初始化项目，由ModelHub XC社区提供模型
Model: ShenaoZhang/0.001_idpo_noreplacerej_iter_2 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
|
||||
64
README.md
Normal file
64
README.md
Normal file
@@ -0,0 +1,64 @@
|
||||
---
|
||||
license: mit
|
||||
base_model: ShenaoZhang/0.001_idpo_noreplacerej_iter_1
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- dpo
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- ShenaoZhang/0.001_idpo_noreplacerej_dataset
|
||||
model-index:
|
||||
- name: 0.001_idpo_noreplacerej_iter_2
|
||||
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. -->
|
||||
|
||||
# 0.001_idpo_noreplacerej_iter_2
|
||||
|
||||
This model is a fine-tuned version of [ShenaoZhang/0.001_idpo_noreplacerej_iter_1](https://huggingface.co/ShenaoZhang/0.001_idpo_noreplacerej_iter_1) on the ShenaoZhang/0.001_idpo_noreplacerej_dataset dataset.
|
||||
|
||||
## 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: 8
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 128
|
||||
- total_eval_batch_size: 64
|
||||
- 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
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.36.2
|
||||
- Pytorch 2.1.2+cu121
|
||||
- Datasets 2.14.6
|
||||
- Tokenizers 0.15.2
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"train_loss": 0.6192928140268386,
|
||||
"train_runtime": 2654.4881,
|
||||
"train_samples": 20378,
|
||||
"train_samples_per_second": 7.677,
|
||||
"train_steps_per_second": 0.06
|
||||
}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "ShenaoZhang/0.001_idpo_noreplacerej_iter_1",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.36.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.36.2"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bdf5985d8223b6c47430ad99cba84d95dc2b68c29aa1e3918204e8548ce83d5c
|
||||
size 4943162336
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:beb5a9a6017777064158951bf1999be636033dcd40828b0d6f6cf53d97f229c4
|
||||
size 4999819336
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:263aafa1206423f13e7e4bc338ab49216bfee07652dd785d8968baaed362ad21
|
||||
size 4540516344
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
35
special_tokens_map.json
Normal file
35
special_tokens_map.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
48
tokenizer_config.json
Normal file
48
tokenizer_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "left",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"train_loss": 0.6192928140268386,
|
||||
"train_runtime": 2654.4881,
|
||||
"train_samples": 20378,
|
||||
"train_samples_per_second": 7.677,
|
||||
"train_steps_per_second": 0.06
|
||||
}
|
||||
254
trainer_state.json
Normal file
254
trainer_state.json
Normal file
@@ -0,0 +1,254 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.9968652037617555,
|
||||
"eval_steps": 500,
|
||||
"global_step": 159,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 3.125e-08,
|
||||
"logits/chosen": -2.689429759979248,
|
||||
"logits/rejected": -2.571552276611328,
|
||||
"logps/chosen": -143.16458129882812,
|
||||
"logps/rejected": -203.93856811523438,
|
||||
"loss": 0.6931,
|
||||
"rewards/accuracies": 0.0,
|
||||
"rewards/chosen": 0.0,
|
||||
"rewards/margins": 0.0,
|
||||
"rewards/rejected": 0.0,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.06,
|
||||
"learning_rate": 3.1249999999999997e-07,
|
||||
"logits/chosen": -2.708827257156372,
|
||||
"logits/rejected": -2.686070680618286,
|
||||
"logps/chosen": -237.31149291992188,
|
||||
"logps/rejected": -247.18511962890625,
|
||||
"loss": 0.6899,
|
||||
"rewards/accuracies": 0.4375,
|
||||
"rewards/chosen": -0.01768648810684681,
|
||||
"rewards/margins": -0.0019140999065712094,
|
||||
"rewards/rejected": -0.015772389248013496,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.13,
|
||||
"learning_rate": 4.990353313429303e-07,
|
||||
"logits/chosen": -2.6622233390808105,
|
||||
"logits/rejected": -2.6616415977478027,
|
||||
"logps/chosen": -279.48223876953125,
|
||||
"logps/rejected": -328.67034912109375,
|
||||
"loss": 0.6672,
|
||||
"rewards/accuracies": 0.518750011920929,
|
||||
"rewards/chosen": -0.3544561564922333,
|
||||
"rewards/margins": 0.08781943470239639,
|
||||
"rewards/rejected": -0.4422755837440491,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.19,
|
||||
"learning_rate": 4.882681251368548e-07,
|
||||
"logits/chosen": -2.530141830444336,
|
||||
"logits/rejected": -2.4791650772094727,
|
||||
"logps/chosen": -242.94580078125,
|
||||
"logps/rejected": -304.83319091796875,
|
||||
"loss": 0.6578,
|
||||
"rewards/accuracies": 0.606249988079071,
|
||||
"rewards/chosen": -0.23640844225883484,
|
||||
"rewards/margins": 0.2698945105075836,
|
||||
"rewards/rejected": -0.5063029527664185,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"learning_rate": 4.6604720940421207e-07,
|
||||
"logits/chosen": -2.3857040405273438,
|
||||
"logits/rejected": -2.350623846054077,
|
||||
"logps/chosen": -262.49359130859375,
|
||||
"logps/rejected": -348.61285400390625,
|
||||
"loss": 0.6375,
|
||||
"rewards/accuracies": 0.612500011920929,
|
||||
"rewards/chosen": -0.4203917384147644,
|
||||
"rewards/margins": 0.2930702269077301,
|
||||
"rewards/rejected": -0.7134619951248169,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"learning_rate": 4.3344075855595097e-07,
|
||||
"logits/chosen": -2.2722487449645996,
|
||||
"logits/rejected": -2.2434167861938477,
|
||||
"logps/chosen": -265.3743591308594,
|
||||
"logps/rejected": -326.30474853515625,
|
||||
"loss": 0.6153,
|
||||
"rewards/accuracies": 0.5375000238418579,
|
||||
"rewards/chosen": -0.47392672300338745,
|
||||
"rewards/margins": 0.19795864820480347,
|
||||
"rewards/rejected": -0.6718853712081909,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.38,
|
||||
"learning_rate": 3.920161866827889e-07,
|
||||
"logits/chosen": -2.1601130962371826,
|
||||
"logits/rejected": -2.137726306915283,
|
||||
"logps/chosen": -290.22393798828125,
|
||||
"logps/rejected": -320.2867736816406,
|
||||
"loss": 0.6209,
|
||||
"rewards/accuracies": 0.625,
|
||||
"rewards/chosen": -0.5836684703826904,
|
||||
"rewards/margins": 0.20530056953430176,
|
||||
"rewards/rejected": -0.7889690399169922,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"learning_rate": 3.4376480090239047e-07,
|
||||
"logits/chosen": -2.1158602237701416,
|
||||
"logits/rejected": -2.0663974285125732,
|
||||
"logps/chosen": -261.1648864746094,
|
||||
"logps/rejected": -325.1148681640625,
|
||||
"loss": 0.629,
|
||||
"rewards/accuracies": 0.637499988079071,
|
||||
"rewards/chosen": -0.49344220757484436,
|
||||
"rewards/margins": 0.26634153723716736,
|
||||
"rewards/rejected": -0.7597836852073669,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.910060778827554e-07,
|
||||
"logits/chosen": -2.0561118125915527,
|
||||
"logits/rejected": -2.0465025901794434,
|
||||
"logps/chosen": -259.88214111328125,
|
||||
"logps/rejected": -330.5330505371094,
|
||||
"loss": 0.5935,
|
||||
"rewards/accuracies": 0.643750011920929,
|
||||
"rewards/chosen": -0.6631507873535156,
|
||||
"rewards/margins": 0.2730056643486023,
|
||||
"rewards/rejected": -0.9361563920974731,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.56,
|
||||
"learning_rate": 2.3627616503391812e-07,
|
||||
"logits/chosen": -2.163104295730591,
|
||||
"logits/rejected": -2.1310901641845703,
|
||||
"logps/chosen": -251.44955444335938,
|
||||
"logps/rejected": -355.19989013671875,
|
||||
"loss": 0.6082,
|
||||
"rewards/accuracies": 0.637499988079071,
|
||||
"rewards/chosen": -0.5009629726409912,
|
||||
"rewards/margins": 0.4423709511756897,
|
||||
"rewards/rejected": -0.9433339834213257,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.63,
|
||||
"learning_rate": 1.8220596619089573e-07,
|
||||
"logits/chosen": -2.061826229095459,
|
||||
"logits/rejected": -2.0707743167877197,
|
||||
"logps/chosen": -275.9271545410156,
|
||||
"logps/rejected": -368.3133850097656,
|
||||
"loss": 0.6033,
|
||||
"rewards/accuracies": 0.699999988079071,
|
||||
"rewards/chosen": -0.5269793272018433,
|
||||
"rewards/margins": 0.3954086899757385,
|
||||
"rewards/rejected": -0.9223880767822266,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.69,
|
||||
"learning_rate": 1.3139467229135998e-07,
|
||||
"logits/chosen": -2.105185031890869,
|
||||
"logits/rejected": -2.079219341278076,
|
||||
"logps/chosen": -246.35910034179688,
|
||||
"logps/rejected": -346.08642578125,
|
||||
"loss": 0.594,
|
||||
"rewards/accuracies": 0.6625000238418579,
|
||||
"rewards/chosen": -0.5222919583320618,
|
||||
"rewards/margins": 0.4267689287662506,
|
||||
"rewards/rejected": -0.9490607976913452,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.75,
|
||||
"learning_rate": 8.628481651367875e-08,
|
||||
"logits/chosen": -2.107372760772705,
|
||||
"logits/rejected": -2.0185680389404297,
|
||||
"logps/chosen": -271.4783935546875,
|
||||
"logps/rejected": -370.3096923828125,
|
||||
"loss": 0.5906,
|
||||
"rewards/accuracies": 0.6875,
|
||||
"rewards/chosen": -0.5639175176620483,
|
||||
"rewards/margins": 0.45396023988723755,
|
||||
"rewards/rejected": -1.0178776979446411,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.82,
|
||||
"learning_rate": 4.904486005914027e-08,
|
||||
"logits/chosen": -2.119300365447998,
|
||||
"logits/rejected": -2.106173515319824,
|
||||
"logps/chosen": -282.1510009765625,
|
||||
"logps/rejected": -376.592041015625,
|
||||
"loss": 0.5895,
|
||||
"rewards/accuracies": 0.643750011920929,
|
||||
"rewards/chosen": -0.6762362718582153,
|
||||
"rewards/margins": 0.3490751385688782,
|
||||
"rewards/rejected": -1.0253114700317383,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.88,
|
||||
"learning_rate": 2.1464952759020856e-08,
|
||||
"logits/chosen": -2.127058267593384,
|
||||
"logits/rejected": -2.0316877365112305,
|
||||
"logps/chosen": -290.1690979003906,
|
||||
"logps/rejected": -389.51116943359375,
|
||||
"loss": 0.5877,
|
||||
"rewards/accuracies": 0.699999988079071,
|
||||
"rewards/chosen": -0.6831713318824768,
|
||||
"rewards/margins": 0.4633623957633972,
|
||||
"rewards/rejected": -1.146533727645874,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.94,
|
||||
"learning_rate": 4.8708793644441086e-09,
|
||||
"logits/chosen": -2.0759072303771973,
|
||||
"logits/rejected": -2.021393299102783,
|
||||
"logps/chosen": -278.86285400390625,
|
||||
"logps/rejected": -323.4399108886719,
|
||||
"loss": 0.5954,
|
||||
"rewards/accuracies": 0.6499999761581421,
|
||||
"rewards/chosen": -0.6692460775375366,
|
||||
"rewards/margins": 0.32712554931640625,
|
||||
"rewards/rejected": -0.9963716268539429,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 159,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.6192928140268386,
|
||||
"train_runtime": 2654.4881,
|
||||
"train_samples_per_second": 7.677,
|
||||
"train_steps_per_second": 0.06
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 159,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 100,
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 8,
|
||||
"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 sha256:9f8e9d068b0cb3de657bf5963e8fe253dc24a8a63e3a73f99045fde2b4edb0f2
|
||||
size 6008
|
||||
Reference in New Issue
Block a user