Hugging Face's logo

Holarissun
/
RM-HH-GPT2Large_helpful_gpt3_loraR64_40000_gpt2-large_shuffleTrue_extractchosenTrue

PEFT
Safetensors
trl
reward-trainer
Generated from Trainer
Model card Files Community
Holarissun commited on
Commit
496dca8
•
1 Parent(s): 4c973e7

End of training

Browse files
Files changed (9) hide show
  1. README.md +160 -0
  2. adapter_config.json +27 -0
  3. adapter_model.safetensors +3 -0
  4. merges.txt +0 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +20 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - reward-trainer
7
+ - generated_from_trainer
8
+ metrics:
9
+ - accuracy
10
+ base_model: openai-community/gpt2-large
11
+ model-index:
12
+ - name: RM-HH-GPT2Large_helpful_gpt3_loraR64_40000_gpt2-large_shuffleTrue_extractchosenTrue
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # RM-HH-GPT2Large_helpful_gpt3_loraR64_40000_gpt2-large_shuffleTrue_extractchosenTrue
20
+
21
+ This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4911
24
+ - Accuracy: 0.7362
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 1.41e-05
44
+ - train_batch_size: 1
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 4
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 2.0
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
57
+ | 0.8065 | 0.02 | 250 | 0.7702 | 0.4763 |
58
+ | 0.7485 | 0.04 | 500 | 0.6903 | 0.5578 |
59
+ | 0.6625 | 0.06 | 750 | 0.6116 | 0.6516 |
60
+ | 0.5815 | 0.08 | 1000 | 0.5742 | 0.6817 |
61
+ | 0.5657 | 0.1 | 1250 | 0.5565 | 0.6940 |
62
+ | 0.5608 | 0.13 | 1500 | 0.5479 | 0.7015 |
63
+ | 0.5611 | 0.15 | 1750 | 0.5418 | 0.7083 |
64
+ | 0.5342 | 0.17 | 2000 | 0.5386 | 0.7105 |
65
+ | 0.5842 | 0.19 | 2250 | 0.5319 | 0.7124 |
66
+ | 0.5096 | 0.21 | 2500 | 0.5293 | 0.7171 |
67
+ | 0.5234 | 0.23 | 2750 | 0.5258 | 0.7173 |
68
+ | 0.5321 | 0.25 | 3000 | 0.5243 | 0.7202 |
69
+ | 0.5295 | 0.27 | 3250 | 0.5212 | 0.7202 |
70
+ | 0.5211 | 0.29 | 3500 | 0.5220 | 0.7200 |
71
+ | 0.5119 | 0.31 | 3750 | 0.5215 | 0.7205 |
72
+ | 0.509 | 0.33 | 4000 | 0.5200 | 0.7226 |
73
+ | 0.5393 | 0.36 | 4250 | 0.5155 | 0.7230 |
74
+ | 0.5343 | 0.38 | 4500 | 0.5143 | 0.7267 |
75
+ | 0.4944 | 0.4 | 4750 | 0.5195 | 0.7277 |
76
+ | 0.5198 | 0.42 | 5000 | 0.5188 | 0.7258 |
77
+ | 0.523 | 0.44 | 5250 | 0.5206 | 0.7282 |
78
+ | 0.53 | 0.46 | 5500 | 0.5082 | 0.7264 |
79
+ | 0.5107 | 0.48 | 5750 | 0.5103 | 0.7307 |
80
+ | 0.502 | 0.5 | 6000 | 0.5163 | 0.7284 |
81
+ | 0.5198 | 0.52 | 6250 | 0.5132 | 0.7305 |
82
+ | 0.5879 | 0.54 | 6500 | 0.5067 | 0.7313 |
83
+ | 0.5174 | 0.57 | 6750 | 0.5061 | 0.7311 |
84
+ | 0.5062 | 0.59 | 7000 | 0.5053 | 0.7298 |
85
+ | 0.5265 | 0.61 | 7250 | 0.5064 | 0.7303 |
86
+ | 0.5043 | 0.63 | 7500 | 0.5096 | 0.7309 |
87
+ | 0.5291 | 0.65 | 7750 | 0.5073 | 0.7299 |
88
+ | 0.4966 | 0.67 | 8000 | 0.5141 | 0.7305 |
89
+ | 0.5361 | 0.69 | 8250 | 0.5086 | 0.7288 |
90
+ | 0.534 | 0.71 | 8500 | 0.5051 | 0.7288 |
91
+ | 0.5073 | 0.73 | 8750 | 0.5104 | 0.7286 |
92
+ | 0.5155 | 0.75 | 9000 | 0.5138 | 0.7290 |
93
+ | 0.5041 | 0.77 | 9250 | 0.5149 | 0.7294 |
94
+ | 0.5552 | 0.8 | 9500 | 0.5030 | 0.7288 |
95
+ | 0.5177 | 0.82 | 9750 | 0.4995 | 0.7294 |
96
+ | 0.4882 | 0.84 | 10000 | 0.5007 | 0.7337 |
97
+ | 0.5409 | 0.86 | 10250 | 0.4992 | 0.7320 |
98
+ | 0.5044 | 0.88 | 10500 | 0.4994 | 0.7311 |
99
+ | 0.4897 | 0.9 | 10750 | 0.5013 | 0.7322 |
100
+ | 0.509 | 0.92 | 11000 | 0.4999 | 0.7331 |
101
+ | 0.5256 | 0.94 | 11250 | 0.4950 | 0.7360 |
102
+ | 0.4976 | 0.96 | 11500 | 0.4937 | 0.7356 |
103
+ | 0.5033 | 0.98 | 11750 | 0.4952 | 0.7358 |
104
+ | 0.4917 | 1.0 | 12000 | 0.4939 | 0.7333 |
105
+ | 0.4615 | 1.03 | 12250 | 0.5005 | 0.7328 |
106
+ | 0.4797 | 1.05 | 12500 | 0.4981 | 0.7347 |
107
+ | 0.4872 | 1.07 | 12750 | 0.4997 | 0.7362 |
108
+ | 0.5106 | 1.09 | 13000 | 0.5012 | 0.7343 |
109
+ | 0.482 | 1.11 | 13250 | 0.5021 | 0.7365 |
110
+ | 0.4916 | 1.13 | 13500 | 0.4946 | 0.7367 |
111
+ | 0.4957 | 1.15 | 13750 | 0.4972 | 0.7379 |
112
+ | 0.4822 | 1.17 | 14000 | 0.5072 | 0.7379 |
113
+ | 0.4911 | 1.19 | 14250 | 0.5080 | 0.7343 |
114
+ | 0.5042 | 1.21 | 14500 | 0.5148 | 0.7343 |
115
+ | 0.4966 | 1.23 | 14750 | 0.5055 | 0.7350 |
116
+ | 0.527 | 1.26 | 15000 | 0.4945 | 0.7345 |
117
+ | 0.4544 | 1.28 | 15250 | 0.5070 | 0.7354 |
118
+ | 0.5198 | 1.3 | 15500 | 0.4993 | 0.7335 |
119
+ | 0.5138 | 1.32 | 15750 | 0.4958 | 0.7358 |
120
+ | 0.5324 | 1.34 | 16000 | 0.4917 | 0.7348 |
121
+ | 0.4695 | 1.36 | 16250 | 0.4951 | 0.7347 |
122
+ | 0.5016 | 1.38 | 16500 | 0.4938 | 0.7360 |
123
+ | 0.478 | 1.4 | 16750 | 0.4969 | 0.7345 |
124
+ | 0.4955 | 1.42 | 17000 | 0.4958 | 0.7345 |
125
+ | 0.5072 | 1.44 | 17250 | 0.4908 | 0.7341 |
126
+ | 0.4764 | 1.46 | 17500 | 0.4957 | 0.7345 |
127
+ | 0.5096 | 1.49 | 17750 | 0.4928 | 0.7347 |
128
+ | 0.4944 | 1.51 | 18000 | 0.4923 | 0.7331 |
129
+ | 0.4766 | 1.53 | 18250 | 0.4931 | 0.7333 |
130
+ | 0.515 | 1.55 | 18500 | 0.4897 | 0.7339 |
131
+ | 0.4672 | 1.57 | 18750 | 0.4920 | 0.7348 |
132
+ | 0.5122 | 1.59 | 19000 | 0.4921 | 0.7337 |
133
+ | 0.5395 | 1.61 | 19250 | 0.4899 | 0.7333 |
134
+ | 0.5088 | 1.63 | 19500 | 0.4892 | 0.7326 |
135
+ | 0.4864 | 1.65 | 19750 | 0.4895 | 0.7358 |
136
+ | 0.4605 | 1.67 | 20000 | 0.4968 | 0.7358 |
137
+ | 0.5165 | 1.7 | 20250 | 0.4940 | 0.7354 |
138
+ | 0.4955 | 1.72 | 20500 | 0.4919 | 0.7348 |
139
+ | 0.4923 | 1.74 | 20750 | 0.4906 | 0.7348 |
140
+ | 0.5121 | 1.76 | 21000 | 0.4905 | 0.7337 |
141
+ | 0.5068 | 1.78 | 21250 | 0.4892 | 0.7356 |
142
+ | 0.4767 | 1.8 | 21500 | 0.4900 | 0.7350 |
143
+ | 0.4976 | 1.82 | 21750 | 0.4904 | 0.7354 |
144
+ | 0.4934 | 1.84 | 22000 | 0.4893 | 0.7356 |
145
+ | 0.479 | 1.86 | 22250 | 0.4905 | 0.7352 |
146
+ | 0.4698 | 1.88 | 22500 | 0.4909 | 0.7347 |
147
+ | 0.4894 | 1.9 | 22750 | 0.4907 | 0.7352 |
148
+ | 0.509 | 1.93 | 23000 | 0.4907 | 0.7354 |
149
+ | 0.4805 | 1.95 | 23250 | 0.4914 | 0.7350 |
150
+ | 0.5152 | 1.97 | 23500 | 0.4911 | 0.7358 |
151
+ | 0.4935 | 1.99 | 23750 | 0.4911 | 0.7362 |
152
+
153
+
154
+ ### Framework versions
155
+
156
+ - PEFT 0.9.0
157
+ - Transformers 4.38.2
158
+ - Pytorch 2.1.2
159
+ - Datasets 2.18.0
160
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openai-community/gpt2-large",
5
+ "bias": "none",
6
+ "fan_in_fan_out": true,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "c_attn"
23
+ ],
24
+ "task_type": "CAUSAL_LM",
25
+ "use_dora": false,
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1399e4f05454f237782c34cec5a21129be0efaa3c07e3b6f9ffaec859a9aee9b
3
+ size 47195336
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464476c5773510f09f4649c10960aa6bbf786ca8755f889fdf98c0e96ea62628
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff