||||
|
"mean_token_accuracy": 0.767846867442131,
|
||||||
|
"num_tokens": 1103620.0,
|
||||||
|
"step": 38
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9116434380412102,
|
||||||
|
"epoch": 0.4642857142857143,
|
||||||
|
"grad_norm": 1.828125,
|
||||||
|
"learning_rate": 1.8898718088114688e-05,
|
||||||
|
"loss": 0.8928,
|
||||||
|
"mean_token_accuracy": 0.7605250775814056,
|
||||||
|
"num_tokens": 1132637.0,
|
||||||
|
"step": 39
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8998617604374886,
|
||||||
|
"epoch": 0.47619047619047616,
|
||||||
|
"grad_norm": 1.6796875,
|
||||||
|
"learning_rate": 1.8841153935046098e-05,
|
||||||
|
"loss": 0.8715,
|
||||||
|
"mean_token_accuracy": 0.7635523602366447,
|
||||||
|
"num_tokens": 1161527.0,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8533368110656738,
|
||||||
|
"epoch": 0.4880952380952381,
|
||||||
|
"grad_norm": 1.7109375,
|
||||||
|
"learning_rate": 1.8782215733702286e-05,
|
||||||
|
"loss": 0.86,
|
||||||
|
"mean_token_accuracy": 0.7679954171180725,
|
||||||
|
"num_tokens": 1190701.0,
|
||||||
|
"step": 41
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9144820719957352,
|
||||||
|
"epoch": 0.5,
|
||||||
|
"grad_norm": 1.9140625,
|
||||||
|
"learning_rate": 1.8721912643966055e-05,
|
||||||
|
"loss": 0.9308,
|
||||||
|
"mean_token_accuracy": 0.7519562095403671,
|
||||||
|
"num_tokens": 1218835.0,
|
||||||
|
"step": 42
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8947170972824097,
|
||||||
|
"epoch": 0.5119047619047619,
|
||||||
|
"grad_norm": 1.78125,
|
||||||
|
"learning_rate": 1.866025403784439e-05,
|
||||||
|
"loss": 0.8931,
|
||||||
|
"mean_token_accuracy": 0.7597509473562241,
|
||||||
|
"num_tokens": 1248679.0,
|
||||||
|
"step": 43
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8477422297000885,
|
||||||
|
"epoch": 0.5238095238095238,
|
||||||
|
"grad_norm": 1.7890625,
|
||||||
|
"learning_rate": 1.8597249498011906e-05,
|
||||||
|
"loss": 0.8518,
|
||||||
|
"mean_token_accuracy": 0.772525392472744,
|
||||||
|
"num_tokens": 1277106.0,
|
||||||
|
"step": 44
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9015490636229515,
|
||||||
|
"epoch": 0.5357142857142857,
|
||||||
|
"grad_norm": 1.8046875,
|
||||||
|
"learning_rate": 1.8532908816321557e-05,
|
||||||
|
"loss": 0.9015,
|
||||||
|
"mean_token_accuracy": 0.7591351941227913,
|
||||||
|
"num_tokens": 1305983.0,
|
||||||
|
"step": 45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.931048758327961,
|
||||||
|
"epoch": 0.5476190476190477,
|
||||||
|
"grad_norm": 1.8515625,
|
||||||
|
"learning_rate": 1.8467241992282842e-05,
|
||||||
|
"loss": 0.9067,
|
||||||
|
"mean_token_accuracy": 0.7518437430262566,
|
||||||
|
"num_tokens": 1334578.0,
|
||||||
|
"step": 46
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8747421428561211,
|
||||||
|
"epoch": 0.5595238095238095,
|
||||||
|
"grad_norm": 1.796875,
|
||||||
|
"learning_rate": 1.8400259231507716e-05,
|
||||||
|
"loss": 0.8576,
|
||||||
|
"mean_token_accuracy": 0.7661429345607758,
|
||||||
|
"num_tokens": 1362873.0,
|
||||||
|
"step": 47
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8680180609226227,
|
||||||
|
"epoch": 0.5714285714285714,
|
||||||
|
"grad_norm": 1.7734375,
|
||||||
|
"learning_rate": 1.833197094412449e-05,
|
||||||
|
"loss": 0.8586,
|
||||||
|
"mean_token_accuracy": 0.7713808715343475,
|
||||||
|
"num_tokens": 1391315.0,
|
||||||
|
"step": 48
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8663084208965302,
|
||||||
|
"epoch": 0.5833333333333334,
|
||||||
|
"grad_norm": 1.7734375,
|
||||||
|
"learning_rate": 1.826238774315995e-05,
|
||||||
|
"loss": 0.8471,
|
||||||
|
"mean_token_accuracy": 0.7667829617857933,
|
||||||
|
"num_tokens": 1419829.0,
|
||||||
|
"step": 49
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8798943981528282,
|
||||||
|
"epoch": 0.5952380952380952,
|
||||||
|
"grad_norm": 1.84375,
|
||||||
|
"learning_rate": 1.819152044288992e-05,
|
||||||
|
"loss": 0.8961,
|
||||||
|
"mean_token_accuracy": 0.7574765011668205,
|
||||||
|
"num_tokens": 1447790.0,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8617029711604118,
|
||||||
|
"epoch": 0.6071428571428571,
|
||||||
|
"grad_norm": 1.8671875,
|
||||||
|
"learning_rate": 1.811938005715857e-05,
|
||||||
|
"loss": 0.8544,
|
||||||
|
"mean_token_accuracy": 0.7637034431099892,
|
||||||
|
"num_tokens": 1476278.0,
|
||||||
|
"step": 51
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9306018576025963,
|
||||||
|
"epoch": 0.6190476190476191,
|
||||||
|
"grad_norm": 1.9453125,
|
||||||
|
"learning_rate": 1.8045977797666685e-05,
|
||||||
|
"loss": 0.9506,
|
||||||
|
"mean_token_accuracy": 0.7459357306361198,
|
||||||
|
"num_tokens": 1503947.0,
|
||||||
|
"step": 52
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8792530596256256,
|
||||||
|
"epoch": 0.6309523809523809,
|
||||||
|
"grad_norm": 1.8046875,
|
||||||
|
"learning_rate": 1.7971325072229227e-05,
|
||||||
|
"loss": 0.9022,
|
||||||
|
"mean_token_accuracy": 0.7546841576695442,
|
||||||
|
"num_tokens": 1533531.0,
|
||||||
|
"step": 53
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8904775232076645,
|
||||||
|
"epoch": 0.6428571428571429,
|
||||||
|
"grad_norm": 1.890625,
|
||||||
|
"learning_rate": 1.7895433483002356e-05,
|
||||||
|
"loss": 0.9174,
|
||||||
|
"mean_token_accuracy": 0.757450558245182,
|
||||||
|
"num_tokens": 1561412.0,
|
||||||
|
"step": 54
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8826311081647873,
|
||||||
|
"epoch": 0.6547619047619048,
|
||||||
|
"grad_norm": 1.8828125,
|
||||||
|
"learning_rate": 1.78183148246803e-05,
|
||||||
|
"loss": 0.8745,
|
||||||
|
"mean_token_accuracy": 0.7593515664339066,
|
||||||
|
"num_tokens": 1590336.0,
|
||||||
|
"step": 55
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8883182108402252,
|
||||||
|
"epoch": 0.6666666666666666,
|
||||||
|
"grad_norm": 1.703125,
|
||||||
|
"learning_rate": 1.7739981082662275e-05,
|
||||||
|
"loss": 0.8739,
|
||||||
|
"mean_token_accuracy": 0.7626457437872887,
|
||||||
|
"num_tokens": 1620442.0,
|
||||||
|
"step": 56
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.9116549044847488,
|
||||||
|
"epoch": 0.6785714285714286,
|
||||||
|
"grad_norm": 1.7734375,
|
||||||
|
"learning_rate": 1.766044443118978e-05,
|
||||||
|
"loss": 0.8924,
|
||||||
|
"mean_token_accuracy": 0.7594088986515999,
|
||||||
|
"num_tokens": 1648762.0,
|
||||||
|
"step": 57
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8485553786158562,
|
||||||
|
"epoch": 0.6904761904761905,
|
||||||
|
"grad_norm": 1.734375,
|
||||||
|
"learning_rate": 1.757971723145453e-05,
|
||||||
|
"loss": 0.8377,
|
||||||
|
"mean_token_accuracy": 0.7698637396097183,
|
||||||
|
"num_tokens": 1677464.0,
|
||||||
|
"step": 58
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8704692050814629,
|
||||||
|
"epoch": 0.7023809523809523,
|
||||||
|
"grad_norm": 1.7890625,
|
||||||
|
"learning_rate": 1.7497812029677344e-05,
|
||||||
|
"loss": 0.856,
|
||||||
|
"mean_token_accuracy": 0.7654970586299896,
|
||||||
|
"num_tokens": 1704994.0,
|
||||||
|
"step": 59
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8928592056035995,
|
||||||
|
"epoch": 0.7142857142857143,
|
||||||
|
"grad_norm": 1.6953125,
|
||||||
|
"learning_rate": 1.741474155515827e-05,
|
||||||
|
"loss": 0.8711,
|
||||||
|
"mean_token_accuracy": 0.7633472010493279,
|
||||||
|
"num_tokens": 1734202.0,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.89468764513731,
|
||||||
|
"epoch": 0.7261904761904762,
|
||||||
|
"grad_norm": 1.734375,
|
||||||
|
"learning_rate": 1.7330518718298263e-05,
|
||||||
|
"loss": 0.8823,
|
||||||
|
"mean_token_accuracy": 0.7610758692026138,
|
||||||
|
"num_tokens": 1763541.0,
|
||||||
|
"step": 61
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8784511089324951,
|
||||||
|
"epoch": 0.7380952380952381,
|
||||||
|
"grad_norm": 1.6953125,
|
||||||
|
"learning_rate": 1.7245156608592727e-05,
|
||||||
|
"loss": 0.8538,
|
||||||
|
"mean_token_accuracy": 0.7677165567874908,
|
||||||
|
"num_tokens": 1793196.0,
|
||||||
|
"step": 62
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.909877359867096,
|
||||||
|
"epoch": 0.75,
|
||||||
|
"grad_norm": 1.9140625,
|
||||||
|
"learning_rate": 1.7158668492597186e-05,
|
||||||
|
"loss": 0.9132,
|
||||||
|
"mean_token_accuracy": 0.7523172721266747,
|
||||||
|
"num_tokens": 1821023.0,
|
||||||
|
"step": 63
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8661764934659004,
|
||||||
|
"epoch": 0.7619047619047619,
|
||||||
|
"grad_norm": 1.828125,
|
||||||
|
"learning_rate": 1.7071067811865477e-05,
|
||||||
|
"loss": 0.8799,
|
||||||
|
"mean_token_accuracy": 0.7596996948122978,
|
||||||
|
"num_tokens": 1849586.0,
|
||||||
|
"step": 64
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.886342890560627,
|
||||||
|
"epoch": 0.7738095238095238,
|
||||||
|
"grad_norm": 1.7890625,
|
||||||
|
"learning_rate": 1.698236818086073e-05,
|
||||||
|
"loss": 0.902,
|
||||||
|
"mean_token_accuracy": 0.7548638582229614,
|
||||||
|
"num_tokens": 1878622.0,
|
||||||
|
"step": 65
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.83852668851614,
|
||||||
|
"epoch": 0.7857142857142857,
|
||||||
|
"grad_norm": 1.75,
|
||||||
|
"learning_rate": 1.689258338483947e-05,
|
||||||
|
"loss": 0.844,
|
||||||
|
"mean_token_accuracy": 0.7697297856211662,
|
||||||
|
"num_tokens": 1907725.0,
|
||||||
|
"step": 66
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8709945902228355,
|
||||||
|
"epoch": 0.7976190476190477,
|
||||||
|
"grad_norm": 1.7265625,
|
||||||
|
"learning_rate": 1.6801727377709195e-05,
|
||||||
|
"loss": 0.8592,
|
||||||
|
"mean_token_accuracy": 0.7622527256608009,
|
||||||
|
"num_tokens": 1936209.0,
|
||||||
|
"step": 67
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8294754698872566,
|
||||||
|
"epoch": 0.8095238095238095,
|
||||||
|
"grad_norm": 1.7578125,
|
||||||
|
"learning_rate": 1.67098142798597e-05,
|
||||||
|
"loss": 0.835,
|
||||||
|
"mean_token_accuracy": 0.7706626355648041,
|
||||||
|
"num_tokens": 1964915.0,
|
||||||
|
"step": 68
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8466374576091766,
|
||||||
|
"epoch": 0.8214285714285714,
|
||||||
|
"grad_norm": 1.8359375,
|
||||||
|
"learning_rate": 1.6616858375968596e-05,
|
||||||
|
"loss": 0.8614,
|
||||||
|
"mean_token_accuracy": 0.7639145851135254,
|
||||||
|
"num_tokens": 1993606.0,
|
||||||
|
"step": 69
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8547898903489113,
|
||||||
|
"epoch": 0.8333333333333334,
|
||||||
|
"grad_norm": 1.78125,
|
||||||
|
"learning_rate": 1.6522874112781213e-05,
|
||||||
|
"loss": 0.8612,
|
||||||
|
"mean_token_accuracy": 0.7676523253321648,
|
||||||
|
"num_tokens": 2022472.0,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8490668088197708,
|
||||||
|
"epoch": 0.8452380952380952,
|
||||||
|
"grad_norm": 1.84375,
|
||||||
|
"learning_rate": 1.6427876096865394e-05,
|
||||||
|
"loss": 0.8569,
|
||||||
|
"mean_token_accuracy": 0.7640745714306831,
|
||||||
|
"num_tokens": 2052746.0,
|
||||||
|
"step": 71
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8580184206366539,
|
||||||
|
"epoch": 0.8571428571428571,
|
||||||
|
"grad_norm": 1.75,
|
||||||
|
"learning_rate": 1.6331879092341402e-05,
|
||||||
|
"loss": 0.858,
|
||||||
|
"mean_token_accuracy": 0.7627410292625427,
|
||||||
|
"num_tokens": 2081889.0,
|
||||||
|
"step": 72
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8156702071428299,
|
||||||
|
"epoch": 0.8690476190476191,
|
||||||
|
"grad_norm": 1.5390625,
|
||||||
|
"learning_rate": 1.6234898018587336e-05,
|
||||||
|
"loss": 0.7916,
|
||||||
|
"mean_token_accuracy": 0.7771949768066406,
|
||||||
|
"num_tokens": 2111616.0,
|
||||||
|
"step": 73
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8689733147621155,
|
||||||
|
"epoch": 0.8809523809523809,
|
||||||
|
"grad_norm": 1.78125,
|
||||||
|
"learning_rate": 1.6136947947920477e-05,
|
||||||
|
"loss": 0.8629,
|
||||||
|
"mean_token_accuracy": 0.7629422098398209,
|
||||||
|
"num_tokens": 2140433.0,
|
||||||
|
"step": 74
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8075756058096886,
|
||||||
|
"epoch": 0.8928571428571429,
|
||||||
|
"grad_norm": 1.6171875,
|
||||||
|
"learning_rate": 1.6038044103254775e-05,
|
||||||
|
"loss": 0.8032,
|
||||||
|
"mean_token_accuracy": 0.7750532627105713,
|
||||||
|
"num_tokens": 2170414.0,
|
||||||
|
"step": 75
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8746250569820404,
|
||||||
|
"epoch": 0.9047619047619048,
|
||||||
|
"grad_norm": 1.765625,
|
||||||
|
"learning_rate": 1.5938201855735017e-05,
|
||||||
|
"loss": 0.8793,
|
||||||
|
"mean_token_accuracy": 0.7575968354940414,
|
||||||
|
"num_tokens": 2198868.0,
|
||||||
|
"step": 76
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8024050742387772,
|
||||||
|
"epoch": 0.9166666666666666,
|
||||||
|
"grad_norm": 1.6796875,
|
||||||
|
"learning_rate": 1.5837436722347902e-05,
|
||||||
|
"loss": 0.7813,
|
||||||
|
"mean_token_accuracy": 0.7871535196900368,
|
||||||
|
"num_tokens": 2228134.0,
|
||||||
|
"step": 77
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8507664054632187,
|
||||||
|
"epoch": 0.9285714285714286,
|
||||||
|
"grad_norm": 1.75,
|
||||||
|
"learning_rate": 1.573576436351046e-05,
|
||||||
|
"loss": 0.8437,
|
||||||
|
"mean_token_accuracy": 0.7693362981081009,
|
||||||
|
"num_tokens": 2257447.0,
|
||||||
|
"step": 78
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8141358867287636,
|
||||||
|
"epoch": 0.9404761904761905,
|
||||||
|
"grad_norm": 1.65625,
|
||||||
|
"learning_rate": 1.563320058063622e-05,
|
||||||
|
"loss": 0.8081,
|
||||||
|
"mean_token_accuracy": 0.7764901369810104,
|
||||||
|
"num_tokens": 2286749.0,
|
||||||
|
"step": 79
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.843724861741066,
|
||||||
|
"epoch": 0.9523809523809523,
|
||||||
|
"grad_norm": 1.7421875,
|
||||||
|
"learning_rate": 1.5529761313679396e-05,
|
||||||
|
"loss": 0.8281,
|
||||||
|
"mean_token_accuracy": 0.7666148692369461,
|
||||||
|
"num_tokens": 2315039.0,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8586638569831848,
|
||||||
|
"epoch": 0.9642857142857143,
|
||||||
|
"grad_norm": 1.7578125,
|
||||||
|
"learning_rate": 1.5425462638657597e-05,
|
||||||
|
"loss": 0.8867,
|
||||||
|
"mean_token_accuracy": 0.760459378361702,
|
||||||
|
"num_tokens": 2344737.0,
|
||||||
|
"step": 81
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8165242671966553,
|
||||||
|
"epoch": 0.9761904761904762,
|
||||||
|
"grad_norm": 1.765625,
|
||||||
|
"learning_rate": 1.5320320765153367e-05,
|
||||||
|
"loss": 0.8006,
|
||||||
|
"mean_token_accuracy": 0.7785647809505463,
|
||||||
|
"num_tokens": 2373710.0,
|
||||||
|
"step": 82
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8401609510183334,
|
||||||
|
"epoch": 0.9880952380952381,
|
||||||
|
"grad_norm": 1.765625,
|
||||||
|
"learning_rate": 1.5214352033794981e-05,
|
||||||
|
"loss": 0.8466,
|
||||||
|
"mean_token_accuracy": 0.7677159905433655,
|
||||||
|
"num_tokens": 2402610.0,
|
||||||
|
"step": 83
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"entropy": 0.8437637463212013,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"grad_norm": 1.8046875,
|
||||||
|
"learning_rate": 1.5107572913716859e-05,
|
||||||
|
"loss": 0.8714,
|
||||||
|
"mean_token_accuracy": 0.7612484693527222,
|
||||||
|
"num_tokens": 2430019.0,
|
||||||
|
"step": 84
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_entropy": 0.8333023413022359,
|
||||||
|
"eval_loss": 0.8408388495445251,
|
||||||
|
"eval_mean_token_accuracy": 0.7681567951043446,
|
||||||
|
"eval_num_tokens": 2430019.0,
|
||||||
|
"eval_runtime": 19.0307,
|
||||||
|
"eval_samples_per_second": 7.882,
|
||||||
|
"eval_steps_per_second": 7.882,
|
||||||
|
"step": 84
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1.0,
|
||||||
|
"max_steps": 252,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 3,
|
||||||
|
"save_steps": 500,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": false
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 5.565870266351002e+16,
|
||||||
|
"train_batch_size": 2,
|
||||||
|
"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:ea9ef0dffb93d55f76a335a30d26696bf61f24952baffcf069f2bee96fd9a86e
|
||||||
|
size 6545
|
||||||
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