初始化项目，由ModelHub XC社区提供模型
Model: Pentland/full_sft_qwen2-5_7b_openr1_3k_context8k 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
|
||||
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen2.5-7B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: full_sft_qwen2-5_7b_openr1_3k_context8k
|
||||
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. -->
|
||||
# full_sft_qwen2-5_7b_openr1_3k_context8k
|
||||
|
||||
This model is a fine-tuned version of [/data2/cwli16/share-models/Qwen2.5-7B-Base](https://huggingface.co//data2/cwli16/share-models/Qwen2.5-7B-Base) on the openr1_math_alpaca 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: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 6
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 12
|
||||
- total_eval_batch_size: 48
|
||||
- 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 4.57.1
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 4.0.0
|
||||
- Tokenizers 0.22.1
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"total_flos": 74683443707904.0,
|
||||
"train_loss": 0.3264822006225586,
|
||||
"train_runtime": 5153.2999,
|
||||
"train_samples_per_second": 1.746,
|
||||
"train_steps_per_second": 0.146
|
||||
}
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
59
config.json
Normal file
59
config.json
Normal file
@@ -0,0 +1,59 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-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 sha256:70bcc67830f62c53326908a1e0ba68e27f5ef349f3c1483bfc1d00467c2190f1
|
||||
size 4877660776
|
||||
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:c90ddf9b3f34a898b108ac428d1aae2b6903b063cd8652db86b56fd4fc7ff881
|
||||
size 4932751008
|
||||
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 sha256:846c5c702dd1127446b409b60e56e81c922dc5784df14d1f42b2f59259ab1b12
|
||||
size 4330865200
|
||||
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:adcb82c9f7b12a0f9b316d391e15acf2df231681e4d51a6b4943ec15d6397de2
|
||||
size 1089994880
|
||||
347
model.safetensors.index.json
Normal file
347
model.safetensors.index.json
Normal file
@@ -0,0 +1,347 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 333312,
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-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_proj.bias": "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_proj.bias": "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.bias": "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-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-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_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.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_proj.bias": "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_proj.bias": "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.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00002-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_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"total_flos": 74683443707904.0,
|
||||
"train_loss": 0.3264822006225586,
|
||||
"train_runtime": 5153.2999,
|
||||
"train_samples_per_second": 1.746,
|
||||
"train_steps_per_second": 0.146
|
||||
}
|
||||
76
trainer_log.jsonl
Normal file
76
trainer_log.jsonl
Normal file
@@ -0,0 +1,76 @@
|
||||
{"current_steps": 10, "total_steps": 750, "loss": 0.6954, "lr": 1.2000000000000002e-06, "epoch": 0.04, "percentage": 1.33, "elapsed_time": "0:01:07", "remaining_time": "1:23:32"}
|
||||
{"current_steps": 20, "total_steps": 750, "loss": 0.6334, "lr": 2.5333333333333338e-06, "epoch": 0.08, "percentage": 2.67, "elapsed_time": "0:02:12", "remaining_time": "1:20:32"}
|
||||
{"current_steps": 30, "total_steps": 750, "loss": 0.5616, "lr": 3.866666666666667e-06, "epoch": 0.12, "percentage": 4.0, "elapsed_time": "0:03:21", "remaining_time": "1:20:38"}
|
||||
{"current_steps": 40, "total_steps": 750, "loss": 0.5148, "lr": 5.2e-06, "epoch": 0.16, "percentage": 5.33, "elapsed_time": "0:04:25", "remaining_time": "1:18:34"}
|
||||
{"current_steps": 50, "total_steps": 750, "loss": 0.4828, "lr": 6.533333333333334e-06, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:05:34", "remaining_time": "1:18:05"}
|
||||
{"current_steps": 60, "total_steps": 750, "loss": 0.4788, "lr": 7.866666666666667e-06, "epoch": 0.24, "percentage": 8.0, "elapsed_time": "0:06:48", "remaining_time": "1:18:15"}
|
||||
{"current_steps": 70, "total_steps": 750, "loss": 0.4728, "lr": 9.200000000000002e-06, "epoch": 0.28, "percentage": 9.33, "elapsed_time": "0:07:53", "remaining_time": "1:16:35"}
|
||||
{"current_steps": 80, "total_steps": 750, "loss": 0.4612, "lr": 9.99913355769784e-06, "epoch": 0.32, "percentage": 10.67, "elapsed_time": "0:09:00", "remaining_time": "1:15:22"}
|
||||
{"current_steps": 90, "total_steps": 750, "loss": 0.4436, "lr": 9.989389530100242e-06, "epoch": 0.36, "percentage": 12.0, "elapsed_time": "0:10:05", "remaining_time": "1:14:01"}
|
||||
{"current_steps": 100, "total_steps": 750, "loss": 0.4572, "lr": 9.968839595802982e-06, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:11:07", "remaining_time": "1:12:16"}
|
||||
{"current_steps": 110, "total_steps": 750, "loss": 0.4503, "lr": 9.937528261387753e-06, "epoch": 0.44, "percentage": 14.67, "elapsed_time": "0:12:09", "remaining_time": "1:10:44"}
|
||||
{"current_steps": 120, "total_steps": 750, "loss": 0.4796, "lr": 9.89552334023258e-06, "epoch": 0.48, "percentage": 16.0, "elapsed_time": "0:13:19", "remaining_time": "1:09:57"}
|
||||
{"current_steps": 130, "total_steps": 750, "loss": 0.4547, "lr": 9.842915805643156e-06, "epoch": 0.52, "percentage": 17.33, "elapsed_time": "0:14:24", "remaining_time": "1:08:41"}
|
||||
{"current_steps": 140, "total_steps": 750, "loss": 0.4402, "lr": 9.779819593824909e-06, "epoch": 0.56, "percentage": 18.67, "elapsed_time": "0:15:29", "remaining_time": "1:07:31"}
|
||||
{"current_steps": 150, "total_steps": 750, "loss": 0.4694, "lr": 9.70637135712256e-06, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "0:16:39", "remaining_time": "1:06:39"}
|
||||
{"current_steps": 160, "total_steps": 750, "loss": 0.4554, "lr": 9.622730168061568e-06, "epoch": 0.64, "percentage": 21.33, "elapsed_time": "0:17:42", "remaining_time": "1:05:18"}
|
||||
{"current_steps": 170, "total_steps": 750, "loss": 0.4291, "lr": 9.529077174832466e-06, "epoch": 0.68, "percentage": 22.67, "elapsed_time": "0:18:51", "remaining_time": "1:04:21"}
|
||||
{"current_steps": 180, "total_steps": 750, "loss": 0.4212, "lr": 9.425615208964217e-06, "epoch": 0.72, "percentage": 24.0, "elapsed_time": "0:19:55", "remaining_time": "1:03:06"}
|
||||
{"current_steps": 190, "total_steps": 750, "loss": 0.4351, "lr": 9.312568346036288e-06, "epoch": 0.76, "percentage": 25.33, "elapsed_time": "0:20:56", "remaining_time": "1:01:44"}
|
||||
{"current_steps": 200, "total_steps": 750, "loss": 0.4441, "lr": 9.190181420380838e-06, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:22:00", "remaining_time": "1:00:32"}
|
||||
{"current_steps": 210, "total_steps": 750, "loss": 0.4131, "lr": 9.058719494826076e-06, "epoch": 0.84, "percentage": 28.0, "elapsed_time": "0:23:09", "remaining_time": "0:59:32"}
|
||||
{"current_steps": 220, "total_steps": 750, "loss": 0.4278, "lr": 8.9184672866292e-06, "epoch": 0.88, "percentage": 29.33, "elapsed_time": "0:24:15", "remaining_time": "0:58:27"}
|
||||
{"current_steps": 230, "total_steps": 750, "loss": 0.4397, "lr": 8.769728550842217e-06, "epoch": 0.92, "percentage": 30.67, "elapsed_time": "0:25:18", "remaining_time": "0:57:12"}
|
||||
{"current_steps": 240, "total_steps": 750, "loss": 0.4462, "lr": 8.61282542244614e-06, "epoch": 0.96, "percentage": 32.0, "elapsed_time": "0:26:27", "remaining_time": "0:56:13"}
|
||||
{"current_steps": 250, "total_steps": 750, "loss": 0.4383, "lr": 8.44809771867835e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:27:33", "remaining_time": "0:55:06"}
|
||||
{"current_steps": 260, "total_steps": 750, "loss": 0.3197, "lr": 8.275902203064125e-06, "epoch": 1.04, "percentage": 34.67, "elapsed_time": "0:28:35", "remaining_time": "0:53:53"}
|
||||
{"current_steps": 270, "total_steps": 750, "loss": 0.3217, "lr": 8.096611812746302e-06, "epoch": 1.08, "percentage": 36.0, "elapsed_time": "0:29:43", "remaining_time": "0:52:50"}
|
||||
{"current_steps": 280, "total_steps": 750, "loss": 0.32, "lr": 7.910614850786448e-06, "epoch": 1.12, "percentage": 37.33, "elapsed_time": "0:30:53", "remaining_time": "0:51:50"}
|
||||
{"current_steps": 290, "total_steps": 750, "loss": 0.3252, "lr": 7.718314145186918e-06, "epoch": 1.16, "percentage": 38.67, "elapsed_time": "0:32:01", "remaining_time": "0:50:48"}
|
||||
{"current_steps": 300, "total_steps": 750, "loss": 0.3223, "lr": 7.520126176455084e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:33:11", "remaining_time": "0:49:46"}
|
||||
{"current_steps": 310, "total_steps": 750, "loss": 0.3167, "lr": 7.31648017559931e-06, "epoch": 1.24, "percentage": 41.33, "elapsed_time": "0:35:04", "remaining_time": "0:49:46"}
|
||||
{"current_steps": 320, "total_steps": 750, "loss": 0.3178, "lr": 7.107817194510157e-06, "epoch": 1.28, "percentage": 42.67, "elapsed_time": "0:36:10", "remaining_time": "0:48:36"}
|
||||
{"current_steps": 330, "total_steps": 750, "loss": 0.3081, "lr": 6.8945891507402075e-06, "epoch": 1.32, "percentage": 44.0, "elapsed_time": "0:37:17", "remaining_time": "0:47:27"}
|
||||
{"current_steps": 340, "total_steps": 750, "loss": 0.3146, "lr": 6.677257848751276e-06, "epoch": 1.3599999999999999, "percentage": 45.33, "elapsed_time": "0:38:25", "remaining_time": "0:46:19"}
|
||||
{"current_steps": 350, "total_steps": 750, "loss": 0.3051, "lr": 6.456293979748778e-06, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "0:39:29", "remaining_time": "0:45:08"}
|
||||
{"current_steps": 360, "total_steps": 750, "loss": 0.305, "lr": 6.23217610226939e-06, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "0:40:33", "remaining_time": "0:43:56"}
|
||||
{"current_steps": 370, "total_steps": 750, "loss": 0.3263, "lr": 6.005389605729824e-06, "epoch": 1.48, "percentage": 49.33, "elapsed_time": "0:41:47", "remaining_time": "0:42:54"}
|
||||
{"current_steps": 380, "total_steps": 750, "loss": 0.3067, "lr": 5.776425659181438e-06, "epoch": 1.52, "percentage": 50.67, "elapsed_time": "0:42:54", "remaining_time": "0:41:46"}
|
||||
{"current_steps": 390, "total_steps": 750, "loss": 0.3145, "lr": 5.54578014754744e-06, "epoch": 1.56, "percentage": 52.0, "elapsed_time": "0:43:59", "remaining_time": "0:40:36"}
|
||||
{"current_steps": 400, "total_steps": 750, "loss": 0.3142, "lr": 5.3139525976465675e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:45:09", "remaining_time": "0:39:30"}
|
||||
{"current_steps": 410, "total_steps": 750, "loss": 0.2968, "lr": 5.081445096329229e-06, "epoch": 1.6400000000000001, "percentage": 54.67, "elapsed_time": "0:46:12", "remaining_time": "0:38:19"}
|
||||
{"current_steps": 420, "total_steps": 750, "loss": 0.3198, "lr": 4.8487612030691975e-06, "epoch": 1.6800000000000002, "percentage": 56.0, "elapsed_time": "0:47:17", "remaining_time": "0:37:09"}
|
||||
{"current_steps": 430, "total_steps": 750, "loss": 0.3064, "lr": 4.6164048593659076e-06, "epoch": 1.72, "percentage": 57.33, "elapsed_time": "0:48:27", "remaining_time": "0:36:03"}
|
||||
{"current_steps": 440, "total_steps": 750, "loss": 0.3094, "lr": 4.384879297319398e-06, "epoch": 1.76, "percentage": 58.67, "elapsed_time": "0:49:31", "remaining_time": "0:34:53"}
|
||||
{"current_steps": 450, "total_steps": 750, "loss": 0.298, "lr": 4.154685949741631e-06, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "0:50:37", "remaining_time": "0:33:45"}
|
||||
{"current_steps": 460, "total_steps": 750, "loss": 0.3079, "lr": 3.926323364164684e-06, "epoch": 1.8399999999999999, "percentage": 61.33, "elapsed_time": "0:51:36", "remaining_time": "0:32:31"}
|
||||
{"current_steps": 470, "total_steps": 750, "loss": 0.3022, "lr": 3.700286123097814e-06, "epoch": 1.88, "percentage": 62.67, "elapsed_time": "0:52:43", "remaining_time": "0:31:24"}
|
||||
{"current_steps": 480, "total_steps": 750, "loss": 0.3186, "lr": 3.4770637728718608e-06, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "0:53:46", "remaining_time": "0:30:15"}
|
||||
{"current_steps": 490, "total_steps": 750, "loss": 0.3181, "lr": 3.2571397633909252e-06, "epoch": 1.96, "percentage": 65.33, "elapsed_time": "0:54:57", "remaining_time": "0:29:09"}
|
||||
{"current_steps": 500, "total_steps": 750, "loss": 0.3097, "lr": 3.040990401087508e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:56:00", "remaining_time": "0:28:00"}
|
||||
{"current_steps": 510, "total_steps": 750, "loss": 0.2099, "lr": 2.82908381734886e-06, "epoch": 2.04, "percentage": 68.0, "elapsed_time": "0:57:04", "remaining_time": "0:26:51"}
|
||||
{"current_steps": 520, "total_steps": 750, "loss": 0.1884, "lr": 2.6218789546486235e-06, "epoch": 2.08, "percentage": 69.33, "elapsed_time": "0:58:05", "remaining_time": "0:25:41"}
|
||||
{"current_steps": 530, "total_steps": 750, "loss": 0.2003, "lr": 2.4198245725796427e-06, "epoch": 2.12, "percentage": 70.67, "elapsed_time": "0:59:13", "remaining_time": "0:24:34"}
|
||||
{"current_steps": 540, "total_steps": 750, "loss": 0.1917, "lr": 2.2233582759406065e-06, "epoch": 2.16, "percentage": 72.0, "elapsed_time": "1:00:16", "remaining_time": "0:23:26"}
|
||||
{"current_steps": 550, "total_steps": 750, "loss": 0.1986, "lr": 2.0329055669814936e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "1:01:22", "remaining_time": "0:22:19"}
|
||||
{"current_steps": 560, "total_steps": 750, "loss": 0.1924, "lr": 1.8488789238604676e-06, "epoch": 2.24, "percentage": 74.67, "elapsed_time": "1:02:35", "remaining_time": "0:21:14"}
|
||||
{"current_steps": 570, "total_steps": 750, "loss": 0.184, "lr": 1.671676907308018e-06, "epoch": 2.2800000000000002, "percentage": 76.0, "elapsed_time": "1:03:37", "remaining_time": "0:20:05"}
|
||||
{"current_steps": 580, "total_steps": 750, "loss": 0.1974, "lr": 1.5016832974331725e-06, "epoch": 2.32, "percentage": 77.33, "elapsed_time": "1:04:44", "remaining_time": "0:18:58"}
|
||||
{"current_steps": 590, "total_steps": 750, "loss": 0.1996, "lr": 1.339266262541249e-06, "epoch": 2.36, "percentage": 78.67, "elapsed_time": "1:05:53", "remaining_time": "0:17:52"}
|
||||
{"current_steps": 600, "total_steps": 750, "loss": 0.1911, "lr": 1.1847775617632746e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "1:06:56", "remaining_time": "0:16:44"}
|
||||
{"current_steps": 610, "total_steps": 750, "loss": 0.1806, "lr": 1.0385517832240472e-06, "epoch": 2.44, "percentage": 81.33, "elapsed_time": "1:09:18", "remaining_time": "0:15:54"}
|
||||
{"current_steps": 620, "total_steps": 750, "loss": 0.1923, "lr": 9.009056193987569e-07, "epoch": 2.48, "percentage": 82.67, "elapsed_time": "1:10:20", "remaining_time": "0:14:44"}
|
||||
{"current_steps": 630, "total_steps": 750, "loss": 0.1982, "lr": 7.72137181227608e-07, "epoch": 2.52, "percentage": 84.0, "elapsed_time": "1:11:25", "remaining_time": "0:13:36"}
|
||||
{"current_steps": 640, "total_steps": 750, "loss": 0.1907, "lr": 6.52525352473905e-07, "epoch": 2.56, "percentage": 85.33, "elapsed_time": "1:12:32", "remaining_time": "0:12:28"}
|
||||
{"current_steps": 650, "total_steps": 750, "loss": 0.1941, "lr": 5.423291857239177e-07, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "1:13:40", "remaining_time": "0:11:20"}
|
||||
{"current_steps": 660, "total_steps": 750, "loss": 0.1976, "lr": 4.417873413366702e-07, "epoch": 2.64, "percentage": 88.0, "elapsed_time": "1:14:46", "remaining_time": "0:10:11"}
|
||||
{"current_steps": 670, "total_steps": 750, "loss": 0.1796, "lr": 3.511175705587433e-07, "epoch": 2.68, "percentage": 89.33, "elapsed_time": "1:15:49", "remaining_time": "0:09:03"}
|
||||
{"current_steps": 680, "total_steps": 750, "loss": 0.1847, "lr": 2.705162439235648e-07, "epoch": 2.7199999999999998, "percentage": 90.67, "elapsed_time": "1:16:54", "remaining_time": "0:07:55"}
|
||||
{"current_steps": 690, "total_steps": 750, "loss": 0.1925, "lr": 2.0015792595656225e-07, "epoch": 2.76, "percentage": 92.0, "elapsed_time": "1:18:04", "remaining_time": "0:06:47"}
|
||||
{"current_steps": 700, "total_steps": 750, "loss": 0.1793, "lr": 1.4019499710726913e-07, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "1:19:13", "remaining_time": "0:05:39"}
|
||||
{"current_steps": 710, "total_steps": 750, "loss": 0.1986, "lr": 9.075732372720414e-08, "epoch": 2.84, "percentage": 94.67, "elapsed_time": "1:20:21", "remaining_time": "0:04:31"}
|
||||
{"current_steps": 720, "total_steps": 750, "loss": 0.2096, "lr": 5.19519768082738e-08, "epoch": 2.88, "percentage": 96.0, "elapsed_time": "1:21:32", "remaining_time": "0:03:23"}
|
||||
{"current_steps": 730, "total_steps": 750, "loss": 0.1879, "lr": 2.386300009084408e-08, "epoch": 2.92, "percentage": 97.33, "elapsed_time": "1:22:38", "remaining_time": "0:02:15"}
|
||||
{"current_steps": 740, "total_steps": 750, "loss": 0.1868, "lr": 6.551228043715218e-09, "epoch": 2.96, "percentage": 98.67, "elapsed_time": "1:23:42", "remaining_time": "0:01:07"}
|
||||
{"current_steps": 750, "total_steps": 750, "loss": 0.1897, "lr": 5.4154110206150465e-11, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:24:47", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 750, "total_steps": 750, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:25:53", "remaining_time": "0:00:00"}
|
||||
568
trainer_state.json
Normal file
568
trainer_state.json
Normal file
@@ -0,0 +1,568 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 3.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 750,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.04,
|
||||
"grad_norm": 3.238205219704208,
|
||||
"learning_rate": 1.2000000000000002e-06,
|
||||
"loss": 0.6954,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.08,
|
||||
"grad_norm": 2.271242025646856,
|
||||
"learning_rate": 2.5333333333333338e-06,
|
||||
"loss": 0.6334,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.12,
|
||||
"grad_norm": 2.1800513767705887,
|
||||
"learning_rate": 3.866666666666667e-06,
|
||||
"loss": 0.5616,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.16,
|
||||
"grad_norm": 1.1648812039750702,
|
||||
"learning_rate": 5.2e-06,
|
||||
"loss": 0.5148,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.2,
|
||||
"grad_norm": 1.1498397092624104,
|
||||
"learning_rate": 6.533333333333334e-06,
|
||||
"loss": 0.4828,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.24,
|
||||
"grad_norm": 1.439054889387191,
|
||||
"learning_rate": 7.866666666666667e-06,
|
||||
"loss": 0.4788,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.28,
|
||||
"grad_norm": 1.261998263366119,
|
||||
"learning_rate": 9.200000000000002e-06,
|
||||
"loss": 0.4728,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"grad_norm": 1.201844069110454,
|
||||
"learning_rate": 9.99913355769784e-06,
|
||||
"loss": 0.4612,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.36,
|
||||
"grad_norm": 1.1591811394080247,
|
||||
"learning_rate": 9.989389530100242e-06,
|
||||
"loss": 0.4436,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.4,
|
||||
"grad_norm": 1.3078102825158529,
|
||||
"learning_rate": 9.968839595802982e-06,
|
||||
"loss": 0.4572,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"grad_norm": 1.3962661244372518,
|
||||
"learning_rate": 9.937528261387753e-06,
|
||||
"loss": 0.4503,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.48,
|
||||
"grad_norm": 1.1977369757824934,
|
||||
"learning_rate": 9.89552334023258e-06,
|
||||
"loss": 0.4796,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.52,
|
||||
"grad_norm": 1.2903900106680968,
|
||||
"learning_rate": 9.842915805643156e-06,
|
||||
"loss": 0.4547,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.56,
|
||||
"grad_norm": 1.133608924238385,
|
||||
"learning_rate": 9.779819593824909e-06,
|
||||
"loss": 0.4402,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.6,
|
||||
"grad_norm": 1.2659380507665736,
|
||||
"learning_rate": 9.70637135712256e-06,
|
||||
"loss": 0.4694,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"grad_norm": 1.4145155140111882,
|
||||
"learning_rate": 9.622730168061568e-06,
|
||||
"loss": 0.4554,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.68,
|
||||
"grad_norm": 1.1814401533026162,
|
||||
"learning_rate": 9.529077174832466e-06,
|
||||
"loss": 0.4291,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.72,
|
||||
"grad_norm": 1.1554822616312184,
|
||||
"learning_rate": 9.425615208964217e-06,
|
||||
"loss": 0.4212,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.76,
|
||||
"grad_norm": 1.1661698221732884,
|
||||
"learning_rate": 9.312568346036288e-06,
|
||||
"loss": 0.4351,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.8,
|
||||
"grad_norm": 1.4701849159841565,
|
||||
"learning_rate": 9.190181420380838e-06,
|
||||
"loss": 0.4441,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.84,
|
||||
"grad_norm": 0.989465732667978,
|
||||
"learning_rate": 9.058719494826076e-06,
|
||||
"loss": 0.4131,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.88,
|
||||
"grad_norm": 1.239658511180224,
|
||||
"learning_rate": 8.9184672866292e-06,
|
||||
"loss": 0.4278,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.92,
|
||||
"grad_norm": 1.089425874622714,
|
||||
"learning_rate": 8.769728550842217e-06,
|
||||
"loss": 0.4397,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.96,
|
||||
"grad_norm": 1.2147944787643823,
|
||||
"learning_rate": 8.61282542244614e-06,
|
||||
"loss": 0.4462,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 1.1427874903675157,
|
||||
"learning_rate": 8.44809771867835e-06,
|
||||
"loss": 0.4383,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 1.04,
|
||||
"grad_norm": 1.1462782760971437,
|
||||
"learning_rate": 8.275902203064125e-06,
|
||||
"loss": 0.3197,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 1.08,
|
||||
"grad_norm": 1.1173783548629352,
|
||||
"learning_rate": 8.096611812746302e-06,
|
||||
"loss": 0.3217,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 1.12,
|
||||
"grad_norm": 1.2777869200415286,
|
||||
"learning_rate": 7.910614850786448e-06,
|
||||
"loss": 0.32,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 1.16,
|
||||
"grad_norm": 1.2517126629173954,
|
||||
"learning_rate": 7.718314145186918e-06,
|
||||
"loss": 0.3252,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 1.2,
|
||||
"grad_norm": 1.1470476886369243,
|
||||
"learning_rate": 7.520126176455084e-06,
|
||||
"loss": 0.3223,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 1.24,
|
||||
"grad_norm": 1.1129643309958803,
|
||||
"learning_rate": 7.31648017559931e-06,
|
||||
"loss": 0.3167,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 1.28,
|
||||
"grad_norm": 0.9919930530594523,
|
||||
"learning_rate": 7.107817194510157e-06,
|
||||
"loss": 0.3178,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 1.32,
|
||||
"grad_norm": 1.0170698896454753,
|
||||
"learning_rate": 6.8945891507402075e-06,
|
||||
"loss": 0.3081,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 1.3599999999999999,
|
||||
"grad_norm": 1.0642304251855126,
|
||||
"learning_rate": 6.677257848751276e-06,
|
||||
"loss": 0.3146,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 1.4,
|
||||
"grad_norm": 1.015720677645443,
|
||||
"learning_rate": 6.456293979748778e-06,
|
||||
"loss": 0.3051,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.44,
|
||||
"grad_norm": 1.011871475120043,
|
||||
"learning_rate": 6.23217610226939e-06,
|
||||
"loss": 0.305,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 1.48,
|
||||
"grad_norm": 0.8935917352634799,
|
||||
"learning_rate": 6.005389605729824e-06,
|
||||
"loss": 0.3263,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 1.52,
|
||||
"grad_norm": 0.9654676799055634,
|
||||
"learning_rate": 5.776425659181438e-06,
|
||||
"loss": 0.3067,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 1.56,
|
||||
"grad_norm": 1.0407814220165412,
|
||||
"learning_rate": 5.54578014754744e-06,
|
||||
"loss": 0.3145,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 1.6,
|
||||
"grad_norm": 1.1735574861995242,
|
||||
"learning_rate": 5.3139525976465675e-06,
|
||||
"loss": 0.3142,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.6400000000000001,
|
||||
"grad_norm": 1.0352433339394025,
|
||||
"learning_rate": 5.081445096329229e-06,
|
||||
"loss": 0.2968,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 1.6800000000000002,
|
||||
"grad_norm": 1.0514219097026112,
|
||||
"learning_rate": 4.8487612030691975e-06,
|
||||
"loss": 0.3198,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 1.72,
|
||||
"grad_norm": 1.1112681652067895,
|
||||
"learning_rate": 4.6164048593659076e-06,
|
||||
"loss": 0.3064,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 1.76,
|
||||
"grad_norm": 1.0048201676188762,
|
||||
"learning_rate": 4.384879297319398e-06,
|
||||
"loss": 0.3094,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.8,
|
||||
"grad_norm": 1.0758653777705578,
|
||||
"learning_rate": 4.154685949741631e-06,
|
||||
"loss": 0.298,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.8399999999999999,
|
||||
"grad_norm": 1.1664913247689033,
|
||||
"learning_rate": 3.926323364164684e-06,
|
||||
"loss": 0.3079,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 1.88,
|
||||
"grad_norm": 1.1338425739168947,
|
||||
"learning_rate": 3.700286123097814e-06,
|
||||
"loss": 0.3022,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 1.92,
|
||||
"grad_norm": 1.015433141233684,
|
||||
"learning_rate": 3.4770637728718608e-06,
|
||||
"loss": 0.3186,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 1.96,
|
||||
"grad_norm": 0.8460014130005209,
|
||||
"learning_rate": 3.2571397633909252e-06,
|
||||
"loss": 0.3181,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 1.0261154780948782,
|
||||
"learning_rate": 3.040990401087508e-06,
|
||||
"loss": 0.3097,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 2.04,
|
||||
"grad_norm": 0.8655997174434865,
|
||||
"learning_rate": 2.82908381734886e-06,
|
||||
"loss": 0.2099,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 2.08,
|
||||
"grad_norm": 0.9651491328248828,
|
||||
"learning_rate": 2.6218789546486235e-06,
|
||||
"loss": 0.1884,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 2.12,
|
||||
"grad_norm": 1.2953511119694772,
|
||||
"learning_rate": 2.4198245725796427e-06,
|
||||
"loss": 0.2003,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 2.16,
|
||||
"grad_norm": 0.9087547978711116,
|
||||
"learning_rate": 2.2233582759406065e-06,
|
||||
"loss": 0.1917,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 2.2,
|
||||
"grad_norm": 0.9541801827955388,
|
||||
"learning_rate": 2.0329055669814936e-06,
|
||||
"loss": 0.1986,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 2.24,
|
||||
"grad_norm": 0.8678726633389815,
|
||||
"learning_rate": 1.8488789238604676e-06,
|
||||
"loss": 0.1924,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 2.2800000000000002,
|
||||
"grad_norm": 0.8113217057232563,
|
||||
"learning_rate": 1.671676907308018e-06,
|
||||
"loss": 0.184,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 2.32,
|
||||
"grad_norm": 0.8358564334561136,
|
||||
"learning_rate": 1.5016832974331725e-06,
|
||||
"loss": 0.1974,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 2.36,
|
||||
"grad_norm": 0.8680751720471733,
|
||||
"learning_rate": 1.339266262541249e-06,
|
||||
"loss": 0.1996,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 2.4,
|
||||
"grad_norm": 0.9201310980151841,
|
||||
"learning_rate": 1.1847775617632746e-06,
|
||||
"loss": 0.1911,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 2.44,
|
||||
"grad_norm": 0.8709439322420328,
|
||||
"learning_rate": 1.0385517832240472e-06,
|
||||
"loss": 0.1806,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 2.48,
|
||||
"grad_norm": 0.9110684302470888,
|
||||
"learning_rate": 9.009056193987569e-07,
|
||||
"loss": 0.1923,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 2.52,
|
||||
"grad_norm": 0.8600274721721193,
|
||||
"learning_rate": 7.72137181227608e-07,
|
||||
"loss": 0.1982,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 2.56,
|
||||
"grad_norm": 0.9440305798432147,
|
||||
"learning_rate": 6.52525352473905e-07,
|
||||
"loss": 0.1907,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 2.6,
|
||||
"grad_norm": 0.8863906599552978,
|
||||
"learning_rate": 5.423291857239177e-07,
|
||||
"loss": 0.1941,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 2.64,
|
||||
"grad_norm": 0.8566897992226741,
|
||||
"learning_rate": 4.417873413366702e-07,
|
||||
"loss": 0.1976,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 2.68,
|
||||
"grad_norm": 0.8775191271488543,
|
||||
"learning_rate": 3.511175705587433e-07,
|
||||
"loss": 0.1796,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 2.7199999999999998,
|
||||
"grad_norm": 0.8190151352692299,
|
||||
"learning_rate": 2.705162439235648e-07,
|
||||
"loss": 0.1847,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 2.76,
|
||||
"grad_norm": 0.9849452914848762,
|
||||
"learning_rate": 2.0015792595656225e-07,
|
||||
"loss": 0.1925,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 2.8,
|
||||
"grad_norm": 0.8247035782367392,
|
||||
"learning_rate": 1.4019499710726913e-07,
|
||||
"loss": 0.1793,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 2.84,
|
||||
"grad_norm": 1.0595539505434528,
|
||||
"learning_rate": 9.075732372720414e-08,
|
||||
"loss": 0.1986,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 2.88,
|
||||
"grad_norm": 0.9332714846129114,
|
||||
"learning_rate": 5.19519768082738e-08,
|
||||
"loss": 0.2096,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 2.92,
|
||||
"grad_norm": 1.0945012473014315,
|
||||
"learning_rate": 2.386300009084408e-08,
|
||||
"loss": 0.1879,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 2.96,
|
||||
"grad_norm": 1.0438096421818555,
|
||||
"learning_rate": 6.551228043715218e-09,
|
||||
"loss": 0.1868,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"grad_norm": 0.9128409856387972,
|
||||
"learning_rate": 5.4154110206150465e-11,
|
||||
"loss": 0.1897,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"step": 750,
|
||||
"total_flos": 74683443707904.0,
|
||||
"train_loss": 0.3264822006225586,
|
||||
"train_runtime": 5153.2999,
|
||||
"train_samples_per_second": 1.746,
|
||||
"train_steps_per_second": 0.146
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 750,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 300,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 74683443707904.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:adbcc10218ccc7f5e427fc42adf8f709f92ba4009f26a8c4f2f38e926c2f06e2
|
||||
size 7800
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 41 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