初始化项目，由ModelHub XC社区提供模型
Model: tanliboy/lambda-qwen2.5-14b-dpo-test Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
83
README.md
Normal file
83
README.md
Normal file
@@ -0,0 +1,83 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-14B-Instruct
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- trl
|
||||
- dpo
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- dpo
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- HuggingFaceH4/ultrafeedback_binarized
|
||||
model-index:
|
||||
- name: lambda-qwen2.5-14b-dpo-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. -->
|
||||
|
||||
# lambda-qwen2.5-14b-dpo-test
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.4919
|
||||
- Rewards/chosen: -2.4745
|
||||
- Rewards/rejected: -3.3729
|
||||
- Rewards/accuracies: 0.7400
|
||||
- Rewards/margins: 0.8984
|
||||
- Logps/rejected: -832.0724
|
||||
- Logps/chosen: -737.5234
|
||||
- Logits/rejected: -1.2739
|
||||
- Logits/chosen: -1.2560
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 5e-07
|
||||
- train_batch_size: 2
|
||||
- eval_batch_size: 2
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 128
|
||||
- total_eval_batch_size: 16
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 1
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
||||
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
||||
| 0.5269 | 0.2094 | 100 | 0.5333 | -1.6756 | -2.3320 | 0.7000 | 0.6564 | -727.9815 | -657.6356 | -1.3952 | -1.3850 |
|
||||
| 0.5086 | 0.4187 | 200 | 0.5044 | -2.0906 | -2.9287 | 0.7040 | 0.8381 | -787.6511 | -699.1298 | -1.2939 | -1.2773 |
|
||||
| 0.4787 | 0.6281 | 300 | 0.4948 | -2.2927 | -3.1689 | 0.7320 | 0.8762 | -811.6696 | -719.3386 | -1.2846 | -1.2646 |
|
||||
| 0.4825 | 0.8375 | 400 | 0.4924 | -2.4470 | -3.3410 | 0.7400 | 0.8939 | -828.8748 | -734.7765 | -1.2644 | -1.2477 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.44.2
|
||||
- Pytorch 2.4.0+cu121
|
||||
- Datasets 2.19.1
|
||||
- Tokenizers 0.19.1
|
||||
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
|
||||
}
|
||||
22
all_results.json
Normal file
22
all_results.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"epoch": 0.998691442030882,
|
||||
"eval_logits/chosen": -1.2559658288955688,
|
||||
"eval_logits/rejected": -1.27387535572052,
|
||||
"eval_logps/chosen": -737.5234375,
|
||||
"eval_logps/rejected": -832.0723876953125,
|
||||
"eval_loss": 0.4919165074825287,
|
||||
"eval_rewards/accuracies": 0.7400000095367432,
|
||||
"eval_rewards/chosen": -2.4745123386383057,
|
||||
"eval_rewards/margins": 0.8984242081642151,
|
||||
"eval_rewards/rejected": -3.372936964035034,
|
||||
"eval_runtime": 171.7011,
|
||||
"eval_samples": 2000,
|
||||
"eval_samples_per_second": 11.648,
|
||||
"eval_steps_per_second": 0.728,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.5192520058629898,
|
||||
"train_runtime": 13862.6582,
|
||||
"train_samples": 61134,
|
||||
"train_samples_per_second": 4.41,
|
||||
"train_steps_per_second": 0.034
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.44.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
16
eval_results.json
Normal file
16
eval_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"epoch": 0.998691442030882,
|
||||
"eval_logits/chosen": -1.2559658288955688,
|
||||
"eval_logits/rejected": -1.27387535572052,
|
||||
"eval_logps/chosen": -737.5234375,
|
||||
"eval_logps/rejected": -832.0723876953125,
|
||||
"eval_loss": 0.4919165074825287,
|
||||
"eval_rewards/accuracies": 0.7400000095367432,
|
||||
"eval_rewards/chosen": -2.4745123386383057,
|
||||
"eval_rewards/margins": 0.8984242081642151,
|
||||
"eval_rewards/rejected": -3.372936964035034,
|
||||
"eval_runtime": 171.7011,
|
||||
"eval_samples": 2000,
|
||||
"eval_samples_per_second": 11.648,
|
||||
"eval_steps_per_second": 0.728
|
||||
}
|
||||
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": "4.44.2"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:516da4aaa4518af2039ac34b5653107ffda5aba90ef9dec3e957335c0b7e75bc
|
||||
size 4986211280
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6aa0837e704042e5770ce3cca698dfafc8d6fa003a4aa097ee8db12ebaa00879
|
||||
size 4954847344
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:84220f70f94e23397e59ef603b18c43769ec1f2ee6a257147b03f9a6e2aca494
|
||||
size 4954847392
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ba462440c51912e635fb74132784d6aeb6226047db401c0fa7b1eae517cfd88
|
||||
size 4954847392
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:898a58dcfe34a5c6fa1b9203fcb36f937f7cde0cbff1c38ee18c4b6c25a6d992
|
||||
size 4954847392
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:472e4bfc245413b2cd381b8e9affbd7455daa36b1d52fd6d68ed1153475378a1
|
||||
size 4734533160
|
||||
586
model.safetensors.index.json
Normal file
586
model.safetensors.index.json
Normal file
@@ -0,0 +1,586 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 29540067328
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5089daf60354357e57d5b98865cb27cdbf35902a0300b6d3c96dcd5ca9e309f5
|
||||
size 42423
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:db571b57bf9273880e77d43e711992ab399746b6048fb1ff1baba3d9e04d96da
|
||||
size 828
|
||||
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
|
||||
}
|
||||
}
|
||||
303283
tokenizer.json
Normal file
303283
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"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",
|
||||
"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": 0.998691442030882,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.5192520058629898,
|
||||
"train_runtime": 13862.6582,
|
||||
"train_samples": 61134,
|
||||
"train_samples_per_second": 4.41,
|
||||
"train_steps_per_second": 0.034
|
||||
}
|
||||
826
trainer_state.json
Normal file
826
trainer_state.json
Normal file
@@ -0,0 +1,826 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.998691442030882,
|
||||
"eval_steps": 100,
|
||||
"global_step": 477,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.002093692750588851,
|
||||
"grad_norm": 5.344821351720907,
|
||||
"learning_rate": 1.0416666666666666e-08,
|
||||
"logits/chosen": -0.9863196015357971,
|
||||
"logits/rejected": -1.0256754159927368,
|
||||
"logps/chosen": -474.4989013671875,
|
||||
"logps/rejected": -524.1282958984375,
|
||||
"loss": 0.6931,
|
||||
"rewards/accuracies": 0.0,
|
||||
"rewards/chosen": 0.0,
|
||||
"rewards/margins": 0.0,
|
||||
"rewards/rejected": 0.0,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.02093692750588851,
|
||||
"grad_norm": 6.122277210971997,
|
||||
"learning_rate": 1.0416666666666667e-07,
|
||||
"logits/chosen": -1.199143886566162,
|
||||
"logits/rejected": -1.211472749710083,
|
||||
"logps/chosen": -504.70758056640625,
|
||||
"logps/rejected": -517.0758666992188,
|
||||
"loss": 0.6927,
|
||||
"rewards/accuracies": 0.4930555522441864,
|
||||
"rewards/chosen": -2.0182769731036387e-05,
|
||||
"rewards/margins": 0.0008512942586094141,
|
||||
"rewards/rejected": -0.0008714771247468889,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.04187385501177702,
|
||||
"grad_norm": 6.385948578335296,
|
||||
"learning_rate": 2.0833333333333333e-07,
|
||||
"logits/chosen": -1.1590700149536133,
|
||||
"logits/rejected": -1.1333811283111572,
|
||||
"logps/chosen": -488.711669921875,
|
||||
"logps/rejected": -505.6346130371094,
|
||||
"loss": 0.6921,
|
||||
"rewards/accuracies": 0.5375000238418579,
|
||||
"rewards/chosen": -0.007256551180034876,
|
||||
"rewards/margins": 0.002894227858632803,
|
||||
"rewards/rejected": -0.010150779038667679,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06281078251766553,
|
||||
"grad_norm": 5.830212722805484,
|
||||
"learning_rate": 3.1249999999999997e-07,
|
||||
"logits/chosen": -1.1879990100860596,
|
||||
"logits/rejected": -1.2821766138076782,
|
||||
"logps/chosen": -507.1835021972656,
|
||||
"logps/rejected": -481.771728515625,
|
||||
"loss": 0.6858,
|
||||
"rewards/accuracies": 0.581250011920929,
|
||||
"rewards/chosen": -0.05630107969045639,
|
||||
"rewards/margins": 0.009836100041866302,
|
||||
"rewards/rejected": -0.06613717973232269,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.08374771002355404,
|
||||
"grad_norm": 6.142811166492132,
|
||||
"learning_rate": 4.1666666666666667e-07,
|
||||
"logits/chosen": -1.2522597312927246,
|
||||
"logits/rejected": -1.2801125049591064,
|
||||
"logps/chosen": -476.06439208984375,
|
||||
"logps/rejected": -518.1241455078125,
|
||||
"loss": 0.6659,
|
||||
"rewards/accuracies": 0.668749988079071,
|
||||
"rewards/chosen": -0.24496185779571533,
|
||||
"rewards/margins": 0.0600227527320385,
|
||||
"rewards/rejected": -0.30498459935188293,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10468463752944256,
|
||||
"grad_norm": 6.8453175062635125,
|
||||
"learning_rate": 4.999731868769026e-07,
|
||||
"logits/chosen": -1.34788978099823,
|
||||
"logits/rejected": -1.364375114440918,
|
||||
"logps/chosen": -533.0452880859375,
|
||||
"logps/rejected": -599.4424438476562,
|
||||
"loss": 0.6196,
|
||||
"rewards/accuracies": 0.737500011920929,
|
||||
"rewards/chosen": -0.7288391590118408,
|
||||
"rewards/margins": 0.277568519115448,
|
||||
"rewards/rejected": -1.006407618522644,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.12562156503533106,
|
||||
"grad_norm": 7.830680395352566,
|
||||
"learning_rate": 4.990353313429303e-07,
|
||||
"logits/chosen": -1.4588544368743896,
|
||||
"logits/rejected": -1.4161434173583984,
|
||||
"logps/chosen": -587.5367431640625,
|
||||
"logps/rejected": -669.0986328125,
|
||||
"loss": 0.5822,
|
||||
"rewards/accuracies": 0.699999988079071,
|
||||
"rewards/chosen": -1.328367829322815,
|
||||
"rewards/margins": 0.5138038396835327,
|
||||
"rewards/rejected": -1.8421716690063477,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.14655849254121958,
|
||||
"grad_norm": 8.114776579993702,
|
||||
"learning_rate": 4.967625656594781e-07,
|
||||
"logits/chosen": -1.4318482875823975,
|
||||
"logits/rejected": -1.4409352540969849,
|
||||
"logps/chosen": -666.4456176757812,
|
||||
"logps/rejected": -729.1796264648438,
|
||||
"loss": 0.5595,
|
||||
"rewards/accuracies": 0.6812499761581421,
|
||||
"rewards/chosen": -1.651793122291565,
|
||||
"rewards/margins": 0.5167388916015625,
|
||||
"rewards/rejected": -2.168531894683838,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.16749542004710807,
|
||||
"grad_norm": 8.8385356864838,
|
||||
"learning_rate": 4.93167072587771e-07,
|
||||
"logits/chosen": -1.4754712581634521,
|
||||
"logits/rejected": -1.5046911239624023,
|
||||
"logps/chosen": -637.0550537109375,
|
||||
"logps/rejected": -683.7327270507812,
|
||||
"loss": 0.5521,
|
||||
"rewards/accuracies": 0.762499988079071,
|
||||
"rewards/chosen": -1.4783751964569092,
|
||||
"rewards/margins": 0.6370193362236023,
|
||||
"rewards/rejected": -2.1153945922851562,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1884323475529966,
|
||||
"grad_norm": 7.273331254641903,
|
||||
"learning_rate": 4.882681251368548e-07,
|
||||
"logits/chosen": -1.4381468296051025,
|
||||
"logits/rejected": -1.4646328687667847,
|
||||
"logps/chosen": -618.9959716796875,
|
||||
"logps/rejected": -673.4351806640625,
|
||||
"loss": 0.534,
|
||||
"rewards/accuracies": 0.699999988079071,
|
||||
"rewards/chosen": -1.519857406616211,
|
||||
"rewards/margins": 0.5099424719810486,
|
||||
"rewards/rejected": -2.0297999382019043,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.2093692750588851,
|
||||
"grad_norm": 7.2496794921936,
|
||||
"learning_rate": 4.820919832540181e-07,
|
||||
"logits/chosen": -1.3987996578216553,
|
||||
"logits/rejected": -1.4214246273040771,
|
||||
"logps/chosen": -632.5852661132812,
|
||||
"logps/rejected": -757.4251098632812,
|
||||
"loss": 0.5269,
|
||||
"rewards/accuracies": 0.824999988079071,
|
||||
"rewards/chosen": -1.539336919784546,
|
||||
"rewards/margins": 0.8474786877632141,
|
||||
"rewards/rejected": -2.3868155479431152,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.2093692750588851,
|
||||
"eval_logits/chosen": -1.3850065469741821,
|
||||
"eval_logits/rejected": -1.3951938152313232,
|
||||
"eval_logps/chosen": -657.6356201171875,
|
||||
"eval_logps/rejected": -727.9815063476562,
|
||||
"eval_loss": 0.5332552194595337,
|
||||
"eval_rewards/accuracies": 0.699999988079071,
|
||||
"eval_rewards/chosen": -1.6756343841552734,
|
||||
"eval_rewards/margins": 0.6563942432403564,
|
||||
"eval_rewards/rejected": -2.332028865814209,
|
||||
"eval_runtime": 174.614,
|
||||
"eval_samples_per_second": 11.454,
|
||||
"eval_steps_per_second": 0.716,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.23030620256477363,
|
||||
"grad_norm": 8.10753128188729,
|
||||
"learning_rate": 4.7467175306295647e-07,
|
||||
"logits/chosen": -1.2935419082641602,
|
||||
"logits/rejected": -1.381008505821228,
|
||||
"logps/chosen": -657.0072021484375,
|
||||
"logps/rejected": -706.2003784179688,
|
||||
"loss": 0.529,
|
||||
"rewards/accuracies": 0.7562500238418579,
|
||||
"rewards/chosen": -1.6493545770645142,
|
||||
"rewards/margins": 0.5988022685050964,
|
||||
"rewards/rejected": -2.248157024383545,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.2512431300706621,
|
||||
"grad_norm": 8.142470959373666,
|
||||
"learning_rate": 4.6604720940421207e-07,
|
||||
"logits/chosen": -1.3212612867355347,
|
||||
"logits/rejected": -1.3621456623077393,
|
||||
"logps/chosen": -609.11181640625,
|
||||
"logps/rejected": -712.6756591796875,
|
||||
"loss": 0.5053,
|
||||
"rewards/accuracies": 0.762499988079071,
|
||||
"rewards/chosen": -1.5495909452438354,
|
||||
"rewards/margins": 0.7342188954353333,
|
||||
"rewards/rejected": -2.2838101387023926,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.2721800575765506,
|
||||
"grad_norm": 6.624266912381754,
|
||||
"learning_rate": 4.5626458262912735e-07,
|
||||
"logits/chosen": -1.3223083019256592,
|
||||
"logits/rejected": -1.3553454875946045,
|
||||
"logps/chosen": -632.750244140625,
|
||||
"logps/rejected": -708.5543823242188,
|
||||
"loss": 0.5004,
|
||||
"rewards/accuracies": 0.762499988079071,
|
||||
"rewards/chosen": -1.4656463861465454,
|
||||
"rewards/margins": 0.7802583575248718,
|
||||
"rewards/rejected": -2.2459044456481934,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.29311698508243916,
|
||||
"grad_norm": 9.216064563940549,
|
||||
"learning_rate": 4.453763107901675e-07,
|
||||
"logits/chosen": -1.4132908582687378,
|
||||
"logits/rejected": -1.4507051706314087,
|
||||
"logps/chosen": -685.0856323242188,
|
||||
"logps/rejected": -762.1068115234375,
|
||||
"loss": 0.5347,
|
||||
"rewards/accuracies": 0.7437499761581421,
|
||||
"rewards/chosen": -1.7906442880630493,
|
||||
"rewards/margins": 0.8574408292770386,
|
||||
"rewards/rejected": -2.648085117340088,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.31405391258832765,
|
||||
"grad_norm": 8.861919067605399,
|
||||
"learning_rate": 4.3344075855595097e-07,
|
||||
"logits/chosen": -1.3353523015975952,
|
||||
"logits/rejected": -1.3859806060791016,
|
||||
"logps/chosen": -644.6119384765625,
|
||||
"logps/rejected": -741.2134399414062,
|
||||
"loss": 0.5072,
|
||||
"rewards/accuracies": 0.831250011920929,
|
||||
"rewards/chosen": -1.672431230545044,
|
||||
"rewards/margins": 0.8643969297409058,
|
||||
"rewards/rejected": -2.5368282794952393,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.33499084009421615,
|
||||
"grad_norm": 9.292299719932993,
|
||||
"learning_rate": 4.2052190435769554e-07,
|
||||
"logits/chosen": -1.2773377895355225,
|
||||
"logits/rejected": -1.3252099752426147,
|
||||
"logps/chosen": -646.8428344726562,
|
||||
"logps/rejected": -767.851806640625,
|
||||
"loss": 0.5175,
|
||||
"rewards/accuracies": 0.7749999761581421,
|
||||
"rewards/chosen": -1.8619630336761475,
|
||||
"rewards/margins": 0.8954536318778992,
|
||||
"rewards/rejected": -2.7574167251586914,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3559277676001047,
|
||||
"grad_norm": 8.535232197560195,
|
||||
"learning_rate": 4.0668899744407567e-07,
|
||||
"logits/chosen": -1.2284882068634033,
|
||||
"logits/rejected": -1.259841799736023,
|
||||
"logps/chosen": -643.7806396484375,
|
||||
"logps/rejected": -719.5083618164062,
|
||||
"loss": 0.5192,
|
||||
"rewards/accuracies": 0.668749988079071,
|
||||
"rewards/chosen": -1.9132611751556396,
|
||||
"rewards/margins": 0.6574370265007019,
|
||||
"rewards/rejected": -2.5706982612609863,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.3768646951059932,
|
||||
"grad_norm": 8.471513794877017,
|
||||
"learning_rate": 3.920161866827889e-07,
|
||||
"logits/chosen": -1.3475391864776611,
|
||||
"logits/rejected": -1.3049246072769165,
|
||||
"logps/chosen": -670.0532836914062,
|
||||
"logps/rejected": -781.0071411132812,
|
||||
"loss": 0.4907,
|
||||
"rewards/accuracies": 0.731249988079071,
|
||||
"rewards/chosen": -2.043039083480835,
|
||||
"rewards/margins": 0.6995586156845093,
|
||||
"rewards/rejected": -2.742597818374634,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.39780162261188173,
|
||||
"grad_norm": 7.575885046762926,
|
||||
"learning_rate": 3.765821230985757e-07,
|
||||
"logits/chosen": -1.3079270124435425,
|
||||
"logits/rejected": -1.2785875797271729,
|
||||
"logps/chosen": -679.8087768554688,
|
||||
"logps/rejected": -808.7610473632812,
|
||||
"loss": 0.501,
|
||||
"rewards/accuracies": 0.71875,
|
||||
"rewards/chosen": -2.0995121002197266,
|
||||
"rewards/margins": 0.7744059562683105,
|
||||
"rewards/rejected": -2.873918056488037,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.4187385501177702,
|
||||
"grad_norm": 11.938650112523503,
|
||||
"learning_rate": 3.604695382782159e-07,
|
||||
"logits/chosen": -1.2764681577682495,
|
||||
"logits/rejected": -1.2830474376678467,
|
||||
"logps/chosen": -700.9818115234375,
|
||||
"logps/rejected": -790.2588500976562,
|
||||
"loss": 0.5086,
|
||||
"rewards/accuracies": 0.6812499761581421,
|
||||
"rewards/chosen": -2.1675782203674316,
|
||||
"rewards/margins": 0.6838473081588745,
|
||||
"rewards/rejected": -2.851425886154175,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.4187385501177702,
|
||||
"eval_logits/chosen": -1.2772727012634277,
|
||||
"eval_logits/rejected": -1.2939157485961914,
|
||||
"eval_logps/chosen": -699.1298217773438,
|
||||
"eval_logps/rejected": -787.651123046875,
|
||||
"eval_loss": 0.504360556602478,
|
||||
"eval_rewards/accuracies": 0.7039999961853027,
|
||||
"eval_rewards/chosen": -2.090576171875,
|
||||
"eval_rewards/margins": 0.8381478786468506,
|
||||
"eval_rewards/rejected": -2.9287240505218506,
|
||||
"eval_runtime": 173.7524,
|
||||
"eval_samples_per_second": 11.511,
|
||||
"eval_steps_per_second": 0.719,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.4396754776236587,
|
||||
"grad_norm": 8.791948417829072,
|
||||
"learning_rate": 3.4376480090239047e-07,
|
||||
"logits/chosen": -1.2757617235183716,
|
||||
"logits/rejected": -1.3068811893463135,
|
||||
"logps/chosen": -736.14794921875,
|
||||
"logps/rejected": -807.1375732421875,
|
||||
"loss": 0.5129,
|
||||
"rewards/accuracies": 0.71875,
|
||||
"rewards/chosen": -2.278721332550049,
|
||||
"rewards/margins": 0.7708470225334167,
|
||||
"rewards/rejected": -3.0495681762695312,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.46061240512954726,
|
||||
"grad_norm": 7.175329586845978,
|
||||
"learning_rate": 3.265574537815398e-07,
|
||||
"logits/chosen": -1.234605312347412,
|
||||
"logits/rejected": -1.238705039024353,
|
||||
"logps/chosen": -686.875244140625,
|
||||
"logps/rejected": -792.4070434570312,
|
||||
"loss": 0.5007,
|
||||
"rewards/accuracies": 0.71875,
|
||||
"rewards/chosen": -2.308474063873291,
|
||||
"rewards/margins": 0.764443039894104,
|
||||
"rewards/rejected": -3.0729172229766846,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.48154933263543576,
|
||||
"grad_norm": 8.60332250684624,
|
||||
"learning_rate": 3.0893973387735683e-07,
|
||||
"logits/chosen": -1.2985376119613647,
|
||||
"logits/rejected": -1.306581974029541,
|
||||
"logps/chosen": -662.0936279296875,
|
||||
"logps/rejected": -823.6008911132812,
|
||||
"loss": 0.5153,
|
||||
"rewards/accuracies": 0.7749999761581421,
|
||||
"rewards/chosen": -2.064509868621826,
|
||||
"rewards/margins": 1.0347161293029785,
|
||||
"rewards/rejected": -3.0992257595062256,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.5024862601413242,
|
||||
"grad_norm": 7.615515586975465,
|
||||
"learning_rate": 2.910060778827554e-07,
|
||||
"logits/chosen": -1.244362711906433,
|
||||
"logits/rejected": -1.250091552734375,
|
||||
"logps/chosen": -670.7986450195312,
|
||||
"logps/rejected": -774.2589721679688,
|
||||
"loss": 0.488,
|
||||
"rewards/accuracies": 0.71875,
|
||||
"rewards/chosen": -2.0815677642822266,
|
||||
"rewards/margins": 0.7600711584091187,
|
||||
"rewards/rejected": -2.8416390419006348,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.5234231876472127,
|
||||
"grad_norm": 8.227460909814754,
|
||||
"learning_rate": 2.7285261601056697e-07,
|
||||
"logits/chosen": -1.2554184198379517,
|
||||
"logits/rejected": -1.2809184789657593,
|
||||
"logps/chosen": -725.0731201171875,
|
||||
"logps/rejected": -819.86181640625,
|
||||
"loss": 0.4948,
|
||||
"rewards/accuracies": 0.7562500238418579,
|
||||
"rewards/chosen": -2.1545822620391846,
|
||||
"rewards/margins": 0.9376426935195923,
|
||||
"rewards/rejected": -3.0922253131866455,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.5443601151531012,
|
||||
"grad_norm": 9.508165144084513,
|
||||
"learning_rate": 2.5457665670441937e-07,
|
||||
"logits/chosen": -1.2575011253356934,
|
||||
"logits/rejected": -1.3054656982421875,
|
||||
"logps/chosen": -716.1454467773438,
|
||||
"logps/rejected": -812.8175659179688,
|
||||
"loss": 0.4996,
|
||||
"rewards/accuracies": 0.737500011920929,
|
||||
"rewards/chosen": -2.350128650665283,
|
||||
"rewards/margins": 0.9231952428817749,
|
||||
"rewards/rejected": -3.2733237743377686,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.5652970426589898,
|
||||
"grad_norm": 9.240543953923092,
|
||||
"learning_rate": 2.3627616503391812e-07,
|
||||
"logits/chosen": -1.2486110925674438,
|
||||
"logits/rejected": -1.25895094871521,
|
||||
"logps/chosen": -710.92724609375,
|
||||
"logps/rejected": -834.6962890625,
|
||||
"loss": 0.5086,
|
||||
"rewards/accuracies": 0.7562500238418579,
|
||||
"rewards/chosen": -2.2452242374420166,
|
||||
"rewards/margins": 1.0662496089935303,
|
||||
"rewards/rejected": -3.3114733695983887,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.5862339701648783,
|
||||
"grad_norm": 8.132372884664997,
|
||||
"learning_rate": 2.1804923757009882e-07,
|
||||
"logits/chosen": -1.2164264917373657,
|
||||
"logits/rejected": -1.3014079332351685,
|
||||
"logps/chosen": -720.0590209960938,
|
||||
"logps/rejected": -770.1983642578125,
|
||||
"loss": 0.4955,
|
||||
"rewards/accuracies": 0.731249988079071,
|
||||
"rewards/chosen": -2.291123867034912,
|
||||
"rewards/margins": 0.673937201499939,
|
||||
"rewards/rejected": -2.9650609493255615,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.6071708976707668,
|
||||
"grad_norm": 7.699636946017558,
|
||||
"learning_rate": 1.9999357655598891e-07,
|
||||
"logits/chosen": -1.249624252319336,
|
||||
"logits/rejected": -1.2436301708221436,
|
||||
"logps/chosen": -687.5323486328125,
|
||||
"logps/rejected": -815.8274536132812,
|
||||
"loss": 0.4944,
|
||||
"rewards/accuracies": 0.7437499761581421,
|
||||
"rewards/chosen": -2.2351253032684326,
|
||||
"rewards/margins": 0.8806158900260925,
|
||||
"rewards/rejected": -3.115741491317749,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.6281078251766553,
|
||||
"grad_norm": 7.183044496877634,
|
||||
"learning_rate": 1.8220596619089573e-07,
|
||||
"logits/chosen": -1.214294672012329,
|
||||
"logits/rejected": -1.278714656829834,
|
||||
"logps/chosen": -711.4762573242188,
|
||||
"logps/rejected": -826.3113403320312,
|
||||
"loss": 0.4787,
|
||||
"rewards/accuracies": 0.793749988079071,
|
||||
"rewards/chosen": -2.1853926181793213,
|
||||
"rewards/margins": 1.0479013919830322,
|
||||
"rewards/rejected": -3.2332940101623535,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.6281078251766553,
|
||||
"eval_logits/chosen": -1.2646288871765137,
|
||||
"eval_logits/rejected": -1.2846323251724243,
|
||||
"eval_logps/chosen": -719.3385620117188,
|
||||
"eval_logps/rejected": -811.6696166992188,
|
||||
"eval_loss": 0.49482667446136475,
|
||||
"eval_rewards/accuracies": 0.7319999933242798,
|
||||
"eval_rewards/chosen": -2.292664051055908,
|
||||
"eval_rewards/margins": 0.8762450218200684,
|
||||
"eval_rewards/rejected": -3.1689090728759766,
|
||||
"eval_runtime": 173.013,
|
||||
"eval_samples_per_second": 11.56,
|
||||
"eval_steps_per_second": 0.722,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.6490447526825438,
|
||||
"grad_norm": 11.871889943001767,
|
||||
"learning_rate": 1.647817538357072e-07,
|
||||
"logits/chosen": -1.2392758131027222,
|
||||
"logits/rejected": -1.3158223628997803,
|
||||
"logps/chosen": -731.3906860351562,
|
||||
"logps/rejected": -812.5341186523438,
|
||||
"loss": 0.4937,
|
||||
"rewards/accuracies": 0.8125,
|
||||
"rewards/chosen": -2.279770851135254,
|
||||
"rewards/margins": 1.1058552265167236,
|
||||
"rewards/rejected": -3.3856253623962402,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.6699816801884323,
|
||||
"grad_norm": 8.733519859905128,
|
||||
"learning_rate": 1.478143389201113e-07,
|
||||
"logits/chosen": -1.255499005317688,
|
||||
"logits/rejected": -1.310626745223999,
|
||||
"logps/chosen": -706.554443359375,
|
||||
"logps/rejected": -809.0241088867188,
|
||||
"loss": 0.4781,
|
||||
"rewards/accuracies": 0.75,
|
||||
"rewards/chosen": -2.4083428382873535,
|
||||
"rewards/margins": 0.9482523202896118,
|
||||
"rewards/rejected": -3.3565948009490967,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.6909186076943209,
|
||||
"grad_norm": 8.449035915191043,
|
||||
"learning_rate": 1.3139467229135998e-07,
|
||||
"logits/chosen": -1.2453768253326416,
|
||||
"logits/rejected": -1.2541320323944092,
|
||||
"logps/chosen": -725.0225830078125,
|
||||
"logps/rejected": -829.4249877929688,
|
||||
"loss": 0.4839,
|
||||
"rewards/accuracies": 0.7562500238418579,
|
||||
"rewards/chosen": -2.4690725803375244,
|
||||
"rewards/margins": 0.8669673800468445,
|
||||
"rewards/rejected": -3.336040496826172,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.7118555352002094,
|
||||
"grad_norm": 9.726561036240426,
|
||||
"learning_rate": 1.1561076868822755e-07,
|
||||
"logits/chosen": -1.1633121967315674,
|
||||
"logits/rejected": -1.2020900249481201,
|
||||
"logps/chosen": -733.0904541015625,
|
||||
"logps/rejected": -856.1812744140625,
|
||||
"loss": 0.499,
|
||||
"rewards/accuracies": 0.7749999761581421,
|
||||
"rewards/chosen": -2.551614284515381,
|
||||
"rewards/margins": 0.9220356941223145,
|
||||
"rewards/rejected": -3.4736499786376953,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.7327924627060979,
|
||||
"grad_norm": 8.334278257541456,
|
||||
"learning_rate": 1.0054723495346482e-07,
|
||||
"logits/chosen": -1.2510846853256226,
|
||||
"logits/rejected": -1.2921613454818726,
|
||||
"logps/chosen": -709.3406982421875,
|
||||
"logps/rejected": -806.6890869140625,
|
||||
"loss": 0.461,
|
||||
"rewards/accuracies": 0.762499988079071,
|
||||
"rewards/chosen": -2.4316649436950684,
|
||||
"rewards/margins": 0.9165409207344055,
|
||||
"rewards/rejected": -3.348206043243408,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.7537293902119864,
|
||||
"grad_norm": 8.447055903339363,
|
||||
"learning_rate": 8.628481651367875e-08,
|
||||
"logits/chosen": -1.2806235551834106,
|
||||
"logits/rejected": -1.3330801725387573,
|
||||
"logps/chosen": -759.4558715820312,
|
||||
"logps/rejected": -859.9752807617188,
|
||||
"loss": 0.5053,
|
||||
"rewards/accuracies": 0.800000011920929,
|
||||
"rewards/chosen": -2.384193181991577,
|
||||
"rewards/margins": 1.1400038003921509,
|
||||
"rewards/rejected": -3.5241971015930176,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.7746663177178749,
|
||||
"grad_norm": 7.277711887873546,
|
||||
"learning_rate": 7.289996455765748e-08,
|
||||
"logits/chosen": -1.254237174987793,
|
||||
"logits/rejected": -1.30390465259552,
|
||||
"logps/chosen": -721.6316528320312,
|
||||
"logps/rejected": -797.1998291015625,
|
||||
"loss": 0.4865,
|
||||
"rewards/accuracies": 0.762499988079071,
|
||||
"rewards/chosen": -2.433364152908325,
|
||||
"rewards/margins": 0.8884729146957397,
|
||||
"rewards/rejected": -3.3218369483947754,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.7956032452237635,
|
||||
"grad_norm": 8.0205493017487,
|
||||
"learning_rate": 6.046442623320145e-08,
|
||||
"logits/chosen": -1.2699052095413208,
|
||||
"logits/rejected": -1.3266394138336182,
|
||||
"logps/chosen": -743.0064086914062,
|
||||
"logps/rejected": -852.3271484375,
|
||||
"loss": 0.4851,
|
||||
"rewards/accuracies": 0.7562500238418579,
|
||||
"rewards/chosen": -2.516409397125244,
|
||||
"rewards/margins": 1.0128896236419678,
|
||||
"rewards/rejected": -3.529299259185791,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.816540172729652,
|
||||
"grad_norm": 8.82315393673875,
|
||||
"learning_rate": 4.904486005914027e-08,
|
||||
"logits/chosen": -1.2463610172271729,
|
||||
"logits/rejected": -1.2608873844146729,
|
||||
"logps/chosen": -727.2433471679688,
|
||||
"logps/rejected": -831.7511596679688,
|
||||
"loss": 0.4765,
|
||||
"rewards/accuracies": 0.731249988079071,
|
||||
"rewards/chosen": -2.392064332962036,
|
||||
"rewards/margins": 0.8088263273239136,
|
||||
"rewards/rejected": -3.200890302658081,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.8374771002355405,
|
||||
"grad_norm": 8.332606925483372,
|
||||
"learning_rate": 3.8702478614051345e-08,
|
||||
"logits/chosen": -1.2610491514205933,
|
||||
"logits/rejected": -1.3101046085357666,
|
||||
"logps/chosen": -675.9216918945312,
|
||||
"logps/rejected": -812.0501708984375,
|
||||
"loss": 0.4825,
|
||||
"rewards/accuracies": 0.8062499761581421,
|
||||
"rewards/chosen": -2.404404401779175,
|
||||
"rewards/margins": 1.064521074295044,
|
||||
"rewards/rejected": -3.4689254760742188,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.8374771002355405,
|
||||
"eval_logits/chosen": -1.247671365737915,
|
||||
"eval_logits/rejected": -1.2644414901733398,
|
||||
"eval_logps/chosen": -734.7764892578125,
|
||||
"eval_logps/rejected": -828.874755859375,
|
||||
"eval_loss": 0.4924214482307434,
|
||||
"eval_rewards/accuracies": 0.7400000095367432,
|
||||
"eval_rewards/chosen": -2.4470431804656982,
|
||||
"eval_rewards/margins": 0.8939173817634583,
|
||||
"eval_rewards/rejected": -3.3409602642059326,
|
||||
"eval_runtime": 172.7999,
|
||||
"eval_samples_per_second": 11.574,
|
||||
"eval_steps_per_second": 0.723,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.8584140277414289,
|
||||
"grad_norm": 7.409919398422161,
|
||||
"learning_rate": 2.9492720416985e-08,
|
||||
"logits/chosen": -1.2109179496765137,
|
||||
"logits/rejected": -1.2863398790359497,
|
||||
"logps/chosen": -763.9716796875,
|
||||
"logps/rejected": -842.8446044921875,
|
||||
"loss": 0.4935,
|
||||
"rewards/accuracies": 0.762499988079071,
|
||||
"rewards/chosen": -2.5099594593048096,
|
||||
"rewards/margins": 0.8958646059036255,
|
||||
"rewards/rejected": -3.4058241844177246,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.8793509552473174,
|
||||
"grad_norm": 7.7696194448634275,
|
||||
"learning_rate": 2.1464952759020856e-08,
|
||||
"logits/chosen": -1.207766056060791,
|
||||
"logits/rejected": -1.2242529392242432,
|
||||
"logps/chosen": -737.0940551757812,
|
||||
"logps/rejected": -902.7199096679688,
|
||||
"loss": 0.4795,
|
||||
"rewards/accuracies": 0.7875000238418579,
|
||||
"rewards/chosen": -2.6334424018859863,
|
||||
"rewards/margins": 1.135379433631897,
|
||||
"rewards/rejected": -3.768822193145752,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.9002878827532059,
|
||||
"grad_norm": 8.567338429000005,
|
||||
"learning_rate": 1.4662207078575684e-08,
|
||||
"logits/chosen": -1.2356188297271729,
|
||||
"logits/rejected": -1.275846242904663,
|
||||
"logps/chosen": -750.3199462890625,
|
||||
"logps/rejected": -832.4161987304688,
|
||||
"loss": 0.4693,
|
||||
"rewards/accuracies": 0.78125,
|
||||
"rewards/chosen": -2.4712231159210205,
|
||||
"rewards/margins": 1.0153119564056396,
|
||||
"rewards/rejected": -3.486534833908081,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 0.9212248102590945,
|
||||
"grad_norm": 8.619770650174253,
|
||||
"learning_rate": 9.12094829893642e-09,
|
||||
"logits/chosen": -1.26433527469635,
|
||||
"logits/rejected": -1.3092998266220093,
|
||||
"logps/chosen": -719.7817993164062,
|
||||
"logps/rejected": -813.6593627929688,
|
||||
"loss": 0.4889,
|
||||
"rewards/accuracies": 0.768750011920929,
|
||||
"rewards/chosen": -2.478425979614258,
|
||||
"rewards/margins": 0.9797126054763794,
|
||||
"rewards/rejected": -3.4581382274627686,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.942161737764983,
|
||||
"grad_norm": 7.405850569844442,
|
||||
"learning_rate": 4.8708793644441086e-09,
|
||||
"logits/chosen": -1.1603410243988037,
|
||||
"logits/rejected": -1.2475802898406982,
|
||||
"logps/chosen": -723.2225341796875,
|
||||
"logps/rejected": -873.5631103515625,
|
||||
"loss": 0.4742,
|
||||
"rewards/accuracies": 0.800000011920929,
|
||||
"rewards/chosen": -2.4385993480682373,
|
||||
"rewards/margins": 1.1800200939178467,
|
||||
"rewards/rejected": -3.618619441986084,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 0.9630986652708715,
|
||||
"grad_norm": 8.784099959292528,
|
||||
"learning_rate": 1.9347820230782295e-09,
|
||||
"logits/chosen": -1.2129580974578857,
|
||||
"logits/rejected": -1.300582766532898,
|
||||
"logps/chosen": -732.4578857421875,
|
||||
"logps/rejected": -833.5997314453125,
|
||||
"loss": 0.4817,
|
||||
"rewards/accuracies": 0.78125,
|
||||
"rewards/chosen": -2.5728919506073,
|
||||
"rewards/margins": 1.036318063735962,
|
||||
"rewards/rejected": -3.609210252761841,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.98403559277676,
|
||||
"grad_norm": 9.493475272094026,
|
||||
"learning_rate": 3.2839470889836627e-10,
|
||||
"logits/chosen": -1.2292336225509644,
|
||||
"logits/rejected": -1.2678720951080322,
|
||||
"logps/chosen": -725.6412963867188,
|
||||
"logps/rejected": -856.3084716796875,
|
||||
"loss": 0.4615,
|
||||
"rewards/accuracies": 0.7437499761581421,
|
||||
"rewards/chosen": -2.491250514984131,
|
||||
"rewards/margins": 1.0373666286468506,
|
||||
"rewards/rejected": -3.5286173820495605,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.998691442030882,
|
||||
"step": 477,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.5192520058629898,
|
||||
"train_runtime": 13862.6582,
|
||||
"train_samples_per_second": 4.41,
|
||||
"train_steps_per_second": 0.034
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 477,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": false,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 2,
|
||||
"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 sha256:99ab02bd175d5ee79de434a512bce065cfdf5a991a72c713eb4a7a6485eec735
|
||||
size 7544
|
||||
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