初始化项目，由ModelHub XC社区提供模型
Model: bespokelabs/qwen3-8b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft Source: Original Platform
This commit is contained in:
ModelHub XC
52
.gitattributes
vendored
Normal file
52
.gitattributes
vendored
Normal file
@@ -0,0 +1,52 @@
|
||||
*.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
|
||||
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00004.safetensors 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/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: qwen3-8b-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. -->
|
||||
|
||||
# qwen3-8b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) 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: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- total_train_batch_size: 8
|
||||
- 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": 12383961956352.0,
|
||||
"train_loss": 0.45606403878101937,
|
||||
"train_runtime": 1434.1495,
|
||||
"train_samples_per_second": 0.352,
|
||||
"train_steps_per_second": 0.045
|
||||
}
|
||||
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": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"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": false,
|
||||
"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": "others", "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-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 sha256:71e029f7cc59461ce40064c76d66c2e690386240d0f03d6e5ebaec7991f8940c
|
||||
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:eef21a982078dc77d73bf49c6824276211ce8d929f9fc4412e3d010222d61bc0
|
||||
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 sha256:661b73d2926cd6ba115495f8457078464152c6727b3ac682ed9c999da20e2394
|
||||
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 sha256:40810892d007b2cdea9f418a7e2b4290fb4dc261f0198e7051e5947d6124ad38
|
||||
size 1580230264
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"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
|
||||
}
|
||||
}
|
||||
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": 12383961956352.0,
|
||||
"train_loss": 0.45606403878101937,
|
||||
"train_runtime": 1434.1495,
|
||||
"train_samples_per_second": 0.352,
|
||||
"train_steps_per_second": 0.045
|
||||
}
|
||||
66
trainer_log.jsonl
Normal file
66
trainer_log.jsonl
Normal file
@@ -0,0 +1,66 @@
|
||||
{"current_steps": 1, "total_steps": 65, "loss": 0.9617, "lr": 0.0, "epoch": 0.07692307692307693, "percentage": 1.54, "elapsed_time": "0:00:19", "remaining_time": "0:20:37"}
|
||||
{"current_steps": 2, "total_steps": 65, "loss": 0.9221, "lr": 1e-05, "epoch": 0.15384615384615385, "percentage": 3.08, "elapsed_time": "0:00:28", "remaining_time": "0:15:09"}
|
||||
{"current_steps": 3, "total_steps": 65, "loss": 0.8516, "lr": 9.993977281025862e-06, "epoch": 0.23076923076923078, "percentage": 4.62, "elapsed_time": "0:00:38", "remaining_time": "0:13:17"}
|
||||
{"current_steps": 4, "total_steps": 65, "loss": 0.7455, "lr": 9.975923633360985e-06, "epoch": 0.3076923076923077, "percentage": 6.15, "elapsed_time": "0:00:53", "remaining_time": "0:13:37"}
|
||||
{"current_steps": 5, "total_steps": 65, "loss": 0.7818, "lr": 9.945882549823906e-06, "epoch": 0.38461538461538464, "percentage": 7.69, "elapsed_time": "0:01:05", "remaining_time": "0:13:08"}
|
||||
{"current_steps": 6, "total_steps": 65, "loss": 0.7056, "lr": 9.903926402016153e-06, "epoch": 0.46153846153846156, "percentage": 9.23, "elapsed_time": "0:01:14", "remaining_time": "0:12:16"}
|
||||
{"current_steps": 7, "total_steps": 65, "loss": 0.6684, "lr": 9.850156265972722e-06, "epoch": 0.5384615384615384, "percentage": 10.77, "elapsed_time": "0:01:27", "remaining_time": "0:12:04"}
|
||||
{"current_steps": 8, "total_steps": 65, "loss": 0.6943, "lr": 9.784701678661045e-06, "epoch": 0.6153846153846154, "percentage": 12.31, "elapsed_time": "0:01:35", "remaining_time": "0:11:17"}
|
||||
{"current_steps": 9, "total_steps": 65, "loss": 0.6606, "lr": 9.707720325915105e-06, "epoch": 0.6923076923076923, "percentage": 13.85, "elapsed_time": "0:01:46", "remaining_time": "0:11:00"}
|
||||
{"current_steps": 10, "total_steps": 65, "loss": 0.662, "lr": 9.619397662556434e-06, "epoch": 0.7692307692307693, "percentage": 15.38, "elapsed_time": "0:01:55", "remaining_time": "0:10:35"}
|
||||
{"current_steps": 11, "total_steps": 65, "loss": 0.6118, "lr": 9.519946465617217e-06, "epoch": 0.8461538461538461, "percentage": 16.92, "elapsed_time": "0:02:08", "remaining_time": "0:10:31"}
|
||||
{"current_steps": 12, "total_steps": 65, "loss": 0.6148, "lr": 9.409606321741776e-06, "epoch": 0.9230769230769231, "percentage": 18.46, "elapsed_time": "0:02:17", "remaining_time": "0:10:07"}
|
||||
{"current_steps": 13, "total_steps": 65, "loss": 0.5794, "lr": 9.288643050001362e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:02:32", "remaining_time": "0:10:10"}
|
||||
{"current_steps": 14, "total_steps": 65, "loss": 0.5439, "lr": 9.157348061512728e-06, "epoch": 1.0769230769230769, "percentage": 21.54, "elapsed_time": "0:02:46", "remaining_time": "0:10:06"}
|
||||
{"current_steps": 15, "total_steps": 65, "loss": 0.5074, "lr": 9.016037657403225e-06, "epoch": 1.1538461538461537, "percentage": 23.08, "elapsed_time": "0:02:59", "remaining_time": "0:09:59"}
|
||||
{"current_steps": 16, "total_steps": 65, "loss": 0.5223, "lr": 8.865052266813686e-06, "epoch": 1.2307692307692308, "percentage": 24.62, "elapsed_time": "0:03:11", "remaining_time": "0:09:45"}
|
||||
{"current_steps": 17, "total_steps": 65, "loss": 0.5032, "lr": 8.704755626774796e-06, "epoch": 1.3076923076923077, "percentage": 26.15, "elapsed_time": "0:03:19", "remaining_time": "0:09:23"}
|
||||
{"current_steps": 18, "total_steps": 65, "loss": 0.5523, "lr": 8.535533905932739e-06, "epoch": 1.3846153846153846, "percentage": 27.69, "elapsed_time": "0:03:29", "remaining_time": "0:09:08"}
|
||||
{"current_steps": 19, "total_steps": 65, "loss": 0.49, "lr": 8.357794774235094e-06, "epoch": 1.4615384615384617, "percentage": 29.23, "elapsed_time": "0:03:41", "remaining_time": "0:08:55"}
|
||||
{"current_steps": 20, "total_steps": 65, "loss": 0.4874, "lr": 8.171966420818227e-06, "epoch": 1.5384615384615383, "percentage": 30.77, "elapsed_time": "0:03:54", "remaining_time": "0:08:48"}
|
||||
{"current_steps": 21, "total_steps": 65, "loss": 0.4622, "lr": 7.978496522462167e-06, "epoch": 1.6153846153846154, "percentage": 32.31, "elapsed_time": "0:04:07", "remaining_time": "0:08:38"}
|
||||
{"current_steps": 22, "total_steps": 65, "loss": 0.4828, "lr": 7.777851165098012e-06, "epoch": 1.6923076923076923, "percentage": 33.85, "elapsed_time": "0:04:15", "remaining_time": "0:08:19"}
|
||||
{"current_steps": 23, "total_steps": 65, "loss": 0.4552, "lr": 7.570513720966108e-06, "epoch": 1.7692307692307692, "percentage": 35.38, "elapsed_time": "0:04:30", "remaining_time": "0:08:14"}
|
||||
{"current_steps": 24, "total_steps": 65, "loss": 0.4797, "lr": 7.3569836841299905e-06, "epoch": 1.8461538461538463, "percentage": 36.92, "elapsed_time": "0:04:40", "remaining_time": "0:07:59"}
|
||||
{"current_steps": 25, "total_steps": 65, "loss": 0.4787, "lr": 7.137775467151411e-06, "epoch": 1.9230769230769231, "percentage": 38.46, "elapsed_time": "0:04:49", "remaining_time": "0:07:43"}
|
||||
{"current_steps": 26, "total_steps": 65, "loss": 0.4329, "lr": 6.913417161825449e-06, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:05:01", "remaining_time": "0:07:32"}
|
||||
{"current_steps": 27, "total_steps": 65, "loss": 0.3743, "lr": 6.684449266961101e-06, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "0:05:13", "remaining_time": "0:07:21"}
|
||||
{"current_steps": 28, "total_steps": 65, "loss": 0.4369, "lr": 6.451423386272312e-06, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "0:05:25", "remaining_time": "0:07:09"}
|
||||
{"current_steps": 29, "total_steps": 65, "loss": 0.4317, "lr": 6.21490089951632e-06, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "0:05:37", "remaining_time": "0:06:59"}
|
||||
{"current_steps": 30, "total_steps": 65, "loss": 0.4278, "lr": 5.975451610080643e-06, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "0:05:46", "remaining_time": "0:06:44"}
|
||||
{"current_steps": 31, "total_steps": 65, "loss": 0.444, "lr": 5.733652372276809e-06, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "0:05:55", "remaining_time": "0:06:29"}
|
||||
{"current_steps": 32, "total_steps": 65, "loss": 0.3575, "lr": 5.490085701647805e-06, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "0:06:07", "remaining_time": "0:06:18"}
|
||||
{"current_steps": 33, "total_steps": 65, "loss": 0.3927, "lr": 5.245338371637091e-06, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "0:06:16", "remaining_time": "0:06:05"}
|
||||
{"current_steps": 34, "total_steps": 65, "loss": 0.4115, "lr": 5e-06, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "0:06:29", "remaining_time": "0:05:55"}
|
||||
{"current_steps": 35, "total_steps": 65, "loss": 0.393, "lr": 4.75466162836291e-06, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "0:06:37", "remaining_time": "0:05:40"}
|
||||
{"current_steps": 36, "total_steps": 65, "loss": 0.3589, "lr": 4.509914298352197e-06, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "0:06:52", "remaining_time": "0:05:32"}
|
||||
{"current_steps": 37, "total_steps": 65, "loss": 0.4319, "lr": 4.266347627723192e-06, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "0:07:02", "remaining_time": "0:05:20"}
|
||||
{"current_steps": 38, "total_steps": 65, "loss": 0.3402, "lr": 4.02454838991936e-06, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "0:07:16", "remaining_time": "0:05:10"}
|
||||
{"current_steps": 39, "total_steps": 65, "loss": 0.3331, "lr": 3.7850991004836813e-06, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:07:26", "remaining_time": "0:04:57"}
|
||||
{"current_steps": 40, "total_steps": 65, "loss": 0.3531, "lr": 3.5485766137276894e-06, "epoch": 3.076923076923077, "percentage": 61.54, "elapsed_time": "0:07:39", "remaining_time": "0:04:46"}
|
||||
{"current_steps": 41, "total_steps": 65, "loss": 0.3531, "lr": 3.3155507330389004e-06, "epoch": 3.1538461538461537, "percentage": 63.08, "elapsed_time": "0:07:52", "remaining_time": "0:04:36"}
|
||||
{"current_steps": 42, "total_steps": 65, "loss": 0.3411, "lr": 3.0865828381745515e-06, "epoch": 3.230769230769231, "percentage": 64.62, "elapsed_time": "0:08:07", "remaining_time": "0:04:27"}
|
||||
{"current_steps": 43, "total_steps": 65, "loss": 0.3315, "lr": 2.862224532848591e-06, "epoch": 3.3076923076923075, "percentage": 66.15, "elapsed_time": "0:13:52", "remaining_time": "0:07:05"}
|
||||
{"current_steps": 44, "total_steps": 65, "loss": 0.3666, "lr": 2.6430163158700116e-06, "epoch": 3.3846153846153846, "percentage": 67.69, "elapsed_time": "0:14:03", "remaining_time": "0:06:42"}
|
||||
{"current_steps": 45, "total_steps": 65, "loss": 0.3705, "lr": 2.429486279033892e-06, "epoch": 3.4615384615384617, "percentage": 69.23, "elapsed_time": "0:14:16", "remaining_time": "0:06:20"}
|
||||
{"current_steps": 46, "total_steps": 65, "loss": 0.3648, "lr": 2.2221488349019903e-06, "epoch": 3.5384615384615383, "percentage": 70.77, "elapsed_time": "0:14:25", "remaining_time": "0:05:57"}
|
||||
{"current_steps": 47, "total_steps": 65, "loss": 0.3223, "lr": 2.0215034775378336e-06, "epoch": 3.6153846153846154, "percentage": 72.31, "elapsed_time": "0:14:34", "remaining_time": "0:05:35"}
|
||||
{"current_steps": 48, "total_steps": 65, "loss": 0.3183, "lr": 1.8280335791817733e-06, "epoch": 3.6923076923076925, "percentage": 73.85, "elapsed_time": "0:14:42", "remaining_time": "0:05:12"}
|
||||
{"current_steps": 49, "total_steps": 65, "loss": 0.3209, "lr": 1.642205225764908e-06, "epoch": 3.769230769230769, "percentage": 75.38, "elapsed_time": "0:14:54", "remaining_time": "0:04:51"}
|
||||
{"current_steps": 50, "total_steps": 65, "loss": 0.3199, "lr": 1.4644660940672628e-06, "epoch": 3.8461538461538463, "percentage": 76.92, "elapsed_time": "0:15:04", "remaining_time": "0:04:31"}
|
||||
{"current_steps": 51, "total_steps": 65, "loss": 0.3426, "lr": 1.2952443732252058e-06, "epoch": 3.9230769230769234, "percentage": 78.46, "elapsed_time": "0:15:17", "remaining_time": "0:04:11"}
|
||||
{"current_steps": 52, "total_steps": 65, "loss": 0.3742, "lr": 1.134947733186315e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:15:27", "remaining_time": "0:03:51"}
|
||||
{"current_steps": 53, "total_steps": 65, "loss": 0.3534, "lr": 9.83962342596776e-07, "epoch": 4.076923076923077, "percentage": 81.54, "elapsed_time": "0:15:49", "remaining_time": "0:03:34"}
|
||||
{"current_steps": 54, "total_steps": 65, "loss": 0.3497, "lr": 8.426519384872733e-07, "epoch": 4.153846153846154, "percentage": 83.08, "elapsed_time": "0:16:04", "remaining_time": "0:03:16"}
|
||||
{"current_steps": 55, "total_steps": 65, "loss": 0.2484, "lr": 7.113569499986401e-07, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "0:16:15", "remaining_time": "0:02:57"}
|
||||
{"current_steps": 56, "total_steps": 65, "loss": 0.244, "lr": 5.903936782582253e-07, "epoch": 4.3076923076923075, "percentage": 86.15, "elapsed_time": "0:16:28", "remaining_time": "0:02:38"}
|
||||
{"current_steps": 57, "total_steps": 65, "loss": 0.3561, "lr": 4.800535343827834e-07, "epoch": 4.384615384615385, "percentage": 87.69, "elapsed_time": "0:16:37", "remaining_time": "0:02:20"}
|
||||
{"current_steps": 58, "total_steps": 65, "loss": 0.3018, "lr": 3.8060233744356634e-07, "epoch": 4.461538461538462, "percentage": 89.23, "elapsed_time": "0:16:48", "remaining_time": "0:02:01"}
|
||||
{"current_steps": 59, "total_steps": 65, "loss": 0.3274, "lr": 2.9227967408489653e-07, "epoch": 4.538461538461538, "percentage": 90.77, "elapsed_time": "0:16:59", "remaining_time": "0:01:43"}
|
||||
{"current_steps": 60, "total_steps": 65, "loss": 0.329, "lr": 2.152983213389559e-07, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "0:17:06", "remaining_time": "0:01:25"}
|
||||
{"current_steps": 61, "total_steps": 65, "loss": 0.3235, "lr": 1.4984373402728014e-07, "epoch": 4.6923076923076925, "percentage": 93.85, "elapsed_time": "0:17:18", "remaining_time": "0:01:08"}
|
||||
{"current_steps": 62, "total_steps": 65, "loss": 0.357, "lr": 9.607359798384785e-08, "epoch": 4.769230769230769, "percentage": 95.38, "elapsed_time": "0:17:31", "remaining_time": "0:00:50"}
|
||||
{"current_steps": 63, "total_steps": 65, "loss": 0.2892, "lr": 5.411745017609493e-08, "epoch": 4.846153846153846, "percentage": 96.92, "elapsed_time": "0:17:45", "remaining_time": "0:00:33"}
|
||||
{"current_steps": 64, "total_steps": 65, "loss": 0.349, "lr": 2.4076366639015914e-08, "epoch": 4.923076923076923, "percentage": 98.46, "elapsed_time": "0:17:53", "remaining_time": "0:00:16"}
|
||||
{"current_steps": 65, "total_steps": 65, "loss": 0.3456, "lr": 6.022718974137976e-09, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:18:07", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 65, "total_steps": 65, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:23:51", "remaining_time": "0:00:00"}
|
||||
498
trainer_state.json
Normal file
498
trainer_state.json
Normal file
@@ -0,0 +1,498 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 5.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 65,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.07692307692307693,
|
||||
"grad_norm": 6.370218968023409,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.9617,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.15384615384615385,
|
||||
"grad_norm": 7.062823048926537,
|
||||
"learning_rate": 1e-05,
|
||||
"loss": 0.9221,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.23076923076923078,
|
||||
"grad_norm": 3.508151848769913,
|
||||
"learning_rate": 9.993977281025862e-06,
|
||||
"loss": 0.8516,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.3076923076923077,
|
||||
"grad_norm": 2.1315111375920908,
|
||||
"learning_rate": 9.975923633360985e-06,
|
||||
"loss": 0.7455,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.38461538461538464,
|
||||
"grad_norm": 2.067690304064468,
|
||||
"learning_rate": 9.945882549823906e-06,
|
||||
"loss": 0.7818,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.46153846153846156,
|
||||
"grad_norm": 2.164959330267267,
|
||||
"learning_rate": 9.903926402016153e-06,
|
||||
"loss": 0.7056,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.5384615384615384,
|
||||
"grad_norm": 1.7114510182271578,
|
||||
"learning_rate": 9.850156265972722e-06,
|
||||
"loss": 0.6684,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.6153846153846154,
|
||||
"grad_norm": 1.4221134607922832,
|
||||
"learning_rate": 9.784701678661045e-06,
|
||||
"loss": 0.6943,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 0.6923076923076923,
|
||||
"grad_norm": 1.2054367990274877,
|
||||
"learning_rate": 9.707720325915105e-06,
|
||||
"loss": 0.6606,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.7692307692307693,
|
||||
"grad_norm": 1.234597606787108,
|
||||
"learning_rate": 9.619397662556434e-06,
|
||||
"loss": 0.662,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.8461538461538461,
|
||||
"grad_norm": 1.0253610984337118,
|
||||
"learning_rate": 9.519946465617217e-06,
|
||||
"loss": 0.6118,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.9230769230769231,
|
||||
"grad_norm": 0.9531385105738269,
|
||||
"learning_rate": 9.409606321741776e-06,
|
||||
"loss": 0.6148,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 0.8797592723988117,
|
||||
"learning_rate": 9.288643050001362e-06,
|
||||
"loss": 0.5794,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 1.0769230769230769,
|
||||
"grad_norm": 0.8614478397135895,
|
||||
"learning_rate": 9.157348061512728e-06,
|
||||
"loss": 0.5439,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 1.1538461538461537,
|
||||
"grad_norm": 0.8816737566077302,
|
||||
"learning_rate": 9.016037657403225e-06,
|
||||
"loss": 0.5074,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 1.2307692307692308,
|
||||
"grad_norm": 0.8669076102244132,
|
||||
"learning_rate": 8.865052266813686e-06,
|
||||
"loss": 0.5223,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 1.3076923076923077,
|
||||
"grad_norm": 0.8101412038742847,
|
||||
"learning_rate": 8.704755626774796e-06,
|
||||
"loss": 0.5032,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 1.3846153846153846,
|
||||
"grad_norm": 0.8569082435438978,
|
||||
"learning_rate": 8.535533905932739e-06,
|
||||
"loss": 0.5523,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 1.4615384615384617,
|
||||
"grad_norm": 0.7453930156975321,
|
||||
"learning_rate": 8.357794774235094e-06,
|
||||
"loss": 0.49,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 1.5384615384615383,
|
||||
"grad_norm": 0.6283060582206399,
|
||||
"learning_rate": 8.171966420818227e-06,
|
||||
"loss": 0.4874,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 1.6153846153846154,
|
||||
"grad_norm": 0.8023986095300789,
|
||||
"learning_rate": 7.978496522462167e-06,
|
||||
"loss": 0.4622,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 1.6923076923076923,
|
||||
"grad_norm": 0.7122469220028385,
|
||||
"learning_rate": 7.777851165098012e-06,
|
||||
"loss": 0.4828,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 1.7692307692307692,
|
||||
"grad_norm": 0.5943006237807561,
|
||||
"learning_rate": 7.570513720966108e-06,
|
||||
"loss": 0.4552,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 1.8461538461538463,
|
||||
"grad_norm": 0.7102435889730987,
|
||||
"learning_rate": 7.3569836841299905e-06,
|
||||
"loss": 0.4797,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 1.9230769230769231,
|
||||
"grad_norm": 0.7244490320083123,
|
||||
"learning_rate": 7.137775467151411e-06,
|
||||
"loss": 0.4787,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 0.6176632029398068,
|
||||
"learning_rate": 6.913417161825449e-06,
|
||||
"loss": 0.4329,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 2.076923076923077,
|
||||
"grad_norm": 0.8216799021152335,
|
||||
"learning_rate": 6.684449266961101e-06,
|
||||
"loss": 0.3743,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 2.1538461538461537,
|
||||
"grad_norm": 0.6005917289643109,
|
||||
"learning_rate": 6.451423386272312e-06,
|
||||
"loss": 0.4369,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 2.230769230769231,
|
||||
"grad_norm": 0.624537941070379,
|
||||
"learning_rate": 6.21490089951632e-06,
|
||||
"loss": 0.4317,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 2.3076923076923075,
|
||||
"grad_norm": 0.6577500844311218,
|
||||
"learning_rate": 5.975451610080643e-06,
|
||||
"loss": 0.4278,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 2.3846153846153846,
|
||||
"grad_norm": 0.5918326665297654,
|
||||
"learning_rate": 5.733652372276809e-06,
|
||||
"loss": 0.444,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 2.4615384615384617,
|
||||
"grad_norm": 0.7154936597726321,
|
||||
"learning_rate": 5.490085701647805e-06,
|
||||
"loss": 0.3575,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 2.5384615384615383,
|
||||
"grad_norm": 0.7058375820227064,
|
||||
"learning_rate": 5.245338371637091e-06,
|
||||
"loss": 0.3927,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 2.6153846153846154,
|
||||
"grad_norm": 0.624999538418926,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 0.4115,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 2.6923076923076925,
|
||||
"grad_norm": 0.6189527167900223,
|
||||
"learning_rate": 4.75466162836291e-06,
|
||||
"loss": 0.393,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 2.769230769230769,
|
||||
"grad_norm": 0.6581614058929585,
|
||||
"learning_rate": 4.509914298352197e-06,
|
||||
"loss": 0.3589,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 2.8461538461538463,
|
||||
"grad_norm": 0.5968832668044702,
|
||||
"learning_rate": 4.266347627723192e-06,
|
||||
"loss": 0.4319,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 2.9230769230769234,
|
||||
"grad_norm": 0.6829725248958235,
|
||||
"learning_rate": 4.02454838991936e-06,
|
||||
"loss": 0.3402,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"grad_norm": 0.6835108217400175,
|
||||
"learning_rate": 3.7850991004836813e-06,
|
||||
"loss": 0.3331,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 3.076923076923077,
|
||||
"grad_norm": 0.7315492211655491,
|
||||
"learning_rate": 3.5485766137276894e-06,
|
||||
"loss": 0.3531,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 3.1538461538461537,
|
||||
"grad_norm": 0.6375294587624502,
|
||||
"learning_rate": 3.3155507330389004e-06,
|
||||
"loss": 0.3531,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 3.230769230769231,
|
||||
"grad_norm": 0.618128196978316,
|
||||
"learning_rate": 3.0865828381745515e-06,
|
||||
"loss": 0.3411,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 3.3076923076923075,
|
||||
"grad_norm": 0.6384871969000007,
|
||||
"learning_rate": 2.862224532848591e-06,
|
||||
"loss": 0.3315,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 3.3846153846153846,
|
||||
"grad_norm": 0.561255153854599,
|
||||
"learning_rate": 2.6430163158700116e-06,
|
||||
"loss": 0.3666,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 3.4615384615384617,
|
||||
"grad_norm": 0.5408489944687312,
|
||||
"learning_rate": 2.429486279033892e-06,
|
||||
"loss": 0.3705,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 3.5384615384615383,
|
||||
"grad_norm": 0.5671728055194564,
|
||||
"learning_rate": 2.2221488349019903e-06,
|
||||
"loss": 0.3648,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 3.6153846153846154,
|
||||
"grad_norm": 0.5700975153063862,
|
||||
"learning_rate": 2.0215034775378336e-06,
|
||||
"loss": 0.3223,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 3.6923076923076925,
|
||||
"grad_norm": 0.664767908088173,
|
||||
"learning_rate": 1.8280335791817733e-06,
|
||||
"loss": 0.3183,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 3.769230769230769,
|
||||
"grad_norm": 0.6330871629952953,
|
||||
"learning_rate": 1.642205225764908e-06,
|
||||
"loss": 0.3209,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 3.8461538461538463,
|
||||
"grad_norm": 0.6309153488529204,
|
||||
"learning_rate": 1.4644660940672628e-06,
|
||||
"loss": 0.3199,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 3.9230769230769234,
|
||||
"grad_norm": 0.55827785835018,
|
||||
"learning_rate": 1.2952443732252058e-06,
|
||||
"loss": 0.3426,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"grad_norm": 0.5523594386231,
|
||||
"learning_rate": 1.134947733186315e-06,
|
||||
"loss": 0.3742,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 4.076923076923077,
|
||||
"grad_norm": 0.5458600271870175,
|
||||
"learning_rate": 9.83962342596776e-07,
|
||||
"loss": 0.3534,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 4.153846153846154,
|
||||
"grad_norm": 0.6854362784340675,
|
||||
"learning_rate": 8.426519384872733e-07,
|
||||
"loss": 0.3497,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 4.230769230769231,
|
||||
"grad_norm": 0.6032529402232379,
|
||||
"learning_rate": 7.113569499986401e-07,
|
||||
"loss": 0.2484,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 4.3076923076923075,
|
||||
"grad_norm": 0.7477132723449166,
|
||||
"learning_rate": 5.903936782582253e-07,
|
||||
"loss": 0.244,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 4.384615384615385,
|
||||
"grad_norm": 0.5868192979660759,
|
||||
"learning_rate": 4.800535343827834e-07,
|
||||
"loss": 0.3561,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 4.461538461538462,
|
||||
"grad_norm": 0.5590511625666816,
|
||||
"learning_rate": 3.8060233744356634e-07,
|
||||
"loss": 0.3018,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 4.538461538461538,
|
||||
"grad_norm": 0.573822252707526,
|
||||
"learning_rate": 2.9227967408489653e-07,
|
||||
"loss": 0.3274,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 4.615384615384615,
|
||||
"grad_norm": 0.5539473518142963,
|
||||
"learning_rate": 2.152983213389559e-07,
|
||||
"loss": 0.329,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 4.6923076923076925,
|
||||
"grad_norm": 0.5602498609734554,
|
||||
"learning_rate": 1.4984373402728014e-07,
|
||||
"loss": 0.3235,
|
||||
"step": 61
|
||||
},
|
||||
{
|
||||
"epoch": 4.769230769230769,
|
||||
"grad_norm": 0.5088498618342225,
|
||||
"learning_rate": 9.607359798384785e-08,
|
||||
"loss": 0.357,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 4.846153846153846,
|
||||
"grad_norm": 0.5487703200660301,
|
||||
"learning_rate": 5.411745017609493e-08,
|
||||
"loss": 0.2892,
|
||||
"step": 63
|
||||
},
|
||||
{
|
||||
"epoch": 4.923076923076923,
|
||||
"grad_norm": 0.5219657252094004,
|
||||
"learning_rate": 2.4076366639015914e-08,
|
||||
"loss": 0.349,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"grad_norm": 0.5380803859588003,
|
||||
"learning_rate": 6.022718974137976e-09,
|
||||
"loss": 0.3456,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"step": 65,
|
||||
"total_flos": 12383961956352.0,
|
||||
"train_loss": 0.45606403878101937,
|
||||
"train_runtime": 1434.1495,
|
||||
"train_samples_per_second": 0.352,
|
||||
"train_steps_per_second": 0.045
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 65,
|
||||
"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": 12383961956352.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:68dc9e872d2f74ce2e9e3e863506c5b7c2aea876c7fab8e0028e4872666d2fa6
|
||||
size 8273
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 43 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