初始化项目，由ModelHub XC社区提供模型
Model: jackf857/qwen3-8b-base-sft-hh-helpful-4xh200-batch-64-20260417-214452 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
|
||||
68
README.md
Normal file
68
README.md
Normal file
@@ -0,0 +1,68 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-8B-Base
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- Anthropic/hh-rlhf
|
||||
model-index:
|
||||
- name: qwen3-8b-base-sft-hh-helpful-4xh200-batch-64-20260417-214452
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# qwen3-8b-base-sft-hh-helpful-4xh200-batch-64-20260417-214452
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base) on the Anthropic/hh-rlhf dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 1.3682
|
||||
|
||||
## 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: 2e-05
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 4
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 64
|
||||
- total_eval_batch_size: 32
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 1
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:------:|:----:|:---------------:|
|
||||
| 1.5038 | 0.3717 | 100 | 1.5039 |
|
||||
| 1.3595 | 0.7435 | 200 | 1.3682 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.51.0
|
||||
- Pytorch 2.3.1+cu121
|
||||
- Datasets 2.21.0
|
||||
- Tokenizers 0.21.4
|
||||
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
|
||||
}
|
||||
14
all_results.json
Normal file
14
all_results.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 1.3495442867279053,
|
||||
"eval_runtime": 5.3484,
|
||||
"eval_samples": 2339,
|
||||
"eval_samples_per_second": 174.071,
|
||||
"eval_steps_per_second": 5.609,
|
||||
"total_flos": 1.000686074462208e+17,
|
||||
"train_loss": 1.5741833559199336,
|
||||
"train_runtime": 402.4792,
|
||||
"train_samples": 43598,
|
||||
"train_samples_per_second": 42.723,
|
||||
"train_steps_per_second": 0.668
|
||||
}
|
||||
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": 151643,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.51.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
8
eval_results.json
Normal file
8
eval_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 1.3495442867279053,
|
||||
"eval_runtime": 5.3484,
|
||||
"eval_samples": 2339,
|
||||
"eval_samples_per_second": 174.071,
|
||||
"eval_steps_per_second": 5.609
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "4.51.0"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fc2a24eeaa799d4c1ad40ed26b3bf0c782800e6d333e706e1c771069ce321cd
|
||||
size 4972454376
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4c0ccf9cbfff5eb857d81061174562a119128fead8015ddaff5c388e04b5ef4
|
||||
size 4832048608
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46d3495143f6cdcb1aa93ee8d851605338179aeacb929ab8521a0062d55f29d2
|
||||
size 4832048656
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9faa565ef468f750e3cb340d17867af37406760da06c61c45ab35660ff6ee5b6
|
||||
size 4999855528
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f840af2b3453d95b9793175d57eb5d474cea17f16429e6337b411e5a0a226dd4
|
||||
size 4832048672
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1f84ef8aff4ee14cde4c5b3a09bbdef9531a98135927170445337d97af5b0e37
|
||||
size 4832048672
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6acba78addf48cea8912131e1f21d89491f424c1154e7a5341dd3dff6e0b51f0
|
||||
size 3462482728
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 32762941440
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00007-of-00007.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.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": "<|endoftext|>",
|
||||
"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,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
9
train_results.json
Normal file
9
train_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"total_flos": 1.000686074462208e+17,
|
||||
"train_loss": 1.5741833559199336,
|
||||
"train_runtime": 402.4792,
|
||||
"train_samples": 43598,
|
||||
"train_samples_per_second": 42.723,
|
||||
"train_steps_per_second": 0.668
|
||||
}
|
||||
437
trainer_state.json
Normal file
437
trainer_state.json
Normal file
@@ -0,0 +1,437 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 100,
|
||||
"global_step": 269,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0037174721189591076,
|
||||
"grad_norm": 14.262325286865234,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 3.044,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.01858736059479554,
|
||||
"grad_norm": 13.0241060256958,
|
||||
"learning_rate": 2.962962962962963e-06,
|
||||
"loss": 3.0801,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.03717472118959108,
|
||||
"grad_norm": 6.920816898345947,
|
||||
"learning_rate": 6.666666666666667e-06,
|
||||
"loss": 2.8515,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.055762081784386616,
|
||||
"grad_norm": 4.249760627746582,
|
||||
"learning_rate": 1.037037037037037e-05,
|
||||
"loss": 2.469,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.07434944237918216,
|
||||
"grad_norm": 5.996034145355225,
|
||||
"learning_rate": 1.4074074074074075e-05,
|
||||
"loss": 2.2633,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.09293680297397769,
|
||||
"grad_norm": 8.92640495300293,
|
||||
"learning_rate": 1.7777777777777777e-05,
|
||||
"loss": 2.152,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.11152416356877323,
|
||||
"grad_norm": 8.087935447692871,
|
||||
"learning_rate": 1.9996629653035128e-05,
|
||||
"loss": 2.0381,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.13011152416356878,
|
||||
"grad_norm": 6.582911968231201,
|
||||
"learning_rate": 1.995873933559535e-05,
|
||||
"loss": 1.9322,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.14869888475836432,
|
||||
"grad_norm": 5.658934593200684,
|
||||
"learning_rate": 1.9878905881817254e-05,
|
||||
"loss": 1.8054,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.16728624535315986,
|
||||
"grad_norm": 3.6228199005126953,
|
||||
"learning_rate": 1.975746552556772e-05,
|
||||
"loss": 1.7393,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.18587360594795538,
|
||||
"grad_norm": 2.397761106491089,
|
||||
"learning_rate": 1.9594929736144978e-05,
|
||||
"loss": 1.6738,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.20446096654275092,
|
||||
"grad_norm": 2.159792423248291,
|
||||
"learning_rate": 1.939198306412775e-05,
|
||||
"loss": 1.6584,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.22304832713754646,
|
||||
"grad_norm": 2.4025373458862305,
|
||||
"learning_rate": 1.9149480258259535e-05,
|
||||
"loss": 1.6347,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.241635687732342,
|
||||
"grad_norm": 2.0866482257843018,
|
||||
"learning_rate": 1.886844266551068e-05,
|
||||
"loss": 1.598,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.26022304832713755,
|
||||
"grad_norm": 1.7645834684371948,
|
||||
"learning_rate": 1.8550053929480202e-05,
|
||||
"loss": 1.5923,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.2788104089219331,
|
||||
"grad_norm": 1.642554759979248,
|
||||
"learning_rate": 1.8195655005254274e-05,
|
||||
"loss": 1.5452,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.29739776951672864,
|
||||
"grad_norm": 1.5671523809432983,
|
||||
"learning_rate": 1.780673851171728e-05,
|
||||
"loss": 1.5275,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.3159851301115242,
|
||||
"grad_norm": 1.6036931276321411,
|
||||
"learning_rate": 1.7384942445101772e-05,
|
||||
"loss": 1.5358,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.3345724907063197,
|
||||
"grad_norm": 1.540089726448059,
|
||||
"learning_rate": 1.6932043280253892e-05,
|
||||
"loss": 1.5234,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.35315985130111527,
|
||||
"grad_norm": 1.1673122644424438,
|
||||
"learning_rate": 1.644994848866964e-05,
|
||||
"loss": 1.5211,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.37174721189591076,
|
||||
"grad_norm": 1.3127870559692383,
|
||||
"learning_rate": 1.5940688504813664e-05,
|
||||
"loss": 1.5038,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.37174721189591076,
|
||||
"eval_loss": 1.5038524866104126,
|
||||
"eval_runtime": 5.4348,
|
||||
"eval_samples_per_second": 171.303,
|
||||
"eval_steps_per_second": 5.52,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.3903345724907063,
|
||||
"grad_norm": 1.1808836460113525,
|
||||
"learning_rate": 1.5406408174555978e-05,
|
||||
"loss": 1.4911,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.40892193308550184,
|
||||
"grad_norm": 8.379034042358398,
|
||||
"learning_rate": 1.4849357721743169e-05,
|
||||
"loss": 1.4598,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.4275092936802974,
|
||||
"grad_norm": 1.090346097946167,
|
||||
"learning_rate": 1.4271883270950073e-05,
|
||||
"loss": 1.4944,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.44609665427509293,
|
||||
"grad_norm": 1.1020578145980835,
|
||||
"learning_rate": 1.3676416966327201e-05,
|
||||
"loss": 1.4808,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.4646840148698885,
|
||||
"grad_norm": 1.1537312269210815,
|
||||
"learning_rate": 1.3065466728160253e-05,
|
||||
"loss": 1.4493,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.483271375464684,
|
||||
"grad_norm": 0.9695990085601807,
|
||||
"learning_rate": 1.2441605690283915e-05,
|
||||
"loss": 1.456,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.5018587360594795,
|
||||
"grad_norm": 1.1512304544448853,
|
||||
"learning_rate": 1.1807461362836382e-05,
|
||||
"loss": 1.4493,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 0.5204460966542751,
|
||||
"grad_norm": 1.1557819843292236,
|
||||
"learning_rate": 1.1165704565997593e-05,
|
||||
"loss": 1.4528,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.5390334572490706,
|
||||
"grad_norm": 0.9956693053245544,
|
||||
"learning_rate": 1.0519038181319e-05,
|
||||
"loss": 1.4129,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 0.5576208178438662,
|
||||
"grad_norm": 0.9141682982444763,
|
||||
"learning_rate": 9.870185768020694e-06,
|
||||
"loss": 1.4179,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.5762081784386617,
|
||||
"grad_norm": 1.0787816047668457,
|
||||
"learning_rate": 9.221880092200601e-06,
|
||||
"loss": 1.4139,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 0.5947955390334573,
|
||||
"grad_norm": 1.0250240564346313,
|
||||
"learning_rate": 8.576851617267151e-06,
|
||||
"loss": 1.3976,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.6133828996282528,
|
||||
"grad_norm": 0.9707216024398804,
|
||||
"learning_rate": 7.93781700407012e-06,
|
||||
"loss": 1.4043,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 0.6319702602230484,
|
||||
"grad_norm": 1.020119309425354,
|
||||
"learning_rate": 7.307467669163655e-06,
|
||||
"loss": 1.4153,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.6505576208178439,
|
||||
"grad_norm": 1.0523854494094849,
|
||||
"learning_rate": 6.688458449390438e-06,
|
||||
"loss": 1.3896,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 0.6691449814126395,
|
||||
"grad_norm": 1.0011796951293945,
|
||||
"learning_rate": 6.083396420528298e-06,
|
||||
"loss": 1.3938,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.6877323420074349,
|
||||
"grad_norm": 0.9738273024559021,
|
||||
"learning_rate": 5.494829917091733e-06,
|
||||
"loss": 1.371,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 0.7063197026022305,
|
||||
"grad_norm": 0.9486119151115417,
|
||||
"learning_rate": 4.925237799533445e-06,
|
||||
"loss": 1.3906,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.724907063197026,
|
||||
"grad_norm": 0.9746046662330627,
|
||||
"learning_rate": 4.377019014049223e-06,
|
||||
"loss": 1.3798,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 0.7434944237918215,
|
||||
"grad_norm": 0.9329619407653809,
|
||||
"learning_rate": 3.852482488956992e-06,
|
||||
"loss": 1.3595,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.7434944237918215,
|
||||
"eval_loss": 1.3681989908218384,
|
||||
"eval_runtime": 5.3831,
|
||||
"eval_samples_per_second": 172.95,
|
||||
"eval_steps_per_second": 5.573,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.7620817843866171,
|
||||
"grad_norm": 1.0122321844100952,
|
||||
"learning_rate": 3.3538374102033865e-06,
|
||||
"loss": 1.3626,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 0.7806691449814126,
|
||||
"grad_norm": 0.9424676895141602,
|
||||
"learning_rate": 2.8831839169543998e-06,
|
||||
"loss": 1.3451,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.7992565055762082,
|
||||
"grad_norm": 0.9907885193824768,
|
||||
"learning_rate": 2.4425042564574186e-06,
|
||||
"loss": 1.371,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 0.8178438661710037,
|
||||
"grad_norm": 0.9360305666923523,
|
||||
"learning_rate": 2.03365443542764e-06,
|
||||
"loss": 1.348,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.8364312267657993,
|
||||
"grad_norm": 1.073083519935608,
|
||||
"learning_rate": 1.6583564031206357e-06,
|
||||
"loss": 1.3557,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 0.8550185873605948,
|
||||
"grad_norm": 0.9857882857322693,
|
||||
"learning_rate": 1.3181907990135624e-06,
|
||||
"loss": 1.3387,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.8736059479553904,
|
||||
"grad_norm": 0.9631243348121643,
|
||||
"learning_rate": 1.0145902956395449e-06,
|
||||
"loss": 1.3554,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 0.8921933085501859,
|
||||
"grad_norm": 1.0025112628936768,
|
||||
"learning_rate": 7.488335646131628e-07,
|
||||
"loss": 1.3396,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.9107806691449815,
|
||||
"grad_norm": 0.9768189191818237,
|
||||
"learning_rate": 5.22039891260262e-07,
|
||||
"loss": 1.3361,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"epoch": 0.929368029739777,
|
||||
"grad_norm": 0.9644155502319336,
|
||||
"learning_rate": 3.3516446053363015e-07,
|
||||
"loss": 1.3138,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.9479553903345725,
|
||||
"grad_norm": 0.9707642197608948,
|
||||
"learning_rate": 1.889943340687961e-07,
|
||||
"loss": 1.3315,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"epoch": 0.966542750929368,
|
||||
"grad_norm": 1.0248664617538452,
|
||||
"learning_rate": 8.41451353233369e-08,
|
||||
"loss": 1.3724,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.9851301115241635,
|
||||
"grad_norm": 0.9727205634117126,
|
||||
"learning_rate": 2.10584567608918e-08,
|
||||
"loss": 1.3296,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 269,
|
||||
"total_flos": 1.000686074462208e+17,
|
||||
"train_loss": 1.5741833559199336,
|
||||
"train_runtime": 402.4792,
|
||||
"train_samples_per_second": 42.723,
|
||||
"train_steps_per_second": 0.668
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 269,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 1000000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": false,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 1.000686074462208e+17,
|
||||
"train_batch_size": 8,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
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