ShenaoZhang
commited on
Model save
Browse files- README.md +60 -0
- all_results.json +8 -0
- config.json +26 -0
- generation_config.json +6 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +298 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +48 -0
- train_results.json +8 -0
- trainer_state.json +286 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: ShenaoZhang/0.001_idpo_same_replacechosen_iter_1
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: 0.001_idpo_same_replacechosen_iter_2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# 0.001_idpo_same_replacechosen_iter_2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [ShenaoZhang/0.001_idpo_same_replacechosen_iter_1](https://huggingface.co/ShenaoZhang/0.001_idpo_same_replacechosen_iter_1) on the None dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-07
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: multi-GPU
|
42 |
+
- num_devices: 8
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 128
|
45 |
+
- total_eval_batch_size: 64
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 1
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.36.2
|
58 |
+
- Pytorch 2.1.2+cu121
|
59 |
+
- Datasets 2.14.6
|
60 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6222286434293544,
|
4 |
+
"train_runtime": 4182.97,
|
5 |
+
"train_samples": 20378,
|
6 |
+
"train_samples_per_second": 4.872,
|
7 |
+
"train_steps_per_second": 0.038
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ShenaoZhang/0.001_idpo_same_replacechosen_iter_1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.36.2",
|
24 |
+
"use_cache": false,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b92ecba1e11bcfc702c54f87238a3dbc8702b2a5fd10defe842685e92f804fd6
|
3 |
+
size 4943162336
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e358f9f8e6c8bed5ecf4920dc95c987ebabb2a32e8912af93d48c6e3a1ec6ed2
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95cf0f2973bf781b1d39b75fb2a53a365447c86399b1eba25f226939e8088f0a
|
3 |
+
size 4540516344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
297 |
+
}
|
298 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"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 %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"model_max_length": 2048,
|
41 |
+
"pad_token": "</s>",
|
42 |
+
"sp_model_kwargs": {},
|
43 |
+
"spaces_between_special_tokens": false,
|
44 |
+
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"truncation_side": "left",
|
46 |
+
"unk_token": "<unk>",
|
47 |
+
"use_default_system_prompt": true
|
48 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6222286434293544,
|
4 |
+
"train_runtime": 4182.97,
|
5 |
+
"train_samples": 20378,
|
6 |
+
"train_samples_per_second": 4.872,
|
7 |
+
"train_steps_per_second": 0.038
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9968652037617555,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 159,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 3.125e-08,
|
14 |
+
"logits/chosen": -2.6679039001464844,
|
15 |
+
"logits/rejected": -2.5546512603759766,
|
16 |
+
"logps/chosen": -164.941650390625,
|
17 |
+
"logps/pi_response": -79.30451965332031,
|
18 |
+
"logps/ref_response": -79.30451965332031,
|
19 |
+
"logps/rejected": -140.9091339111328,
|
20 |
+
"loss": 0.6931,
|
21 |
+
"rewards/accuracies": 0.0,
|
22 |
+
"rewards/chosen": 0.0,
|
23 |
+
"rewards/margins": 0.0,
|
24 |
+
"rewards/rejected": 0.0,
|
25 |
+
"step": 1
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.06,
|
29 |
+
"learning_rate": 3.1249999999999997e-07,
|
30 |
+
"logits/chosen": -2.6873955726623535,
|
31 |
+
"logits/rejected": -2.689854145050049,
|
32 |
+
"logps/chosen": -237.33799743652344,
|
33 |
+
"logps/pi_response": -119.61322784423828,
|
34 |
+
"logps/ref_response": -118.72599029541016,
|
35 |
+
"logps/rejected": -235.4971466064453,
|
36 |
+
"loss": 0.6916,
|
37 |
+
"rewards/accuracies": 0.4722222089767456,
|
38 |
+
"rewards/chosen": -0.011896245181560516,
|
39 |
+
"rewards/margins": 0.0006968590896576643,
|
40 |
+
"rewards/rejected": -0.012593105435371399,
|
41 |
+
"step": 10
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.13,
|
45 |
+
"learning_rate": 4.990353313429303e-07,
|
46 |
+
"logits/chosen": -2.7025179862976074,
|
47 |
+
"logits/rejected": -2.67500638961792,
|
48 |
+
"logps/chosen": -270.3321838378906,
|
49 |
+
"logps/pi_response": -143.97360229492188,
|
50 |
+
"logps/ref_response": -130.33164978027344,
|
51 |
+
"logps/rejected": -248.6990966796875,
|
52 |
+
"loss": 0.6777,
|
53 |
+
"rewards/accuracies": 0.4937500059604645,
|
54 |
+
"rewards/chosen": -0.16961950063705444,
|
55 |
+
"rewards/margins": 0.03370685502886772,
|
56 |
+
"rewards/rejected": -0.20332637429237366,
|
57 |
+
"step": 20
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.19,
|
61 |
+
"learning_rate": 4.882681251368548e-07,
|
62 |
+
"logits/chosen": -2.5037894248962402,
|
63 |
+
"logits/rejected": -2.4394562244415283,
|
64 |
+
"logps/chosen": -244.659423828125,
|
65 |
+
"logps/pi_response": -130.29275512695312,
|
66 |
+
"logps/ref_response": -112.08052825927734,
|
67 |
+
"logps/rejected": -252.48519897460938,
|
68 |
+
"loss": 0.6661,
|
69 |
+
"rewards/accuracies": 0.5687500238418579,
|
70 |
+
"rewards/chosen": -0.18323533236980438,
|
71 |
+
"rewards/margins": 0.1224108338356018,
|
72 |
+
"rewards/rejected": -0.3056461215019226,
|
73 |
+
"step": 30
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.25,
|
77 |
+
"learning_rate": 4.6604720940421207e-07,
|
78 |
+
"logits/chosen": -2.298877239227295,
|
79 |
+
"logits/rejected": -2.2800426483154297,
|
80 |
+
"logps/chosen": -256.75372314453125,
|
81 |
+
"logps/pi_response": -161.98574829101562,
|
82 |
+
"logps/ref_response": -110.90777587890625,
|
83 |
+
"logps/rejected": -324.766845703125,
|
84 |
+
"loss": 0.6473,
|
85 |
+
"rewards/accuracies": 0.6812499761581421,
|
86 |
+
"rewards/chosen": -0.49192649126052856,
|
87 |
+
"rewards/margins": 0.17362619936466217,
|
88 |
+
"rewards/rejected": -0.6655526757240295,
|
89 |
+
"step": 40
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.31,
|
93 |
+
"learning_rate": 4.3344075855595097e-07,
|
94 |
+
"logits/chosen": -2.197845935821533,
|
95 |
+
"logits/rejected": -2.1729886531829834,
|
96 |
+
"logps/chosen": -286.7721252441406,
|
97 |
+
"logps/pi_response": -180.2733917236328,
|
98 |
+
"logps/ref_response": -117.65016174316406,
|
99 |
+
"logps/rejected": -298.1932678222656,
|
100 |
+
"loss": 0.6403,
|
101 |
+
"rewards/accuracies": 0.59375,
|
102 |
+
"rewards/chosen": -0.5857284069061279,
|
103 |
+
"rewards/margins": 0.10038965940475464,
|
104 |
+
"rewards/rejected": -0.6861181259155273,
|
105 |
+
"step": 50
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.38,
|
109 |
+
"learning_rate": 3.920161866827889e-07,
|
110 |
+
"logits/chosen": -2.1232476234436035,
|
111 |
+
"logits/rejected": -2.0888590812683105,
|
112 |
+
"logps/chosen": -276.8944396972656,
|
113 |
+
"logps/pi_response": -186.1301727294922,
|
114 |
+
"logps/ref_response": -108.0089340209961,
|
115 |
+
"logps/rejected": -310.871826171875,
|
116 |
+
"loss": 0.6327,
|
117 |
+
"rewards/accuracies": 0.6625000238418579,
|
118 |
+
"rewards/chosen": -0.5667150020599365,
|
119 |
+
"rewards/margins": 0.3353308141231537,
|
120 |
+
"rewards/rejected": -0.9020459055900574,
|
121 |
+
"step": 60
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.44,
|
125 |
+
"learning_rate": 3.4376480090239047e-07,
|
126 |
+
"logits/chosen": -2.0895802974700928,
|
127 |
+
"logits/rejected": -2.040750503540039,
|
128 |
+
"logps/chosen": -284.739501953125,
|
129 |
+
"logps/pi_response": -197.33822631835938,
|
130 |
+
"logps/ref_response": -112.66800689697266,
|
131 |
+
"logps/rejected": -308.96185302734375,
|
132 |
+
"loss": 0.6129,
|
133 |
+
"rewards/accuracies": 0.668749988079071,
|
134 |
+
"rewards/chosen": -0.746911883354187,
|
135 |
+
"rewards/margins": 0.3234737515449524,
|
136 |
+
"rewards/rejected": -1.0703856945037842,
|
137 |
+
"step": 70
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.5,
|
141 |
+
"learning_rate": 2.910060778827554e-07,
|
142 |
+
"logits/chosen": -2.077698230743408,
|
143 |
+
"logits/rejected": -2.019683361053467,
|
144 |
+
"logps/chosen": -285.592529296875,
|
145 |
+
"logps/pi_response": -201.0194549560547,
|
146 |
+
"logps/ref_response": -101.95613098144531,
|
147 |
+
"logps/rejected": -329.99365234375,
|
148 |
+
"loss": 0.6269,
|
149 |
+
"rewards/accuracies": 0.706250011920929,
|
150 |
+
"rewards/chosen": -0.8359489440917969,
|
151 |
+
"rewards/margins": 0.2896420359611511,
|
152 |
+
"rewards/rejected": -1.1255908012390137,
|
153 |
+
"step": 80
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.56,
|
157 |
+
"learning_rate": 2.3627616503391812e-07,
|
158 |
+
"logits/chosen": -2.1262636184692383,
|
159 |
+
"logits/rejected": -2.0831663608551025,
|
160 |
+
"logps/chosen": -301.2969970703125,
|
161 |
+
"logps/pi_response": -201.43801879882812,
|
162 |
+
"logps/ref_response": -100.02299499511719,
|
163 |
+
"logps/rejected": -323.3294677734375,
|
164 |
+
"loss": 0.6113,
|
165 |
+
"rewards/accuracies": 0.65625,
|
166 |
+
"rewards/chosen": -0.8298277854919434,
|
167 |
+
"rewards/margins": 0.32933610677719116,
|
168 |
+
"rewards/rejected": -1.1591640710830688,
|
169 |
+
"step": 90
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.63,
|
173 |
+
"learning_rate": 1.8220596619089573e-07,
|
174 |
+
"logits/chosen": -2.0351803302764893,
|
175 |
+
"logits/rejected": -2.0266597270965576,
|
176 |
+
"logps/chosen": -320.48626708984375,
|
177 |
+
"logps/pi_response": -233.0988311767578,
|
178 |
+
"logps/ref_response": -112.04389953613281,
|
179 |
+
"logps/rejected": -384.39801025390625,
|
180 |
+
"loss": 0.5891,
|
181 |
+
"rewards/accuracies": 0.699999988079071,
|
182 |
+
"rewards/chosen": -1.0577332973480225,
|
183 |
+
"rewards/margins": 0.3904644846916199,
|
184 |
+
"rewards/rejected": -1.4481977224349976,
|
185 |
+
"step": 100
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.69,
|
189 |
+
"learning_rate": 1.3139467229135998e-07,
|
190 |
+
"logits/chosen": -2.0701494216918945,
|
191 |
+
"logits/rejected": -2.0804686546325684,
|
192 |
+
"logps/chosen": -326.40399169921875,
|
193 |
+
"logps/pi_response": -230.00381469726562,
|
194 |
+
"logps/ref_response": -100.44270324707031,
|
195 |
+
"logps/rejected": -366.92144775390625,
|
196 |
+
"loss": 0.6036,
|
197 |
+
"rewards/accuracies": 0.6499999761581421,
|
198 |
+
"rewards/chosen": -1.151390552520752,
|
199 |
+
"rewards/margins": 0.32332736253738403,
|
200 |
+
"rewards/rejected": -1.4747179746627808,
|
201 |
+
"step": 110
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.75,
|
205 |
+
"learning_rate": 8.628481651367875e-08,
|
206 |
+
"logits/chosen": -2.0780344009399414,
|
207 |
+
"logits/rejected": -2.005913019180298,
|
208 |
+
"logps/chosen": -350.05859375,
|
209 |
+
"logps/pi_response": -259.2313537597656,
|
210 |
+
"logps/ref_response": -129.4988250732422,
|
211 |
+
"logps/rejected": -373.9602355957031,
|
212 |
+
"loss": 0.5968,
|
213 |
+
"rewards/accuracies": 0.6875,
|
214 |
+
"rewards/chosen": -1.1450227499008179,
|
215 |
+
"rewards/margins": 0.2739308774471283,
|
216 |
+
"rewards/rejected": -1.4189536571502686,
|
217 |
+
"step": 120
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.82,
|
221 |
+
"learning_rate": 4.904486005914027e-08,
|
222 |
+
"logits/chosen": -2.1151814460754395,
|
223 |
+
"logits/rejected": -2.09941029548645,
|
224 |
+
"logps/chosen": -314.6081848144531,
|
225 |
+
"logps/pi_response": -237.43270874023438,
|
226 |
+
"logps/ref_response": -112.079345703125,
|
227 |
+
"logps/rejected": -380.1162414550781,
|
228 |
+
"loss": 0.5854,
|
229 |
+
"rewards/accuracies": 0.6625000238418579,
|
230 |
+
"rewards/chosen": -1.1245102882385254,
|
231 |
+
"rewards/margins": 0.32735899090766907,
|
232 |
+
"rewards/rejected": -1.4518693685531616,
|
233 |
+
"step": 130
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.88,
|
237 |
+
"learning_rate": 2.1464952759020856e-08,
|
238 |
+
"logits/chosen": -2.0996551513671875,
|
239 |
+
"logits/rejected": -2.0452041625976562,
|
240 |
+
"logps/chosen": -353.1548767089844,
|
241 |
+
"logps/pi_response": -273.06121826171875,
|
242 |
+
"logps/ref_response": -119.2865219116211,
|
243 |
+
"logps/rejected": -395.5834045410156,
|
244 |
+
"loss": 0.5958,
|
245 |
+
"rewards/accuracies": 0.6937500238418579,
|
246 |
+
"rewards/chosen": -1.241917371749878,
|
247 |
+
"rewards/margins": 0.4515906274318695,
|
248 |
+
"rewards/rejected": -1.6935079097747803,
|
249 |
+
"step": 140
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.94,
|
253 |
+
"learning_rate": 4.8708793644441086e-09,
|
254 |
+
"logits/chosen": -2.0539727210998535,
|
255 |
+
"logits/rejected": -2.024879217147827,
|
256 |
+
"logps/chosen": -331.5842590332031,
|
257 |
+
"logps/pi_response": -237.0673370361328,
|
258 |
+
"logps/ref_response": -101.13041687011719,
|
259 |
+
"logps/rejected": -359.00762939453125,
|
260 |
+
"loss": 0.5711,
|
261 |
+
"rewards/accuracies": 0.65625,
|
262 |
+
"rewards/chosen": -1.1688032150268555,
|
263 |
+
"rewards/margins": 0.34362536668777466,
|
264 |
+
"rewards/rejected": -1.5124285221099854,
|
265 |
+
"step": 150
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.0,
|
269 |
+
"step": 159,
|
270 |
+
"total_flos": 0.0,
|
271 |
+
"train_loss": 0.6222286434293544,
|
272 |
+
"train_runtime": 4182.97,
|
273 |
+
"train_samples_per_second": 4.872,
|
274 |
+
"train_steps_per_second": 0.038
|
275 |
+
}
|
276 |
+
],
|
277 |
+
"logging_steps": 10,
|
278 |
+
"max_steps": 159,
|
279 |
+
"num_input_tokens_seen": 0,
|
280 |
+
"num_train_epochs": 1,
|
281 |
+
"save_steps": 100,
|
282 |
+
"total_flos": 0.0,
|
283 |
+
"train_batch_size": 8,
|
284 |
+
"trial_name": null,
|
285 |
+
"trial_params": null
|
286 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aac4ac7f0ef9ff0bdf7d3f7c7bf4d7b1ace76dc2d1b75bff50cd2b85a240b732
|
3 |
+
size 6008
|