初始化项目，由ModelHub XC社区提供模型
Model: CAS-SIAT-XinHai/MeasHalu-3B-Instruct 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
|
||||
72
README.md
Normal file
72
README.md
Normal file
@@ -0,0 +1,72 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
# base_model: /home/huangruijun/grpo_contract_penalty/test_3b/lora_merge/5500step
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: reasoning_test
|
||||
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. -->
|
||||
|
||||
# reasoning_test
|
||||
|
||||
<!-- This model is a fine-tuned version of [/home/huangruijun/grpo_contract_penalty/test_3b/lora_merge/5500step](https://huggingface.co//home/huangruijun/grpo_contract_penalty/test_3b/lora_merge/5500step) on the reasoning_test dataset. -->
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.0904
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 1e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 1
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 2
|
||||
- gradient_accumulation_steps: 16
|
||||
- total_train_batch_size: 32
|
||||
- total_eval_batch_size: 2
|
||||
- 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 |
|
||||
|:-------------:|:-------:|:----:|:---------------:|
|
||||
| 0.0385 | 3.5039 | 25 | 0.0498 |
|
||||
| 0.0047 | 7.1260 | 50 | 0.0598 |
|
||||
| 0.001 | 10.6299 | 75 | 0.0682 |
|
||||
| 0.0002 | 14.2520 | 100 | 0.0857 |
|
||||
| 0.0 | 17.7559 | 125 | 0.0882 |
|
||||
| 0.0 | 21.3780 | 150 | 0.0904 |
|
||||
| 0.0 | 24.8819 | 175 | 0.0904 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.51.3
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 3.2.0
|
||||
- Tokenizers 0.21.0
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|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": 24.881889763779526,
|
||||
"eval_loss": 0.0903918594121933,
|
||||
"eval_runtime": 3.6049,
|
||||
"eval_samples_per_second": 8.045,
|
||||
"eval_steps_per_second": 4.161,
|
||||
"total_flos": 8801054883840.0,
|
||||
"train_loss": 0.039481030342618136,
|
||||
"train_runtime": 3513.9873,
|
||||
"train_samples_per_second": 1.807,
|
||||
"train_steps_per_second": 0.05
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.3",
|
||||
"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": 24.881889763779526,
|
||||
"eval_loss": 0.0903918594121933,
|
||||
"eval_runtime": 3.6049,
|
||||
"eval_samples_per_second": 8.045,
|
||||
"eval_steps_per_second": 4.161
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
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 sha256:7f4bf6120a2ab620e72bed1fba311257f2f22c1be9973ed1d5bcb088412535b1
|
||||
size 4957560304
|
||||
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 sha256:4ef48946fecd9070e76e38877df8165ba5be0d8075aa93b5308e6207cccceaab
|
||||
size 1214366696
|
||||
441
model.safetensors.index.json
Normal file
441
model.safetensors.index.json
Normal file
@@ -0,0 +1,441 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 6171877376
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-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_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
209
tokenizer_config.json
Normal file
209
tokenizer_config.json
Normal file
@@ -0,0 +1,209 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"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,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"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": 24.881889763779526,
|
||||
"total_flos": 8801054883840.0,
|
||||
"train_loss": 0.039481030342618136,
|
||||
"train_runtime": 3513.9873,
|
||||
"train_samples_per_second": 1.807,
|
||||
"train_steps_per_second": 0.05
|
||||
}
|
||||
43
trainer_log.jsonl
Normal file
43
trainer_log.jsonl
Normal file
@@ -0,0 +1,43 @@
|
||||
{"current_steps": 5, "total_steps": 175, "loss": 0.5498, "lr": 2.222222222222222e-06, "epoch": 0.6299212598425197, "percentage": 2.86, "elapsed_time": "0:01:33", "remaining_time": "0:53:05"}
|
||||
{"current_steps": 10, "total_steps": 175, "loss": 0.5156, "lr": 5e-06, "epoch": 1.3779527559055118, "percentage": 5.71, "elapsed_time": "0:03:15", "remaining_time": "0:53:48"}
|
||||
{"current_steps": 15, "total_steps": 175, "loss": 0.1575, "lr": 7.77777777777778e-06, "epoch": 2.1259842519685037, "percentage": 8.57, "elapsed_time": "0:04:59", "remaining_time": "0:53:14"}
|
||||
{"current_steps": 20, "total_steps": 175, "loss": 0.0449, "lr": 9.998999018714264e-06, "epoch": 2.7559055118110236, "percentage": 11.43, "elapsed_time": "0:06:26", "remaining_time": "0:49:53"}
|
||||
{"current_steps": 25, "total_steps": 175, "loss": 0.0385, "lr": 9.964006738212574e-06, "epoch": 3.5039370078740157, "percentage": 14.29, "elapsed_time": "0:08:05", "remaining_time": "0:48:35"}
|
||||
{"current_steps": 25, "total_steps": 175, "eval_loss": 0.049805961549282074, "epoch": 3.5039370078740157, "percentage": 14.29, "elapsed_time": "0:08:09", "remaining_time": "0:48:58"}
|
||||
{"current_steps": 30, "total_steps": 175, "loss": 0.0247, "lr": 9.879365458117678e-06, "epoch": 4.251968503937007, "percentage": 17.14, "elapsed_time": "0:09:49", "remaining_time": "0:47:27"}
|
||||
{"current_steps": 35, "total_steps": 175, "loss": 0.0157, "lr": 9.745921743533653e-06, "epoch": 4.881889763779528, "percentage": 20.0, "elapsed_time": "0:11:17", "remaining_time": "0:45:08"}
|
||||
{"current_steps": 40, "total_steps": 175, "loss": 0.0125, "lr": 9.565010271724353e-06, "epoch": 5.6299212598425195, "percentage": 22.86, "elapsed_time": "0:12:59", "remaining_time": "0:43:52"}
|
||||
{"current_steps": 45, "total_steps": 175, "loss": 0.0069, "lr": 9.338440482939146e-06, "epoch": 6.377952755905512, "percentage": 25.71, "elapsed_time": "0:14:41", "remaining_time": "0:42:26"}
|
||||
{"current_steps": 50, "total_steps": 175, "loss": 0.0047, "lr": 9.068478482754532e-06, "epoch": 7.125984251968504, "percentage": 28.57, "elapsed_time": "0:16:24", "remaining_time": "0:41:00"}
|
||||
{"current_steps": 50, "total_steps": 175, "eval_loss": 0.05980484187602997, "epoch": 7.125984251968504, "percentage": 28.57, "elapsed_time": "0:16:28", "remaining_time": "0:41:10"}
|
||||
{"current_steps": 55, "total_steps": 175, "loss": 0.0019, "lr": 8.757824376940748e-06, "epoch": 7.755905511811024, "percentage": 31.43, "elapsed_time": "0:17:54", "remaining_time": "0:39:04"}
|
||||
{"current_steps": 60, "total_steps": 175, "loss": 0.0023, "lr": 8.409585265545509e-06, "epoch": 8.503937007874015, "percentage": 34.29, "elapsed_time": "0:19:36", "remaining_time": "0:37:35"}
|
||||
{"current_steps": 65, "total_steps": 175, "loss": 0.002, "lr": 8.027244166302641e-06, "epoch": 9.251968503937007, "percentage": 37.14, "elapsed_time": "0:21:20", "remaining_time": "0:36:06"}
|
||||
{"current_steps": 70, "total_steps": 175, "loss": 0.0016, "lr": 7.614625178187402e-06, "epoch": 9.881889763779528, "percentage": 40.0, "elapsed_time": "0:22:49", "remaining_time": "0:34:13"}
|
||||
{"current_steps": 75, "total_steps": 175, "loss": 0.001, "lr": 7.175855233545669e-06, "epoch": 10.62992125984252, "percentage": 42.86, "elapsed_time": "0:24:31", "remaining_time": "0:32:42"}
|
||||
{"current_steps": 75, "total_steps": 175, "eval_loss": 0.06815612316131592, "epoch": 10.62992125984252, "percentage": 42.86, "elapsed_time": "0:24:35", "remaining_time": "0:32:47"}
|
||||
{"current_steps": 80, "total_steps": 175, "loss": 0.0007, "lr": 6.715322821344495e-06, "epoch": 11.377952755905511, "percentage": 45.71, "elapsed_time": "0:26:18", "remaining_time": "0:31:14"}
|
||||
{"current_steps": 85, "total_steps": 175, "loss": 0.0004, "lr": 6.237634094385814e-06, "epoch": 12.125984251968504, "percentage": 48.57, "elapsed_time": "0:28:04", "remaining_time": "0:29:43"}
|
||||
{"current_steps": 90, "total_steps": 175, "loss": 0.0002, "lr": 5.7475667994901316e-06, "epoch": 12.755905511811024, "percentage": 51.43, "elapsed_time": "0:29:33", "remaining_time": "0:27:55"}
|
||||
{"current_steps": 95, "total_steps": 175, "loss": 0.0002, "lr": 5.250022491431259e-06, "epoch": 13.503937007874015, "percentage": 54.29, "elapsed_time": "0:31:17", "remaining_time": "0:26:21"}
|
||||
{"current_steps": 100, "total_steps": 175, "loss": 0.0002, "lr": 4.749977508568742e-06, "epoch": 14.251968503937007, "percentage": 57.14, "elapsed_time": "0:32:59", "remaining_time": "0:24:44"}
|
||||
{"current_steps": 100, "total_steps": 175, "eval_loss": 0.08573012053966522, "epoch": 14.251968503937007, "percentage": 57.14, "elapsed_time": "0:33:03", "remaining_time": "0:24:47"}
|
||||
{"current_steps": 105, "total_steps": 175, "loss": 0.0001, "lr": 4.252433200509869e-06, "epoch": 14.881889763779528, "percentage": 60.0, "elapsed_time": "0:34:51", "remaining_time": "0:23:14"}
|
||||
{"current_steps": 110, "total_steps": 175, "loss": 0.0001, "lr": 3.762365905614187e-06, "epoch": 15.62992125984252, "percentage": 62.86, "elapsed_time": "0:36:35", "remaining_time": "0:21:37"}
|
||||
{"current_steps": 115, "total_steps": 175, "loss": 0.0001, "lr": 3.2846771786555075e-06, "epoch": 16.37795275590551, "percentage": 65.71, "elapsed_time": "0:38:22", "remaining_time": "0:20:01"}
|
||||
{"current_steps": 120, "total_steps": 175, "loss": 0.0, "lr": 2.824144766454333e-06, "epoch": 17.125984251968504, "percentage": 68.57, "elapsed_time": "0:40:07", "remaining_time": "0:18:23"}
|
||||
{"current_steps": 125, "total_steps": 175, "loss": 0.0, "lr": 2.3853748218126e-06, "epoch": 17.755905511811022, "percentage": 71.43, "elapsed_time": "0:41:38", "remaining_time": "0:16:39"}
|
||||
{"current_steps": 125, "total_steps": 175, "eval_loss": 0.08820342272520065, "epoch": 17.755905511811022, "percentage": 71.43, "elapsed_time": "0:41:42", "remaining_time": "0:16:40"}
|
||||
{"current_steps": 130, "total_steps": 175, "loss": 0.0, "lr": 1.9727558336973594e-06, "epoch": 18.503937007874015, "percentage": 74.29, "elapsed_time": "0:43:26", "remaining_time": "0:15:02"}
|
||||
{"current_steps": 135, "total_steps": 175, "loss": 0.0, "lr": 1.5904147344544928e-06, "epoch": 19.251968503937007, "percentage": 77.14, "elapsed_time": "0:45:10", "remaining_time": "0:13:23"}
|
||||
{"current_steps": 140, "total_steps": 175, "loss": 0.0, "lr": 1.2421756230592535e-06, "epoch": 19.881889763779526, "percentage": 80.0, "elapsed_time": "0:46:38", "remaining_time": "0:11:39"}
|
||||
{"current_steps": 145, "total_steps": 175, "loss": 0.0, "lr": 9.315215172454689e-07, "epoch": 20.62992125984252, "percentage": 82.86, "elapsed_time": "0:48:23", "remaining_time": "0:10:00"}
|
||||
{"current_steps": 150, "total_steps": 175, "loss": 0.0, "lr": 6.615595170608541e-07, "epoch": 21.37795275590551, "percentage": 85.71, "elapsed_time": "0:50:08", "remaining_time": "0:08:21"}
|
||||
{"current_steps": 150, "total_steps": 175, "eval_loss": 0.09042119234800339, "epoch": 21.37795275590551, "percentage": 85.71, "elapsed_time": "0:50:12", "remaining_time": "0:08:22"}
|
||||
{"current_steps": 155, "total_steps": 175, "loss": 0.0, "lr": 4.349897282756488e-07, "epoch": 22.125984251968504, "percentage": 88.57, "elapsed_time": "0:51:55", "remaining_time": "0:06:41"}
|
||||
{"current_steps": 160, "total_steps": 175, "loss": 0.0, "lr": 2.54078256466348e-07, "epoch": 22.755905511811022, "percentage": 91.43, "elapsed_time": "0:53:24", "remaining_time": "0:05:00"}
|
||||
{"current_steps": 165, "total_steps": 175, "loss": 0.0, "lr": 1.206345418823235e-07, "epoch": 23.503937007874015, "percentage": 94.29, "elapsed_time": "0:55:07", "remaining_time": "0:03:20"}
|
||||
{"current_steps": 170, "total_steps": 175, "loss": 0.0, "lr": 3.599326178742535e-08, "epoch": 24.251968503937007, "percentage": 97.14, "elapsed_time": "0:56:51", "remaining_time": "0:01:40"}
|
||||
{"current_steps": 175, "total_steps": 175, "loss": 0.0, "lr": 1.0009812857370016e-09, "epoch": 24.881889763779526, "percentage": 100.0, "elapsed_time": "0:58:19", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 175, "total_steps": 175, "eval_loss": 0.0903918594121933, "epoch": 24.881889763779526, "percentage": 100.0, "elapsed_time": "0:58:23", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 175, "total_steps": 175, "epoch": 24.881889763779526, "percentage": 100.0, "elapsed_time": "0:58:33", "remaining_time": "0:00:00"}
|
||||
344
trainer_state.json
Normal file
344
trainer_state.json
Normal file
@@ -0,0 +1,344 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 24.881889763779526,
|
||||
"eval_steps": 25,
|
||||
"global_step": 175,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.6299212598425197,
|
||||
"grad_norm": 5.632317132462053,
|
||||
"learning_rate": 2.222222222222222e-06,
|
||||
"loss": 0.5498,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 1.3779527559055118,
|
||||
"grad_norm": 2.7309533902724237,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 0.5156,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 2.1259842519685037,
|
||||
"grad_norm": 1.2157903681282713,
|
||||
"learning_rate": 7.77777777777778e-06,
|
||||
"loss": 0.1575,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 2.7559055118110236,
|
||||
"grad_norm": 0.4902690514544274,
|
||||
"learning_rate": 9.998999018714264e-06,
|
||||
"loss": 0.0449,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 3.5039370078740157,
|
||||
"grad_norm": 0.4746290087026016,
|
||||
"learning_rate": 9.964006738212574e-06,
|
||||
"loss": 0.0385,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 3.5039370078740157,
|
||||
"eval_loss": 0.049805961549282074,
|
||||
"eval_runtime": 3.8791,
|
||||
"eval_samples_per_second": 7.476,
|
||||
"eval_steps_per_second": 3.867,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 4.251968503937007,
|
||||
"grad_norm": 0.2525712314895859,
|
||||
"learning_rate": 9.879365458117678e-06,
|
||||
"loss": 0.0247,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 4.881889763779528,
|
||||
"grad_norm": 0.31313562383003646,
|
||||
"learning_rate": 9.745921743533653e-06,
|
||||
"loss": 0.0157,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 5.6299212598425195,
|
||||
"grad_norm": 0.21515126665369913,
|
||||
"learning_rate": 9.565010271724353e-06,
|
||||
"loss": 0.0125,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 6.377952755905512,
|
||||
"grad_norm": 0.34914670734943754,
|
||||
"learning_rate": 9.338440482939146e-06,
|
||||
"loss": 0.0069,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 7.125984251968504,
|
||||
"grad_norm": 0.14477627700807097,
|
||||
"learning_rate": 9.068478482754532e-06,
|
||||
"loss": 0.0047,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 7.125984251968504,
|
||||
"eval_loss": 0.05980484187602997,
|
||||
"eval_runtime": 3.7853,
|
||||
"eval_samples_per_second": 7.661,
|
||||
"eval_steps_per_second": 3.963,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 7.755905511811024,
|
||||
"grad_norm": 0.3479903618887373,
|
||||
"learning_rate": 8.757824376940748e-06,
|
||||
"loss": 0.0019,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 8.503937007874015,
|
||||
"grad_norm": 0.5106959959750706,
|
||||
"learning_rate": 8.409585265545509e-06,
|
||||
"loss": 0.0023,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 9.251968503937007,
|
||||
"grad_norm": 0.14853492351867037,
|
||||
"learning_rate": 8.027244166302641e-06,
|
||||
"loss": 0.002,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 9.881889763779528,
|
||||
"grad_norm": 0.16542609484128554,
|
||||
"learning_rate": 7.614625178187402e-06,
|
||||
"loss": 0.0016,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 10.62992125984252,
|
||||
"grad_norm": 0.1706483384230398,
|
||||
"learning_rate": 7.175855233545669e-06,
|
||||
"loss": 0.001,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 10.62992125984252,
|
||||
"eval_loss": 0.06815612316131592,
|
||||
"eval_runtime": 3.9081,
|
||||
"eval_samples_per_second": 7.42,
|
||||
"eval_steps_per_second": 3.838,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 11.377952755905511,
|
||||
"grad_norm": 0.12734977176199208,
|
||||
"learning_rate": 6.715322821344495e-06,
|
||||
"loss": 0.0007,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 12.125984251968504,
|
||||
"grad_norm": 0.055045406105188224,
|
||||
"learning_rate": 6.237634094385814e-06,
|
||||
"loss": 0.0004,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 12.755905511811024,
|
||||
"grad_norm": 0.24933655723456083,
|
||||
"learning_rate": 5.7475667994901316e-06,
|
||||
"loss": 0.0002,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 13.503937007874015,
|
||||
"grad_norm": 0.08486520999135673,
|
||||
"learning_rate": 5.250022491431259e-06,
|
||||
"loss": 0.0002,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 14.251968503937007,
|
||||
"grad_norm": 0.03626525027130318,
|
||||
"learning_rate": 4.749977508568742e-06,
|
||||
"loss": 0.0002,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 14.251968503937007,
|
||||
"eval_loss": 0.08573012053966522,
|
||||
"eval_runtime": 3.9129,
|
||||
"eval_samples_per_second": 7.411,
|
||||
"eval_steps_per_second": 3.833,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 14.881889763779528,
|
||||
"grad_norm": 0.005000292928153053,
|
||||
"learning_rate": 4.252433200509869e-06,
|
||||
"loss": 0.0001,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 15.62992125984252,
|
||||
"grad_norm": 0.0070081305200095844,
|
||||
"learning_rate": 3.762365905614187e-06,
|
||||
"loss": 0.0001,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 16.37795275590551,
|
||||
"grad_norm": 0.023387552639621518,
|
||||
"learning_rate": 3.2846771786555075e-06,
|
||||
"loss": 0.0001,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 17.125984251968504,
|
||||
"grad_norm": 0.008314297434967715,
|
||||
"learning_rate": 2.824144766454333e-06,
|
||||
"loss": 0.0,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 17.755905511811022,
|
||||
"grad_norm": 0.0028401414939199423,
|
||||
"learning_rate": 2.3853748218126e-06,
|
||||
"loss": 0.0,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 17.755905511811022,
|
||||
"eval_loss": 0.08820342272520065,
|
||||
"eval_runtime": 3.889,
|
||||
"eval_samples_per_second": 7.457,
|
||||
"eval_steps_per_second": 3.857,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 18.503937007874015,
|
||||
"grad_norm": 0.002171915506295924,
|
||||
"learning_rate": 1.9727558336973594e-06,
|
||||
"loss": 0.0,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 19.251968503937007,
|
||||
"grad_norm": 0.002247395436703256,
|
||||
"learning_rate": 1.5904147344544928e-06,
|
||||
"loss": 0.0,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 19.881889763779526,
|
||||
"grad_norm": 0.020207725975457932,
|
||||
"learning_rate": 1.2421756230592535e-06,
|
||||
"loss": 0.0,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 20.62992125984252,
|
||||
"grad_norm": 0.002114011246814878,
|
||||
"learning_rate": 9.315215172454689e-07,
|
||||
"loss": 0.0,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 21.37795275590551,
|
||||
"grad_norm": 0.0025524711331419707,
|
||||
"learning_rate": 6.615595170608541e-07,
|
||||
"loss": 0.0,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 21.37795275590551,
|
||||
"eval_loss": 0.09042119234800339,
|
||||
"eval_runtime": 3.8398,
|
||||
"eval_samples_per_second": 7.552,
|
||||
"eval_steps_per_second": 3.906,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 22.125984251968504,
|
||||
"grad_norm": 0.003056620821824751,
|
||||
"learning_rate": 4.349897282756488e-07,
|
||||
"loss": 0.0,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 22.755905511811022,
|
||||
"grad_norm": 0.0022376804480244176,
|
||||
"learning_rate": 2.54078256466348e-07,
|
||||
"loss": 0.0,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 23.503937007874015,
|
||||
"grad_norm": 0.0023153643544619597,
|
||||
"learning_rate": 1.206345418823235e-07,
|
||||
"loss": 0.0,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 24.251968503937007,
|
||||
"grad_norm": 0.0024824470278455323,
|
||||
"learning_rate": 3.599326178742535e-08,
|
||||
"loss": 0.0,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 24.881889763779526,
|
||||
"grad_norm": 0.002034088863587326,
|
||||
"learning_rate": 1.0009812857370016e-09,
|
||||
"loss": 0.0,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 24.881889763779526,
|
||||
"eval_loss": 0.0903918594121933,
|
||||
"eval_runtime": 3.9075,
|
||||
"eval_samples_per_second": 7.422,
|
||||
"eval_steps_per_second": 3.839,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 24.881889763779526,
|
||||
"step": 175,
|
||||
"total_flos": 8801054883840.0,
|
||||
"train_loss": 0.039481030342618136,
|
||||
"train_runtime": 3513.9873,
|
||||
"train_samples_per_second": 1.807,
|
||||
"train_steps_per_second": 0.05
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 175,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 25,
|
||||
"save_steps": 100,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 8801054883840.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:877566db24f2cd098ca434e2a9038fd35017dc0eb3a7a0a24a61c72a0591c0b6
|
||||
size 7544
|
||||
BIN
training_eval_loss.png
Normal file
BIN
training_eval_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 29 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