初始化项目，由ModelHub XC社区提供模型
Model: chifural/TradingAgentRL-Qwen3-8B-SFT Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
cloudflared-linux-amd64.deb filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
68
.ipynb_checkpoints/config-checkpoint.json
Normal file
68
.ipynb_checkpoints/config-checkpoint.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 81920,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {"type": "yarn", "factor": 2.0, "original_max_position_embeddings": 40960},
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: TradingRL-Qwen3-8B-v01
|
||||
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. -->
|
||||
|
||||
# TradingRL-Qwen3-8B-v01
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the identity and the alpaca_en_demo datasets.
|
||||
|
||||
## 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: 2
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 4
|
||||
- total_eval_batch_size: 16
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 2.10.0+cu128
|
||||
- Datasets 4.0.0
|
||||
- Tokenizers 0.22.2
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"total_flos": 2.4661134707523584e+16,
|
||||
"train_loss": 0.5229038521192595,
|
||||
"train_runtime": 549.5617,
|
||||
"train_samples_per_second": 5.95,
|
||||
"train_steps_per_second": 1.49
|
||||
}
|
||||
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 %}
|
||||
3
cloudflared-linux-amd64.deb
Normal file
3
cloudflared-linux-amd64.deb
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:00f2475bad5874e9a110c2f5b8d1ce8a1bf5b6280628886a68bdc4ee76fd376c
|
||||
size 19308942
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 81920,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {"type": "yarn", "factor": 2.0, "original_max_position_embeddings": 40960},
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
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 sha256:7e7baa38be6da05f673c39f4c7e98901646e29073a7c625b90be3a972bb9083f
|
||||
size 4902257696
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5e57f4902558b482a2cdaa57cb90daf155cff1633b4bd85745ecd7d2891eb7d2
|
||||
size 4915960368
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e04132308f683e518e1e3c676a8f0806dec420ff64ab272b6e9d3aadab6783c2
|
||||
size 4983068496
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:64f3a00cd3ace7f27e844b2660cfc1c2cf580bb8509fa3a5b65e6f8503ca9993
|
||||
size 1580230264
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8190735360,
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
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": 3.0,
|
||||
"total_flos": 2.4661134707523584e+16,
|
||||
"train_loss": 0.5229038521192595,
|
||||
"train_runtime": 549.5617,
|
||||
"train_samples_per_second": 5.95,
|
||||
"train_steps_per_second": 1.49
|
||||
}
|
||||
82
trainer_log.jsonl
Normal file
82
trainer_log.jsonl
Normal file
@@ -0,0 +1,82 @@
|
||||
{"current_steps": 10, "total_steps": 819, "loss": 1.7545, "lr": 1.0975609756097562e-06, "epoch": 0.03669724770642202, "percentage": 1.22, "elapsed_time": "0:00:06", "remaining_time": "0:09:19"}
|
||||
{"current_steps": 20, "total_steps": 819, "loss": 1.6752, "lr": 2.317073170731708e-06, "epoch": 0.07339449541284404, "percentage": 2.44, "elapsed_time": "0:00:11", "remaining_time": "0:07:43"}
|
||||
{"current_steps": 30, "total_steps": 819, "loss": 1.1488, "lr": 3.5365853658536588e-06, "epoch": 0.11009174311926606, "percentage": 3.66, "elapsed_time": "0:00:16", "remaining_time": "0:07:10"}
|
||||
{"current_steps": 40, "total_steps": 819, "loss": 1.0, "lr": 4.75609756097561e-06, "epoch": 0.14678899082568808, "percentage": 4.88, "elapsed_time": "0:00:21", "remaining_time": "0:06:51"}
|
||||
{"current_steps": 50, "total_steps": 819, "loss": 1.0514, "lr": 5.9756097560975615e-06, "epoch": 0.1834862385321101, "percentage": 6.11, "elapsed_time": "0:00:25", "remaining_time": "0:06:37"}
|
||||
{"current_steps": 60, "total_steps": 819, "loss": 1.0813, "lr": 7.1951219512195125e-06, "epoch": 0.22018348623853212, "percentage": 7.33, "elapsed_time": "0:00:30", "remaining_time": "0:06:26"}
|
||||
{"current_steps": 70, "total_steps": 819, "loss": 1.147, "lr": 8.414634146341464e-06, "epoch": 0.25688073394495414, "percentage": 8.55, "elapsed_time": "0:00:35", "remaining_time": "0:06:18"}
|
||||
{"current_steps": 80, "total_steps": 819, "loss": 0.9877, "lr": 9.634146341463415e-06, "epoch": 0.29357798165137616, "percentage": 9.77, "elapsed_time": "0:00:40", "remaining_time": "0:06:10"}
|
||||
{"current_steps": 90, "total_steps": 819, "loss": 1.0414, "lr": 9.997774289701648e-06, "epoch": 0.3302752293577982, "percentage": 10.99, "elapsed_time": "0:00:44", "remaining_time": "0:06:03"}
|
||||
{"current_steps": 100, "total_steps": 819, "loss": 1.0481, "lr": 9.986877621396878e-06, "epoch": 0.3669724770642202, "percentage": 12.21, "elapsed_time": "0:00:49", "remaining_time": "0:05:56"}
|
||||
{"current_steps": 110, "total_steps": 819, "loss": 1.0144, "lr": 9.966920963089052e-06, "epoch": 0.4036697247706422, "percentage": 13.43, "elapsed_time": "0:00:54", "remaining_time": "0:05:50"}
|
||||
{"current_steps": 120, "total_steps": 819, "loss": 0.9278, "lr": 9.937940571357636e-06, "epoch": 0.44036697247706424, "percentage": 14.65, "elapsed_time": "0:00:59", "remaining_time": "0:05:43"}
|
||||
{"current_steps": 130, "total_steps": 819, "loss": 1.0083, "lr": 9.899989096794704e-06, "epoch": 0.47706422018348627, "percentage": 15.87, "elapsed_time": "0:01:03", "remaining_time": "0:05:37"}
|
||||
{"current_steps": 140, "total_steps": 819, "loss": 0.9663, "lr": 9.853135488351135e-06, "epoch": 0.5137614678899083, "percentage": 17.09, "elapsed_time": "0:01:08", "remaining_time": "0:05:31"}
|
||||
{"current_steps": 150, "total_steps": 819, "loss": 0.7779, "lr": 9.797464868072489e-06, "epoch": 0.5504587155963303, "percentage": 18.32, "elapsed_time": "0:01:13", "remaining_time": "0:05:25"}
|
||||
{"current_steps": 160, "total_steps": 819, "loss": 0.9394, "lr": 9.733078376452172e-06, "epoch": 0.5871559633027523, "percentage": 19.54, "elapsed_time": "0:01:17", "remaining_time": "0:05:20"}
|
||||
{"current_steps": 170, "total_steps": 819, "loss": 1.0285, "lr": 9.660092988682822e-06, "epoch": 0.6238532110091743, "percentage": 20.76, "elapsed_time": "0:01:22", "remaining_time": "0:05:14"}
|
||||
{"current_steps": 180, "total_steps": 819, "loss": 1.0908, "lr": 9.578641302139741e-06, "epoch": 0.6605504587155964, "percentage": 21.98, "elapsed_time": "0:01:27", "remaining_time": "0:05:09"}
|
||||
{"current_steps": 190, "total_steps": 819, "loss": 1.0413, "lr": 9.488871295482492e-06, "epoch": 0.6972477064220184, "percentage": 23.2, "elapsed_time": "0:01:31", "remaining_time": "0:05:03"}
|
||||
{"current_steps": 200, "total_steps": 819, "loss": 0.8251, "lr": 9.390946059812289e-06, "epoch": 0.7339449541284404, "percentage": 24.42, "elapsed_time": "0:01:36", "remaining_time": "0:04:58"}
|
||||
{"current_steps": 210, "total_steps": 819, "loss": 0.9724, "lr": 9.285043502373616e-06, "epoch": 0.7706422018348624, "percentage": 25.64, "elapsed_time": "0:01:41", "remaining_time": "0:04:53"}
|
||||
{"current_steps": 220, "total_steps": 819, "loss": 1.0862, "lr": 9.171356023338395e-06, "epoch": 0.8073394495412844, "percentage": 26.86, "elapsed_time": "0:01:45", "remaining_time": "0:04:48"}
|
||||
{"current_steps": 230, "total_steps": 819, "loss": 0.9361, "lr": 9.050090166259873e-06, "epoch": 0.8440366972477065, "percentage": 28.08, "elapsed_time": "0:01:50", "remaining_time": "0:04:43"}
|
||||
{"current_steps": 240, "total_steps": 819, "loss": 1.0586, "lr": 8.921466242831305e-06, "epoch": 0.8807339449541285, "percentage": 29.3, "elapsed_time": "0:01:55", "remaining_time": "0:04:38"}
|
||||
{"current_steps": 250, "total_steps": 819, "loss": 1.098, "lr": 8.785717932631157e-06, "epoch": 0.9174311926605505, "percentage": 30.53, "elapsed_time": "0:02:00", "remaining_time": "0:04:33"}
|
||||
{"current_steps": 260, "total_steps": 819, "loss": 0.9883, "lr": 8.643091858581971e-06, "epoch": 0.9541284403669725, "percentage": 31.75, "elapsed_time": "0:02:04", "remaining_time": "0:04:28"}
|
||||
{"current_steps": 270, "total_steps": 819, "loss": 0.9031, "lr": 8.49384713889421e-06, "epoch": 0.9908256880733946, "percentage": 32.97, "elapsed_time": "0:02:09", "remaining_time": "0:04:23"}
|
||||
{"current_steps": 280, "total_steps": 819, "loss": 0.5494, "lr": 8.33825491630909e-06, "epoch": 1.0256880733944955, "percentage": 34.19, "elapsed_time": "0:02:14", "remaining_time": "0:04:18"}
|
||||
{"current_steps": 290, "total_steps": 819, "loss": 0.3599, "lr": 8.176597865495654e-06, "epoch": 1.0623853211009173, "percentage": 35.41, "elapsed_time": "0:02:19", "remaining_time": "0:04:13"}
|
||||
{"current_steps": 300, "total_steps": 819, "loss": 0.4398, "lr": 8.00916967949702e-06, "epoch": 1.0990825688073396, "percentage": 36.63, "elapsed_time": "0:02:23", "remaining_time": "0:04:08"}
|
||||
{"current_steps": 310, "total_steps": 819, "loss": 0.4224, "lr": 7.836274536158834e-06, "epoch": 1.1357798165137614, "percentage": 37.85, "elapsed_time": "0:02:28", "remaining_time": "0:04:03"}
|
||||
{"current_steps": 320, "total_steps": 819, "loss": 0.4323, "lr": 7.658226545509286e-06, "epoch": 1.1724770642201836, "percentage": 39.07, "elapsed_time": "0:02:33", "remaining_time": "0:03:58"}
|
||||
{"current_steps": 330, "total_steps": 819, "loss": 0.3882, "lr": 7.475349179094661e-06, "epoch": 1.2091743119266054, "percentage": 40.29, "elapsed_time": "0:02:37", "remaining_time": "0:03:53"}
|
||||
{"current_steps": 340, "total_steps": 819, "loss": 0.3982, "lr": 7.287974682307226e-06, "epoch": 1.2458715596330276, "percentage": 41.51, "elapsed_time": "0:02:42", "remaining_time": "0:03:49"}
|
||||
{"current_steps": 350, "total_steps": 819, "loss": 0.4527, "lr": 7.096443470773071e-06, "epoch": 1.2825688073394494, "percentage": 42.74, "elapsed_time": "0:02:47", "remaining_time": "0:03:44"}
|
||||
{"current_steps": 360, "total_steps": 819, "loss": 0.403, "lr": 6.901103511896556e-06, "epoch": 1.3192660550458717, "percentage": 43.96, "elapsed_time": "0:02:52", "remaining_time": "0:03:39"}
|
||||
{"current_steps": 370, "total_steps": 819, "loss": 0.3596, "lr": 6.702309692684938e-06, "epoch": 1.3559633027522935, "percentage": 45.18, "elapsed_time": "0:02:56", "remaining_time": "0:03:34"}
|
||||
{"current_steps": 380, "total_steps": 819, "loss": 0.4125, "lr": 6.500423175001705e-06, "epoch": 1.3926605504587157, "percentage": 46.4, "elapsed_time": "0:03:01", "remaining_time": "0:03:29"}
|
||||
{"current_steps": 390, "total_steps": 819, "loss": 0.3864, "lr": 6.2958107394199556e-06, "epoch": 1.4293577981651375, "percentage": 47.62, "elapsed_time": "0:03:06", "remaining_time": "0:03:24"}
|
||||
{"current_steps": 400, "total_steps": 819, "loss": 0.4277, "lr": 6.088844118867912e-06, "epoch": 1.4660550458715598, "percentage": 48.84, "elapsed_time": "0:03:10", "remaining_time": "0:03:20"}
|
||||
{"current_steps": 410, "total_steps": 819, "loss": 0.3528, "lr": 5.879899323277142e-06, "epoch": 1.5027522935779816, "percentage": 50.06, "elapsed_time": "0:03:15", "remaining_time": "0:03:15"}
|
||||
{"current_steps": 420, "total_steps": 819, "loss": 0.4281, "lr": 5.669355956460483e-06, "epoch": 1.5394495412844038, "percentage": 51.28, "elapsed_time": "0:03:20", "remaining_time": "0:03:10"}
|
||||
{"current_steps": 430, "total_steps": 819, "loss": 0.3896, "lr": 5.457596526460722e-06, "epoch": 1.5761467889908256, "percentage": 52.5, "elapsed_time": "0:03:25", "remaining_time": "0:03:05"}
|
||||
{"current_steps": 440, "total_steps": 819, "loss": 0.3418, "lr": 5.245005750622961e-06, "epoch": 1.6128440366972479, "percentage": 53.72, "elapsed_time": "0:03:29", "remaining_time": "0:03:00"}
|
||||
{"current_steps": 450, "total_steps": 819, "loss": 0.3813, "lr": 5.031969856653204e-06, "epoch": 1.6495412844036696, "percentage": 54.95, "elapsed_time": "0:03:34", "remaining_time": "0:02:55"}
|
||||
{"current_steps": 460, "total_steps": 819, "loss": 0.4144, "lr": 4.818875880932967e-06, "epoch": 1.686238532110092, "percentage": 56.17, "elapsed_time": "0:03:39", "remaining_time": "0:02:51"}
|
||||
{"current_steps": 470, "total_steps": 819, "loss": 0.3708, "lr": 4.606110965364721e-06, "epoch": 1.7229357798165137, "percentage": 57.39, "elapsed_time": "0:03:44", "remaining_time": "0:02:46"}
|
||||
{"current_steps": 480, "total_steps": 819, "loss": 0.474, "lr": 4.394061654025622e-06, "epoch": 1.759633027522936, "percentage": 58.61, "elapsed_time": "0:03:48", "remaining_time": "0:02:41"}
|
||||
{"current_steps": 490, "total_steps": 819, "loss": 0.3914, "lr": 4.183113190907349e-06, "epoch": 1.7963302752293577, "percentage": 59.83, "elapsed_time": "0:03:53", "remaining_time": "0:02:36"}
|
||||
{"current_steps": 500, "total_steps": 819, "loss": 0.3545, "lr": 3.9736488200179e-06, "epoch": 1.83302752293578, "percentage": 61.05, "elapsed_time": "0:03:58", "remaining_time": "0:02:31"}
|
||||
{"current_steps": 510, "total_steps": 819, "loss": 0.2496, "lr": 3.7660490891168805e-06, "epoch": 1.8697247706422018, "percentage": 62.27, "elapsed_time": "0:05:23", "remaining_time": "0:03:16"}
|
||||
{"current_steps": 520, "total_steps": 819, "loss": 0.3805, "lr": 3.5606911583492554e-06, "epoch": 1.906422018348624, "percentage": 63.49, "elapsed_time": "0:05:28", "remaining_time": "0:03:08"}
|
||||
{"current_steps": 530, "total_steps": 819, "loss": 0.3653, "lr": 3.3579481150335914e-06, "epoch": 1.9431192660550458, "percentage": 64.71, "elapsed_time": "0:05:33", "remaining_time": "0:03:01"}
|
||||
{"current_steps": 540, "total_steps": 819, "loss": 0.4381, "lr": 3.158188295849689e-06, "epoch": 1.979816513761468, "percentage": 65.93, "elapsed_time": "0:05:37", "remaining_time": "0:02:54"}
|
||||
{"current_steps": 550, "total_steps": 819, "loss": 0.3913, "lr": 2.9617746176569985e-06, "epoch": 2.014678899082569, "percentage": 67.16, "elapsed_time": "0:05:42", "remaining_time": "0:02:47"}
|
||||
{"current_steps": 560, "total_steps": 819, "loss": 0.1341, "lr": 2.769063918159588e-06, "epoch": 2.051376146788991, "percentage": 68.38, "elapsed_time": "0:05:47", "remaining_time": "0:02:40"}
|
||||
{"current_steps": 570, "total_steps": 819, "loss": 0.1474, "lr": 2.5804063076155143e-06, "epoch": 2.088073394495413, "percentage": 69.6, "elapsed_time": "0:05:52", "remaining_time": "0:02:33"}
|
||||
{"current_steps": 580, "total_steps": 819, "loss": 0.0981, "lr": 2.3961445327683914e-06, "epoch": 2.1247706422018346, "percentage": 70.82, "elapsed_time": "0:05:56", "remaining_time": "0:02:27"}
|
||||
{"current_steps": 590, "total_steps": 819, "loss": 0.0771, "lr": 2.2166133541567376e-06, "epoch": 2.161467889908257, "percentage": 72.04, "elapsed_time": "0:06:01", "remaining_time": "0:02:20"}
|
||||
{"current_steps": 600, "total_steps": 819, "loss": 0.1397, "lr": 2.042138937932388e-06, "epoch": 2.198165137614679, "percentage": 73.26, "elapsed_time": "0:06:06", "remaining_time": "0:02:13"}
|
||||
{"current_steps": 610, "total_steps": 819, "loss": 0.1724, "lr": 1.8730382632929107e-06, "epoch": 2.234862385321101, "percentage": 74.48, "elapsed_time": "0:06:11", "remaining_time": "0:02:07"}
|
||||
{"current_steps": 620, "total_steps": 819, "loss": 0.1204, "lr": 1.7096185466045446e-06, "epoch": 2.2715596330275227, "percentage": 75.7, "elapsed_time": "0:06:16", "remaining_time": "0:02:00"}
|
||||
{"current_steps": 630, "total_steps": 819, "loss": 0.1063, "lr": 1.5521766832619472e-06, "epoch": 2.308256880733945, "percentage": 76.92, "elapsed_time": "0:06:20", "remaining_time": "0:01:54"}
|
||||
{"current_steps": 640, "total_steps": 819, "loss": 0.1189, "lr": 1.4009987082987064e-06, "epoch": 2.344954128440367, "percentage": 78.14, "elapsed_time": "0:06:25", "remaining_time": "0:01:47"}
|
||||
{"current_steps": 650, "total_steps": 819, "loss": 0.0995, "lr": 1.2563592767286087e-06, "epoch": 2.381651376146789, "percentage": 79.37, "elapsed_time": "0:06:30", "remaining_time": "0:01:41"}
|
||||
{"current_steps": 660, "total_steps": 819, "loss": 0.1157, "lr": 1.1185211645617271e-06, "epoch": 2.418348623853211, "percentage": 80.59, "elapsed_time": "0:06:35", "remaining_time": "0:01:35"}
|
||||
{"current_steps": 670, "total_steps": 819, "loss": 0.1093, "lr": 9.877347914018853e-07, "epoch": 2.455045871559633, "percentage": 81.81, "elapsed_time": "0:06:39", "remaining_time": "0:01:28"}
|
||||
{"current_steps": 680, "total_steps": 819, "loss": 0.0994, "lr": 8.642377654928253e-07, "epoch": 2.4917431192660553, "percentage": 83.03, "elapsed_time": "0:06:44", "remaining_time": "0:01:22"}
|
||||
{"current_steps": 690, "total_steps": 819, "loss": 0.1265, "lr": 7.482544520396057e-07, "epoch": 2.528440366972477, "percentage": 84.25, "elapsed_time": "0:06:49", "remaining_time": "0:01:16"}
|
||||
{"current_steps": 700, "total_steps": 819, "loss": 0.1134, "lr": 6.39995565589524e-07, "epoch": 2.565137614678899, "percentage": 85.47, "elapsed_time": "0:06:54", "remaining_time": "0:01:10"}
|
||||
{"current_steps": 710, "total_steps": 819, "loss": 0.0987, "lr": 5.396577872130676e-07, "epoch": 2.601834862385321, "percentage": 86.69, "elapsed_time": "0:06:58", "remaining_time": "0:01:04"}
|
||||
{"current_steps": 720, "total_steps": 819, "loss": 0.1145, "lr": 4.474234071804312e-07, "epoch": 2.6385321100917434, "percentage": 87.91, "elapsed_time": "0:07:03", "remaining_time": "0:00:58"}
|
||||
{"current_steps": 730, "total_steps": 819, "loss": 0.1119, "lr": 3.63459993782731e-07, "epoch": 2.675229357798165, "percentage": 89.13, "elapsed_time": "0:07:08", "remaining_time": "0:00:52"}
|
||||
{"current_steps": 740, "total_steps": 819, "loss": 0.1588, "lr": 2.879200888996286e-07, "epoch": 2.711926605504587, "percentage": 90.35, "elapsed_time": "0:07:12", "remaining_time": "0:00:46"}
|
||||
{"current_steps": 750, "total_steps": 819, "loss": 0.1061, "lr": 2.2094093086641844e-07, "epoch": 2.748623853211009, "percentage": 91.58, "elapsed_time": "0:07:17", "remaining_time": "0:00:40"}
|
||||
{"current_steps": 760, "total_steps": 819, "loss": 0.1122, "lr": 1.6264420514407574e-07, "epoch": 2.7853211009174315, "percentage": 92.8, "elapsed_time": "0:07:22", "remaining_time": "0:00:34"}
|
||||
{"current_steps": 770, "total_steps": 819, "loss": 0.143, "lr": 1.1313582324524564e-07, "epoch": 2.8220183486238533, "percentage": 94.02, "elapsed_time": "0:07:26", "remaining_time": "0:00:28"}
|
||||
{"current_steps": 780, "total_steps": 819, "loss": 0.0635, "lr": 7.250573031779895e-08, "epoch": 2.858715596330275, "percentage": 95.24, "elapsed_time": "0:07:31", "remaining_time": "0:00:22"}
|
||||
{"current_steps": 790, "total_steps": 819, "loss": 0.1221, "lr": 4.082774173554127e-08, "epoch": 2.8954128440366973, "percentage": 96.46, "elapsed_time": "0:07:36", "remaining_time": "0:00:16"}
|
||||
{"current_steps": 800, "total_steps": 819, "loss": 0.08, "lr": 1.8159408992947103e-08, "epoch": 2.9321100917431195, "percentage": 97.68, "elapsed_time": "0:07:41", "remaining_time": "0:00:10"}
|
||||
{"current_steps": 810, "total_steps": 819, "loss": 0.1056, "lr": 4.541915147557307e-09, "epoch": 2.9688073394495413, "percentage": 98.9, "elapsed_time": "0:07:45", "remaining_time": "0:00:05"}
|
||||
{"current_steps": 819, "total_steps": 819, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:09:09", "remaining_time": "0:00:00"}
|
||||
610
trainer_state.json
Normal file
610
trainer_state.json
Normal file
@@ -0,0 +1,610 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 3.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 819,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.03669724770642202,
|
||||
"grad_norm": 45.576416015625,
|
||||
"learning_rate": 1.0975609756097562e-06,
|
||||
"loss": 1.7545,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.07339449541284404,
|
||||
"grad_norm": 10.582867622375488,
|
||||
"learning_rate": 2.317073170731708e-06,
|
||||
"loss": 1.6752,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.11009174311926606,
|
||||
"grad_norm": 9.395275115966797,
|
||||
"learning_rate": 3.5365853658536588e-06,
|
||||
"loss": 1.1488,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.14678899082568808,
|
||||
"grad_norm": 10.377723693847656,
|
||||
"learning_rate": 4.75609756097561e-06,
|
||||
"loss": 1.0,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.1834862385321101,
|
||||
"grad_norm": 8.154882431030273,
|
||||
"learning_rate": 5.9756097560975615e-06,
|
||||
"loss": 1.0514,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.22018348623853212,
|
||||
"grad_norm": 8.073173522949219,
|
||||
"learning_rate": 7.1951219512195125e-06,
|
||||
"loss": 1.0813,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.25688073394495414,
|
||||
"grad_norm": 5.49383020401001,
|
||||
"learning_rate": 8.414634146341464e-06,
|
||||
"loss": 1.147,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.29357798165137616,
|
||||
"grad_norm": 6.546836853027344,
|
||||
"learning_rate": 9.634146341463415e-06,
|
||||
"loss": 0.9877,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.3302752293577982,
|
||||
"grad_norm": 4.730407238006592,
|
||||
"learning_rate": 9.997774289701648e-06,
|
||||
"loss": 1.0414,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.3669724770642202,
|
||||
"grad_norm": 6.055862903594971,
|
||||
"learning_rate": 9.986877621396878e-06,
|
||||
"loss": 1.0481,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.4036697247706422,
|
||||
"grad_norm": 12.908507347106934,
|
||||
"learning_rate": 9.966920963089052e-06,
|
||||
"loss": 1.0144,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.44036697247706424,
|
||||
"grad_norm": 10.134546279907227,
|
||||
"learning_rate": 9.937940571357636e-06,
|
||||
"loss": 0.9278,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.47706422018348627,
|
||||
"grad_norm": 4.411650657653809,
|
||||
"learning_rate": 9.899989096794704e-06,
|
||||
"loss": 1.0083,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.5137614678899083,
|
||||
"grad_norm": 5.51439094543457,
|
||||
"learning_rate": 9.853135488351135e-06,
|
||||
"loss": 0.9663,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.5504587155963303,
|
||||
"grad_norm": 5.0115227699279785,
|
||||
"learning_rate": 9.797464868072489e-06,
|
||||
"loss": 0.7779,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.5871559633027523,
|
||||
"grad_norm": 10.19095516204834,
|
||||
"learning_rate": 9.733078376452172e-06,
|
||||
"loss": 0.9394,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.6238532110091743,
|
||||
"grad_norm": 5.4709553718566895,
|
||||
"learning_rate": 9.660092988682822e-06,
|
||||
"loss": 1.0285,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.6605504587155964,
|
||||
"grad_norm": 6.946798801422119,
|
||||
"learning_rate": 9.578641302139741e-06,
|
||||
"loss": 1.0908,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.6972477064220184,
|
||||
"grad_norm": 13.150769233703613,
|
||||
"learning_rate": 9.488871295482492e-06,
|
||||
"loss": 1.0413,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.7339449541284404,
|
||||
"grad_norm": 7.462345123291016,
|
||||
"learning_rate": 9.390946059812289e-06,
|
||||
"loss": 0.8251,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.7706422018348624,
|
||||
"grad_norm": 4.613824367523193,
|
||||
"learning_rate": 9.285043502373616e-06,
|
||||
"loss": 0.9724,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.8073394495412844,
|
||||
"grad_norm": 6.828705787658691,
|
||||
"learning_rate": 9.171356023338395e-06,
|
||||
"loss": 1.0862,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.8440366972477065,
|
||||
"grad_norm": 5.334705352783203,
|
||||
"learning_rate": 9.050090166259873e-06,
|
||||
"loss": 0.9361,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.8807339449541285,
|
||||
"grad_norm": 6.761337757110596,
|
||||
"learning_rate": 8.921466242831305e-06,
|
||||
"loss": 1.0586,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.9174311926605505,
|
||||
"grad_norm": 7.450784206390381,
|
||||
"learning_rate": 8.785717932631157e-06,
|
||||
"loss": 1.098,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.9541284403669725,
|
||||
"grad_norm": 6.033744812011719,
|
||||
"learning_rate": 8.643091858581971e-06,
|
||||
"loss": 0.9883,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.9908256880733946,
|
||||
"grad_norm": 3.838776111602783,
|
||||
"learning_rate": 8.49384713889421e-06,
|
||||
"loss": 0.9031,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 1.0256880733944955,
|
||||
"grad_norm": 7.545208930969238,
|
||||
"learning_rate": 8.33825491630909e-06,
|
||||
"loss": 0.5494,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 1.0623853211009173,
|
||||
"grad_norm": 8.683798789978027,
|
||||
"learning_rate": 8.176597865495654e-06,
|
||||
"loss": 0.3599,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 1.0990825688073396,
|
||||
"grad_norm": 4.903615474700928,
|
||||
"learning_rate": 8.00916967949702e-06,
|
||||
"loss": 0.4398,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 1.1357798165137614,
|
||||
"grad_norm": 6.409444332122803,
|
||||
"learning_rate": 7.836274536158834e-06,
|
||||
"loss": 0.4224,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 1.1724770642201836,
|
||||
"grad_norm": 4.087878704071045,
|
||||
"learning_rate": 7.658226545509286e-06,
|
||||
"loss": 0.4323,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 1.2091743119266054,
|
||||
"grad_norm": 5.2519707679748535,
|
||||
"learning_rate": 7.475349179094661e-06,
|
||||
"loss": 0.3882,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 1.2458715596330276,
|
||||
"grad_norm": 6.870487689971924,
|
||||
"learning_rate": 7.287974682307226e-06,
|
||||
"loss": 0.3982,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 1.2825688073394494,
|
||||
"grad_norm": 3.5328145027160645,
|
||||
"learning_rate": 7.096443470773071e-06,
|
||||
"loss": 0.4527,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.3192660550458717,
|
||||
"grad_norm": 6.628715991973877,
|
||||
"learning_rate": 6.901103511896556e-06,
|
||||
"loss": 0.403,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 1.3559633027522935,
|
||||
"grad_norm": 4.482091903686523,
|
||||
"learning_rate": 6.702309692684938e-06,
|
||||
"loss": 0.3596,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 1.3926605504587157,
|
||||
"grad_norm": 3.9413254261016846,
|
||||
"learning_rate": 6.500423175001705e-06,
|
||||
"loss": 0.4125,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 1.4293577981651375,
|
||||
"grad_norm": 4.185613632202148,
|
||||
"learning_rate": 6.2958107394199556e-06,
|
||||
"loss": 0.3864,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 1.4660550458715598,
|
||||
"grad_norm": 5.547845363616943,
|
||||
"learning_rate": 6.088844118867912e-06,
|
||||
"loss": 0.4277,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.5027522935779816,
|
||||
"grad_norm": 2.854694366455078,
|
||||
"learning_rate": 5.879899323277142e-06,
|
||||
"loss": 0.3528,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 1.5394495412844038,
|
||||
"grad_norm": 3.989434003829956,
|
||||
"learning_rate": 5.669355956460483e-06,
|
||||
"loss": 0.4281,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 1.5761467889908256,
|
||||
"grad_norm": 3.780809164047241,
|
||||
"learning_rate": 5.457596526460722e-06,
|
||||
"loss": 0.3896,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 1.6128440366972479,
|
||||
"grad_norm": 5.487133979797363,
|
||||
"learning_rate": 5.245005750622961e-06,
|
||||
"loss": 0.3418,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.6495412844036696,
|
||||
"grad_norm": 4.815535545349121,
|
||||
"learning_rate": 5.031969856653204e-06,
|
||||
"loss": 0.3813,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.686238532110092,
|
||||
"grad_norm": 4.234831809997559,
|
||||
"learning_rate": 4.818875880932967e-06,
|
||||
"loss": 0.4144,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 1.7229357798165137,
|
||||
"grad_norm": 5.422831058502197,
|
||||
"learning_rate": 4.606110965364721e-06,
|
||||
"loss": 0.3708,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 1.759633027522936,
|
||||
"grad_norm": 4.2414445877075195,
|
||||
"learning_rate": 4.394061654025622e-06,
|
||||
"loss": 0.474,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 1.7963302752293577,
|
||||
"grad_norm": 4.653387069702148,
|
||||
"learning_rate": 4.183113190907349e-06,
|
||||
"loss": 0.3914,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 1.83302752293578,
|
||||
"grad_norm": 3.6565375328063965,
|
||||
"learning_rate": 3.9736488200179e-06,
|
||||
"loss": 0.3545,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.8697247706422018,
|
||||
"grad_norm": 4.018605709075928,
|
||||
"learning_rate": 3.7660490891168805e-06,
|
||||
"loss": 0.2496,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 1.906422018348624,
|
||||
"grad_norm": 4.249181747436523,
|
||||
"learning_rate": 3.5606911583492554e-06,
|
||||
"loss": 0.3805,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 1.9431192660550458,
|
||||
"grad_norm": 4.361818790435791,
|
||||
"learning_rate": 3.3579481150335914e-06,
|
||||
"loss": 0.3653,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 1.979816513761468,
|
||||
"grad_norm": 6.0414347648620605,
|
||||
"learning_rate": 3.158188295849689e-06,
|
||||
"loss": 0.4381,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 2.014678899082569,
|
||||
"grad_norm": 4.7412800788879395,
|
||||
"learning_rate": 2.9617746176569985e-06,
|
||||
"loss": 0.3913,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 2.051376146788991,
|
||||
"grad_norm": 3.8450918197631836,
|
||||
"learning_rate": 2.769063918159588e-06,
|
||||
"loss": 0.1341,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 2.088073394495413,
|
||||
"grad_norm": 3.0494792461395264,
|
||||
"learning_rate": 2.5804063076155143e-06,
|
||||
"loss": 0.1474,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 2.1247706422018346,
|
||||
"grad_norm": 3.925137996673584,
|
||||
"learning_rate": 2.3961445327683914e-06,
|
||||
"loss": 0.0981,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 2.161467889908257,
|
||||
"grad_norm": 2.9667370319366455,
|
||||
"learning_rate": 2.2166133541567376e-06,
|
||||
"loss": 0.0771,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 2.198165137614679,
|
||||
"grad_norm": 8.277497291564941,
|
||||
"learning_rate": 2.042138937932388e-06,
|
||||
"loss": 0.1397,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 2.234862385321101,
|
||||
"grad_norm": 3.4491753578186035,
|
||||
"learning_rate": 1.8730382632929107e-06,
|
||||
"loss": 0.1724,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 2.2715596330275227,
|
||||
"grad_norm": 3.367347240447998,
|
||||
"learning_rate": 1.7096185466045446e-06,
|
||||
"loss": 0.1204,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 2.308256880733945,
|
||||
"grad_norm": 4.588388919830322,
|
||||
"learning_rate": 1.5521766832619472e-06,
|
||||
"loss": 0.1063,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 2.344954128440367,
|
||||
"grad_norm": 12.237441062927246,
|
||||
"learning_rate": 1.4009987082987064e-06,
|
||||
"loss": 0.1189,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 2.381651376146789,
|
||||
"grad_norm": 3.8440685272216797,
|
||||
"learning_rate": 1.2563592767286087e-06,
|
||||
"loss": 0.0995,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 2.418348623853211,
|
||||
"grad_norm": 3.6825640201568604,
|
||||
"learning_rate": 1.1185211645617271e-06,
|
||||
"loss": 0.1157,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 2.455045871559633,
|
||||
"grad_norm": 2.4990882873535156,
|
||||
"learning_rate": 9.877347914018853e-07,
|
||||
"loss": 0.1093,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 2.4917431192660553,
|
||||
"grad_norm": 8.954373359680176,
|
||||
"learning_rate": 8.642377654928253e-07,
|
||||
"loss": 0.0994,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 2.528440366972477,
|
||||
"grad_norm": 4.092501640319824,
|
||||
"learning_rate": 7.482544520396057e-07,
|
||||
"loss": 0.1265,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 2.565137614678899,
|
||||
"grad_norm": 2.5047497749328613,
|
||||
"learning_rate": 6.39995565589524e-07,
|
||||
"loss": 0.1134,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 2.601834862385321,
|
||||
"grad_norm": 3.976468801498413,
|
||||
"learning_rate": 5.396577872130676e-07,
|
||||
"loss": 0.0987,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 2.6385321100917434,
|
||||
"grad_norm": 2.5786423683166504,
|
||||
"learning_rate": 4.474234071804312e-07,
|
||||
"loss": 0.1145,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 2.675229357798165,
|
||||
"grad_norm": 0.8380916118621826,
|
||||
"learning_rate": 3.63459993782731e-07,
|
||||
"loss": 0.1119,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 2.711926605504587,
|
||||
"grad_norm": 7.706490516662598,
|
||||
"learning_rate": 2.879200888996286e-07,
|
||||
"loss": 0.1588,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 2.748623853211009,
|
||||
"grad_norm": 4.898327827453613,
|
||||
"learning_rate": 2.2094093086641844e-07,
|
||||
"loss": 0.1061,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 2.7853211009174315,
|
||||
"grad_norm": 1.936378002166748,
|
||||
"learning_rate": 1.6264420514407574e-07,
|
||||
"loss": 0.1122,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 2.8220183486238533,
|
||||
"grad_norm": 9.376118659973145,
|
||||
"learning_rate": 1.1313582324524564e-07,
|
||||
"loss": 0.143,
|
||||
"step": 770
|
||||
},
|
||||
{
|
||||
"epoch": 2.858715596330275,
|
||||
"grad_norm": 2.7180027961730957,
|
||||
"learning_rate": 7.250573031779895e-08,
|
||||
"loss": 0.0635,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 2.8954128440366973,
|
||||
"grad_norm": 8.308465957641602,
|
||||
"learning_rate": 4.082774173554127e-08,
|
||||
"loss": 0.1221,
|
||||
"step": 790
|
||||
},
|
||||
{
|
||||
"epoch": 2.9321100917431195,
|
||||
"grad_norm": 6.079627513885498,
|
||||
"learning_rate": 1.8159408992947103e-08,
|
||||
"loss": 0.08,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 2.9688073394495413,
|
||||
"grad_norm": 0.4067806601524353,
|
||||
"learning_rate": 4.541915147557307e-09,
|
||||
"loss": 0.1056,
|
||||
"step": 810
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"step": 819,
|
||||
"total_flos": 2.4661134707523584e+16,
|
||||
"train_loss": 0.5229038521192595,
|
||||
"train_runtime": 549.5617,
|
||||
"train_samples_per_second": 5.95,
|
||||
"train_steps_per_second": 1.49
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 819,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 2.4661134707523584e+16,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13972b51b82aa097023968622fce2869184187c341b8e5b65c5b3e7e6963631a
|
||||
size 8145
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 46 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