初始化项目，由ModelHub XC社区提供模型
Model: huseyinatahaninan/appworld_distillation_sft_v2-SFT-Qwen3-8B 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
|
||||
90
README.md
Normal file
90
README.md
Normal file
@@ -0,0 +1,90 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: appworld_distillation_sft_v2-SFT-Qwen3-8B
|
||||
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. -->
|
||||
|
||||
# appworld_distillation_sft_v2-SFT-Qwen3-8B
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the appworld_distillation_sft_v2 dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.6342
|
||||
|
||||
## 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: 1
|
||||
- eval_batch_size: 1
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 32
|
||||
- total_eval_batch_size: 8
|
||||
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 25.0
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 1.1697 | 1.0 | 2 | 1.2944 |
|
||||
| 1.0781 | 2.0 | 4 | 1.1407 |
|
||||
| 0.9806 | 3.0 | 6 | 1.0041 |
|
||||
| 0.9093 | 4.0 | 8 | 0.9051 |
|
||||
| 0.8595 | 5.0 | 10 | 0.8866 |
|
||||
| 0.7688 | 6.0 | 12 | 0.8013 |
|
||||
| 0.7223 | 7.0 | 14 | 0.7614 |
|
||||
| 0.689 | 8.0 | 16 | 0.7272 |
|
||||
| 0.6641 | 9.0 | 18 | 0.7127 |
|
||||
| 0.5795 | 10.0 | 20 | 0.6720 |
|
||||
| 0.5451 | 11.0 | 22 | 0.6551 |
|
||||
| 0.5059 | 12.0 | 24 | 0.6409 |
|
||||
| 0.5035 | 13.0 | 26 | 0.6352 |
|
||||
| 0.484 | 14.0 | 28 | 0.6281 |
|
||||
| 0.4436 | 15.0 | 30 | 0.6252 |
|
||||
| 0.4347 | 16.0 | 32 | 0.6250 |
|
||||
| 0.4139 | 17.0 | 34 | 0.6253 |
|
||||
| 0.4108 | 18.0 | 36 | 0.6265 |
|
||||
| 0.3969 | 19.0 | 38 | 0.6287 |
|
||||
| 0.3825 | 20.0 | 40 | 0.6303 |
|
||||
| 0.3839 | 21.0 | 42 | 0.6313 |
|
||||
| 0.3699 | 22.0 | 44 | 0.6326 |
|
||||
| 0.3871 | 23.0 | 46 | 0.6336 |
|
||||
| 0.382 | 24.0 | 48 | 0.6338 |
|
||||
| 0.3879 | 25.0 | 50 | 0.6342 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.52.4
|
||||
- Pytorch 2.8.0+cu128
|
||||
- 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
|
||||
}
|
||||
12
all_results.json
Normal file
12
all_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"eval_loss": 0.6342211961746216,
|
||||
"eval_runtime": 11.956,
|
||||
"eval_samples_per_second": 2.927,
|
||||
"eval_steps_per_second": 0.418,
|
||||
"total_flos": 9.581916505872794e+16,
|
||||
"train_loss": 0.6022347152233124,
|
||||
"train_runtime": 1896.7685,
|
||||
"train_samples_per_second": 0.685,
|
||||
"train_steps_per_second": 0.026
|
||||
}
|
||||
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
|
||||
}
|
||||
7
eval_results.json
Normal file
7
eval_results.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"eval_loss": 0.6342211961746216,
|
||||
"eval_runtime": 11.956,
|
||||
"eval_samples_per_second": 2.927,
|
||||
"eval_steps_per_second": 0.418
|
||||
}
|
||||
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:bb03707fe25d979a64c80952f4f12493ede8c74ff21b773f89331aed10af9101
|
||||
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 sha256:099aaaa6191a38bf44a69c18154203376fb284624b380d69812a6090721729be
|
||||
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 sha256:08d8d85c2e9ec2c1cfb3758fd66943d7c544ea8f19951e1300bb8550d806de26
|
||||
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 sha256:85a3958ea4ed8a477777512f5c9fe64f93252932d6344dfef3de0bc9f6b5899d
|
||||
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": 25.0,
|
||||
"total_flos": 9.581916505872794e+16,
|
||||
"train_loss": 0.6022347152233124,
|
||||
"train_runtime": 1896.7685,
|
||||
"train_samples_per_second": 0.685,
|
||||
"train_steps_per_second": 0.026
|
||||
}
|
||||
76
trainer_log.jsonl
Normal file
76
trainer_log.jsonl
Normal file
@@ -0,0 +1,76 @@
|
||||
{"current_steps": 1, "total_steps": 50, "loss": 1.2369, "lr": 0.0, "epoch": 0.5714285714285714, "percentage": 2.0, "elapsed_time": "0:00:41", "remaining_time": "0:33:58"}
|
||||
{"current_steps": 2, "total_steps": 50, "loss": 1.1697, "lr": 1.0000000000000002e-06, "epoch": 1.0, "percentage": 4.0, "elapsed_time": "0:01:08", "remaining_time": "0:27:23"}
|
||||
{"current_steps": 2, "total_steps": 50, "eval_loss": 1.2943594455718994, "epoch": 1.0, "percentage": 4.0, "elapsed_time": "0:01:22", "remaining_time": "0:32:59"}
|
||||
{"current_steps": 3, "total_steps": 50, "loss": 1.2156, "lr": 2.0000000000000003e-06, "epoch": 1.5714285714285714, "percentage": 6.0, "elapsed_time": "0:01:58", "remaining_time": "0:30:51"}
|
||||
{"current_steps": 4, "total_steps": 50, "loss": 1.0781, "lr": 3e-06, "epoch": 2.0, "percentage": 8.0, "elapsed_time": "0:02:24", "remaining_time": "0:27:43"}
|
||||
{"current_steps": 4, "total_steps": 50, "eval_loss": 1.1406848430633545, "epoch": 2.0, "percentage": 8.0, "elapsed_time": "0:02:36", "remaining_time": "0:30:02"}
|
||||
{"current_steps": 5, "total_steps": 50, "loss": 0.9982, "lr": 4.000000000000001e-06, "epoch": 2.571428571428571, "percentage": 10.0, "elapsed_time": "0:03:11", "remaining_time": "0:28:44"}
|
||||
{"current_steps": 6, "total_steps": 50, "loss": 0.9806, "lr": 5e-06, "epoch": 3.0, "percentage": 12.0, "elapsed_time": "0:03:37", "remaining_time": "0:26:35"}
|
||||
{"current_steps": 6, "total_steps": 50, "eval_loss": 1.0041135549545288, "epoch": 3.0, "percentage": 12.0, "elapsed_time": "0:03:49", "remaining_time": "0:28:03"}
|
||||
{"current_steps": 7, "total_steps": 50, "loss": 0.9273, "lr": 4.993910125649561e-06, "epoch": 3.571428571428571, "percentage": 14.0, "elapsed_time": "0:04:25", "remaining_time": "0:27:10"}
|
||||
{"current_steps": 8, "total_steps": 50, "loss": 0.9093, "lr": 4.975670171853926e-06, "epoch": 4.0, "percentage": 16.0, "elapsed_time": "0:04:50", "remaining_time": "0:25:26"}
|
||||
{"current_steps": 8, "total_steps": 50, "eval_loss": 0.9050876498222351, "epoch": 4.0, "percentage": 16.0, "elapsed_time": "0:05:02", "remaining_time": "0:26:29"}
|
||||
{"current_steps": 9, "total_steps": 50, "loss": 0.86, "lr": 4.9453690018345144e-06, "epoch": 4.571428571428571, "percentage": 18.0, "elapsed_time": "0:05:38", "remaining_time": "0:25:41"}
|
||||
{"current_steps": 10, "total_steps": 50, "loss": 0.8595, "lr": 4.903154239845798e-06, "epoch": 5.0, "percentage": 20.0, "elapsed_time": "0:06:02", "remaining_time": "0:24:09"}
|
||||
{"current_steps": 10, "total_steps": 50, "eval_loss": 0.8866418600082397, "epoch": 5.0, "percentage": 20.0, "elapsed_time": "0:06:14", "remaining_time": "0:24:58"}
|
||||
{"current_steps": 11, "total_steps": 50, "loss": 0.7986, "lr": 4.849231551964771e-06, "epoch": 5.571428571428571, "percentage": 22.0, "elapsed_time": "0:06:49", "remaining_time": "0:24:11"}
|
||||
{"current_steps": 12, "total_steps": 50, "loss": 0.7688, "lr": 4.783863644106502e-06, "epoch": 6.0, "percentage": 24.0, "elapsed_time": "0:07:16", "remaining_time": "0:23:02"}
|
||||
{"current_steps": 12, "total_steps": 50, "eval_loss": 0.8012941479682922, "epoch": 6.0, "percentage": 24.0, "elapsed_time": "0:07:28", "remaining_time": "0:23:40"}
|
||||
{"current_steps": 13, "total_steps": 50, "loss": 0.7405, "lr": 4.707368982147318e-06, "epoch": 6.571428571428571, "percentage": 26.0, "elapsed_time": "0:08:04", "remaining_time": "0:22:59"}
|
||||
{"current_steps": 14, "total_steps": 50, "loss": 0.7223, "lr": 4.620120240391065e-06, "epoch": 7.0, "percentage": 28.0, "elapsed_time": "0:08:29", "remaining_time": "0:21:50"}
|
||||
{"current_steps": 14, "total_steps": 50, "eval_loss": 0.7613986730575562, "epoch": 7.0, "percentage": 28.0, "elapsed_time": "0:08:41", "remaining_time": "0:22:21"}
|
||||
{"current_steps": 15, "total_steps": 50, "loss": 0.7031, "lr": 4.522542485937369e-06, "epoch": 7.571428571428571, "percentage": 30.0, "elapsed_time": "0:09:17", "remaining_time": "0:21:40"}
|
||||
{"current_steps": 16, "total_steps": 50, "loss": 0.689, "lr": 4.415111107797445e-06, "epoch": 8.0, "percentage": 32.0, "elapsed_time": "0:09:43", "remaining_time": "0:20:40"}
|
||||
{"current_steps": 16, "total_steps": 50, "eval_loss": 0.727152407169342, "epoch": 8.0, "percentage": 32.0, "elapsed_time": "0:09:55", "remaining_time": "0:21:06"}
|
||||
{"current_steps": 17, "total_steps": 50, "loss": 0.6511, "lr": 4.2983495008466285e-06, "epoch": 8.571428571428571, "percentage": 34.0, "elapsed_time": "0:10:30", "remaining_time": "0:20:23"}
|
||||
{"current_steps": 18, "total_steps": 50, "loss": 0.6641, "lr": 4.172826515897146e-06, "epoch": 9.0, "percentage": 36.0, "elapsed_time": "0:10:56", "remaining_time": "0:19:26"}
|
||||
{"current_steps": 18, "total_steps": 50, "eval_loss": 0.7126601934432983, "epoch": 9.0, "percentage": 36.0, "elapsed_time": "0:11:08", "remaining_time": "0:19:48"}
|
||||
{"current_steps": 19, "total_steps": 50, "loss": 0.6349, "lr": 4.039153688314146e-06, "epoch": 9.571428571428571, "percentage": 38.0, "elapsed_time": "0:11:43", "remaining_time": "0:19:07"}
|
||||
{"current_steps": 20, "total_steps": 50, "loss": 0.5795, "lr": 3.897982258676867e-06, "epoch": 10.0, "percentage": 40.0, "elapsed_time": "0:12:09", "remaining_time": "0:18:14"}
|
||||
{"current_steps": 20, "total_steps": 50, "eval_loss": 0.6720197796821594, "epoch": 10.0, "percentage": 40.0, "elapsed_time": "0:12:21", "remaining_time": "0:18:32"}
|
||||
{"current_steps": 21, "total_steps": 50, "loss": 0.5678, "lr": 3.7500000000000005e-06, "epoch": 10.571428571428571, "percentage": 42.0, "elapsed_time": "0:12:57", "remaining_time": "0:17:53"}
|
||||
{"current_steps": 22, "total_steps": 50, "loss": 0.5451, "lr": 3.595927866972694e-06, "epoch": 11.0, "percentage": 44.0, "elapsed_time": "0:13:24", "remaining_time": "0:17:03"}
|
||||
{"current_steps": 22, "total_steps": 50, "eval_loss": 0.655051589012146, "epoch": 11.0, "percentage": 44.0, "elapsed_time": "0:13:36", "remaining_time": "0:17:18"}
|
||||
{"current_steps": 23, "total_steps": 50, "loss": 0.5435, "lr": 3.436516483539781e-06, "epoch": 11.571428571428571, "percentage": 46.0, "elapsed_time": "0:14:11", "remaining_time": "0:16:40"}
|
||||
{"current_steps": 24, "total_steps": 50, "loss": 0.5059, "lr": 3.272542485937369e-06, "epoch": 12.0, "percentage": 48.0, "elapsed_time": "0:14:37", "remaining_time": "0:15:50"}
|
||||
{"current_steps": 24, "total_steps": 50, "eval_loss": 0.6408958435058594, "epoch": 12.0, "percentage": 48.0, "elapsed_time": "0:14:49", "remaining_time": "0:16:03"}
|
||||
{"current_steps": 25, "total_steps": 50, "loss": 0.5038, "lr": 3.1048047389991693e-06, "epoch": 12.571428571428571, "percentage": 50.0, "elapsed_time": "0:15:23", "remaining_time": "0:15:23"}
|
||||
{"current_steps": 26, "total_steps": 50, "loss": 0.5035, "lr": 2.9341204441673267e-06, "epoch": 13.0, "percentage": 52.0, "elapsed_time": "0:15:50", "remaining_time": "0:14:37"}
|
||||
{"current_steps": 26, "total_steps": 50, "eval_loss": 0.6351635456085205, "epoch": 13.0, "percentage": 52.0, "elapsed_time": "0:16:02", "remaining_time": "0:14:48"}
|
||||
{"current_steps": 27, "total_steps": 50, "loss": 0.489, "lr": 2.761321158169134e-06, "epoch": 13.571428571428571, "percentage": 54.0, "elapsed_time": "0:16:38", "remaining_time": "0:14:10"}
|
||||
{"current_steps": 28, "total_steps": 50, "loss": 0.484, "lr": 2.587248741756253e-06, "epoch": 14.0, "percentage": 56.0, "elapsed_time": "0:17:04", "remaining_time": "0:13:24"}
|
||||
{"current_steps": 28, "total_steps": 50, "eval_loss": 0.6280523538589478, "epoch": 14.0, "percentage": 56.0, "elapsed_time": "0:17:16", "remaining_time": "0:13:34"}
|
||||
{"current_steps": 29, "total_steps": 50, "loss": 0.4683, "lr": 2.4127512582437486e-06, "epoch": 14.571428571428571, "percentage": 58.0, "elapsed_time": "0:17:52", "remaining_time": "0:12:56"}
|
||||
{"current_steps": 30, "total_steps": 50, "loss": 0.4436, "lr": 2.238678841830867e-06, "epoch": 15.0, "percentage": 60.0, "elapsed_time": "0:18:18", "remaining_time": "0:12:12"}
|
||||
{"current_steps": 30, "total_steps": 50, "eval_loss": 0.6252209544181824, "epoch": 15.0, "percentage": 60.0, "elapsed_time": "0:18:30", "remaining_time": "0:12:20"}
|
||||
{"current_steps": 31, "total_steps": 50, "loss": 0.4466, "lr": 2.0658795558326745e-06, "epoch": 15.571428571428571, "percentage": 62.0, "elapsed_time": "0:19:05", "remaining_time": "0:11:42"}
|
||||
{"current_steps": 32, "total_steps": 50, "loss": 0.4347, "lr": 1.895195261000831e-06, "epoch": 16.0, "percentage": 64.0, "elapsed_time": "0:19:32", "remaining_time": "0:10:59"}
|
||||
{"current_steps": 32, "total_steps": 50, "eval_loss": 0.6249921321868896, "epoch": 16.0, "percentage": 64.0, "elapsed_time": "0:19:44", "remaining_time": "0:11:06"}
|
||||
{"current_steps": 33, "total_steps": 50, "loss": 0.4275, "lr": 1.7274575140626318e-06, "epoch": 16.571428571428573, "percentage": 66.0, "elapsed_time": "0:20:19", "remaining_time": "0:10:28"}
|
||||
{"current_steps": 34, "total_steps": 50, "loss": 0.4139, "lr": 1.56348351646022e-06, "epoch": 17.0, "percentage": 68.0, "elapsed_time": "0:20:45", "remaining_time": "0:09:45"}
|
||||
{"current_steps": 34, "total_steps": 50, "eval_loss": 0.6253374218940735, "epoch": 17.0, "percentage": 68.0, "elapsed_time": "0:20:57", "remaining_time": "0:09:51"}
|
||||
{"current_steps": 35, "total_steps": 50, "loss": 0.4033, "lr": 1.4040721330273063e-06, "epoch": 17.571428571428573, "percentage": 70.0, "elapsed_time": "0:21:33", "remaining_time": "0:09:14"}
|
||||
{"current_steps": 36, "total_steps": 50, "loss": 0.4108, "lr": 1.2500000000000007e-06, "epoch": 18.0, "percentage": 72.0, "elapsed_time": "0:21:58", "remaining_time": "0:08:32"}
|
||||
{"current_steps": 36, "total_steps": 50, "eval_loss": 0.6265431642532349, "epoch": 18.0, "percentage": 72.0, "elapsed_time": "0:22:11", "remaining_time": "0:08:37"}
|
||||
{"current_steps": 37, "total_steps": 50, "loss": 0.3948, "lr": 1.1020177413231334e-06, "epoch": 18.571428571428573, "percentage": 74.0, "elapsed_time": "0:22:45", "remaining_time": "0:07:59"}
|
||||
{"current_steps": 38, "total_steps": 50, "loss": 0.3969, "lr": 9.608463116858544e-07, "epoch": 19.0, "percentage": 76.0, "elapsed_time": "0:23:12", "remaining_time": "0:07:19"}
|
||||
{"current_steps": 38, "total_steps": 50, "eval_loss": 0.6287420392036438, "epoch": 19.0, "percentage": 76.0, "elapsed_time": "0:23:24", "remaining_time": "0:07:23"}
|
||||
{"current_steps": 39, "total_steps": 50, "loss": 0.3965, "lr": 8.271734841028553e-07, "epoch": 19.571428571428573, "percentage": 78.0, "elapsed_time": "0:23:59", "remaining_time": "0:06:45"}
|
||||
{"current_steps": 40, "total_steps": 50, "loss": 0.3825, "lr": 7.016504991533727e-07, "epoch": 20.0, "percentage": 80.0, "elapsed_time": "0:24:25", "remaining_time": "0:06:06"}
|
||||
{"current_steps": 40, "total_steps": 50, "eval_loss": 0.6303004026412964, "epoch": 20.0, "percentage": 80.0, "elapsed_time": "0:24:37", "remaining_time": "0:06:09"}
|
||||
{"current_steps": 41, "total_steps": 50, "loss": 0.3825, "lr": 5.848888922025553e-07, "epoch": 20.571428571428573, "percentage": 82.0, "elapsed_time": "0:25:14", "remaining_time": "0:05:32"}
|
||||
{"current_steps": 42, "total_steps": 50, "loss": 0.3839, "lr": 4.774575140626317e-07, "epoch": 21.0, "percentage": 84.0, "elapsed_time": "0:25:39", "remaining_time": "0:04:53"}
|
||||
{"current_steps": 42, "total_steps": 50, "eval_loss": 0.6313385367393494, "epoch": 21.0, "percentage": 84.0, "elapsed_time": "0:25:51", "remaining_time": "0:04:55"}
|
||||
{"current_steps": 43, "total_steps": 50, "loss": 0.3821, "lr": 3.798797596089351e-07, "epoch": 21.571428571428573, "percentage": 86.0, "elapsed_time": "0:26:25", "remaining_time": "0:04:18"}
|
||||
{"current_steps": 44, "total_steps": 50, "loss": 0.3699, "lr": 2.9263101785268253e-07, "epoch": 22.0, "percentage": 88.0, "elapsed_time": "0:26:51", "remaining_time": "0:03:39"}
|
||||
{"current_steps": 44, "total_steps": 50, "eval_loss": 0.6325893998146057, "epoch": 22.0, "percentage": 88.0, "elapsed_time": "0:27:03", "remaining_time": "0:03:41"}
|
||||
{"current_steps": 45, "total_steps": 50, "loss": 0.3652, "lr": 2.1613635589349756e-07, "epoch": 22.571428571428573, "percentage": 90.0, "elapsed_time": "0:27:39", "remaining_time": "0:03:04"}
|
||||
{"current_steps": 46, "total_steps": 50, "loss": 0.3871, "lr": 1.507684480352292e-07, "epoch": 23.0, "percentage": 92.0, "elapsed_time": "0:28:05", "remaining_time": "0:02:26"}
|
||||
{"current_steps": 46, "total_steps": 50, "eval_loss": 0.6336179971694946, "epoch": 23.0, "percentage": 92.0, "elapsed_time": "0:28:17", "remaining_time": "0:02:27"}
|
||||
{"current_steps": 47, "total_steps": 50, "loss": 0.3612, "lr": 9.684576015420277e-08, "epoch": 23.571428571428573, "percentage": 94.0, "elapsed_time": "0:28:52", "remaining_time": "0:01:50"}
|
||||
{"current_steps": 48, "total_steps": 50, "loss": 0.382, "lr": 5.463099816548578e-08, "epoch": 24.0, "percentage": 96.0, "elapsed_time": "0:29:19", "remaining_time": "0:01:13"}
|
||||
{"current_steps": 48, "total_steps": 50, "eval_loss": 0.6337578892707825, "epoch": 24.0, "percentage": 96.0, "elapsed_time": "0:29:31", "remaining_time": "0:01:13"}
|
||||
{"current_steps": 49, "total_steps": 50, "loss": 0.3611, "lr": 2.4329828146074096e-08, "epoch": 24.571428571428573, "percentage": 98.0, "elapsed_time": "0:30:07", "remaining_time": "0:00:36"}
|
||||
{"current_steps": 50, "total_steps": 50, "loss": 0.3879, "lr": 6.089874350439507e-09, "epoch": 25.0, "percentage": 100.0, "elapsed_time": "0:30:33", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 50, "total_steps": 50, "eval_loss": 0.6342211961746216, "epoch": 25.0, "percentage": 100.0, "elapsed_time": "0:31:34", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 50, "total_steps": 50, "epoch": 25.0, "percentage": 100.0, "elapsed_time": "0:31:34", "remaining_time": "0:00:00"}
|
||||
593
trainer_state.json
Normal file
593
trainer_state.json
Normal file
@@ -0,0 +1,593 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 25.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 50,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5714285714285714,
|
||||
"grad_norm": 27.379572188798917,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 1.2369,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 27.379572188798917,
|
||||
"learning_rate": 1.0000000000000002e-06,
|
||||
"loss": 1.1697,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 1.2943594455718994,
|
||||
"eval_runtime": 13.9947,
|
||||
"eval_samples_per_second": 2.501,
|
||||
"eval_steps_per_second": 0.357,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.5714285714285714,
|
||||
"grad_norm": 31.930876552830178,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"loss": 1.2156,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 24.003107200324983,
|
||||
"learning_rate": 3e-06,
|
||||
"loss": 1.0781,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"eval_loss": 1.1406848430633545,
|
||||
"eval_runtime": 12.0925,
|
||||
"eval_samples_per_second": 2.894,
|
||||
"eval_steps_per_second": 0.413,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 2.571428571428571,
|
||||
"grad_norm": 11.488887862580302,
|
||||
"learning_rate": 4.000000000000001e-06,
|
||||
"loss": 0.9982,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"grad_norm": 4.84397184489544,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 0.9806,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"eval_loss": 1.0041135549545288,
|
||||
"eval_runtime": 12.0103,
|
||||
"eval_samples_per_second": 2.914,
|
||||
"eval_steps_per_second": 0.416,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 3.571428571428571,
|
||||
"grad_norm": 3.7919066688172225,
|
||||
"learning_rate": 4.993910125649561e-06,
|
||||
"loss": 0.9273,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"grad_norm": 2.816005416926627,
|
||||
"learning_rate": 4.975670171853926e-06,
|
||||
"loss": 0.9093,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"eval_loss": 0.9050876498222351,
|
||||
"eval_runtime": 12.0336,
|
||||
"eval_samples_per_second": 2.909,
|
||||
"eval_steps_per_second": 0.416,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 4.571428571428571,
|
||||
"grad_norm": 1.8900642576089526,
|
||||
"learning_rate": 4.9453690018345144e-06,
|
||||
"loss": 0.86,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"grad_norm": 1.8900642576089526,
|
||||
"learning_rate": 4.903154239845798e-06,
|
||||
"loss": 0.8595,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"eval_loss": 0.8866418600082397,
|
||||
"eval_runtime": 12.0514,
|
||||
"eval_samples_per_second": 2.904,
|
||||
"eval_steps_per_second": 0.415,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 5.571428571428571,
|
||||
"grad_norm": 2.388409790695317,
|
||||
"learning_rate": 4.849231551964771e-06,
|
||||
"loss": 0.7986,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"grad_norm": 1.9351948554401477,
|
||||
"learning_rate": 4.783863644106502e-06,
|
||||
"loss": 0.7688,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"eval_loss": 0.8012941479682922,
|
||||
"eval_runtime": 12.0289,
|
||||
"eval_samples_per_second": 2.91,
|
||||
"eval_steps_per_second": 0.416,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 6.571428571428571,
|
||||
"grad_norm": 1.9475837570279504,
|
||||
"learning_rate": 4.707368982147318e-06,
|
||||
"loss": 0.7405,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"grad_norm": 1.7205847922715594,
|
||||
"learning_rate": 4.620120240391065e-06,
|
||||
"loss": 0.7223,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"eval_loss": 0.7613986730575562,
|
||||
"eval_runtime": 12.0755,
|
||||
"eval_samples_per_second": 2.898,
|
||||
"eval_steps_per_second": 0.414,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 7.571428571428571,
|
||||
"grad_norm": 1.3353634306020017,
|
||||
"learning_rate": 4.522542485937369e-06,
|
||||
"loss": 0.7031,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"grad_norm": 1.3800382206930182,
|
||||
"learning_rate": 4.415111107797445e-06,
|
||||
"loss": 0.689,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"eval_loss": 0.727152407169342,
|
||||
"eval_runtime": 11.966,
|
||||
"eval_samples_per_second": 2.925,
|
||||
"eval_steps_per_second": 0.418,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 8.571428571428571,
|
||||
"grad_norm": 0.9321182321446594,
|
||||
"learning_rate": 4.2983495008466285e-06,
|
||||
"loss": 0.6511,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"grad_norm": 0.9321182321446594,
|
||||
"learning_rate": 4.172826515897146e-06,
|
||||
"loss": 0.6641,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"eval_loss": 0.7126601934432983,
|
||||
"eval_runtime": 12.059,
|
||||
"eval_samples_per_second": 2.902,
|
||||
"eval_steps_per_second": 0.415,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 9.571428571428571,
|
||||
"grad_norm": 1.284468249112213,
|
||||
"learning_rate": 4.039153688314146e-06,
|
||||
"loss": 0.6349,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"grad_norm": 1.209401710296371,
|
||||
"learning_rate": 3.897982258676867e-06,
|
||||
"loss": 0.5795,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"eval_loss": 0.6720197796821594,
|
||||
"eval_runtime": 12.0161,
|
||||
"eval_samples_per_second": 2.913,
|
||||
"eval_steps_per_second": 0.416,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 10.571428571428571,
|
||||
"grad_norm": 1.5344113073991625,
|
||||
"learning_rate": 3.7500000000000005e-06,
|
||||
"loss": 0.5678,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"grad_norm": 1.086081561802662,
|
||||
"learning_rate": 3.595927866972694e-06,
|
||||
"loss": 0.5451,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"eval_loss": 0.655051589012146,
|
||||
"eval_runtime": 12.1049,
|
||||
"eval_samples_per_second": 2.891,
|
||||
"eval_steps_per_second": 0.413,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 11.571428571428571,
|
||||
"grad_norm": 1.3512413194371768,
|
||||
"learning_rate": 3.436516483539781e-06,
|
||||
"loss": 0.5435,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"grad_norm": 1.1140031619845532,
|
||||
"learning_rate": 3.272542485937369e-06,
|
||||
"loss": 0.5059,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"eval_loss": 0.6408958435058594,
|
||||
"eval_runtime": 12.063,
|
||||
"eval_samples_per_second": 2.901,
|
||||
"eval_steps_per_second": 0.414,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 12.571428571428571,
|
||||
"grad_norm": 0.9212734048420463,
|
||||
"learning_rate": 3.1048047389991693e-06,
|
||||
"loss": 0.5038,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"grad_norm": 0.9212734048420463,
|
||||
"learning_rate": 2.9341204441673267e-06,
|
||||
"loss": 0.5035,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"eval_loss": 0.6351635456085205,
|
||||
"eval_runtime": 12.0596,
|
||||
"eval_samples_per_second": 2.902,
|
||||
"eval_steps_per_second": 0.415,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 13.571428571428571,
|
||||
"grad_norm": 1.1395169936217417,
|
||||
"learning_rate": 2.761321158169134e-06,
|
||||
"loss": 0.489,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"grad_norm": 0.8506966891650993,
|
||||
"learning_rate": 2.587248741756253e-06,
|
||||
"loss": 0.484,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"eval_loss": 0.6280523538589478,
|
||||
"eval_runtime": 12.0505,
|
||||
"eval_samples_per_second": 2.904,
|
||||
"eval_steps_per_second": 0.415,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 14.571428571428571,
|
||||
"grad_norm": 0.9887201931904582,
|
||||
"learning_rate": 2.4127512582437486e-06,
|
||||
"loss": 0.4683,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"grad_norm": 0.9155854743888291,
|
||||
"learning_rate": 2.238678841830867e-06,
|
||||
"loss": 0.4436,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"eval_loss": 0.6252209544181824,
|
||||
"eval_runtime": 12.0701,
|
||||
"eval_samples_per_second": 2.9,
|
||||
"eval_steps_per_second": 0.414,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 15.571428571428571,
|
||||
"grad_norm": 1.01480533363197,
|
||||
"learning_rate": 2.0658795558326745e-06,
|
||||
"loss": 0.4466,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"grad_norm": 0.940925597770304,
|
||||
"learning_rate": 1.895195261000831e-06,
|
||||
"loss": 0.4347,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"eval_loss": 0.6249921321868896,
|
||||
"eval_runtime": 12.0063,
|
||||
"eval_samples_per_second": 2.915,
|
||||
"eval_steps_per_second": 0.416,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 16.571428571428573,
|
||||
"grad_norm": 0.745543391044636,
|
||||
"learning_rate": 1.7274575140626318e-06,
|
||||
"loss": 0.4275,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"grad_norm": 0.745543391044636,
|
||||
"learning_rate": 1.56348351646022e-06,
|
||||
"loss": 0.4139,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"eval_loss": 0.6253374218940735,
|
||||
"eval_runtime": 12.0584,
|
||||
"eval_samples_per_second": 2.903,
|
||||
"eval_steps_per_second": 0.415,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 17.571428571428573,
|
||||
"grad_norm": 1.240672425729672,
|
||||
"learning_rate": 1.4040721330273063e-06,
|
||||
"loss": 0.4033,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"grad_norm": 0.8138297069132504,
|
||||
"learning_rate": 1.2500000000000007e-06,
|
||||
"loss": 0.4108,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"eval_loss": 0.6265431642532349,
|
||||
"eval_runtime": 12.0931,
|
||||
"eval_samples_per_second": 2.894,
|
||||
"eval_steps_per_second": 0.413,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 18.571428571428573,
|
||||
"grad_norm": 1.0257247393101925,
|
||||
"learning_rate": 1.1020177413231334e-06,
|
||||
"loss": 0.3948,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"grad_norm": 0.8730540573897112,
|
||||
"learning_rate": 9.608463116858544e-07,
|
||||
"loss": 0.3969,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"eval_loss": 0.6287420392036438,
|
||||
"eval_runtime": 12.0278,
|
||||
"eval_samples_per_second": 2.91,
|
||||
"eval_steps_per_second": 0.416,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 19.571428571428573,
|
||||
"grad_norm": 0.9053129240846155,
|
||||
"learning_rate": 8.271734841028553e-07,
|
||||
"loss": 0.3965,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"grad_norm": 0.9013824277926773,
|
||||
"learning_rate": 7.016504991533727e-07,
|
||||
"loss": 0.3825,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"eval_loss": 0.6303004026412964,
|
||||
"eval_runtime": 12.1106,
|
||||
"eval_samples_per_second": 2.89,
|
||||
"eval_steps_per_second": 0.413,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 20.571428571428573,
|
||||
"grad_norm": 0.6882077843880618,
|
||||
"learning_rate": 5.848888922025553e-07,
|
||||
"loss": 0.3825,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"grad_norm": 0.6882077843880618,
|
||||
"learning_rate": 4.774575140626317e-07,
|
||||
"loss": 0.3839,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"eval_loss": 0.6313385367393494,
|
||||
"eval_runtime": 11.905,
|
||||
"eval_samples_per_second": 2.94,
|
||||
"eval_steps_per_second": 0.42,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 21.571428571428573,
|
||||
"grad_norm": 1.0040896510913107,
|
||||
"learning_rate": 3.798797596089351e-07,
|
||||
"loss": 0.3821,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"grad_norm": 0.8312442360781623,
|
||||
"learning_rate": 2.9263101785268253e-07,
|
||||
"loss": 0.3699,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"eval_loss": 0.6325893998146057,
|
||||
"eval_runtime": 11.9284,
|
||||
"eval_samples_per_second": 2.934,
|
||||
"eval_steps_per_second": 0.419,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 22.571428571428573,
|
||||
"grad_norm": 0.8906586628247445,
|
||||
"learning_rate": 2.1613635589349756e-07,
|
||||
"loss": 0.3652,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"grad_norm": 0.8407663191838467,
|
||||
"learning_rate": 1.507684480352292e-07,
|
||||
"loss": 0.3871,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"eval_loss": 0.6336179971694946,
|
||||
"eval_runtime": 11.9514,
|
||||
"eval_samples_per_second": 2.929,
|
||||
"eval_steps_per_second": 0.418,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 23.571428571428573,
|
||||
"grad_norm": 0.8820384716444405,
|
||||
"learning_rate": 9.684576015420277e-08,
|
||||
"loss": 0.3612,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"grad_norm": 0.9165057903043542,
|
||||
"learning_rate": 5.463099816548578e-08,
|
||||
"loss": 0.382,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"eval_loss": 0.6337578892707825,
|
||||
"eval_runtime": 11.8972,
|
||||
"eval_samples_per_second": 2.942,
|
||||
"eval_steps_per_second": 0.42,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 24.571428571428573,
|
||||
"grad_norm": 0.7173736876587623,
|
||||
"learning_rate": 2.4329828146074096e-08,
|
||||
"loss": 0.3611,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"grad_norm": 0.7173736876587623,
|
||||
"learning_rate": 6.089874350439507e-09,
|
||||
"loss": 0.3879,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"eval_loss": 0.6342211961746216,
|
||||
"eval_runtime": 12.0027,
|
||||
"eval_samples_per_second": 2.916,
|
||||
"eval_steps_per_second": 0.417,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"step": 50,
|
||||
"total_flos": 9.581916505872794e+16,
|
||||
"train_loss": 0.6022347152233124,
|
||||
"train_runtime": 1896.7685,
|
||||
"train_samples_per_second": 0.685,
|
||||
"train_steps_per_second": 0.026
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 50,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 25,
|
||||
"save_steps": 2000000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 9.581916505872794e+16,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5975f322175807a5800830df9d11f42a5902a6fb29bfa6fa014c5fe6102dad2a
|
||||
size 8017
|
||||
BIN
training_eval_loss.png
Normal file
BIN
training_eval_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 30 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 31 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