初始化项目，由ModelHub XC社区提供模型
Model: huseyinatahaninan/appworld_distillation_sft_v2-SFT-Qwen3-4B-Instruct-2507 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
|
||||
94
README.md
Normal file
94
README.md
Normal file
@@ -0,0 +1,94 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: appworld_distillation_sft_v2-SFT-Qwen3-4B-Instruct-2507
|
||||
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-Qwen3-4B-Instruct-2507
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the appworld_distillation_sft_v2 dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.7486
|
||||
|
||||
## 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: 4
|
||||
- eval_batch_size: 1
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- 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: 30.0
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 1.7313 | 1.0 | 2 | 1.7900 |
|
||||
| 1.6378 | 2.0 | 4 | 1.5365 |
|
||||
| 1.1356 | 3.0 | 6 | 1.1186 |
|
||||
| 0.9041 | 4.0 | 8 | 0.9372 |
|
||||
| 0.8762 | 5.0 | 10 | 0.8529 |
|
||||
| 0.7807 | 6.0 | 12 | 0.8198 |
|
||||
| 0.7323 | 7.0 | 14 | 0.7646 |
|
||||
| 0.6814 | 8.0 | 16 | 0.7229 |
|
||||
| 0.6211 | 9.0 | 18 | 0.6847 |
|
||||
| 0.5738 | 10.0 | 20 | 0.6639 |
|
||||
| 0.5171 | 11.0 | 22 | 0.6499 |
|
||||
| 0.4868 | 12.0 | 24 | 0.6385 |
|
||||
| 0.4371 | 13.0 | 26 | 0.6327 |
|
||||
| 0.407 | 14.0 | 28 | 0.6306 |
|
||||
| 0.3924 | 15.0 | 30 | 0.6330 |
|
||||
| 0.3505 | 16.0 | 32 | 0.6393 |
|
||||
| 0.3339 | 17.0 | 34 | 0.6493 |
|
||||
| 0.3086 | 18.0 | 36 | 0.6623 |
|
||||
| 0.2803 | 19.0 | 38 | 0.6748 |
|
||||
| 0.2687 | 20.0 | 40 | 0.6873 |
|
||||
| 0.25 | 21.0 | 42 | 0.6983 |
|
||||
| 0.2306 | 22.0 | 44 | 0.7100 |
|
||||
| 0.2168 | 23.0 | 46 | 0.7205 |
|
||||
| 0.2125 | 24.0 | 48 | 0.7301 |
|
||||
| 0.2031 | 25.0 | 50 | 0.7378 |
|
||||
| 0.1975 | 26.0 | 52 | 0.7433 |
|
||||
| 0.2001 | 27.0 | 54 | 0.7474 |
|
||||
| 0.1953 | 28.0 | 56 | 0.7487 |
|
||||
| 0.1895 | 29.0 | 58 | 0.7487 |
|
||||
| 0.1976 | 30.0 | 60 | 0.7486 |
|
||||
|
||||
|
||||
### 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": 30.0,
|
||||
"eval_loss": 0.7485920190811157,
|
||||
"eval_runtime": 7.2071,
|
||||
"eval_samples_per_second": 4.856,
|
||||
"eval_steps_per_second": 0.694,
|
||||
"total_flos": 1.0166485230865613e+18,
|
||||
"train_loss": 0.5314400238295396,
|
||||
"train_runtime": 1496.8474,
|
||||
"train_samples_per_second": 1.022,
|
||||
"train_steps_per_second": 0.04
|
||||
}
|
||||
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
|
||||
}
|
||||
7
eval_results.json
Normal file
7
eval_results.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"epoch": 30.0,
|
||||
"eval_loss": 0.7485920190811157,
|
||||
"eval_runtime": 7.2071,
|
||||
"eval_samples_per_second": 4.856,
|
||||
"eval_steps_per_second": 0.694
|
||||
}
|
||||
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 sha256:4ea65744901e731a3c465842b3247fc0e5258e17a382767950b1f6768c231e40
|
||||
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 sha256:394e2002569ad6a20f4cf4a4a5ab3c5be8bea1a7a81c7994f8c66e66a4a4b4f1
|
||||
size 3855679144
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 8822848512
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 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": 30.0,
|
||||
"total_flos": 1.0166485230865613e+18,
|
||||
"train_loss": 0.5314400238295396,
|
||||
"train_runtime": 1496.8474,
|
||||
"train_samples_per_second": 1.022,
|
||||
"train_steps_per_second": 0.04
|
||||
}
|
||||
91
trainer_log.jsonl
Normal file
91
trainer_log.jsonl
Normal file
@@ -0,0 +1,91 @@
|
||||
{"current_steps": 1, "total_steps": 60, "loss": 1.669, "lr": 0.0, "epoch": 0.5, "percentage": 1.67, "elapsed_time": "0:01:03", "remaining_time": "1:02:35"}
|
||||
{"current_steps": 2, "total_steps": 60, "loss": 1.7313, "lr": 8.333333333333333e-07, "epoch": 1.0, "percentage": 3.33, "elapsed_time": "0:01:23", "remaining_time": "0:40:12"}
|
||||
{"current_steps": 2, "total_steps": 60, "eval_loss": 1.7900009155273438, "epoch": 1.0, "percentage": 3.33, "elapsed_time": "0:01:30", "remaining_time": "0:43:52"}
|
||||
{"current_steps": 3, "total_steps": 60, "loss": 1.662, "lr": 1.6666666666666667e-06, "epoch": 1.5, "percentage": 5.0, "elapsed_time": "0:01:50", "remaining_time": "0:35:01"}
|
||||
{"current_steps": 4, "total_steps": 60, "loss": 1.6378, "lr": 2.5e-06, "epoch": 2.0, "percentage": 6.67, "elapsed_time": "0:02:09", "remaining_time": "0:30:14"}
|
||||
{"current_steps": 4, "total_steps": 60, "eval_loss": 1.5364655256271362, "epoch": 2.0, "percentage": 6.67, "elapsed_time": "0:02:17", "remaining_time": "0:31:58"}
|
||||
{"current_steps": 5, "total_steps": 60, "loss": 1.4225, "lr": 3.3333333333333333e-06, "epoch": 2.5, "percentage": 8.33, "elapsed_time": "0:02:37", "remaining_time": "0:28:47"}
|
||||
{"current_steps": 6, "total_steps": 60, "loss": 1.1356, "lr": 4.166666666666667e-06, "epoch": 3.0, "percentage": 10.0, "elapsed_time": "0:02:55", "remaining_time": "0:26:22"}
|
||||
{"current_steps": 6, "total_steps": 60, "eval_loss": 1.1185977458953857, "epoch": 3.0, "percentage": 10.0, "elapsed_time": "0:03:03", "remaining_time": "0:27:29"}
|
||||
{"current_steps": 7, "total_steps": 60, "loss": 1.0871, "lr": 5e-06, "epoch": 3.5, "percentage": 11.67, "elapsed_time": "0:03:23", "remaining_time": "0:25:38"}
|
||||
{"current_steps": 8, "total_steps": 60, "loss": 0.9041, "lr": 4.995770395678171e-06, "epoch": 4.0, "percentage": 13.33, "elapsed_time": "0:03:42", "remaining_time": "0:24:08"}
|
||||
{"current_steps": 8, "total_steps": 60, "eval_loss": 0.9372425079345703, "epoch": 4.0, "percentage": 13.33, "elapsed_time": "0:03:50", "remaining_time": "0:24:57"}
|
||||
{"current_steps": 9, "total_steps": 60, "loss": 0.8773, "lr": 4.983095894354858e-06, "epoch": 4.5, "percentage": 15.0, "elapsed_time": "0:04:11", "remaining_time": "0:23:42"}
|
||||
{"current_steps": 10, "total_steps": 60, "loss": 0.8762, "lr": 4.962019382530521e-06, "epoch": 5.0, "percentage": 16.67, "elapsed_time": "0:04:30", "remaining_time": "0:22:34"}
|
||||
{"current_steps": 10, "total_steps": 60, "eval_loss": 0.8529078364372253, "epoch": 5.0, "percentage": 16.67, "elapsed_time": "0:04:38", "remaining_time": "0:23:11"}
|
||||
{"current_steps": 11, "total_steps": 60, "loss": 0.8024, "lr": 4.93261217644956e-06, "epoch": 5.5, "percentage": 18.33, "elapsed_time": "0:04:58", "remaining_time": "0:22:11"}
|
||||
{"current_steps": 12, "total_steps": 60, "loss": 0.7807, "lr": 4.894973780788722e-06, "epoch": 6.0, "percentage": 20.0, "elapsed_time": "0:05:19", "remaining_time": "0:21:19"}
|
||||
{"current_steps": 12, "total_steps": 60, "eval_loss": 0.8198402523994446, "epoch": 6.0, "percentage": 20.0, "elapsed_time": "0:05:27", "remaining_time": "0:21:49"}
|
||||
{"current_steps": 13, "total_steps": 60, "loss": 0.758, "lr": 4.849231551964771e-06, "epoch": 6.5, "percentage": 21.67, "elapsed_time": "0:05:47", "remaining_time": "0:20:55"}
|
||||
{"current_steps": 14, "total_steps": 60, "loss": 0.7323, "lr": 4.7955402672006855e-06, "epoch": 7.0, "percentage": 23.33, "elapsed_time": "0:06:07", "remaining_time": "0:20:08"}
|
||||
{"current_steps": 14, "total_steps": 60, "eval_loss": 0.7645982503890991, "epoch": 7.0, "percentage": 23.33, "elapsed_time": "0:06:15", "remaining_time": "0:20:32"}
|
||||
{"current_steps": 15, "total_steps": 60, "loss": 0.7175, "lr": 4.734081600808531e-06, "epoch": 7.5, "percentage": 25.0, "elapsed_time": "0:06:35", "remaining_time": "0:19:46"}
|
||||
{"current_steps": 16, "total_steps": 60, "loss": 0.6814, "lr": 4.665063509461098e-06, "epoch": 8.0, "percentage": 26.67, "elapsed_time": "0:06:55", "remaining_time": "0:19:03"}
|
||||
{"current_steps": 16, "total_steps": 60, "eval_loss": 0.7229499816894531, "epoch": 8.0, "percentage": 26.67, "elapsed_time": "0:07:03", "remaining_time": "0:19:24"}
|
||||
{"current_steps": 17, "total_steps": 60, "loss": 0.6536, "lr": 4.588719528532342e-06, "epoch": 8.5, "percentage": 28.33, "elapsed_time": "0:07:24", "remaining_time": "0:18:43"}
|
||||
{"current_steps": 18, "total_steps": 60, "loss": 0.6211, "lr": 4.50530798188761e-06, "epoch": 9.0, "percentage": 30.0, "elapsed_time": "0:07:44", "remaining_time": "0:18:03"}
|
||||
{"current_steps": 18, "total_steps": 60, "eval_loss": 0.6847367882728577, "epoch": 9.0, "percentage": 30.0, "elapsed_time": "0:07:51", "remaining_time": "0:18:21"}
|
||||
{"current_steps": 19, "total_steps": 60, "loss": 0.5956, "lr": 4.415111107797445e-06, "epoch": 9.5, "percentage": 31.67, "elapsed_time": "0:08:13", "remaining_time": "0:17:44"}
|
||||
{"current_steps": 20, "total_steps": 60, "loss": 0.5738, "lr": 4.318434103932622e-06, "epoch": 10.0, "percentage": 33.33, "elapsed_time": "0:08:32", "remaining_time": "0:17:04"}
|
||||
{"current_steps": 20, "total_steps": 60, "eval_loss": 0.6638691425323486, "epoch": 10.0, "percentage": 33.33, "elapsed_time": "0:08:39", "remaining_time": "0:17:19"}
|
||||
{"current_steps": 21, "total_steps": 60, "loss": 0.5499, "lr": 4.215604094671835e-06, "epoch": 10.5, "percentage": 35.0, "elapsed_time": "0:08:59", "remaining_time": "0:16:41"}
|
||||
{"current_steps": 22, "total_steps": 60, "loss": 0.5171, "lr": 4.106969024216348e-06, "epoch": 11.0, "percentage": 36.67, "elapsed_time": "0:09:19", "remaining_time": "0:16:07"}
|
||||
{"current_steps": 22, "total_steps": 60, "eval_loss": 0.6498724222183228, "epoch": 11.0, "percentage": 36.67, "elapsed_time": "0:09:27", "remaining_time": "0:16:20"}
|
||||
{"current_steps": 23, "total_steps": 60, "loss": 0.5088, "lr": 3.992896479256966e-06, "epoch": 11.5, "percentage": 38.33, "elapsed_time": "0:09:46", "remaining_time": "0:15:43"}
|
||||
{"current_steps": 24, "total_steps": 60, "loss": 0.4868, "lr": 3.8737724451770155e-06, "epoch": 12.0, "percentage": 40.0, "elapsed_time": "0:10:06", "remaining_time": "0:15:09"}
|
||||
{"current_steps": 24, "total_steps": 60, "eval_loss": 0.6385172605514526, "epoch": 12.0, "percentage": 40.0, "elapsed_time": "0:10:13", "remaining_time": "0:15:20"}
|
||||
{"current_steps": 25, "total_steps": 60, "loss": 0.4697, "lr": 3.7500000000000005e-06, "epoch": 12.5, "percentage": 41.67, "elapsed_time": "0:10:33", "remaining_time": "0:14:46"}
|
||||
{"current_steps": 26, "total_steps": 60, "loss": 0.4371, "lr": 3.621997950501156e-06, "epoch": 13.0, "percentage": 43.33, "elapsed_time": "0:10:52", "remaining_time": "0:14:13"}
|
||||
{"current_steps": 26, "total_steps": 60, "eval_loss": 0.6327239871025085, "epoch": 13.0, "percentage": 43.33, "elapsed_time": "0:11:00", "remaining_time": "0:14:23"}
|
||||
{"current_steps": 27, "total_steps": 60, "loss": 0.4361, "lr": 3.4901994150978926e-06, "epoch": 13.5, "percentage": 45.0, "elapsed_time": "0:11:20", "remaining_time": "0:13:51"}
|
||||
{"current_steps": 28, "total_steps": 60, "loss": 0.407, "lr": 3.3550503583141726e-06, "epoch": 14.0, "percentage": 46.67, "elapsed_time": "0:11:39", "remaining_time": "0:13:19"}
|
||||
{"current_steps": 28, "total_steps": 60, "eval_loss": 0.6305895447731018, "epoch": 14.0, "percentage": 46.67, "elapsed_time": "0:11:46", "remaining_time": "0:13:27"}
|
||||
{"current_steps": 29, "total_steps": 60, "loss": 0.4015, "lr": 3.217008081777726e-06, "epoch": 14.5, "percentage": 48.33, "elapsed_time": "0:12:06", "remaining_time": "0:12:56"}
|
||||
{"current_steps": 30, "total_steps": 60, "loss": 0.3924, "lr": 3.0765396768561005e-06, "epoch": 15.0, "percentage": 50.0, "elapsed_time": "0:12:26", "remaining_time": "0:12:26"}
|
||||
{"current_steps": 30, "total_steps": 60, "eval_loss": 0.6329755187034607, "epoch": 15.0, "percentage": 50.0, "elapsed_time": "0:12:34", "remaining_time": "0:12:34"}
|
||||
{"current_steps": 31, "total_steps": 60, "loss": 0.378, "lr": 2.9341204441673267e-06, "epoch": 15.5, "percentage": 51.67, "elapsed_time": "0:12:55", "remaining_time": "0:12:05"}
|
||||
{"current_steps": 32, "total_steps": 60, "loss": 0.3505, "lr": 2.7902322853130758e-06, "epoch": 16.0, "percentage": 53.33, "elapsed_time": "0:13:15", "remaining_time": "0:11:35"}
|
||||
{"current_steps": 32, "total_steps": 60, "eval_loss": 0.6392822861671448, "epoch": 16.0, "percentage": 53.33, "elapsed_time": "0:13:22", "remaining_time": "0:11:42"}
|
||||
{"current_steps": 33, "total_steps": 60, "loss": 0.3475, "lr": 2.6453620722761897e-06, "epoch": 16.5, "percentage": 55.0, "elapsed_time": "0:13:42", "remaining_time": "0:11:13"}
|
||||
{"current_steps": 34, "total_steps": 60, "loss": 0.3339, "lr": 2.5e-06, "epoch": 17.0, "percentage": 56.67, "elapsed_time": "0:14:03", "remaining_time": "0:10:44"}
|
||||
{"current_steps": 34, "total_steps": 60, "eval_loss": 0.6492648124694824, "epoch": 17.0, "percentage": 56.67, "elapsed_time": "0:14:10", "remaining_time": "0:10:50"}
|
||||
{"current_steps": 35, "total_steps": 60, "loss": 0.3202, "lr": 2.3546379277238107e-06, "epoch": 17.5, "percentage": 58.33, "elapsed_time": "0:14:30", "remaining_time": "0:10:21"}
|
||||
{"current_steps": 36, "total_steps": 60, "loss": 0.3086, "lr": 2.2097677146869242e-06, "epoch": 18.0, "percentage": 60.0, "elapsed_time": "0:14:50", "remaining_time": "0:09:53"}
|
||||
{"current_steps": 36, "total_steps": 60, "eval_loss": 0.6622989773750305, "epoch": 18.0, "percentage": 60.0, "elapsed_time": "0:14:57", "remaining_time": "0:09:58"}
|
||||
{"current_steps": 37, "total_steps": 60, "loss": 0.3004, "lr": 2.0658795558326745e-06, "epoch": 18.5, "percentage": 61.67, "elapsed_time": "0:15:17", "remaining_time": "0:09:30"}
|
||||
{"current_steps": 38, "total_steps": 60, "loss": 0.2803, "lr": 1.9234603231439e-06, "epoch": 19.0, "percentage": 63.33, "elapsed_time": "0:15:37", "remaining_time": "0:09:02"}
|
||||
{"current_steps": 38, "total_steps": 60, "eval_loss": 0.6748006343841553, "epoch": 19.0, "percentage": 63.33, "elapsed_time": "0:15:45", "remaining_time": "0:09:07"}
|
||||
{"current_steps": 39, "total_steps": 60, "loss": 0.2751, "lr": 1.7829919182222752e-06, "epoch": 19.5, "percentage": 65.0, "elapsed_time": "0:16:05", "remaining_time": "0:08:39"}
|
||||
{"current_steps": 40, "total_steps": 60, "loss": 0.2687, "lr": 1.6449496416858285e-06, "epoch": 20.0, "percentage": 66.67, "elapsed_time": "0:16:24", "remaining_time": "0:08:12"}
|
||||
{"current_steps": 40, "total_steps": 60, "eval_loss": 0.6873091459274292, "epoch": 20.0, "percentage": 66.67, "elapsed_time": "0:16:32", "remaining_time": "0:08:16"}
|
||||
{"current_steps": 41, "total_steps": 60, "loss": 0.2556, "lr": 1.509800584902108e-06, "epoch": 20.5, "percentage": 68.33, "elapsed_time": "0:16:52", "remaining_time": "0:07:49"}
|
||||
{"current_steps": 42, "total_steps": 60, "loss": 0.25, "lr": 1.3780020494988447e-06, "epoch": 21.0, "percentage": 70.0, "elapsed_time": "0:17:13", "remaining_time": "0:07:22"}
|
||||
{"current_steps": 42, "total_steps": 60, "eval_loss": 0.6983169913291931, "epoch": 21.0, "percentage": 70.0, "elapsed_time": "0:17:20", "remaining_time": "0:07:25"}
|
||||
{"current_steps": 43, "total_steps": 60, "loss": 0.238, "lr": 1.2500000000000007e-06, "epoch": 21.5, "percentage": 71.67, "elapsed_time": "0:17:40", "remaining_time": "0:06:59"}
|
||||
{"current_steps": 44, "total_steps": 60, "loss": 0.2306, "lr": 1.1262275548229852e-06, "epoch": 22.0, "percentage": 73.33, "elapsed_time": "0:18:01", "remaining_time": "0:06:33"}
|
||||
{"current_steps": 44, "total_steps": 60, "eval_loss": 0.7099719047546387, "epoch": 22.0, "percentage": 73.33, "elapsed_time": "0:18:09", "remaining_time": "0:06:36"}
|
||||
{"current_steps": 45, "total_steps": 60, "loss": 0.227, "lr": 1.0071035207430352e-06, "epoch": 22.5, "percentage": 75.0, "elapsed_time": "0:18:29", "remaining_time": "0:06:09"}
|
||||
{"current_steps": 46, "total_steps": 60, "loss": 0.2168, "lr": 8.930309757836517e-07, "epoch": 23.0, "percentage": 76.67, "elapsed_time": "0:18:50", "remaining_time": "0:05:44"}
|
||||
{"current_steps": 46, "total_steps": 60, "eval_loss": 0.720533549785614, "epoch": 23.0, "percentage": 76.67, "elapsed_time": "0:18:58", "remaining_time": "0:05:46"}
|
||||
{"current_steps": 47, "total_steps": 60, "loss": 0.2105, "lr": 7.843959053281663e-07, "epoch": 23.5, "percentage": 78.33, "elapsed_time": "0:19:18", "remaining_time": "0:05:20"}
|
||||
{"current_steps": 48, "total_steps": 60, "loss": 0.2125, "lr": 6.815658960673782e-07, "epoch": 24.0, "percentage": 80.0, "elapsed_time": "0:19:38", "remaining_time": "0:04:54"}
|
||||
{"current_steps": 48, "total_steps": 60, "eval_loss": 0.7300633192062378, "epoch": 24.0, "percentage": 80.0, "elapsed_time": "0:19:46", "remaining_time": "0:04:56"}
|
||||
{"current_steps": 49, "total_steps": 60, "loss": 0.2052, "lr": 5.848888922025553e-07, "epoch": 24.5, "percentage": 81.67, "elapsed_time": "0:20:06", "remaining_time": "0:04:30"}
|
||||
{"current_steps": 50, "total_steps": 60, "loss": 0.2031, "lr": 4.946920181123904e-07, "epoch": 25.0, "percentage": 83.33, "elapsed_time": "0:20:25", "remaining_time": "0:04:05"}
|
||||
{"current_steps": 50, "total_steps": 60, "eval_loss": 0.7378360629081726, "epoch": 25.0, "percentage": 83.33, "elapsed_time": "0:20:33", "remaining_time": "0:04:06"}
|
||||
{"current_steps": 51, "total_steps": 60, "loss": 0.2048, "lr": 4.1128047146765936e-07, "epoch": 25.5, "percentage": 85.0, "elapsed_time": "0:20:52", "remaining_time": "0:03:40"}
|
||||
{"current_steps": 52, "total_steps": 60, "loss": 0.1975, "lr": 3.3493649053890325e-07, "epoch": 26.0, "percentage": 86.67, "elapsed_time": "0:21:11", "remaining_time": "0:03:15"}
|
||||
{"current_steps": 52, "total_steps": 60, "eval_loss": 0.7432867288589478, "epoch": 26.0, "percentage": 86.67, "elapsed_time": "0:21:19", "remaining_time": "0:03:16"}
|
||||
{"current_steps": 53, "total_steps": 60, "loss": 0.1925, "lr": 2.6591839919146963e-07, "epoch": 26.5, "percentage": 88.33, "elapsed_time": "0:21:40", "remaining_time": "0:02:51"}
|
||||
{"current_steps": 54, "total_steps": 60, "loss": 0.2001, "lr": 2.044597327993153e-07, "epoch": 27.0, "percentage": 90.0, "elapsed_time": "0:21:59", "remaining_time": "0:02:26"}
|
||||
{"current_steps": 54, "total_steps": 60, "eval_loss": 0.7474139928817749, "epoch": 27.0, "percentage": 90.0, "elapsed_time": "0:22:07", "remaining_time": "0:02:27"}
|
||||
{"current_steps": 55, "total_steps": 60, "loss": 0.1942, "lr": 1.507684480352292e-07, "epoch": 27.5, "percentage": 91.67, "elapsed_time": "0:22:26", "remaining_time": "0:02:02"}
|
||||
{"current_steps": 56, "total_steps": 60, "loss": 0.1953, "lr": 1.0502621921127776e-07, "epoch": 28.0, "percentage": 93.33, "elapsed_time": "0:22:47", "remaining_time": "0:01:37"}
|
||||
{"current_steps": 56, "total_steps": 60, "eval_loss": 0.7486553192138672, "epoch": 28.0, "percentage": 93.33, "elapsed_time": "0:22:54", "remaining_time": "0:01:38"}
|
||||
{"current_steps": 57, "total_steps": 60, "loss": 0.1883, "lr": 6.738782355044048e-08, "epoch": 28.5, "percentage": 95.0, "elapsed_time": "0:23:15", "remaining_time": "0:01:13"}
|
||||
{"current_steps": 58, "total_steps": 60, "loss": 0.1895, "lr": 3.798061746947995e-08, "epoch": 29.0, "percentage": 96.67, "elapsed_time": "0:23:35", "remaining_time": "0:00:48"}
|
||||
{"current_steps": 58, "total_steps": 60, "eval_loss": 0.7486764788627625, "epoch": 29.0, "percentage": 96.67, "elapsed_time": "0:23:42", "remaining_time": "0:00:49"}
|
||||
{"current_steps": 59, "total_steps": 60, "loss": 0.1886, "lr": 1.6904105645142443e-08, "epoch": 29.5, "percentage": 98.33, "elapsed_time": "0:24:02", "remaining_time": "0:00:24"}
|
||||
{"current_steps": 60, "total_steps": 60, "loss": 0.1976, "lr": 4.229604321829561e-09, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:24:22", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 60, "total_steps": 60, "eval_loss": 0.7485920190811157, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:24:55", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 60, "total_steps": 60, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:24:55", "remaining_time": "0:00:00"}
|
||||
703
trainer_state.json
Normal file
703
trainer_state.json
Normal file
@@ -0,0 +1,703 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 30.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 60,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 38.81770706176758,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 1.669,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 42.17606735229492,
|
||||
"learning_rate": 8.333333333333333e-07,
|
||||
"loss": 1.7313,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 1.7900009155273438,
|
||||
"eval_runtime": 7.5875,
|
||||
"eval_samples_per_second": 4.613,
|
||||
"eval_steps_per_second": 0.659,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"grad_norm": 40.34153366088867,
|
||||
"learning_rate": 1.6666666666666667e-06,
|
||||
"loss": 1.662,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 37.466861724853516,
|
||||
"learning_rate": 2.5e-06,
|
||||
"loss": 1.6378,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"eval_loss": 1.5364655256271362,
|
||||
"eval_runtime": 7.4642,
|
||||
"eval_samples_per_second": 4.689,
|
||||
"eval_steps_per_second": 0.67,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"grad_norm": 29.840675354003906,
|
||||
"learning_rate": 3.3333333333333333e-06,
|
||||
"loss": 1.4225,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"grad_norm": 13.304512977600098,
|
||||
"learning_rate": 4.166666666666667e-06,
|
||||
"loss": 1.1356,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"eval_loss": 1.1185977458953857,
|
||||
"eval_runtime": 7.4596,
|
||||
"eval_samples_per_second": 4.692,
|
||||
"eval_steps_per_second": 0.67,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 3.5,
|
||||
"grad_norm": 10.08704662322998,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 1.0871,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"grad_norm": 3.6056466102600098,
|
||||
"learning_rate": 4.995770395678171e-06,
|
||||
"loss": 0.9041,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"eval_loss": 0.9372425079345703,
|
||||
"eval_runtime": 7.4702,
|
||||
"eval_samples_per_second": 4.685,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 4.5,
|
||||
"grad_norm": 3.1515934467315674,
|
||||
"learning_rate": 4.983095894354858e-06,
|
||||
"loss": 0.8773,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"grad_norm": 2.810807704925537,
|
||||
"learning_rate": 4.962019382530521e-06,
|
||||
"loss": 0.8762,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"eval_loss": 0.8529078364372253,
|
||||
"eval_runtime": 7.4567,
|
||||
"eval_samples_per_second": 4.694,
|
||||
"eval_steps_per_second": 0.671,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 5.5,
|
||||
"grad_norm": 2.751431465148926,
|
||||
"learning_rate": 4.93261217644956e-06,
|
||||
"loss": 0.8024,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"grad_norm": 3.107816219329834,
|
||||
"learning_rate": 4.894973780788722e-06,
|
||||
"loss": 0.7807,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"eval_loss": 0.8198402523994446,
|
||||
"eval_runtime": 7.4664,
|
||||
"eval_samples_per_second": 4.688,
|
||||
"eval_steps_per_second": 0.67,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 6.5,
|
||||
"grad_norm": 2.681008815765381,
|
||||
"learning_rate": 4.849231551964771e-06,
|
||||
"loss": 0.758,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"grad_norm": 2.2834079265594482,
|
||||
"learning_rate": 4.7955402672006855e-06,
|
||||
"loss": 0.7323,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"eval_loss": 0.7645982503890991,
|
||||
"eval_runtime": 7.482,
|
||||
"eval_samples_per_second": 4.678,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"grad_norm": 1.8697445392608643,
|
||||
"learning_rate": 4.734081600808531e-06,
|
||||
"loss": 0.7175,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"grad_norm": 1.4500072002410889,
|
||||
"learning_rate": 4.665063509461098e-06,
|
||||
"loss": 0.6814,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 8.0,
|
||||
"eval_loss": 0.7229499816894531,
|
||||
"eval_runtime": 7.4866,
|
||||
"eval_samples_per_second": 4.675,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 8.5,
|
||||
"grad_norm": 1.2065025568008423,
|
||||
"learning_rate": 4.588719528532342e-06,
|
||||
"loss": 0.6536,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"grad_norm": 1.2752524614334106,
|
||||
"learning_rate": 4.50530798188761e-06,
|
||||
"loss": 0.6211,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 9.0,
|
||||
"eval_loss": 0.6847367882728577,
|
||||
"eval_runtime": 7.4811,
|
||||
"eval_samples_per_second": 4.678,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 9.5,
|
||||
"grad_norm": 1.4255502223968506,
|
||||
"learning_rate": 4.415111107797445e-06,
|
||||
"loss": 0.5956,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"grad_norm": 1.2353219985961914,
|
||||
"learning_rate": 4.318434103932622e-06,
|
||||
"loss": 0.5738,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"eval_loss": 0.6638691425323486,
|
||||
"eval_runtime": 7.4794,
|
||||
"eval_samples_per_second": 4.68,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 10.5,
|
||||
"grad_norm": 1.1523832082748413,
|
||||
"learning_rate": 4.215604094671835e-06,
|
||||
"loss": 0.5499,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"grad_norm": 1.1074179410934448,
|
||||
"learning_rate": 4.106969024216348e-06,
|
||||
"loss": 0.5171,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 11.0,
|
||||
"eval_loss": 0.6498724222183228,
|
||||
"eval_runtime": 7.4888,
|
||||
"eval_samples_per_second": 4.674,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 11.5,
|
||||
"grad_norm": 1.0679000616073608,
|
||||
"learning_rate": 3.992896479256966e-06,
|
||||
"loss": 0.5088,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"grad_norm": 1.0380491018295288,
|
||||
"learning_rate": 3.8737724451770155e-06,
|
||||
"loss": 0.4868,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 12.0,
|
||||
"eval_loss": 0.6385172605514526,
|
||||
"eval_runtime": 7.495,
|
||||
"eval_samples_per_second": 4.67,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 12.5,
|
||||
"grad_norm": 0.8720147609710693,
|
||||
"learning_rate": 3.7500000000000005e-06,
|
||||
"loss": 0.4697,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"grad_norm": 0.9460955858230591,
|
||||
"learning_rate": 3.621997950501156e-06,
|
||||
"loss": 0.4371,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 13.0,
|
||||
"eval_loss": 0.6327239871025085,
|
||||
"eval_runtime": 7.4987,
|
||||
"eval_samples_per_second": 4.667,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 13.5,
|
||||
"grad_norm": 0.9779807925224304,
|
||||
"learning_rate": 3.4901994150978926e-06,
|
||||
"loss": 0.4361,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"grad_norm": 0.9678999185562134,
|
||||
"learning_rate": 3.3550503583141726e-06,
|
||||
"loss": 0.407,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 14.0,
|
||||
"eval_loss": 0.6305895447731018,
|
||||
"eval_runtime": 7.492,
|
||||
"eval_samples_per_second": 4.672,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 14.5,
|
||||
"grad_norm": 0.9876528978347778,
|
||||
"learning_rate": 3.217008081777726e-06,
|
||||
"loss": 0.4015,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"grad_norm": 0.9497820734977722,
|
||||
"learning_rate": 3.0765396768561005e-06,
|
||||
"loss": 0.3924,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 15.0,
|
||||
"eval_loss": 0.6329755187034607,
|
||||
"eval_runtime": 7.4793,
|
||||
"eval_samples_per_second": 4.68,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 15.5,
|
||||
"grad_norm": 0.9186223745346069,
|
||||
"learning_rate": 2.9341204441673267e-06,
|
||||
"loss": 0.378,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"grad_norm": 0.9468213319778442,
|
||||
"learning_rate": 2.7902322853130758e-06,
|
||||
"loss": 0.3505,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 16.0,
|
||||
"eval_loss": 0.6392822861671448,
|
||||
"eval_runtime": 7.4979,
|
||||
"eval_samples_per_second": 4.668,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 16.5,
|
||||
"grad_norm": 0.9568607807159424,
|
||||
"learning_rate": 2.6453620722761897e-06,
|
||||
"loss": 0.3475,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"grad_norm": 1.3522801399230957,
|
||||
"learning_rate": 2.5e-06,
|
||||
"loss": 0.3339,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 17.0,
|
||||
"eval_loss": 0.6492648124694824,
|
||||
"eval_runtime": 7.479,
|
||||
"eval_samples_per_second": 4.68,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 17.5,
|
||||
"grad_norm": 0.9427582025527954,
|
||||
"learning_rate": 2.3546379277238107e-06,
|
||||
"loss": 0.3202,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"grad_norm": 1.018237829208374,
|
||||
"learning_rate": 2.2097677146869242e-06,
|
||||
"loss": 0.3086,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 18.0,
|
||||
"eval_loss": 0.6622989773750305,
|
||||
"eval_runtime": 7.4939,
|
||||
"eval_samples_per_second": 4.67,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 18.5,
|
||||
"grad_norm": 0.9453594088554382,
|
||||
"learning_rate": 2.0658795558326745e-06,
|
||||
"loss": 0.3004,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"grad_norm": 1.172818899154663,
|
||||
"learning_rate": 1.9234603231439e-06,
|
||||
"loss": 0.2803,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 19.0,
|
||||
"eval_loss": 0.6748006343841553,
|
||||
"eval_runtime": 7.4995,
|
||||
"eval_samples_per_second": 4.667,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 19.5,
|
||||
"grad_norm": 1.2339236736297607,
|
||||
"learning_rate": 1.7829919182222752e-06,
|
||||
"loss": 0.2751,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"grad_norm": 1.0225498676300049,
|
||||
"learning_rate": 1.6449496416858285e-06,
|
||||
"loss": 0.2687,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 20.0,
|
||||
"eval_loss": 0.6873091459274292,
|
||||
"eval_runtime": 7.4881,
|
||||
"eval_samples_per_second": 4.674,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 20.5,
|
||||
"grad_norm": 0.9979678392410278,
|
||||
"learning_rate": 1.509800584902108e-06,
|
||||
"loss": 0.2556,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"grad_norm": 0.9665634632110596,
|
||||
"learning_rate": 1.3780020494988447e-06,
|
||||
"loss": 0.25,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 21.0,
|
||||
"eval_loss": 0.6983169913291931,
|
||||
"eval_runtime": 7.4891,
|
||||
"eval_samples_per_second": 4.673,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 21.5,
|
||||
"grad_norm": 1.0296282768249512,
|
||||
"learning_rate": 1.2500000000000007e-06,
|
||||
"loss": 0.238,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"grad_norm": 1.0459901094436646,
|
||||
"learning_rate": 1.1262275548229852e-06,
|
||||
"loss": 0.2306,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 22.0,
|
||||
"eval_loss": 0.7099719047546387,
|
||||
"eval_runtime": 7.5003,
|
||||
"eval_samples_per_second": 4.667,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 22.5,
|
||||
"grad_norm": 1.0921026468276978,
|
||||
"learning_rate": 1.0071035207430352e-06,
|
||||
"loss": 0.227,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"grad_norm": 0.9770745635032654,
|
||||
"learning_rate": 8.930309757836517e-07,
|
||||
"loss": 0.2168,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 23.0,
|
||||
"eval_loss": 0.720533549785614,
|
||||
"eval_runtime": 7.4879,
|
||||
"eval_samples_per_second": 4.674,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 23.5,
|
||||
"grad_norm": 1.0788757801055908,
|
||||
"learning_rate": 7.843959053281663e-07,
|
||||
"loss": 0.2105,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"grad_norm": 1.103110432624817,
|
||||
"learning_rate": 6.815658960673782e-07,
|
||||
"loss": 0.2125,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 24.0,
|
||||
"eval_loss": 0.7300633192062378,
|
||||
"eval_runtime": 7.479,
|
||||
"eval_samples_per_second": 4.68,
|
||||
"eval_steps_per_second": 0.669,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 24.5,
|
||||
"grad_norm": 0.9235285520553589,
|
||||
"learning_rate": 5.848888922025553e-07,
|
||||
"loss": 0.2052,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"grad_norm": 1.4067970514297485,
|
||||
"learning_rate": 4.946920181123904e-07,
|
||||
"loss": 0.2031,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 25.0,
|
||||
"eval_loss": 0.7378360629081726,
|
||||
"eval_runtime": 7.5148,
|
||||
"eval_samples_per_second": 4.657,
|
||||
"eval_steps_per_second": 0.665,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 25.5,
|
||||
"grad_norm": 0.960370659828186,
|
||||
"learning_rate": 4.1128047146765936e-07,
|
||||
"loss": 0.2048,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"grad_norm": 1.2136261463165283,
|
||||
"learning_rate": 3.3493649053890325e-07,
|
||||
"loss": 0.1975,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 26.0,
|
||||
"eval_loss": 0.7432867288589478,
|
||||
"eval_runtime": 7.4969,
|
||||
"eval_samples_per_second": 4.669,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 26.5,
|
||||
"grad_norm": 1.0613588094711304,
|
||||
"learning_rate": 2.6591839919146963e-07,
|
||||
"loss": 0.1925,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 27.0,
|
||||
"grad_norm": 1.117826223373413,
|
||||
"learning_rate": 2.044597327993153e-07,
|
||||
"loss": 0.2001,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 27.0,
|
||||
"eval_loss": 0.7474139928817749,
|
||||
"eval_runtime": 7.4824,
|
||||
"eval_samples_per_second": 4.678,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 27.5,
|
||||
"grad_norm": 1.350067138671875,
|
||||
"learning_rate": 1.507684480352292e-07,
|
||||
"loss": 0.1942,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 28.0,
|
||||
"grad_norm": 0.8971886038780212,
|
||||
"learning_rate": 1.0502621921127776e-07,
|
||||
"loss": 0.1953,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 28.0,
|
||||
"eval_loss": 0.7486553192138672,
|
||||
"eval_runtime": 7.4958,
|
||||
"eval_samples_per_second": 4.669,
|
||||
"eval_steps_per_second": 0.667,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 28.5,
|
||||
"grad_norm": 0.9421606063842773,
|
||||
"learning_rate": 6.738782355044048e-08,
|
||||
"loss": 0.1883,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 29.0,
|
||||
"grad_norm": 1.1213371753692627,
|
||||
"learning_rate": 3.798061746947995e-08,
|
||||
"loss": 0.1895,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 29.0,
|
||||
"eval_loss": 0.7486764788627625,
|
||||
"eval_runtime": 7.4875,
|
||||
"eval_samples_per_second": 4.674,
|
||||
"eval_steps_per_second": 0.668,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 29.5,
|
||||
"grad_norm": 1.0604745149612427,
|
||||
"learning_rate": 1.6904105645142443e-08,
|
||||
"loss": 0.1886,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 30.0,
|
||||
"grad_norm": 1.0217480659484863,
|
||||
"learning_rate": 4.229604321829561e-09,
|
||||
"loss": 0.1976,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 30.0,
|
||||
"eval_loss": 0.7485920190811157,
|
||||
"eval_runtime": 7.2053,
|
||||
"eval_samples_per_second": 4.858,
|
||||
"eval_steps_per_second": 0.694,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 30.0,
|
||||
"step": 60,
|
||||
"total_flos": 1.0166485230865613e+18,
|
||||
"train_loss": 0.5314400238295396,
|
||||
"train_runtime": 1496.8474,
|
||||
"train_samples_per_second": 1.022,
|
||||
"train_steps_per_second": 0.04
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 60,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 30,
|
||||
"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": 1.0166485230865613e+18,
|
||||
"train_batch_size": 4,
|
||||
"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 sha256:289f6e0a2005b133a4e985b7ce21633dc75b26d5ebf1015c34a314b7df731560
|
||||
size 7889
|
||||
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: 32 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