初始化项目，由ModelHub XC社区提供模型
Model: bespokelabs/qwen3-4b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm 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: apache-2.0
|
||||||
|
base_model: Qwen/Qwen3-4B
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: qwen3-4b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft
|
||||||
|
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. -->
|
||||||
|
|
||||||
|
# qwen3-4b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the eval-ds-dabstep-reasoning-108-fixed-reasoning-sharegpt 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
|
||||||
|
- total_train_batch_size: 16
|
||||||
|
- 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: 0.01
|
||||||
|
- num_epochs: 5.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.52.4
|
||||||
|
- Pytorch 2.7.0+cu126
|
||||||
|
- Datasets 3.6.0
|
||||||
|
- Tokenizers 0.21.1
|
||||||
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": 5.0,
|
||||||
|
"total_flos": 9984310984704.0,
|
||||||
|
"train_loss": 0.5776977070740291,
|
||||||
|
"train_runtime": 1052.4329,
|
||||||
|
"train_samples_per_second": 0.48,
|
||||||
|
"train_steps_per_second": 0.033
|
||||||
|
}
|
||||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- 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 message.content is string 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.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.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' }}
|
||||||
|
{{- 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 %}
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2560,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9728,
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.52.4",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "4.52.4"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:66657161b3a991e5f97fa7148725ed3df7f0d91f9ab55f14e47a7b46341c5299
|
||||||
|
size 4967215360
|
||||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5095b529be53390f844067f4d1b2dffdfd1af8ec72e4c33ebbc2eebc95d8e138
|
||||||
|
size 3077766632
|
||||||
405
model.safetensors.index.json
Normal file
405
model.safetensors.index.json
Normal file
@@ -0,0 +1,405 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 8044936192
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
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
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 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": 5.0,
|
||||||
|
"total_flos": 9984310984704.0,
|
||||||
|
"train_loss": 0.5776977070740291,
|
||||||
|
"train_runtime": 1052.4329,
|
||||||
|
"train_samples_per_second": 0.48,
|
||||||
|
"train_steps_per_second": 0.033
|
||||||
|
}
|
||||||
36
trainer_log.jsonl
Normal file
36
trainer_log.jsonl
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
{"current_steps": 1, "total_steps": 35, "loss": 0.9792, "lr": 0.0, "epoch": 0.14285714285714285, "percentage": 2.86, "elapsed_time": "0:00:35", "remaining_time": "0:20:23"}
|
||||||
|
{"current_steps": 2, "total_steps": 35, "loss": 0.9867, "lr": 1e-05, "epoch": 0.2857142857142857, "percentage": 5.71, "elapsed_time": "0:01:04", "remaining_time": "0:17:50"}
|
||||||
|
{"current_steps": 3, "total_steps": 35, "loss": 0.8843, "lr": 9.978670881475173e-06, "epoch": 0.42857142857142855, "percentage": 8.57, "elapsed_time": "0:01:30", "remaining_time": "0:16:08"}
|
||||||
|
{"current_steps": 4, "total_steps": 35, "loss": 0.8005, "lr": 9.91486549841951e-06, "epoch": 0.5714285714285714, "percentage": 11.43, "elapsed_time": "0:01:56", "remaining_time": "0:15:00"}
|
||||||
|
{"current_steps": 5, "total_steps": 35, "loss": 0.7994, "lr": 9.809128215864096e-06, "epoch": 0.7142857142857143, "percentage": 14.29, "elapsed_time": "0:02:21", "remaining_time": "0:14:10"}
|
||||||
|
{"current_steps": 6, "total_steps": 35, "loss": 0.7365, "lr": 9.66236114702178e-06, "epoch": 0.8571428571428571, "percentage": 17.14, "elapsed_time": "0:02:46", "remaining_time": "0:13:24"}
|
||||||
|
{"current_steps": 7, "total_steps": 35, "loss": 0.7101, "lr": 9.475816456775313e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:03:11", "remaining_time": "0:12:47"}
|
||||||
|
{"current_steps": 8, "total_steps": 35, "loss": 0.6625, "lr": 9.251085678648072e-06, "epoch": 1.1428571428571428, "percentage": 22.86, "elapsed_time": "0:03:39", "remaining_time": "0:12:19"}
|
||||||
|
{"current_steps": 9, "total_steps": 35, "loss": 0.626, "lr": 8.990086136401199e-06, "epoch": 1.2857142857142856, "percentage": 25.71, "elapsed_time": "0:04:03", "remaining_time": "0:11:44"}
|
||||||
|
{"current_steps": 10, "total_steps": 35, "loss": 0.656, "lr": 8.695044586103297e-06, "epoch": 1.4285714285714286, "percentage": 28.57, "elapsed_time": "0:04:29", "remaining_time": "0:11:12"}
|
||||||
|
{"current_steps": 11, "total_steps": 35, "loss": 0.5878, "lr": 8.368478218232787e-06, "epoch": 1.5714285714285714, "percentage": 31.43, "elapsed_time": "0:04:53", "remaining_time": "0:10:41"}
|
||||||
|
{"current_steps": 12, "total_steps": 35, "loss": 0.5721, "lr": 8.013173181896283e-06, "epoch": 1.7142857142857144, "percentage": 34.29, "elapsed_time": "0:05:19", "remaining_time": "0:10:11"}
|
||||||
|
{"current_steps": 13, "total_steps": 35, "loss": 0.5933, "lr": 7.63216081438678e-06, "epoch": 1.8571428571428572, "percentage": 37.14, "elapsed_time": "0:05:43", "remaining_time": "0:09:41"}
|
||||||
|
{"current_steps": 14, "total_steps": 35, "loss": 0.5497, "lr": 7.2286917788826926e-06, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:06:09", "remaining_time": "0:09:13"}
|
||||||
|
{"current_steps": 15, "total_steps": 35, "loss": 0.5418, "lr": 6.806208330935766e-06, "epoch": 2.142857142857143, "percentage": 42.86, "elapsed_time": "0:06:36", "remaining_time": "0:08:48"}
|
||||||
|
{"current_steps": 16, "total_steps": 35, "loss": 0.5445, "lr": 6.368314950360416e-06, "epoch": 2.2857142857142856, "percentage": 45.71, "elapsed_time": "0:07:00", "remaining_time": "0:08:19"}
|
||||||
|
{"current_steps": 17, "total_steps": 35, "loss": 0.5367, "lr": 5.918747589082853e-06, "epoch": 2.4285714285714284, "percentage": 48.57, "elapsed_time": "0:07:25", "remaining_time": "0:07:51"}
|
||||||
|
{"current_steps": 18, "total_steps": 35, "loss": 0.5187, "lr": 5.46134179731651e-06, "epoch": 2.571428571428571, "percentage": 51.43, "elapsed_time": "0:07:50", "remaining_time": "0:07:24"}
|
||||||
|
{"current_steps": 19, "total_steps": 35, "loss": 0.4862, "lr": 5e-06, "epoch": 2.7142857142857144, "percentage": 54.29, "elapsed_time": "0:08:15", "remaining_time": "0:06:57"}
|
||||||
|
{"current_steps": 20, "total_steps": 35, "loss": 0.4859, "lr": 4.53865820268349e-06, "epoch": 2.857142857142857, "percentage": 57.14, "elapsed_time": "0:08:40", "remaining_time": "0:06:30"}
|
||||||
|
{"current_steps": 21, "total_steps": 35, "loss": 0.4726, "lr": 4.081252410917148e-06, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:09:05", "remaining_time": "0:06:03"}
|
||||||
|
{"current_steps": 22, "total_steps": 35, "loss": 0.5075, "lr": 3.6316850496395863e-06, "epoch": 3.142857142857143, "percentage": 62.86, "elapsed_time": "0:09:32", "remaining_time": "0:05:38"}
|
||||||
|
{"current_steps": 23, "total_steps": 35, "loss": 0.4833, "lr": 3.1937916690642356e-06, "epoch": 3.2857142857142856, "percentage": 65.71, "elapsed_time": "0:09:57", "remaining_time": "0:05:11"}
|
||||||
|
{"current_steps": 24, "total_steps": 35, "loss": 0.468, "lr": 2.771308221117309e-06, "epoch": 3.4285714285714284, "percentage": 68.57, "elapsed_time": "0:10:22", "remaining_time": "0:04:45"}
|
||||||
|
{"current_steps": 25, "total_steps": 35, "loss": 0.4651, "lr": 2.3678391856132203e-06, "epoch": 3.571428571428571, "percentage": 71.43, "elapsed_time": "0:10:47", "remaining_time": "0:04:19"}
|
||||||
|
{"current_steps": 26, "total_steps": 35, "loss": 0.4682, "lr": 1.9868268181037186e-06, "epoch": 3.7142857142857144, "percentage": 74.29, "elapsed_time": "0:11:12", "remaining_time": "0:03:52"}
|
||||||
|
{"current_steps": 27, "total_steps": 35, "loss": 0.4514, "lr": 1.6315217817672142e-06, "epoch": 3.857142857142857, "percentage": 77.14, "elapsed_time": "0:11:37", "remaining_time": "0:03:26"}
|
||||||
|
{"current_steps": 28, "total_steps": 35, "loss": 0.4789, "lr": 1.3049554138967052e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:12:03", "remaining_time": "0:03:00"}
|
||||||
|
{"current_steps": 29, "total_steps": 35, "loss": 0.4695, "lr": 1.0099138635988026e-06, "epoch": 4.142857142857143, "percentage": 82.86, "elapsed_time": "0:12:30", "remaining_time": "0:02:35"}
|
||||||
|
{"current_steps": 30, "total_steps": 35, "loss": 0.4236, "lr": 7.489143213519301e-07, "epoch": 4.285714285714286, "percentage": 85.71, "elapsed_time": "0:12:55", "remaining_time": "0:02:09"}
|
||||||
|
{"current_steps": 31, "total_steps": 35, "loss": 0.4557, "lr": 5.241835432246888e-07, "epoch": 4.428571428571429, "percentage": 88.57, "elapsed_time": "0:13:20", "remaining_time": "0:01:43"}
|
||||||
|
{"current_steps": 32, "total_steps": 35, "loss": 0.4666, "lr": 3.3763885297822153e-07, "epoch": 4.571428571428571, "percentage": 91.43, "elapsed_time": "0:13:44", "remaining_time": "0:01:17"}
|
||||||
|
{"current_steps": 33, "total_steps": 35, "loss": 0.4402, "lr": 1.908717841359048e-07, "epoch": 4.714285714285714, "percentage": 94.29, "elapsed_time": "0:14:09", "remaining_time": "0:00:51"}
|
||||||
|
{"current_steps": 34, "total_steps": 35, "loss": 0.4539, "lr": 8.513450158049109e-08, "epoch": 4.857142857142857, "percentage": 97.14, "elapsed_time": "0:14:33", "remaining_time": "0:00:25"}
|
||||||
|
{"current_steps": 35, "total_steps": 35, "loss": 0.4573, "lr": 2.1329118524827662e-08, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:15:00", "remaining_time": "0:00:00"}
|
||||||
|
{"current_steps": 35, "total_steps": 35, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:17:30", "remaining_time": "0:00:00"}
|
||||||
288
trainer_state.json
Normal file
288
trainer_state.json
Normal file
@@ -0,0 +1,288 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 5.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 35,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.14285714285714285,
|
||||||
|
"grad_norm": 9.303076493883763,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 0.9792,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2857142857142857,
|
||||||
|
"grad_norm": 9.717944059478823,
|
||||||
|
"learning_rate": 1e-05,
|
||||||
|
"loss": 0.9867,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.42857142857142855,
|
||||||
|
"grad_norm": 4.596472947786303,
|
||||||
|
"learning_rate": 9.978670881475173e-06,
|
||||||
|
"loss": 0.8843,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5714285714285714,
|
||||||
|
"grad_norm": 2.3617356503729585,
|
||||||
|
"learning_rate": 9.91486549841951e-06,
|
||||||
|
"loss": 0.8005,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7142857142857143,
|
||||||
|
"grad_norm": 2.2676316282563183,
|
||||||
|
"learning_rate": 9.809128215864096e-06,
|
||||||
|
"loss": 0.7994,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8571428571428571,
|
||||||
|
"grad_norm": 2.246406385939518,
|
||||||
|
"learning_rate": 9.66236114702178e-06,
|
||||||
|
"loss": 0.7365,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"grad_norm": 1.8834051955191673,
|
||||||
|
"learning_rate": 9.475816456775313e-06,
|
||||||
|
"loss": 0.7101,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1428571428571428,
|
||||||
|
"grad_norm": 1.3376525812163877,
|
||||||
|
"learning_rate": 9.251085678648072e-06,
|
||||||
|
"loss": 0.6625,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2857142857142856,
|
||||||
|
"grad_norm": 1.0334003924250443,
|
||||||
|
"learning_rate": 8.990086136401199e-06,
|
||||||
|
"loss": 0.626,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4285714285714286,
|
||||||
|
"grad_norm": 1.1270833913483167,
|
||||||
|
"learning_rate": 8.695044586103297e-06,
|
||||||
|
"loss": 0.656,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5714285714285714,
|
||||||
|
"grad_norm": 0.914746603740364,
|
||||||
|
"learning_rate": 8.368478218232787e-06,
|
||||||
|
"loss": 0.5878,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7142857142857144,
|
||||||
|
"grad_norm": 0.818200644259025,
|
||||||
|
"learning_rate": 8.013173181896283e-06,
|
||||||
|
"loss": 0.5721,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8571428571428572,
|
||||||
|
"grad_norm": 0.7861145956482819,
|
||||||
|
"learning_rate": 7.63216081438678e-06,
|
||||||
|
"loss": 0.5933,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"grad_norm": 0.670471249816862,
|
||||||
|
"learning_rate": 7.2286917788826926e-06,
|
||||||
|
"loss": 0.5497,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.142857142857143,
|
||||||
|
"grad_norm": 0.6783701796467253,
|
||||||
|
"learning_rate": 6.806208330935766e-06,
|
||||||
|
"loss": 0.5418,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2857142857142856,
|
||||||
|
"grad_norm": 0.7130802321996181,
|
||||||
|
"learning_rate": 6.368314950360416e-06,
|
||||||
|
"loss": 0.5445,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4285714285714284,
|
||||||
|
"grad_norm": 0.7237611676544982,
|
||||||
|
"learning_rate": 5.918747589082853e-06,
|
||||||
|
"loss": 0.5367,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.571428571428571,
|
||||||
|
"grad_norm": 0.6234236353208849,
|
||||||
|
"learning_rate": 5.46134179731651e-06,
|
||||||
|
"loss": 0.5187,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7142857142857144,
|
||||||
|
"grad_norm": 0.5483554337403505,
|
||||||
|
"learning_rate": 5e-06,
|
||||||
|
"loss": 0.4862,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.857142857142857,
|
||||||
|
"grad_norm": 0.5729608404090003,
|
||||||
|
"learning_rate": 4.53865820268349e-06,
|
||||||
|
"loss": 0.4859,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"grad_norm": 0.6525783085630301,
|
||||||
|
"learning_rate": 4.081252410917148e-06,
|
||||||
|
"loss": 0.4726,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.142857142857143,
|
||||||
|
"grad_norm": 0.6234485276585319,
|
||||||
|
"learning_rate": 3.6316850496395863e-06,
|
||||||
|
"loss": 0.5075,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.2857142857142856,
|
||||||
|
"grad_norm": 0.5624289294983126,
|
||||||
|
"learning_rate": 3.1937916690642356e-06,
|
||||||
|
"loss": 0.4833,
|
||||||
|
"step": 23
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.4285714285714284,
|
||||||
|
"grad_norm": 0.4801723823114017,
|
||||||
|
"learning_rate": 2.771308221117309e-06,
|
||||||
|
"loss": 0.468,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.571428571428571,
|
||||||
|
"grad_norm": 0.5258811679866904,
|
||||||
|
"learning_rate": 2.3678391856132203e-06,
|
||||||
|
"loss": 0.4651,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.7142857142857144,
|
||||||
|
"grad_norm": 0.7644061359252237,
|
||||||
|
"learning_rate": 1.9868268181037186e-06,
|
||||||
|
"loss": 0.4682,
|
||||||
|
"step": 26
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.857142857142857,
|
||||||
|
"grad_norm": 0.6929173124252979,
|
||||||
|
"learning_rate": 1.6315217817672142e-06,
|
||||||
|
"loss": 0.4514,
|
||||||
|
"step": 27
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.0,
|
||||||
|
"grad_norm": 0.5297753035187348,
|
||||||
|
"learning_rate": 1.3049554138967052e-06,
|
||||||
|
"loss": 0.4789,
|
||||||
|
"step": 28
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.142857142857143,
|
||||||
|
"grad_norm": 0.5415909130252555,
|
||||||
|
"learning_rate": 1.0099138635988026e-06,
|
||||||
|
"loss": 0.4695,
|
||||||
|
"step": 29
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.285714285714286,
|
||||||
|
"grad_norm": 0.5282132594942947,
|
||||||
|
"learning_rate": 7.489143213519301e-07,
|
||||||
|
"loss": 0.4236,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.428571428571429,
|
||||||
|
"grad_norm": 0.5270375217775852,
|
||||||
|
"learning_rate": 5.241835432246888e-07,
|
||||||
|
"loss": 0.4557,
|
||||||
|
"step": 31
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.571428571428571,
|
||||||
|
"grad_norm": 0.47428708038578266,
|
||||||
|
"learning_rate": 3.3763885297822153e-07,
|
||||||
|
"loss": 0.4666,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.714285714285714,
|
||||||
|
"grad_norm": 0.44077245455561864,
|
||||||
|
"learning_rate": 1.908717841359048e-07,
|
||||||
|
"loss": 0.4402,
|
||||||
|
"step": 33
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.857142857142857,
|
||||||
|
"grad_norm": 0.4840165144194508,
|
||||||
|
"learning_rate": 8.513450158049109e-08,
|
||||||
|
"loss": 0.4539,
|
||||||
|
"step": 34
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"grad_norm": 0.45298550256117076,
|
||||||
|
"learning_rate": 2.1329118524827662e-08,
|
||||||
|
"loss": 0.4573,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"step": 35,
|
||||||
|
"total_flos": 9984310984704.0,
|
||||||
|
"train_loss": 0.5776977070740291,
|
||||||
|
"train_runtime": 1052.4329,
|
||||||
|
"train_samples_per_second": 0.48,
|
||||||
|
"train_steps_per_second": 0.033
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 35,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 5,
|
||||||
|
"save_steps": 42,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 9984310984704.0,
|
||||||
|
"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:a0437b052c3ec7543f5edf0d0890367a46505255c7f0b2f08eb0a530aa490ce9
|
||||||
|
size 8273
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 39 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