初始化项目，由ModelHub XC社区提供模型
Model: ShenaoZhang/0.001_idpo_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_iter_1
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- dpo
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- ShenaoZhang/0.001_idpo_dataset
|
||||
model-index:
|
||||
- name: 0.001_idpo_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_iter_2
|
||||
|
||||
This model is a fine-tuned version of [ShenaoZhang/0.001_idpo_iter_1](https://huggingface.co/ShenaoZhang/0.001_idpo_iter_1) on the ShenaoZhang/0.001_idpo_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": 0.6627466093819097,
|
||||
"train_runtime": 2639.006,
|
||||
"train_samples": 20378,
|
||||
"train_samples_per_second": 7.722,
|
||||
"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_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 sha256:7c671cb00276c058cedcbf63951c962668146e9edf87ce4b13ce9be75695b487
|
||||
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 sha256:5964cfe00f34166526934d9dc45f4b503dbcc5640f12423fdef7d5a98c8a5f93
|
||||
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 sha256:0340ce98a2aefb937b1c88a8e6391594ce0707f3276fa1ecd0fb2bf2ca412f0d
|
||||
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": 0.6627466093819097,
|
||||
"train_runtime": 2639.006,
|
||||
"train_samples": 20378,
|
||||
"train_samples_per_second": 7.722,
|
||||
"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": -2.605907440185547,
|
||||
"logps/chosen": -143.16458129882812,
|
||||
"logps/rejected": -148.07847595214844,
|
||||
"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": -2.69895076751709,
|
||||
"logits/rejected": -2.6911985874176025,
|
||||
"logps/chosen": -234.76565551757812,
|
||||
"logps/rejected": -260.6521911621094,
|
||||
"loss": 0.6922,
|
||||
"rewards/accuracies": 0.4166666567325592,
|
||||
"rewards/chosen": -0.010081589221954346,
|
||||
"rewards/margins": -0.0022414023987948895,
|
||||
"rewards/rejected": -0.007840188220143318,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.13,
|
||||
"learning_rate": 4.990353313429303e-07,
|
||||
"logits/chosen": -2.6826164722442627,
|
||||
"logits/rejected": -2.676023006439209,
|
||||
"logps/chosen": -270.6432189941406,
|
||||
"logps/rejected": -290.40869140625,
|
||||
"loss": 0.6794,
|
||||
"rewards/accuracies": 0.5062500238418579,
|
||||
"rewards/chosen": -0.2684400975704193,
|
||||
"rewards/margins": 0.04983901605010033,
|
||||
"rewards/rejected": -0.31827908754348755,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.19,
|
||||
"learning_rate": 4.882681251368548e-07,
|
||||
"logits/chosen": -2.6072068214416504,
|
||||
"logits/rejected": -2.588265895843506,
|
||||
"logps/chosen": -228.98974609375,
|
||||
"logps/rejected": -268.8215637207031,
|
||||
"loss": 0.6895,
|
||||
"rewards/accuracies": 0.5625,
|
||||
"rewards/chosen": -0.09740053117275238,
|
||||
"rewards/margins": 0.05857750028371811,
|
||||
"rewards/rejected": -0.1559780389070511,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"learning_rate": 4.6604720940421207e-07,
|
||||
"logits/chosen": -2.5079424381256104,
|
||||
"logits/rejected": -2.485220432281494,
|
||||
"logps/chosen": -233.1949462890625,
|
||||
"logps/rejected": -272.9608459472656,
|
||||
"loss": 0.6737,
|
||||
"rewards/accuracies": 0.5874999761581421,
|
||||
"rewards/chosen": -0.1403357833623886,
|
||||
"rewards/margins": 0.14330314099788666,
|
||||
"rewards/rejected": -0.28363892436027527,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"learning_rate": 4.3344075855595097e-07,
|
||||
"logits/chosen": -2.430572986602783,
|
||||
"logits/rejected": -2.4246697425842285,
|
||||
"logps/chosen": -258.1377868652344,
|
||||
"logps/rejected": -303.17877197265625,
|
||||
"loss": 0.6657,
|
||||
"rewards/accuracies": 0.5687500238418579,
|
||||
"rewards/chosen": -0.4008946418762207,
|
||||
"rewards/margins": 0.11444135755300522,
|
||||
"rewards/rejected": -0.5153360366821289,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.38,
|
||||
"learning_rate": 3.920161866827889e-07,
|
||||
"logits/chosen": -2.3226020336151123,
|
||||
"logits/rejected": -2.313552141189575,
|
||||
"logps/chosen": -289.2204284667969,
|
||||
"logps/rejected": -296.24609375,
|
||||
"loss": 0.6682,
|
||||
"rewards/accuracies": 0.59375,
|
||||
"rewards/chosen": -0.5691416263580322,
|
||||
"rewards/margins": 0.10885188728570938,
|
||||
"rewards/rejected": -0.6779934167861938,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"learning_rate": 3.4376480090239047e-07,
|
||||
"logits/chosen": -2.2763919830322266,
|
||||
"logits/rejected": -2.2820637226104736,
|
||||
"logps/chosen": -253.41159057617188,
|
||||
"logps/rejected": -296.48333740234375,
|
||||
"loss": 0.667,
|
||||
"rewards/accuracies": 0.574999988079071,
|
||||
"rewards/chosen": -0.4127040505409241,
|
||||
"rewards/margins": 0.14596061408519745,
|
||||
"rewards/rejected": -0.5586646199226379,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 2.910060778827554e-07,
|
||||
"logits/chosen": -2.2447080612182617,
|
||||
"logits/rejected": -2.2723259925842285,
|
||||
"logps/chosen": -234.634521484375,
|
||||
"logps/rejected": -309.20513916015625,
|
||||
"loss": 0.653,
|
||||
"rewards/accuracies": 0.581250011920929,
|
||||
"rewards/chosen": -0.40885549783706665,
|
||||
"rewards/margins": 0.18530671298503876,
|
||||
"rewards/rejected": -0.5941622257232666,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.56,
|
||||
"learning_rate": 2.3627616503391812e-07,
|
||||
"logits/chosen": -2.330038070678711,
|
||||
"logits/rejected": -2.3056416511535645,
|
||||
"logps/chosen": -243.3378448486328,
|
||||
"logps/rejected": -270.39666748046875,
|
||||
"loss": 0.6571,
|
||||
"rewards/accuracies": 0.5375000238418579,
|
||||
"rewards/chosen": -0.4189552664756775,
|
||||
"rewards/margins": 0.1503242701292038,
|
||||
"rewards/rejected": -0.5692795515060425,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.63,
|
||||
"learning_rate": 1.8220596619089573e-07,
|
||||
"logits/chosen": -2.235563278198242,
|
||||
"logits/rejected": -2.2629618644714355,
|
||||
"logps/chosen": -269.2986145019531,
|
||||
"logps/rejected": -299.86138916015625,
|
||||
"loss": 0.6631,
|
||||
"rewards/accuracies": 0.65625,
|
||||
"rewards/chosen": -0.46052223443984985,
|
||||
"rewards/margins": 0.18169686198234558,
|
||||
"rewards/rejected": -0.6422190070152283,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.69,
|
||||
"learning_rate": 1.3139467229135998e-07,
|
||||
"logits/chosen": -2.3022847175598145,
|
||||
"logits/rejected": -2.3016762733459473,
|
||||
"logps/chosen": -234.77597045898438,
|
||||
"logps/rejected": -316.5335998535156,
|
||||
"loss": 0.6379,
|
||||
"rewards/accuracies": 0.643750011920929,
|
||||
"rewards/chosen": -0.4068765640258789,
|
||||
"rewards/margins": 0.2481352835893631,
|
||||
"rewards/rejected": -0.6550118923187256,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.75,
|
||||
"learning_rate": 8.628481651367875e-08,
|
||||
"logits/chosen": -2.2812705039978027,
|
||||
"logits/rejected": -2.2640042304992676,
|
||||
"logps/chosen": -265.8632507324219,
|
||||
"logps/rejected": -339.9316101074219,
|
||||
"loss": 0.6563,
|
||||
"rewards/accuracies": 0.6187499761581421,
|
||||
"rewards/chosen": -0.49150800704956055,
|
||||
"rewards/margins": 0.2535227835178375,
|
||||
"rewards/rejected": -0.7450307607650757,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.82,
|
||||
"learning_rate": 4.904486005914027e-08,
|
||||
"logits/chosen": -2.3139283657073975,
|
||||
"logits/rejected": -2.327219247817993,
|
||||
"logps/chosen": -259.82452392578125,
|
||||
"logps/rejected": -339.85772705078125,
|
||||
"loss": 0.6411,
|
||||
"rewards/accuracies": 0.637499988079071,
|
||||
"rewards/chosen": -0.4681639075279236,
|
||||
"rewards/margins": 0.2101978361606598,
|
||||
"rewards/rejected": -0.6783617734909058,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.88,
|
||||
"learning_rate": 2.1464952759020856e-08,
|
||||
"logits/chosen": -2.3203117847442627,
|
||||
"logits/rejected": -2.3070220947265625,
|
||||
"logps/chosen": -270.1856994628906,
|
||||
"logps/rejected": -336.08758544921875,
|
||||
"loss": 0.6446,
|
||||
"rewards/accuracies": 0.65625,
|
||||
"rewards/chosen": -0.48976272344589233,
|
||||
"rewards/margins": 0.19642502069473267,
|
||||
"rewards/rejected": -0.686187744140625,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.94,
|
||||
"learning_rate": 4.8708793644441086e-09,
|
||||
"logits/chosen": -2.2997617721557617,
|
||||
"logits/rejected": -2.2623441219329834,
|
||||
"logps/chosen": -261.05316162109375,
|
||||
"logps/rejected": -276.8531188964844,
|
||||
"loss": 0.6467,
|
||||
"rewards/accuracies": 0.5625,
|
||||
"rewards/chosen": -0.49157172441482544,
|
||||
"rewards/margins": 0.11737655103206635,
|
||||
"rewards/rejected": -0.6089483499526978,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 159,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.6627466093819097,
|
||||
"train_runtime": 2639.006,
|
||||
"train_samples_per_second": 7.722,
|
||||
"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:c4bbe803cbb109b7f9c8d058419892cd57841e941df87d4b7d79a88d6313de61
|
||||
size 6008
|
||||
Reference in New Issue
Block a user