初始化项目，由ModelHub XC社区提供模型
Model: lihaoxin2020/qwen3-4b-refiner-gpt54-ep3 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: 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. -->
|
||||
|
||||
# sft
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the refiner_gpt54_sft 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: 5e-06
|
||||
- train_batch_size: 2
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 2
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 32
|
||||
- total_eval_batch_size: 16
|
||||
- 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: 0.05
|
||||
- num_epochs: 3.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.52.4
|
||||
- Pytorch 2.11.0+cu130
|
||||
- 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": 3.0,
|
||||
"total_flos": 75263551668224.0,
|
||||
"train_loss": 0.37880756392959475,
|
||||
"train_runtime": 12221.4211,
|
||||
"train_samples_per_second": 3.375,
|
||||
"train_steps_per_second": 0.106
|
||||
}
|
||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
||||
{%- 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 %}
|
||||
{%- 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" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- 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' }}
|
||||
{%- endif %}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"max_position_embeddings": 262144,
|
||||
"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": 5000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
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": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f736f21e8fd1732ac9e5f8ccc5e104009be2261e7ab261d0c3bcf0dbbcdebc2
|
||||
size 4967215360
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f2aff010e114c8b1bfd34d5aa6a8395104bf25f936fa648d93e4680fd36064fc
|
||||
size 3077766632
|
||||
405
model.safetensors.index.json
Normal file
405
model.safetensors.index.json
Normal file
@@ -0,0 +1,405 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 8044936192
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
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": 1010000,
|
||||
"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": 75263551668224.0,
|
||||
"train_loss": 0.37880756392959475,
|
||||
"train_runtime": 12221.4211,
|
||||
"train_samples_per_second": 3.375,
|
||||
"train_steps_per_second": 0.106
|
||||
}
|
||||
130
trainer_log.jsonl
Normal file
130
trainer_log.jsonl
Normal file
@@ -0,0 +1,130 @@
|
||||
{"current_steps": 10, "total_steps": 1290, "loss": 2.2478, "lr": 6.923076923076924e-07, "epoch": 0.02327611288914751, "percentage": 0.78, "elapsed_time": "0:01:50", "remaining_time": "3:56:32"}
|
||||
{"current_steps": 20, "total_steps": 1290, "loss": 1.6832, "lr": 1.4615384615384618e-06, "epoch": 0.04655222577829502, "percentage": 1.55, "elapsed_time": "0:03:22", "remaining_time": "3:33:58"}
|
||||
{"current_steps": 30, "total_steps": 1290, "loss": 0.9955, "lr": 2.230769230769231e-06, "epoch": 0.06982833866744254, "percentage": 2.33, "elapsed_time": "0:04:59", "remaining_time": "3:29:57"}
|
||||
{"current_steps": 40, "total_steps": 1290, "loss": 0.7928, "lr": 3e-06, "epoch": 0.09310445155659004, "percentage": 3.1, "elapsed_time": "0:06:31", "remaining_time": "3:23:54"}
|
||||
{"current_steps": 50, "total_steps": 1290, "loss": 0.6649, "lr": 3.7692307692307694e-06, "epoch": 0.11638056444573756, "percentage": 3.88, "elapsed_time": "0:08:05", "remaining_time": "3:20:28"}
|
||||
{"current_steps": 60, "total_steps": 1290, "loss": 0.6307, "lr": 4.538461538461539e-06, "epoch": 0.13965667733488507, "percentage": 4.65, "elapsed_time": "0:09:38", "remaining_time": "3:17:41"}
|
||||
{"current_steps": 70, "total_steps": 1290, "loss": 0.5959, "lr": 4.999868461236464e-06, "epoch": 0.1629327902240326, "percentage": 5.43, "elapsed_time": "0:11:11", "remaining_time": "3:14:55"}
|
||||
{"current_steps": 80, "total_steps": 1290, "loss": 0.5783, "lr": 4.998388809108304e-06, "epoch": 0.18620890311318009, "percentage": 6.2, "elapsed_time": "0:12:54", "remaining_time": "3:15:16"}
|
||||
{"current_steps": 90, "total_steps": 1290, "loss": 0.5601, "lr": 4.995266057755046e-06, "epoch": 0.2094850160023276, "percentage": 6.98, "elapsed_time": "0:14:26", "remaining_time": "3:12:28"}
|
||||
{"current_steps": 100, "total_steps": 1290, "loss": 0.5336, "lr": 4.990502260896396e-06, "epoch": 0.23276112889147513, "percentage": 7.75, "elapsed_time": "0:16:01", "remaining_time": "3:10:47"}
|
||||
{"current_steps": 110, "total_steps": 1290, "loss": 0.5411, "lr": 4.984100551507853e-06, "epoch": 0.25603724178062265, "percentage": 8.53, "elapsed_time": "0:17:36", "remaining_time": "3:08:54"}
|
||||
{"current_steps": 120, "total_steps": 1290, "loss": 0.5278, "lr": 4.9760651397602675e-06, "epoch": 0.27931335466977014, "percentage": 9.3, "elapsed_time": "0:19:13", "remaining_time": "3:07:24"}
|
||||
{"current_steps": 130, "total_steps": 1290, "loss": 0.5168, "lr": 4.966401310250963e-06, "epoch": 0.30258946755891764, "percentage": 10.08, "elapsed_time": "0:20:42", "remaining_time": "3:04:43"}
|
||||
{"current_steps": 140, "total_steps": 1290, "loss": 0.5178, "lr": 4.9551154185282504e-06, "epoch": 0.3258655804480652, "percentage": 10.85, "elapsed_time": "0:22:21", "remaining_time": "3:03:40"}
|
||||
{"current_steps": 150, "total_steps": 1290, "loss": 0.5023, "lr": 4.942214886911619e-06, "epoch": 0.3491416933372127, "percentage": 11.63, "elapsed_time": "0:23:55", "remaining_time": "3:01:49"}
|
||||
{"current_steps": 160, "total_steps": 1290, "loss": 0.4943, "lr": 4.9277081996103415e-06, "epoch": 0.37241780622636017, "percentage": 12.4, "elapsed_time": "0:25:28", "remaining_time": "2:59:58"}
|
||||
{"current_steps": 170, "total_steps": 1290, "loss": 0.4814, "lr": 4.911604897143723e-06, "epoch": 0.3956939191155077, "percentage": 13.18, "elapsed_time": "0:27:05", "remaining_time": "2:58:27"}
|
||||
{"current_steps": 180, "total_steps": 1290, "loss": 0.4853, "lr": 4.893915570066645e-06, "epoch": 0.4189700320046552, "percentage": 13.95, "elapsed_time": "0:28:38", "remaining_time": "2:56:36"}
|
||||
{"current_steps": 190, "total_steps": 1290, "loss": 0.476, "lr": 4.8746518520045515e-06, "epoch": 0.44224614489380276, "percentage": 14.73, "elapsed_time": "0:30:07", "remaining_time": "2:54:25"}
|
||||
{"current_steps": 200, "total_steps": 1290, "loss": 0.5165, "lr": 4.853826412002429e-06, "epoch": 0.46552225778295026, "percentage": 15.5, "elapsed_time": "0:31:42", "remaining_time": "2:52:49"}
|
||||
{"current_steps": 210, "total_steps": 1290, "loss": 0.5073, "lr": 4.831452946192845e-06, "epoch": 0.48879837067209775, "percentage": 16.28, "elapsed_time": "0:33:17", "remaining_time": "2:51:11"}
|
||||
{"current_steps": 220, "total_steps": 1290, "loss": 0.4773, "lr": 4.8075461687884935e-06, "epoch": 0.5120744835612453, "percentage": 17.05, "elapsed_time": "0:34:49", "remaining_time": "2:49:20"}
|
||||
{"current_steps": 230, "total_steps": 1290, "loss": 0.4843, "lr": 4.782121802405201e-06, "epoch": 0.5353505964503927, "percentage": 17.83, "elapsed_time": "0:36:27", "remaining_time": "2:48:00"}
|
||||
{"current_steps": 240, "total_steps": 1290, "loss": 0.4858, "lr": 4.75519656772173e-06, "epoch": 0.5586267093395403, "percentage": 18.6, "elapsed_time": "0:38:01", "remaining_time": "2:46:19"}
|
||||
{"current_steps": 250, "total_steps": 1290, "loss": 0.4821, "lr": 4.726788172483202e-06, "epoch": 0.5819028222286878, "percentage": 19.38, "elapsed_time": "0:39:38", "remaining_time": "2:44:55"}
|
||||
{"current_steps": 260, "total_steps": 1290, "loss": 0.4796, "lr": 4.696915299855357e-06, "epoch": 0.6051789351178353, "percentage": 20.16, "elapsed_time": "0:41:07", "remaining_time": "2:42:55"}
|
||||
{"current_steps": 270, "total_steps": 1290, "loss": 0.4713, "lr": 4.665597596137315e-06, "epoch": 0.6284550480069828, "percentage": 20.93, "elapsed_time": "0:42:41", "remaining_time": "2:41:17"}
|
||||
{"current_steps": 280, "total_steps": 1290, "loss": 0.4736, "lr": 4.632855657840926e-06, "epoch": 0.6517311608961304, "percentage": 21.71, "elapsed_time": "0:44:17", "remaining_time": "2:39:47"}
|
||||
{"current_steps": 290, "total_steps": 1290, "loss": 0.4487, "lr": 4.598711018145193e-06, "epoch": 0.6750072737852778, "percentage": 22.48, "elapsed_time": "0:45:49", "remaining_time": "2:37:59"}
|
||||
{"current_steps": 300, "total_steps": 1290, "loss": 0.4848, "lr": 4.563186132734684e-06, "epoch": 0.6982833866744254, "percentage": 23.26, "elapsed_time": "0:47:27", "remaining_time": "2:36:37"}
|
||||
{"current_steps": 310, "total_steps": 1290, "loss": 0.4992, "lr": 4.526304365031245e-06, "epoch": 0.7215594995635729, "percentage": 24.03, "elapsed_time": "0:49:04", "remaining_time": "2:35:07"}
|
||||
{"current_steps": 320, "total_steps": 1290, "loss": 0.461, "lr": 4.488089970828739e-06, "epoch": 0.7448356124527203, "percentage": 24.81, "elapsed_time": "0:50:34", "remaining_time": "2:33:19"}
|
||||
{"current_steps": 330, "total_steps": 1290, "loss": 0.4903, "lr": 4.448568082340882e-06, "epoch": 0.7681117253418679, "percentage": 25.58, "elapsed_time": "0:52:09", "remaining_time": "2:31:44"}
|
||||
{"current_steps": 340, "total_steps": 1290, "loss": 0.4634, "lr": 4.4077646916727105e-06, "epoch": 0.7913878382310154, "percentage": 26.36, "elapsed_time": "0:53:40", "remaining_time": "2:29:58"}
|
||||
{"current_steps": 350, "total_steps": 1290, "loss": 0.4924, "lr": 4.36570663372652e-06, "epoch": 0.814663951120163, "percentage": 27.13, "elapsed_time": "0:55:15", "remaining_time": "2:28:23"}
|
||||
{"current_steps": 360, "total_steps": 1290, "loss": 0.4725, "lr": 4.322421568553529e-06, "epoch": 0.8379400640093104, "percentage": 27.91, "elapsed_time": "0:56:49", "remaining_time": "2:26:47"}
|
||||
{"current_steps": 370, "total_steps": 1290, "loss": 0.4822, "lr": 4.277937963162869e-06, "epoch": 0.861216176898458, "percentage": 28.68, "elapsed_time": "0:58:22", "remaining_time": "2:25:09"}
|
||||
{"current_steps": 380, "total_steps": 1290, "loss": 0.4876, "lr": 4.232285072799871e-06, "epoch": 0.8844922897876055, "percentage": 29.46, "elapsed_time": "1:00:01", "remaining_time": "2:23:45"}
|
||||
{"current_steps": 390, "total_steps": 1290, "loss": 0.47, "lr": 4.185492921705962e-06, "epoch": 0.907768402676753, "percentage": 30.23, "elapsed_time": "1:01:37", "remaining_time": "2:22:13"}
|
||||
{"current_steps": 400, "total_steps": 1290, "loss": 0.4763, "lr": 4.137592283372812e-06, "epoch": 0.9310445155659005, "percentage": 31.01, "elapsed_time": "1:03:13", "remaining_time": "2:20:41"}
|
||||
{"current_steps": 410, "total_steps": 1290, "loss": 0.4627, "lr": 4.088614660303728e-06, "epoch": 0.9543206284550481, "percentage": 31.78, "elapsed_time": "1:04:43", "remaining_time": "2:18:54"}
|
||||
{"current_steps": 420, "total_steps": 1290, "loss": 0.463, "lr": 4.038592263295612e-06, "epoch": 0.9775967413441955, "percentage": 32.56, "elapsed_time": "1:06:16", "remaining_time": "2:17:16"}
|
||||
{"current_steps": 430, "total_steps": 1290, "loss": 0.4702, "lr": 3.987557990255093e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:07:47", "remaining_time": "2:15:35"}
|
||||
{"current_steps": 440, "total_steps": 1290, "loss": 0.351, "lr": 3.93554540456277e-06, "epoch": 1.0232761128891474, "percentage": 34.11, "elapsed_time": "1:09:22", "remaining_time": "2:14:01"}
|
||||
{"current_steps": 450, "total_steps": 1290, "loss": 0.3331, "lr": 3.882588712999804e-06, "epoch": 1.046552225778295, "percentage": 34.88, "elapsed_time": "1:10:56", "remaining_time": "2:12:25"}
|
||||
{"current_steps": 460, "total_steps": 1290, "loss": 0.3353, "lr": 3.8287227432513616e-06, "epoch": 1.0698283386674425, "percentage": 35.66, "elapsed_time": "1:12:29", "remaining_time": "2:10:47"}
|
||||
{"current_steps": 470, "total_steps": 1290, "loss": 0.3296, "lr": 3.7739829210017207e-06, "epoch": 1.09310445155659, "percentage": 36.43, "elapsed_time": "1:14:01", "remaining_time": "2:09:08"}
|
||||
{"current_steps": 480, "total_steps": 1290, "loss": 0.3418, "lr": 3.718405246636087e-06, "epoch": 1.1163805644457376, "percentage": 37.21, "elapsed_time": "1:15:33", "remaining_time": "2:07:29"}
|
||||
{"current_steps": 490, "total_steps": 1290, "loss": 0.3447, "lr": 3.662026271564452e-06, "epoch": 1.139656677334885, "percentage": 37.98, "elapsed_time": "1:17:10", "remaining_time": "2:06:00"}
|
||||
{"current_steps": 500, "total_steps": 1290, "loss": 0.3349, "lr": 3.6048830741830678e-06, "epoch": 1.1629327902240325, "percentage": 38.76, "elapsed_time": "1:18:47", "remaining_time": "2:04:29"}
|
||||
{"current_steps": 510, "total_steps": 1290, "loss": 0.3286, "lr": 3.5470132354893317e-06, "epoch": 1.1862089031131802, "percentage": 39.53, "elapsed_time": "1:20:33", "remaining_time": "2:03:12"}
|
||||
{"current_steps": 520, "total_steps": 1290, "loss": 0.3267, "lr": 3.48845481436614e-06, "epoch": 1.2094850160023276, "percentage": 40.31, "elapsed_time": "1:22:11", "remaining_time": "2:01:42"}
|
||||
{"current_steps": 530, "total_steps": 1290, "loss": 0.3178, "lr": 3.429246322551947e-06, "epoch": 1.232761128891475, "percentage": 41.09, "elapsed_time": "1:23:49", "remaining_time": "2:00:11"}
|
||||
{"current_steps": 540, "total_steps": 1290, "loss": 0.3187, "lr": 3.3694266993129963e-06, "epoch": 1.2560372417806227, "percentage": 41.86, "elapsed_time": "1:25:22", "remaining_time": "1:58:34"}
|
||||
{"current_steps": 550, "total_steps": 1290, "loss": 0.3436, "lr": 3.3090352858343855e-06, "epoch": 1.2793133546697701, "percentage": 42.64, "elapsed_time": "1:26:54", "remaining_time": "1:56:55"}
|
||||
{"current_steps": 560, "total_steps": 1290, "loss": 0.3169, "lr": 3.2481117993468096e-06, "epoch": 1.3025894675589176, "percentage": 43.41, "elapsed_time": "1:28:27", "remaining_time": "1:55:19"}
|
||||
{"current_steps": 570, "total_steps": 1290, "loss": 0.3396, "lr": 3.186696307005976e-06, "epoch": 1.3258655804480652, "percentage": 44.19, "elapsed_time": "1:30:03", "remaining_time": "1:53:45"}
|
||||
{"current_steps": 580, "total_steps": 1290, "loss": 0.3366, "lr": 3.1248291995419057e-06, "epoch": 1.3491416933372127, "percentage": 44.96, "elapsed_time": "1:31:37", "remaining_time": "1:52:09"}
|
||||
{"current_steps": 590, "total_steps": 1290, "loss": 0.3379, "lr": 3.0625511646954187e-06, "epoch": 1.3724178062263601, "percentage": 45.74, "elapsed_time": "1:33:12", "remaining_time": "1:50:35"}
|
||||
{"current_steps": 600, "total_steps": 1290, "loss": 0.3244, "lr": 2.999903160459292e-06, "epoch": 1.3956939191155078, "percentage": 46.51, "elapsed_time": "1:34:49", "remaining_time": "1:49:02"}
|
||||
{"current_steps": 610, "total_steps": 1290, "loss": 0.3263, "lr": 2.93692638814168e-06, "epoch": 1.4189700320046552, "percentage": 47.29, "elapsed_time": "1:36:22", "remaining_time": "1:47:25"}
|
||||
{"current_steps": 620, "total_steps": 1290, "loss": 0.3162, "lr": 2.8736622652695178e-06, "epoch": 1.4422461448938027, "percentage": 48.06, "elapsed_time": "1:37:48", "remaining_time": "1:45:41"}
|
||||
{"current_steps": 630, "total_steps": 1290, "loss": 0.3317, "lr": 2.8101523983497214e-06, "epoch": 1.4655222577829503, "percentage": 48.84, "elapsed_time": "1:39:23", "remaining_time": "1:44:07"}
|
||||
{"current_steps": 640, "total_steps": 1290, "loss": 0.3316, "lr": 2.7464385555061092e-06, "epoch": 1.4887983706720977, "percentage": 49.61, "elapsed_time": "1:40:56", "remaining_time": "1:42:31"}
|
||||
{"current_steps": 650, "total_steps": 1290, "loss": 0.3357, "lr": 2.682562639010025e-06, "epoch": 1.5120744835612454, "percentage": 50.39, "elapsed_time": "1:42:27", "remaining_time": "1:40:52"}
|
||||
{"current_steps": 660, "total_steps": 1290, "loss": 0.3363, "lr": 2.6185666577227464e-06, "epoch": 1.5353505964503928, "percentage": 51.16, "elapsed_time": "1:44:04", "remaining_time": "1:39:20"}
|
||||
{"current_steps": 670, "total_steps": 1290, "loss": 0.3441, "lr": 2.5544926994677847e-06, "epoch": 1.5586267093395403, "percentage": 51.94, "elapsed_time": "1:45:39", "remaining_time": "1:37:46"}
|
||||
{"current_steps": 680, "total_steps": 1290, "loss": 0.3199, "lr": 2.490382903351261e-06, "epoch": 1.5819028222286877, "percentage": 52.71, "elapsed_time": "1:47:13", "remaining_time": "1:36:11"}
|
||||
{"current_steps": 690, "total_steps": 1290, "loss": 0.3413, "lr": 2.4262794320485505e-06, "epoch": 1.6051789351178352, "percentage": 53.49, "elapsed_time": "1:48:45", "remaining_time": "1:34:34"}
|
||||
{"current_steps": 700, "total_steps": 1290, "loss": 0.3215, "lr": 2.3622244440754306e-06, "epoch": 1.6284550480069828, "percentage": 54.26, "elapsed_time": "1:50:19", "remaining_time": "1:32:59"}
|
||||
{"current_steps": 710, "total_steps": 1290, "loss": 0.3245, "lr": 2.2982600660619574e-06, "epoch": 1.6517311608961305, "percentage": 55.04, "elapsed_time": "1:51:54", "remaining_time": "1:31:25"}
|
||||
{"current_steps": 720, "total_steps": 1290, "loss": 0.3132, "lr": 2.234428365047323e-06, "epoch": 1.675007273785278, "percentage": 55.81, "elapsed_time": "1:53:30", "remaining_time": "1:29:51"}
|
||||
{"current_steps": 730, "total_steps": 1290, "loss": 0.3249, "lr": 2.1707713208138942e-06, "epoch": 1.6982833866744254, "percentage": 56.59, "elapsed_time": "1:55:02", "remaining_time": "1:28:15"}
|
||||
{"current_steps": 740, "total_steps": 1290, "loss": 0.3252, "lr": 2.1073307982786402e-06, "epoch": 1.7215594995635728, "percentage": 57.36, "elapsed_time": "1:56:40", "remaining_time": "1:26:43"}
|
||||
{"current_steps": 750, "total_steps": 1290, "loss": 0.3242, "lr": 2.044148519960106e-06, "epoch": 1.7448356124527202, "percentage": 58.14, "elapsed_time": "1:58:14", "remaining_time": "1:25:08"}
|
||||
{"current_steps": 760, "total_steps": 1290, "loss": 0.3183, "lr": 1.981266038539029e-06, "epoch": 1.768111725341868, "percentage": 58.91, "elapsed_time": "1:59:49", "remaining_time": "1:23:33"}
|
||||
{"current_steps": 770, "total_steps": 1290, "loss": 0.337, "lr": 1.91872470953066e-06, "epoch": 1.7913878382310156, "percentage": 59.69, "elapsed_time": "2:01:22", "remaining_time": "1:21:57"}
|
||||
{"current_steps": 780, "total_steps": 1290, "loss": 0.3442, "lr": 1.8565656640867448e-06, "epoch": 1.814663951120163, "percentage": 60.47, "elapsed_time": "2:02:56", "remaining_time": "1:20:23"}
|
||||
{"current_steps": 790, "total_steps": 1290, "loss": 0.3351, "lr": 1.7948297819450686e-06, "epoch": 1.8379400640093104, "percentage": 61.24, "elapsed_time": "2:04:31", "remaining_time": "1:18:48"}
|
||||
{"current_steps": 800, "total_steps": 1290, "loss": 0.3363, "lr": 1.7335576645443431e-06, "epoch": 1.8612161768984579, "percentage": 62.02, "elapsed_time": "2:06:12", "remaining_time": "1:17:17"}
|
||||
{"current_steps": 810, "total_steps": 1290, "loss": 0.32, "lr": 1.6727896083221161e-06, "epoch": 1.8844922897876055, "percentage": 62.79, "elapsed_time": "2:07:47", "remaining_time": "1:15:43"}
|
||||
{"current_steps": 820, "total_steps": 1290, "loss": 0.3131, "lr": 1.61256557821328e-06, "epoch": 1.907768402676753, "percentage": 63.57, "elapsed_time": "2:09:22", "remaining_time": "1:14:09"}
|
||||
{"current_steps": 830, "total_steps": 1290, "loss": 0.3146, "lr": 1.552925181366588e-06, "epoch": 1.9310445155659006, "percentage": 64.34, "elapsed_time": "2:10:55", "remaining_time": "1:12:33"}
|
||||
{"current_steps": 840, "total_steps": 1290, "loss": 0.3262, "lr": 1.4939076410964754e-06, "epoch": 1.954320628455048, "percentage": 65.12, "elapsed_time": "2:12:33", "remaining_time": "1:11:00"}
|
||||
{"current_steps": 850, "total_steps": 1290, "loss": 0.3265, "lr": 1.4355517710873184e-06, "epoch": 1.9775967413441955, "percentage": 65.89, "elapsed_time": "2:14:07", "remaining_time": "1:09:25"}
|
||||
{"current_steps": 860, "total_steps": 1290, "loss": 0.328, "lr": 1.377895949867088e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:15:35", "remaining_time": "1:07:47"}
|
||||
{"current_steps": 870, "total_steps": 1290, "loss": 0.2291, "lr": 1.3209780955671906e-06, "epoch": 2.0232761128891474, "percentage": 67.44, "elapsed_time": "2:17:11", "remaining_time": "1:06:13"}
|
||||
{"current_steps": 880, "total_steps": 1290, "loss": 0.2303, "lr": 1.264835640985096e-06, "epoch": 2.046552225778295, "percentage": 68.22, "elapsed_time": "2:18:42", "remaining_time": "1:04:37"}
|
||||
{"current_steps": 890, "total_steps": 1290, "loss": 0.2198, "lr": 1.2095055089661545e-06, "epoch": 2.0698283386674428, "percentage": 68.99, "elapsed_time": "2:20:14", "remaining_time": "1:03:01"}
|
||||
{"current_steps": 900, "total_steps": 1290, "loss": 0.2123, "lr": 1.1550240881207821e-06, "epoch": 2.09310445155659, "percentage": 69.77, "elapsed_time": "2:21:51", "remaining_time": "1:01:28"}
|
||||
{"current_steps": 910, "total_steps": 1290, "loss": 0.224, "lr": 1.1014272088930014e-06, "epoch": 2.1163805644457376, "percentage": 70.54, "elapsed_time": "2:23:25", "remaining_time": "0:59:53"}
|
||||
{"current_steps": 920, "total_steps": 1290, "loss": 0.2244, "lr": 1.048750119996066e-06, "epoch": 2.139656677334885, "percentage": 71.32, "elapsed_time": "2:25:03", "remaining_time": "0:58:20"}
|
||||
{"current_steps": 930, "total_steps": 1290, "loss": 0.2131, "lr": 9.970274652306667e-07, "epoch": 2.1629327902240325, "percentage": 72.09, "elapsed_time": "2:26:37", "remaining_time": "0:56:45"}
|
||||
{"current_steps": 940, "total_steps": 1290, "loss": 0.2307, "lr": 9.46293260700962e-07, "epoch": 2.18620890311318, "percentage": 72.87, "elapsed_time": "2:28:14", "remaining_time": "0:55:11"}
|
||||
{"current_steps": 950, "total_steps": 1290, "loss": 0.2132, "lr": 8.96580872443435e-07, "epoch": 2.2094850160023274, "percentage": 73.64, "elapsed_time": "2:29:50", "remaining_time": "0:53:37"}
|
||||
{"current_steps": 960, "total_steps": 1290, "loss": 0.2172, "lr": 8.479229944832601e-07, "epoch": 2.2327611288914753, "percentage": 74.42, "elapsed_time": "2:31:22", "remaining_time": "0:52:02"}
|
||||
{"current_steps": 970, "total_steps": 1290, "loss": 0.2117, "lr": 8.003516273326392e-07, "epoch": 2.2560372417806227, "percentage": 75.19, "elapsed_time": "2:32:57", "remaining_time": "0:50:27"}
|
||||
{"current_steps": 980, "total_steps": 1290, "loss": 0.2166, "lr": 7.538980569452314e-07, "epoch": 2.27931335466977, "percentage": 75.97, "elapsed_time": "2:34:31", "remaining_time": "0:48:52"}
|
||||
{"current_steps": 990, "total_steps": 1290, "loss": 0.2266, "lr": 7.085928341405193e-07, "epoch": 2.3025894675589176, "percentage": 76.74, "elapsed_time": "2:36:04", "remaining_time": "0:47:17"}
|
||||
{"current_steps": 1000, "total_steps": 1290, "loss": 0.2192, "lr": 6.644657545116528e-07, "epoch": 2.325865580448065, "percentage": 77.52, "elapsed_time": "2:37:41", "remaining_time": "0:45:43"}
|
||||
{"current_steps": 1010, "total_steps": 1290, "loss": 0.2119, "lr": 6.215458388299689e-07, "epoch": 2.349141693337213, "percentage": 78.29, "elapsed_time": "2:39:26", "remaining_time": "0:44:12"}
|
||||
{"current_steps": 1020, "total_steps": 1290, "loss": 0.207, "lr": 5.798613139590945e-07, "epoch": 2.3724178062263603, "percentage": 79.07, "elapsed_time": "2:40:59", "remaining_time": "0:42:36"}
|
||||
{"current_steps": 1030, "total_steps": 1290, "loss": 0.2184, "lr": 5.394395942911618e-07, "epoch": 2.3956939191155078, "percentage": 79.84, "elapsed_time": "2:42:35", "remaining_time": "0:41:02"}
|
||||
{"current_steps": 1040, "total_steps": 1290, "loss": 0.2125, "lr": 5.003072637173653e-07, "epoch": 2.418970032004655, "percentage": 80.62, "elapsed_time": "2:44:04", "remaining_time": "0:39:26"}
|
||||
{"current_steps": 1050, "total_steps": 1290, "loss": 0.211, "lr": 4.6249005814470616e-07, "epoch": 2.4422461448938027, "percentage": 81.4, "elapsed_time": "2:45:43", "remaining_time": "0:37:52"}
|
||||
{"current_steps": 1060, "total_steps": 1290, "loss": 0.2176, "lr": 4.2601284857042263e-07, "epoch": 2.46552225778295, "percentage": 82.17, "elapsed_time": "2:47:14", "remaining_time": "0:36:17"}
|
||||
{"current_steps": 1070, "total_steps": 1290, "loss": 0.2241, "lr": 3.908996247252422e-07, "epoch": 2.4887983706720975, "percentage": 82.95, "elapsed_time": "2:48:59", "remaining_time": "0:34:44"}
|
||||
{"current_steps": 1080, "total_steps": 1290, "loss": 0.2145, "lr": 3.5717347929621254e-07, "epoch": 2.5120744835612454, "percentage": 83.72, "elapsed_time": "2:50:35", "remaining_time": "0:33:10"}
|
||||
{"current_steps": 1090, "total_steps": 1290, "loss": 0.2144, "lr": 3.24856592739482e-07, "epoch": 2.535350596450393, "percentage": 84.5, "elapsed_time": "2:52:08", "remaining_time": "0:31:35"}
|
||||
{"current_steps": 1100, "total_steps": 1290, "loss": 0.2187, "lr": 2.9397021869302073e-07, "epoch": 2.5586267093395403, "percentage": 85.27, "elapsed_time": "2:53:40", "remaining_time": "0:29:59"}
|
||||
{"current_steps": 1110, "total_steps": 1290, "loss": 0.214, "lr": 2.6453466999887906e-07, "epoch": 2.5819028222286877, "percentage": 86.05, "elapsed_time": "2:55:16", "remaining_time": "0:28:25"}
|
||||
{"current_steps": 1120, "total_steps": 1290, "loss": 0.218, "lr": 2.365693053441742e-07, "epoch": 2.605178935117835, "percentage": 86.82, "elapsed_time": "2:56:54", "remaining_time": "0:26:51"}
|
||||
{"current_steps": 1130, "total_steps": 1290, "loss": 0.2179, "lr": 2.100925165295839e-07, "epoch": 2.628455048006983, "percentage": 87.6, "elapsed_time": "2:58:28", "remaining_time": "0:25:16"}
|
||||
{"current_steps": 1140, "total_steps": 1290, "loss": 0.2082, "lr": 1.851217163737315e-07, "epoch": 2.6517311608961305, "percentage": 88.37, "elapsed_time": "3:00:03", "remaining_time": "0:23:41"}
|
||||
{"current_steps": 1150, "total_steps": 1290, "loss": 0.2206, "lr": 1.6167332726141072e-07, "epoch": 2.675007273785278, "percentage": 89.15, "elapsed_time": "3:01:41", "remaining_time": "0:22:07"}
|
||||
{"current_steps": 1160, "total_steps": 1290, "loss": 0.2221, "lr": 1.3976277034317976e-07, "epoch": 2.6982833866744254, "percentage": 89.92, "elapsed_time": "3:03:14", "remaining_time": "0:20:32"}
|
||||
{"current_steps": 1170, "total_steps": 1290, "loss": 0.219, "lr": 1.1940445539343564e-07, "epoch": 2.721559499563573, "percentage": 90.7, "elapsed_time": "3:04:50", "remaining_time": "0:18:57"}
|
||||
{"current_steps": 1180, "total_steps": 1290, "loss": 0.2223, "lr": 1.0061177133362937e-07, "epoch": 2.7448356124527202, "percentage": 91.47, "elapsed_time": "3:06:25", "remaining_time": "0:17:22"}
|
||||
{"current_steps": 1190, "total_steps": 1290, "loss": 0.211, "lr": 8.33970774268597e-08, "epoch": 2.7681117253418677, "percentage": 92.25, "elapsed_time": "3:07:55", "remaining_time": "0:15:47"}
|
||||
{"current_steps": 1200, "total_steps": 1290, "loss": 0.2168, "lr": 6.777169514963766e-08, "epoch": 2.7913878382310156, "percentage": 93.02, "elapsed_time": "3:09:29", "remaining_time": "0:14:12"}
|
||||
{"current_steps": 1210, "total_steps": 1290, "loss": 0.2228, "lr": 5.3745900746165205e-08, "epoch": 2.814663951120163, "percentage": 93.8, "elapsed_time": "3:11:05", "remaining_time": "0:12:38"}
|
||||
{"current_steps": 1220, "total_steps": 1290, "loss": 0.2166, "lr": 4.132891847002107e-08, "epoch": 2.8379400640093104, "percentage": 94.57, "elapsed_time": "3:12:45", "remaining_time": "0:11:03"}
|
||||
{"current_steps": 1230, "total_steps": 1290, "loss": 0.2193, "lr": 3.052891451770873e-08, "epoch": 2.861216176898458, "percentage": 95.35, "elapsed_time": "3:14:15", "remaining_time": "0:09:28"}
|
||||
{"current_steps": 1240, "total_steps": 1290, "loss": 0.2142, "lr": 2.1352991658044885e-08, "epoch": 2.8844922897876053, "percentage": 96.12, "elapsed_time": "3:15:44", "remaining_time": "0:07:53"}
|
||||
{"current_steps": 1250, "total_steps": 1290, "loss": 0.2074, "lr": 1.3807184560927222e-08, "epoch": 2.907768402676753, "percentage": 96.9, "elapsed_time": "3:17:17", "remaining_time": "0:06:18"}
|
||||
{"current_steps": 1260, "total_steps": 1290, "loss": 0.2219, "lr": 7.896455828553528e-09, "epoch": 2.9310445155659006, "percentage": 97.67, "elapsed_time": "3:18:51", "remaining_time": "0:04:44"}
|
||||
{"current_steps": 1270, "total_steps": 1290, "loss": 0.2131, "lr": 3.6246927316976875e-09, "epoch": 2.954320628455048, "percentage": 98.45, "elapsed_time": "3:20:28", "remaining_time": "0:03:09"}
|
||||
{"current_steps": 1280, "total_steps": 1290, "loss": 0.235, "lr": 9.947046531944004e-10, "epoch": 2.9775967413441955, "percentage": 99.22, "elapsed_time": "3:22:00", "remaining_time": "0:01:34"}
|
||||
{"current_steps": 1290, "total_steps": 1290, "loss": 0.2024, "lr": 8.221240309636003e-12, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:23:31", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 1290, "total_steps": 1290, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:23:41", "remaining_time": "0:00:00"}
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 37 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