Hugging Face's logo

Holarissun
/
RM-HH-GPT2Large_helpful_gpt3_loraR64_40000_gpt2-large_shuffleFalse_extractchosenFalse

PEFT
Safetensors
trl
reward-trainer
Generated from Trainer
Model card Files Community
Holarissun commited on
Commit
2e1fea3
•
1 Parent(s): 76d5f4a

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_shuffleFalse_extractchosenFalse
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_shuffleFalse_extractchosenFalse
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: 0.0335
24
+ - Accuracy: 0.9906
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
+ | 0.6956 | 0.02 | 250 | 0.5812 | 0.7384 |
58
+ | 0.6388 | 0.04 | 500 | 0.3891 | 0.9145 |
59
+ | 0.5931 | 0.06 | 750 | 0.2579 | 0.9580 |
60
+ | 0.5705 | 0.08 | 1000 | 0.1982 | 0.9750 |
61
+ | 0.5449 | 0.1 | 1250 | 0.1534 | 0.9797 |
62
+ | 0.577 | 0.13 | 1500 | 0.1506 | 0.9821 |
63
+ | 0.5225 | 0.15 | 1750 | 0.1299 | 0.9836 |
64
+ | 0.5516 | 0.17 | 2000 | 0.1285 | 0.9866 |
65
+ | 0.5528 | 0.19 | 2250 | 0.1244 | 0.9870 |
66
+ | 0.579 | 0.21 | 2500 | 0.1299 | 0.9881 |
67
+ | 0.5386 | 0.23 | 2750 | 0.1140 | 0.9881 |
68
+ | 0.5427 | 0.25 | 3000 | 0.1057 | 0.9885 |
69
+ | 0.5502 | 0.27 | 3250 | 0.1000 | 0.9889 |
70
+ | 0.5309 | 0.29 | 3500 | 0.0818 | 0.9895 |
71
+ | 0.558 | 0.31 | 3750 | 0.0966 | 0.9896 |
72
+ | 0.5523 | 0.33 | 4000 | 0.0833 | 0.9898 |
73
+ | 0.545 | 0.36 | 4250 | 0.0920 | 0.9902 |
74
+ | 0.5402 | 0.38 | 4500 | 0.0928 | 0.9898 |
75
+ | 0.5271 | 0.4 | 4750 | 0.0824 | 0.9902 |
76
+ | 0.5613 | 0.42 | 5000 | 0.0903 | 0.9915 |
77
+ | 0.5064 | 0.44 | 5250 | 0.0723 | 0.9913 |
78
+ | 0.5714 | 0.46 | 5500 | 0.0738 | 0.9915 |
79
+ | 0.5285 | 0.48 | 5750 | 0.0756 | 0.9908 |
80
+ | 0.5311 | 0.5 | 6000 | 0.0757 | 0.9906 |
81
+ | 0.5205 | 0.52 | 6250 | 0.0730 | 0.9895 |
82
+ | 0.5311 | 0.54 | 6500 | 0.0729 | 0.9904 |
83
+ | 0.5209 | 0.57 | 6750 | 0.0666 | 0.9896 |
84
+ | 0.5529 | 0.59 | 7000 | 0.0795 | 0.9904 |
85
+ | 0.5495 | 0.61 | 7250 | 0.0698 | 0.9910 |
86
+ | 0.5184 | 0.63 | 7500 | 0.0695 | 0.9902 |
87
+ | 0.5609 | 0.65 | 7750 | 0.0722 | 0.9904 |
88
+ | 0.5024 | 0.67 | 8000 | 0.0656 | 0.9904 |
89
+ | 0.5536 | 0.69 | 8250 | 0.0779 | 0.9889 |
90
+ | 0.5402 | 0.71 | 8500 | 0.0715 | 0.9893 |
91
+ | 0.5204 | 0.73 | 8750 | 0.0681 | 0.9896 |
92
+ | 0.544 | 0.75 | 9000 | 0.0700 | 0.9896 |
93
+ | 0.5502 | 0.77 | 9250 | 0.0722 | 0.9902 |
94
+ | 0.5334 | 0.8 | 9500 | 0.0650 | 0.9910 |
95
+ | 0.5229 | 0.82 | 9750 | 0.0606 | 0.9900 |
96
+ | 0.5235 | 0.84 | 10000 | 0.0525 | 0.9906 |
97
+ | 0.534 | 0.86 | 10250 | 0.0623 | 0.9895 |
98
+ | 0.5314 | 0.88 | 10500 | 0.0561 | 0.9904 |
99
+ | 0.5311 | 0.9 | 10750 | 0.0503 | 0.9902 |
100
+ | 0.5457 | 0.92 | 11000 | 0.0515 | 0.9910 |
101
+ | 0.548 | 0.94 | 11250 | 0.0589 | 0.9910 |
102
+ | 0.5504 | 0.96 | 11500 | 0.0612 | 0.9908 |
103
+ | 0.5102 | 0.98 | 11750 | 0.0501 | 0.9908 |
104
+ | 0.5197 | 1.0 | 12000 | 0.0505 | 0.9913 |
105
+ | 0.5406 | 1.03 | 12250 | 0.0458 | 0.9908 |
106
+ | 0.5372 | 1.05 | 12500 | 0.0468 | 0.9908 |
107
+ | 0.4972 | 1.07 | 12750 | 0.0429 | 0.9910 |
108
+ | 0.5059 | 1.09 | 13000 | 0.0422 | 0.9906 |
109
+ | 0.536 | 1.11 | 13250 | 0.0462 | 0.9900 |
110
+ | 0.5116 | 1.13 | 13500 | 0.0408 | 0.9904 |
111
+ | 0.5504 | 1.15 | 13750 | 0.0479 | 0.9908 |
112
+ | 0.5393 | 1.17 | 14000 | 0.0462 | 0.9908 |
113
+ | 0.511 | 1.19 | 14250 | 0.0426 | 0.9908 |
114
+ | 0.5059 | 1.21 | 14500 | 0.0403 | 0.9906 |
115
+ | 0.5324 | 1.23 | 14750 | 0.0381 | 0.9906 |
116
+ | 0.5227 | 1.26 | 15000 | 0.0368 | 0.9906 |
117
+ | 0.5377 | 1.28 | 15250 | 0.0442 | 0.9904 |
118
+ | 0.5269 | 1.3 | 15500 | 0.0446 | 0.9906 |
119
+ | 0.5088 | 1.32 | 15750 | 0.0487 | 0.9904 |
120
+ | 0.5271 | 1.34 | 16000 | 0.0474 | 0.9908 |
121
+ | 0.4952 | 1.36 | 16250 | 0.0377 | 0.9915 |
122
+ | 0.5201 | 1.38 | 16500 | 0.0392 | 0.9906 |
123
+ | 0.5316 | 1.4 | 16750 | 0.0431 | 0.9908 |
124
+ | 0.5186 | 1.42 | 17000 | 0.0421 | 0.9900 |
125
+ | 0.4963 | 1.44 | 17250 | 0.0366 | 0.9908 |
126
+ | 0.5324 | 1.46 | 17500 | 0.0392 | 0.9906 |
127
+ | 0.5257 | 1.49 | 17750 | 0.0392 | 0.9911 |
128
+ | 0.4908 | 1.51 | 18000 | 0.0348 | 0.9910 |
129
+ | 0.5186 | 1.53 | 18250 | 0.0371 | 0.9906 |
130
+ | 0.5385 | 1.55 | 18500 | 0.0385 | 0.9906 |
131
+ | 0.5267 | 1.57 | 18750 | 0.0370 | 0.9910 |
132
+ | 0.5294 | 1.59 | 19000 | 0.0372 | 0.9906 |
133
+ | 0.5243 | 1.61 | 19250 | 0.0360 | 0.9908 |
134
+ | 0.5414 | 1.63 | 19500 | 0.0376 | 0.9906 |
135
+ | 0.5171 | 1.65 | 19750 | 0.0403 | 0.9904 |
136
+ | 0.5081 | 1.67 | 20000 | 0.0363 | 0.9908 |
137
+ | 0.543 | 1.7 | 20250 | 0.0353 | 0.9908 |
138
+ | 0.5121 | 1.72 | 20500 | 0.0341 | 0.9910 |
139
+ | 0.5047 | 1.74 | 20750 | 0.0330 | 0.9908 |
140
+ | 0.5386 | 1.76 | 21000 | 0.0327 | 0.9911 |
141
+ | 0.5261 | 1.78 | 21250 | 0.0341 | 0.9910 |
142
+ | 0.4973 | 1.8 | 21500 | 0.0329 | 0.9913 |
143
+ | 0.5185 | 1.82 | 21750 | 0.0329 | 0.9911 |
144
+ | 0.5215 | 1.84 | 22000 | 0.0325 | 0.9911 |
145
+ | 0.4922 | 1.86 | 22250 | 0.0314 | 0.9911 |
146
+ | 0.5354 | 1.88 | 22500 | 0.0327 | 0.9908 |
147
+ | 0.5489 | 1.9 | 22750 | 0.0337 | 0.9911 |
148
+ | 0.538 | 1.93 | 23000 | 0.0336 | 0.9913 |
149
+ | 0.508 | 1.95 | 23250 | 0.0335 | 0.9910 |
150
+ | 0.5316 | 1.97 | 23500 | 0.0333 | 0.9910 |
151
+ | 0.5496 | 1.99 | 23750 | 0.0335 | 0.9906 |
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:a011b1e9601f060a98c50ad3a67d59b4fe73151741992cb8c49df458db67b226
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:daa746d3dd20736e30e6443b9c49253ce58824af2d765d21799d2d68c01159a3
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff