初始化项目，由ModelHub XC社区提供模型
Model: miiikiik/Qwen3-8B-music-movie-coa-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
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: miiikiik/Qwen3-8B-music-movie-coa-sft
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: Qwen3-8B-music-movie-coa-sft-v2
|
||||
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. -->
|
||||
|
||||
# Qwen3-8B-music-movie-coa-sft-v2
|
||||
|
||||
This model is a fine-tuned version of [/mnt/tidal-alsh01/usr/zhongmeizhi/meiwangyi/models/Qwen3-8B-music-coa-sft](https://huggingface.co//mnt/tidal-alsh01/usr/zhongmeizhi/meiwangyi/models/Qwen3-8B-music-coa-sft) on the movie_coa_sft_v2 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: 1e-05
|
||||
- train_batch_size: 2
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 64
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 3.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.6
|
||||
- Pytorch 2.7.1+cu126
|
||||
- Datasets 3.4.1
|
||||
- Tokenizers 0.22.1
|
||||
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
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"total_flos": 629471101583360.0,
|
||||
"train_loss": 0.1980447881822045,
|
||||
"train_runtime": 15010.1192,
|
||||
"train_samples_per_second": 3.003,
|
||||
"train_steps_per_second": 0.047
|
||||
}
|
||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
||||
{%- 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 %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- 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' }}
|
||||
{{- 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' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
72
config.json
Normal file
72
config.json
Normal file
@@ -0,0 +1,72 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"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": 40960,
|
||||
"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_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
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": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"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-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a12f6f9ac83a856e3a6f97ad8a439beb124a34a0100452c8895cd560b2526c42
|
||||
size 4902257696
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bccfc3c696a30ca2be7a44734dfd1dfadcc946de00d9f9d0a461e897dc66eb89
|
||||
size 4915960368
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0d8e77a6bcecb4287dbaa4a6349a1e3470ff7da6b17c26a93e7bfeca0c373cbf
|
||||
size 4983068496
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7fc135527c7e037ba6ddb45debdee830384653e382963d78a6d5e6b8d791eb0d
|
||||
size 1580230264
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 308224,
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"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:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
227
tokenizer_config.json
Normal file
227
tokenizer_config.json
Normal file
@@ -0,0 +1,227 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"is_local": true,
|
||||
"local_files_only": false,
|
||||
"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": 3.0,
|
||||
"total_flos": 629471101583360.0,
|
||||
"train_loss": 0.1980447881822045,
|
||||
"train_runtime": 15010.1192,
|
||||
"train_samples_per_second": 3.003,
|
||||
"train_steps_per_second": 0.047
|
||||
}
|
||||
71
trainer_log.jsonl
Normal file
71
trainer_log.jsonl
Normal file
@@ -0,0 +1,71 @@
|
||||
{"current_steps": 10, "total_steps": 705, "loss": 2.4664, "lr": 1.267605633802817e-06, "epoch": 0.042598509052183174, "percentage": 1.42, "elapsed_time": "0:03:33", "remaining_time": "4:07:34"}
|
||||
{"current_steps": 20, "total_steps": 705, "loss": 2.1878, "lr": 2.676056338028169e-06, "epoch": 0.08519701810436635, "percentage": 2.84, "elapsed_time": "0:07:06", "remaining_time": "4:03:15"}
|
||||
{"current_steps": 30, "total_steps": 705, "loss": 1.4846, "lr": 4.0845070422535216e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:10:36", "remaining_time": "3:58:36"}
|
||||
{"current_steps": 40, "total_steps": 705, "loss": 0.9678, "lr": 5.492957746478874e-06, "epoch": 0.1703940362087327, "percentage": 5.67, "elapsed_time": "0:14:08", "remaining_time": "3:55:07"}
|
||||
{"current_steps": 50, "total_steps": 705, "loss": 0.5819, "lr": 6.901408450704225e-06, "epoch": 0.21299254526091588, "percentage": 7.09, "elapsed_time": "0:17:40", "remaining_time": "3:51:37"}
|
||||
{"current_steps": 60, "total_steps": 705, "loss": 0.4161, "lr": 8.309859154929578e-06, "epoch": 0.25559105431309903, "percentage": 8.51, "elapsed_time": "0:21:13", "remaining_time": "3:48:07"}
|
||||
{"current_steps": 70, "total_steps": 705, "loss": 0.3151, "lr": 9.71830985915493e-06, "epoch": 0.29818956336528224, "percentage": 9.93, "elapsed_time": "0:24:45", "remaining_time": "3:44:36"}
|
||||
{"current_steps": 80, "total_steps": 705, "loss": 0.2595, "lr": 9.996071883688333e-06, "epoch": 0.3407880724174654, "percentage": 11.35, "elapsed_time": "0:28:17", "remaining_time": "3:41:01"}
|
||||
{"current_steps": 90, "total_steps": 705, "loss": 0.2459, "lr": 9.980124488638774e-06, "epoch": 0.38338658146964855, "percentage": 12.77, "elapsed_time": "0:31:49", "remaining_time": "3:37:31"}
|
||||
{"current_steps": 100, "total_steps": 705, "loss": 0.2227, "lr": 9.951951426568852e-06, "epoch": 0.42598509052183176, "percentage": 14.18, "elapsed_time": "0:35:22", "remaining_time": "3:33:58"}
|
||||
{"current_steps": 110, "total_steps": 705, "loss": 0.2181, "lr": 9.91162185929904e-06, "epoch": 0.4685835995740149, "percentage": 15.6, "elapsed_time": "0:38:54", "remaining_time": "3:30:27"}
|
||||
{"current_steps": 120, "total_steps": 705, "loss": 0.1952, "lr": 9.859234791555356e-06, "epoch": 0.5111821086261981, "percentage": 17.02, "elapsed_time": "0:42:24", "remaining_time": "3:26:45"}
|
||||
{"current_steps": 130, "total_steps": 705, "loss": 0.1918, "lr": 9.794918827923458e-06, "epoch": 0.5537806176783813, "percentage": 18.44, "elapsed_time": "0:45:57", "remaining_time": "3:23:14"}
|
||||
{"current_steps": 140, "total_steps": 705, "loss": 0.175, "lr": 9.718831857138308e-06, "epoch": 0.5963791267305645, "percentage": 19.86, "elapsed_time": "0:49:29", "remaining_time": "3:19:44"}
|
||||
{"current_steps": 150, "total_steps": 705, "loss": 0.1943, "lr": 9.631160664484398e-06, "epoch": 0.6389776357827476, "percentage": 21.28, "elapsed_time": "0:53:02", "remaining_time": "3:16:13"}
|
||||
{"current_steps": 160, "total_steps": 705, "loss": 0.1566, "lr": 9.532120473258075e-06, "epoch": 0.6815761448349308, "percentage": 22.7, "elapsed_time": "0:56:32", "remaining_time": "3:12:34"}
|
||||
{"current_steps": 170, "total_steps": 705, "loss": 0.1534, "lr": 9.421954416417624e-06, "epoch": 0.724174653887114, "percentage": 24.11, "elapsed_time": "1:00:04", "remaining_time": "3:09:02"}
|
||||
{"current_steps": 180, "total_steps": 705, "loss": 0.1586, "lr": 9.300932939718159e-06, "epoch": 0.7667731629392971, "percentage": 25.53, "elapsed_time": "1:03:36", "remaining_time": "3:05:32"}
|
||||
{"current_steps": 190, "total_steps": 705, "loss": 0.1424, "lr": 9.169353137796533e-06, "epoch": 0.8093716719914803, "percentage": 26.95, "elapsed_time": "1:07:06", "remaining_time": "3:01:53"}
|
||||
{"current_steps": 200, "total_steps": 705, "loss": 0.1585, "lr": 9.027538024836143e-06, "epoch": 0.8519701810436635, "percentage": 28.37, "elapsed_time": "1:10:38", "remaining_time": "2:58:22"}
|
||||
{"current_steps": 210, "total_steps": 705, "loss": 0.1397, "lr": 8.875835741602031e-06, "epoch": 0.8945686900958466, "percentage": 29.79, "elapsed_time": "1:14:10", "remaining_time": "2:54:51"}
|
||||
{"current_steps": 220, "total_steps": 705, "loss": 0.1546, "lr": 8.714618700792975e-06, "epoch": 0.9371671991480298, "percentage": 31.21, "elapsed_time": "1:17:43", "remaining_time": "2:51:20"}
|
||||
{"current_steps": 230, "total_steps": 705, "loss": 0.1324, "lr": 8.54428267280858e-06, "epoch": 0.979765708200213, "percentage": 32.62, "elapsed_time": "1:21:15", "remaining_time": "2:47:49"}
|
||||
{"current_steps": 240, "total_steps": 705, "loss": 0.1333, "lr": 8.365245814175744e-06, "epoch": 1.0212992545260915, "percentage": 34.04, "elapsed_time": "1:24:42", "remaining_time": "2:44:07"}
|
||||
{"current_steps": 250, "total_steps": 705, "loss": 0.0952, "lr": 8.177947641019622e-06, "epoch": 1.0638977635782747, "percentage": 35.46, "elapsed_time": "1:28:14", "remaining_time": "2:40:36"}
|
||||
{"current_steps": 260, "total_steps": 705, "loss": 0.0946, "lr": 7.982847950099055e-06, "epoch": 1.106496272630458, "percentage": 36.88, "elapsed_time": "1:31:47", "remaining_time": "2:37:05"}
|
||||
{"current_steps": 270, "total_steps": 705, "loss": 0.1067, "lr": 7.780425690055275e-06, "epoch": 1.1490947816826411, "percentage": 38.3, "elapsed_time": "1:35:19", "remaining_time": "2:33:34"}
|
||||
{"current_steps": 280, "total_steps": 705, "loss": 0.0897, "lr": 7.571177785644766e-06, "epoch": 1.1916932907348243, "percentage": 39.72, "elapsed_time": "1:38:51", "remaining_time": "2:30:03"}
|
||||
{"current_steps": 290, "total_steps": 705, "loss": 0.088, "lr": 7.355617917842751e-06, "epoch": 1.2342917997870075, "percentage": 41.13, "elapsed_time": "1:42:23", "remaining_time": "2:26:31"}
|
||||
{"current_steps": 300, "total_steps": 705, "loss": 0.0909, "lr": 7.134275262811935e-06, "epoch": 1.2768903088391905, "percentage": 42.55, "elapsed_time": "1:45:56", "remaining_time": "2:23:00"}
|
||||
{"current_steps": 310, "total_steps": 705, "loss": 0.0923, "lr": 6.907693192832263e-06, "epoch": 1.3194888178913737, "percentage": 43.97, "elapsed_time": "1:49:28", "remaining_time": "2:19:29"}
|
||||
{"current_steps": 320, "total_steps": 705, "loss": 0.0844, "lr": 6.676427942380741e-06, "epoch": 1.362087326943557, "percentage": 45.39, "elapsed_time": "1:53:01", "remaining_time": "2:15:58"}
|
||||
{"current_steps": 330, "total_steps": 705, "loss": 0.0877, "lr": 6.441047242635947e-06, "epoch": 1.4046858359957402, "percentage": 46.81, "elapsed_time": "1:56:33", "remaining_time": "2:12:27"}
|
||||
{"current_steps": 340, "total_steps": 705, "loss": 0.0846, "lr": 6.202128927759391e-06, "epoch": 1.4472843450479234, "percentage": 48.23, "elapsed_time": "2:00:06", "remaining_time": "2:08:56"}
|
||||
{"current_steps": 350, "total_steps": 705, "loss": 0.0876, "lr": 5.960259516375134e-06, "epoch": 1.4898828541001066, "percentage": 49.65, "elapsed_time": "2:03:39", "remaining_time": "2:05:25"}
|
||||
{"current_steps": 360, "total_steps": 705, "loss": 0.0869, "lr": 5.716032771730008e-06, "epoch": 1.5324813631522898, "percentage": 51.06, "elapsed_time": "2:07:11", "remaining_time": "2:01:53"}
|
||||
{"current_steps": 370, "total_steps": 705, "loss": 0.0771, "lr": 5.470048244069055e-06, "epoch": 1.5750798722044728, "percentage": 52.48, "elapsed_time": "2:10:43", "remaining_time": "1:58:21"}
|
||||
{"current_steps": 380, "total_steps": 705, "loss": 0.0766, "lr": 5.222909798804515e-06, "epoch": 1.617678381256656, "percentage": 53.9, "elapsed_time": "2:14:16", "remaining_time": "1:54:50"}
|
||||
{"current_steps": 390, "total_steps": 705, "loss": 0.0717, "lr": 4.975224134091551e-06, "epoch": 1.6602768903088392, "percentage": 55.32, "elapsed_time": "2:17:48", "remaining_time": "1:51:18"}
|
||||
{"current_steps": 400, "total_steps": 705, "loss": 0.0845, "lr": 4.727599291449887e-06, "epoch": 1.7028753993610224, "percentage": 56.74, "elapsed_time": "2:21:21", "remaining_time": "1:47:46"}
|
||||
{"current_steps": 410, "total_steps": 705, "loss": 0.0717, "lr": 4.480643163087644e-06, "epoch": 1.7454739084132056, "percentage": 58.16, "elapsed_time": "2:24:53", "remaining_time": "1:44:15"}
|
||||
{"current_steps": 420, "total_steps": 705, "loss": 0.0789, "lr": 4.234961999591706e-06, "epoch": 1.7880724174653886, "percentage": 59.57, "elapsed_time": "2:28:22", "remaining_time": "1:40:40"}
|
||||
{"current_steps": 430, "total_steps": 705, "loss": 0.0795, "lr": 3.991158921648096e-06, "epoch": 1.830670926517572, "percentage": 60.99, "elapsed_time": "2:31:54", "remaining_time": "1:37:09"}
|
||||
{"current_steps": 440, "total_steps": 705, "loss": 0.0718, "lr": 3.7498324394459253e-06, "epoch": 1.873269435569755, "percentage": 62.41, "elapsed_time": "2:35:26", "remaining_time": "1:33:37"}
|
||||
{"current_steps": 450, "total_steps": 705, "loss": 0.0592, "lr": 3.511574983399599e-06, "epoch": 1.9158679446219382, "percentage": 63.83, "elapsed_time": "2:38:57", "remaining_time": "1:30:04"}
|
||||
{"current_steps": 460, "total_steps": 705, "loss": 0.0631, "lr": 3.2769714497962235e-06, "epoch": 1.9584664536741214, "percentage": 65.25, "elapsed_time": "2:42:31", "remaining_time": "1:26:33"}
|
||||
{"current_steps": 470, "total_steps": 705, "loss": 0.0568, "lr": 3.0465977649384813e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:58", "remaining_time": "1:22:59"}
|
||||
{"current_steps": 480, "total_steps": 705, "loss": 0.0342, "lr": 2.8210194713078408e-06, "epoch": 2.042598509052183, "percentage": 68.09, "elapsed_time": "2:49:31", "remaining_time": "1:19:27"}
|
||||
{"current_steps": 490, "total_steps": 705, "loss": 0.029, "lr": 2.600790339218926e-06, "epoch": 2.0851970181043664, "percentage": 69.5, "elapsed_time": "2:53:01", "remaining_time": "1:15:55"}
|
||||
{"current_steps": 500, "total_steps": 705, "loss": 0.0317, "lr": 2.3864510073732914e-06, "epoch": 2.1277955271565494, "percentage": 70.92, "elapsed_time": "2:56:31", "remaining_time": "1:12:22"}
|
||||
{"current_steps": 510, "total_steps": 705, "loss": 0.0308, "lr": 2.178527655649868e-06, "epoch": 2.170394036208733, "percentage": 72.34, "elapsed_time": "3:00:49", "remaining_time": "1:09:08"}
|
||||
{"current_steps": 520, "total_steps": 705, "loss": 0.0287, "lr": 1.977530713390281e-06, "epoch": 2.212992545260916, "percentage": 73.76, "elapsed_time": "3:04:21", "remaining_time": "1:05:35"}
|
||||
{"current_steps": 530, "total_steps": 705, "loss": 0.0284, "lr": 1.783953606350005e-06, "epoch": 2.255591054313099, "percentage": 75.18, "elapsed_time": "3:07:51", "remaining_time": "1:02:01"}
|
||||
{"current_steps": 540, "total_steps": 705, "loss": 0.0282, "lr": 1.5982715453915082e-06, "epoch": 2.2981895633652822, "percentage": 76.6, "elapsed_time": "3:11:23", "remaining_time": "0:58:28"}
|
||||
{"current_steps": 550, "total_steps": 705, "loss": 0.0298, "lr": 1.4209403598929711e-06, "epoch": 2.3407880724174652, "percentage": 78.01, "elapsed_time": "3:14:55", "remaining_time": "0:54:56"}
|
||||
{"current_steps": 560, "total_steps": 705, "loss": 0.0269, "lr": 1.2523953787364723e-06, "epoch": 2.3833865814696487, "percentage": 79.43, "elapsed_time": "3:18:27", "remaining_time": "0:51:23"}
|
||||
{"current_steps": 570, "total_steps": 705, "loss": 0.0258, "lr": 1.0930503616226495e-06, "epoch": 2.4259850905218316, "percentage": 80.85, "elapsed_time": "3:22:00", "remaining_time": "0:47:50"}
|
||||
{"current_steps": 580, "total_steps": 705, "loss": 0.0285, "lr": 9.432964833353947e-07, "epoch": 2.468583599574015, "percentage": 82.27, "elapsed_time": "3:25:32", "remaining_time": "0:44:17"}
|
||||
{"current_steps": 590, "total_steps": 705, "loss": 0.0304, "lr": 8.035013734500557e-07, "epoch": 2.511182108626198, "percentage": 83.69, "elapsed_time": "3:29:04", "remaining_time": "0:40:45"}
|
||||
{"current_steps": 600, "total_steps": 705, "loss": 0.0284, "lr": 6.740082138425963e-07, "epoch": 2.553780617678381, "percentage": 85.11, "elapsed_time": "3:32:37", "remaining_time": "0:37:12"}
|
||||
{"current_steps": 610, "total_steps": 705, "loss": 0.0249, "lr": 5.551348962151965e-07, "epoch": 2.5963791267305645, "percentage": 86.52, "elapsed_time": "3:36:08", "remaining_time": "0:33:39"}
|
||||
{"current_steps": 620, "total_steps": 705, "loss": 0.0227, "lr": 4.471732417065144e-07, "epoch": 2.6389776357827475, "percentage": 87.94, "elapsed_time": "3:39:41", "remaining_time": "0:30:07"}
|
||||
{"current_steps": 630, "total_steps": 705, "loss": 0.0229, "lr": 3.5038828450233874e-07, "epoch": 2.681576144834931, "percentage": 89.36, "elapsed_time": "3:43:11", "remaining_time": "0:26:34"}
|
||||
{"current_steps": 640, "total_steps": 705, "loss": 0.025, "lr": 2.65017621205339e-07, "epoch": 2.724174653887114, "percentage": 90.78, "elapsed_time": "3:46:44", "remaining_time": "0:23:01"}
|
||||
{"current_steps": 650, "total_steps": 705, "loss": 0.0281, "lr": 1.9127082756109138e-07, "epoch": 2.7667731629392973, "percentage": 92.2, "elapsed_time": "3:50:16", "remaining_time": "0:19:29"}
|
||||
{"current_steps": 660, "total_steps": 705, "loss": 0.0222, "lr": 1.293289439722961e-07, "epoch": 2.8093716719914803, "percentage": 93.62, "elapsed_time": "3:53:48", "remaining_time": "0:15:56"}
|
||||
{"current_steps": 670, "total_steps": 705, "loss": 0.0249, "lr": 7.934403106416245e-08, "epoch": 2.8519701810436633, "percentage": 95.04, "elapsed_time": "3:57:18", "remaining_time": "0:12:23"}
|
||||
{"current_steps": 680, "total_steps": 705, "loss": 0.0221, "lr": 4.1438796392025416e-08, "epoch": 2.8945686900958467, "percentage": 96.45, "elapsed_time": "4:00:50", "remaining_time": "0:08:51"}
|
||||
{"current_steps": 690, "total_steps": 705, "loss": 0.0227, "lr": 1.5706293207561896e-08, "epoch": 2.9371671991480297, "percentage": 97.87, "elapsed_time": "4:04:23", "remaining_time": "0:05:18"}
|
||||
{"current_steps": 700, "total_steps": 705, "loss": 0.0223, "lr": 2.209692023126819e-09, "epoch": 2.979765708200213, "percentage": 99.29, "elapsed_time": "4:07:55", "remaining_time": "0:01:46"}
|
||||
{"current_steps": 705, "total_steps": 705, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:10:10", "remaining_time": "0:00:00"}
|
||||
533
trainer_state.json
Normal file
533
trainer_state.json
Normal file
@@ -0,0 +1,533 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 3.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 705,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.042598509052183174,
|
||||
"grad_norm": 21.082965129152086,
|
||||
"learning_rate": 1.267605633802817e-06,
|
||||
"loss": 2.4664,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.08519701810436635,
|
||||
"grad_norm": 19.188427968641975,
|
||||
"learning_rate": 2.676056338028169e-06,
|
||||
"loss": 2.1878,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.12779552715654952,
|
||||
"grad_norm": 9.475226745542779,
|
||||
"learning_rate": 4.0845070422535216e-06,
|
||||
"loss": 1.4846,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.1703940362087327,
|
||||
"grad_norm": 5.306762711198587,
|
||||
"learning_rate": 5.492957746478874e-06,
|
||||
"loss": 0.9678,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.21299254526091588,
|
||||
"grad_norm": 4.590929790305963,
|
||||
"learning_rate": 6.901408450704225e-06,
|
||||
"loss": 0.5819,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.25559105431309903,
|
||||
"grad_norm": 1.6438823894653778,
|
||||
"learning_rate": 8.309859154929578e-06,
|
||||
"loss": 0.4161,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.29818956336528224,
|
||||
"grad_norm": 1.5007646688888001,
|
||||
"learning_rate": 9.71830985915493e-06,
|
||||
"loss": 0.3151,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.3407880724174654,
|
||||
"grad_norm": 3.1817046176810218,
|
||||
"learning_rate": 9.996071883688333e-06,
|
||||
"loss": 0.2595,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.38338658146964855,
|
||||
"grad_norm": 0.9853382945850364,
|
||||
"learning_rate": 9.980124488638774e-06,
|
||||
"loss": 0.2459,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.42598509052183176,
|
||||
"grad_norm": 1.0026092175101524,
|
||||
"learning_rate": 9.951951426568852e-06,
|
||||
"loss": 0.2227,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.4685835995740149,
|
||||
"grad_norm": 0.9467415606864195,
|
||||
"learning_rate": 9.91162185929904e-06,
|
||||
"loss": 0.2181,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.5111821086261981,
|
||||
"grad_norm": 1.018005381246591,
|
||||
"learning_rate": 9.859234791555356e-06,
|
||||
"loss": 0.1952,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.5537806176783813,
|
||||
"grad_norm": 1.2269238583843798,
|
||||
"learning_rate": 9.794918827923458e-06,
|
||||
"loss": 0.1918,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.5963791267305645,
|
||||
"grad_norm": 0.8698678847845421,
|
||||
"learning_rate": 9.718831857138308e-06,
|
||||
"loss": 0.175,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.6389776357827476,
|
||||
"grad_norm": 1.0480947036630484,
|
||||
"learning_rate": 9.631160664484398e-06,
|
||||
"loss": 0.1943,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.6815761448349308,
|
||||
"grad_norm": 8.384047626201337,
|
||||
"learning_rate": 9.532120473258075e-06,
|
||||
"loss": 0.1566,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.724174653887114,
|
||||
"grad_norm": 0.7386254552014561,
|
||||
"learning_rate": 9.421954416417624e-06,
|
||||
"loss": 0.1534,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.7667731629392971,
|
||||
"grad_norm": 0.7400271137846004,
|
||||
"learning_rate": 9.300932939718159e-06,
|
||||
"loss": 0.1586,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.8093716719914803,
|
||||
"grad_norm": 1.2075602319421987,
|
||||
"learning_rate": 9.169353137796533e-06,
|
||||
"loss": 0.1424,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.8519701810436635,
|
||||
"grad_norm": 1.1410187483647192,
|
||||
"learning_rate": 9.027538024836143e-06,
|
||||
"loss": 0.1585,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.8945686900958466,
|
||||
"grad_norm": 0.7379523855872633,
|
||||
"learning_rate": 8.875835741602031e-06,
|
||||
"loss": 0.1397,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.9371671991480298,
|
||||
"grad_norm": 0.8356428492042096,
|
||||
"learning_rate": 8.714618700792975e-06,
|
||||
"loss": 0.1546,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.979765708200213,
|
||||
"grad_norm": 0.8699813474717787,
|
||||
"learning_rate": 8.54428267280858e-06,
|
||||
"loss": 0.1324,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 1.0212992545260915,
|
||||
"grad_norm": 0.6842065606451512,
|
||||
"learning_rate": 8.365245814175744e-06,
|
||||
"loss": 0.1333,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 1.0638977635782747,
|
||||
"grad_norm": 1.2090377509101662,
|
||||
"learning_rate": 8.177947641019622e-06,
|
||||
"loss": 0.0952,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 1.106496272630458,
|
||||
"grad_norm": 1.0148320458452715,
|
||||
"learning_rate": 7.982847950099055e-06,
|
||||
"loss": 0.0946,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 1.1490947816826411,
|
||||
"grad_norm": 0.7338241692333486,
|
||||
"learning_rate": 7.780425690055275e-06,
|
||||
"loss": 0.1067,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 1.1916932907348243,
|
||||
"grad_norm": 0.6498746772924805,
|
||||
"learning_rate": 7.571177785644766e-06,
|
||||
"loss": 0.0897,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 1.2342917997870075,
|
||||
"grad_norm": 0.6563332988784214,
|
||||
"learning_rate": 7.355617917842751e-06,
|
||||
"loss": 0.088,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 1.2768903088391905,
|
||||
"grad_norm": 0.6389752490843476,
|
||||
"learning_rate": 7.134275262811935e-06,
|
||||
"loss": 0.0909,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194888178913737,
|
||||
"grad_norm": 0.7462566848514381,
|
||||
"learning_rate": 6.907693192832263e-06,
|
||||
"loss": 0.0923,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 1.362087326943557,
|
||||
"grad_norm": 0.6894751379258567,
|
||||
"learning_rate": 6.676427942380741e-06,
|
||||
"loss": 0.0844,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 1.4046858359957402,
|
||||
"grad_norm": 0.8021156814880915,
|
||||
"learning_rate": 6.441047242635947e-06,
|
||||
"loss": 0.0877,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 1.4472843450479234,
|
||||
"grad_norm": 0.9964737342042037,
|
||||
"learning_rate": 6.202128927759391e-06,
|
||||
"loss": 0.0846,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 1.4898828541001066,
|
||||
"grad_norm": 0.7290481485894376,
|
||||
"learning_rate": 5.960259516375134e-06,
|
||||
"loss": 0.0876,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.5324813631522898,
|
||||
"grad_norm": 0.8198141163509329,
|
||||
"learning_rate": 5.716032771730008e-06,
|
||||
"loss": 0.0869,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 1.5750798722044728,
|
||||
"grad_norm": 0.6135413073318677,
|
||||
"learning_rate": 5.470048244069055e-06,
|
||||
"loss": 0.0771,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 1.617678381256656,
|
||||
"grad_norm": 0.668818900512361,
|
||||
"learning_rate": 5.222909798804515e-06,
|
||||
"loss": 0.0766,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 1.6602768903088392,
|
||||
"grad_norm": 0.9193125817511787,
|
||||
"learning_rate": 4.975224134091551e-06,
|
||||
"loss": 0.0717,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 1.7028753993610224,
|
||||
"grad_norm": 0.615193996483177,
|
||||
"learning_rate": 4.727599291449887e-06,
|
||||
"loss": 0.0845,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.7454739084132056,
|
||||
"grad_norm": 0.6604596855515968,
|
||||
"learning_rate": 4.480643163087644e-06,
|
||||
"loss": 0.0717,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 1.7880724174653886,
|
||||
"grad_norm": 1.2030577374834739,
|
||||
"learning_rate": 4.234961999591706e-06,
|
||||
"loss": 0.0789,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 1.830670926517572,
|
||||
"grad_norm": 0.7106477349898497,
|
||||
"learning_rate": 3.991158921648096e-06,
|
||||
"loss": 0.0795,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 1.873269435569755,
|
||||
"grad_norm": 1.0462717462476079,
|
||||
"learning_rate": 3.7498324394459253e-06,
|
||||
"loss": 0.0718,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.9158679446219382,
|
||||
"grad_norm": 0.7333608814823522,
|
||||
"learning_rate": 3.511574983399599e-06,
|
||||
"loss": 0.0592,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.9584664536741214,
|
||||
"grad_norm": 0.7101356242832322,
|
||||
"learning_rate": 3.2769714497962235e-06,
|
||||
"loss": 0.0631,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 0.7020066069562629,
|
||||
"learning_rate": 3.0465977649384813e-06,
|
||||
"loss": 0.0568,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 2.042598509052183,
|
||||
"grad_norm": 0.6143078466051928,
|
||||
"learning_rate": 2.8210194713078408e-06,
|
||||
"loss": 0.0342,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 2.0851970181043664,
|
||||
"grad_norm": 0.6960923290338111,
|
||||
"learning_rate": 2.600790339218926e-06,
|
||||
"loss": 0.029,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 2.1277955271565494,
|
||||
"grad_norm": 0.9794654564748295,
|
||||
"learning_rate": 2.3864510073732914e-06,
|
||||
"loss": 0.0317,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 2.170394036208733,
|
||||
"grad_norm": 0.6109166519427666,
|
||||
"learning_rate": 2.178527655649868e-06,
|
||||
"loss": 0.0308,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 2.212992545260916,
|
||||
"grad_norm": 0.6909646211341572,
|
||||
"learning_rate": 1.977530713390281e-06,
|
||||
"loss": 0.0287,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 2.255591054313099,
|
||||
"grad_norm": 0.6589603986660724,
|
||||
"learning_rate": 1.783953606350005e-06,
|
||||
"loss": 0.0284,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 2.2981895633652822,
|
||||
"grad_norm": 0.6418548129511306,
|
||||
"learning_rate": 1.5982715453915082e-06,
|
||||
"loss": 0.0282,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 2.3407880724174652,
|
||||
"grad_norm": 0.6688667188008208,
|
||||
"learning_rate": 1.4209403598929711e-06,
|
||||
"loss": 0.0298,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 2.3833865814696487,
|
||||
"grad_norm": 0.7442269287548521,
|
||||
"learning_rate": 1.2523953787364723e-06,
|
||||
"loss": 0.0269,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 2.4259850905218316,
|
||||
"grad_norm": 0.6780001132564086,
|
||||
"learning_rate": 1.0930503616226495e-06,
|
||||
"loss": 0.0258,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 2.468583599574015,
|
||||
"grad_norm": 0.6994808194521467,
|
||||
"learning_rate": 9.432964833353947e-07,
|
||||
"loss": 0.0285,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 2.511182108626198,
|
||||
"grad_norm": 0.6396237745490303,
|
||||
"learning_rate": 8.035013734500557e-07,
|
||||
"loss": 0.0304,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 2.553780617678381,
|
||||
"grad_norm": 0.8456007385218226,
|
||||
"learning_rate": 6.740082138425963e-07,
|
||||
"loss": 0.0284,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 2.5963791267305645,
|
||||
"grad_norm": 0.6627352659197506,
|
||||
"learning_rate": 5.551348962151965e-07,
|
||||
"loss": 0.0249,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 2.6389776357827475,
|
||||
"grad_norm": 0.5102316456936122,
|
||||
"learning_rate": 4.471732417065144e-07,
|
||||
"loss": 0.0227,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 2.681576144834931,
|
||||
"grad_norm": 0.7802646932680122,
|
||||
"learning_rate": 3.5038828450233874e-07,
|
||||
"loss": 0.0229,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 2.724174653887114,
|
||||
"grad_norm": 0.5730030349099514,
|
||||
"learning_rate": 2.65017621205339e-07,
|
||||
"loss": 0.025,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 2.7667731629392973,
|
||||
"grad_norm": 0.6632255868965671,
|
||||
"learning_rate": 1.9127082756109138e-07,
|
||||
"loss": 0.0281,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 2.8093716719914803,
|
||||
"grad_norm": 0.797692366915009,
|
||||
"learning_rate": 1.293289439722961e-07,
|
||||
"loss": 0.0222,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 2.8519701810436633,
|
||||
"grad_norm": 0.6808158703012352,
|
||||
"learning_rate": 7.934403106416245e-08,
|
||||
"loss": 0.0249,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 2.8945686900958467,
|
||||
"grad_norm": 0.6210288358669318,
|
||||
"learning_rate": 4.1438796392025416e-08,
|
||||
"loss": 0.0221,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 2.9371671991480297,
|
||||
"grad_norm": 0.6568231883800221,
|
||||
"learning_rate": 1.5706293207561896e-08,
|
||||
"loss": 0.0227,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 2.979765708200213,
|
||||
"grad_norm": 0.5276073549263733,
|
||||
"learning_rate": 2.209692023126819e-09,
|
||||
"loss": 0.0223,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"step": 705,
|
||||
"total_flos": 629471101583360.0,
|
||||
"train_loss": 0.1980447881822045,
|
||||
"train_runtime": 15010.1192,
|
||||
"train_samples_per_second": 3.003,
|
||||
"train_steps_per_second": 0.047
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 705,
|
||||
"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": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 629471101583360.0,
|
||||
"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:b7470bd23452aaa6216f1590154331402afcdb7d58e528f96c9caf07cba2345d
|
||||
size 8465
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 34 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