Holarissun commited on
Commit
9ceb3ed
1 Parent(s): 3cb99ca

End of training

Browse files
README.md ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - reward-trainer
7
+ - generated_from_trainer
8
+ base_model: openai-community/gpt2-large
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: RM-HH-Human_helpful_human_loraR64_40000_gpt2-large_shuffleTrue_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-Human_helpful_human_loraR64_40000_gpt2-large_shuffleTrue_extractchosenFalse
20
+
21
+ This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.6036
24
+ - Accuracy: 0.6751
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
+ | 0.7205 | 0.03 | 250 | 0.7030 | 0.5251 |
58
+ | 0.6845 | 0.06 | 500 | 0.6752 | 0.5739 |
59
+ | 0.6715 | 0.08 | 750 | 0.6636 | 0.5934 |
60
+ | 0.6632 | 0.11 | 1000 | 0.6542 | 0.6102 |
61
+ | 0.6432 | 0.14 | 1250 | 0.6492 | 0.6125 |
62
+ | 0.635 | 0.17 | 1500 | 0.6462 | 0.6200 |
63
+ | 0.6708 | 0.19 | 1750 | 0.6413 | 0.6240 |
64
+ | 0.6565 | 0.22 | 2000 | 0.6394 | 0.6285 |
65
+ | 0.6194 | 0.25 | 2250 | 0.6355 | 0.6315 |
66
+ | 0.6405 | 0.28 | 2500 | 0.6326 | 0.6380 |
67
+ | 0.6431 | 0.31 | 2750 | 0.6285 | 0.6428 |
68
+ | 0.6526 | 0.33 | 3000 | 0.6254 | 0.6415 |
69
+ | 0.639 | 0.36 | 3250 | 0.6246 | 0.6433 |
70
+ | 0.621 | 0.39 | 3500 | 0.6217 | 0.6501 |
71
+ | 0.6305 | 0.42 | 3750 | 0.6200 | 0.6488 |
72
+ | 0.6146 | 0.45 | 4000 | 0.6194 | 0.6501 |
73
+ | 0.6382 | 0.47 | 4250 | 0.6166 | 0.6558 |
74
+ | 0.6211 | 0.5 | 4500 | 0.6143 | 0.6606 |
75
+ | 0.6141 | 0.53 | 4750 | 0.6135 | 0.6601 |
76
+ | 0.6272 | 0.56 | 5000 | 0.6119 | 0.6591 |
77
+ | 0.6242 | 0.58 | 5250 | 0.6103 | 0.6608 |
78
+ | 0.6202 | 0.61 | 5500 | 0.6087 | 0.6658 |
79
+ | 0.6205 | 0.64 | 5750 | 0.6080 | 0.6666 |
80
+ | 0.6268 | 0.67 | 6000 | 0.6069 | 0.6663 |
81
+ | 0.6017 | 0.7 | 6250 | 0.6064 | 0.6638 |
82
+ | 0.5942 | 0.72 | 6500 | 0.6060 | 0.6656 |
83
+ | 0.6186 | 0.75 | 6750 | 0.6053 | 0.6668 |
84
+ | 0.6316 | 0.78 | 7000 | 0.6040 | 0.6688 |
85
+ | 0.6031 | 0.81 | 7250 | 0.6039 | 0.6738 |
86
+ | 0.6143 | 0.84 | 7500 | 0.6021 | 0.6703 |
87
+ | 0.6217 | 0.86 | 7750 | 0.6020 | 0.6759 |
88
+ | 0.6099 | 0.89 | 8000 | 0.6017 | 0.6754 |
89
+ | 0.5951 | 0.92 | 8250 | 0.6010 | 0.6748 |
90
+ | 0.603 | 0.95 | 8500 | 0.6005 | 0.6721 |
91
+ | 0.6098 | 0.97 | 8750 | 0.6005 | 0.6769 |
92
+ | 0.6222 | 1.0 | 9000 | 0.5991 | 0.6741 |
93
+ | 0.6005 | 1.03 | 9250 | 0.5991 | 0.6743 |
94
+ | 0.5972 | 1.06 | 9500 | 0.5998 | 0.6706 |
95
+ | 0.582 | 1.09 | 9750 | 0.6043 | 0.6691 |
96
+ | 0.6004 | 1.11 | 10000 | 0.6187 | 0.6711 |
97
+ | 0.5985 | 1.14 | 10250 | 0.6195 | 0.6663 |
98
+ | 0.6206 | 1.17 | 10500 | 0.6122 | 0.6693 |
99
+ | 0.6216 | 1.2 | 10750 | 0.6069 | 0.6741 |
100
+ | 0.6091 | 1.22 | 11000 | 0.6236 | 0.6691 |
101
+ | 0.5863 | 1.25 | 11250 | 0.6209 | 0.6713 |
102
+ | 0.641 | 1.28 | 11500 | 0.6184 | 0.6698 |
103
+ | 0.6144 | 1.31 | 11750 | 0.6051 | 0.6713 |
104
+ | 0.6527 | 1.34 | 12000 | 0.6067 | 0.6703 |
105
+ | 0.6059 | 1.36 | 12250 | 0.6048 | 0.6711 |
106
+ | 0.6138 | 1.39 | 12500 | 0.6015 | 0.6741 |
107
+ | 0.6376 | 1.42 | 12750 | 0.6002 | 0.6726 |
108
+ | 0.6273 | 1.45 | 13000 | 0.5989 | 0.6721 |
109
+ | 0.6028 | 1.48 | 13250 | 0.6011 | 0.6713 |
110
+ | 0.6116 | 1.5 | 13500 | 0.5999 | 0.6723 |
111
+ | 0.6201 | 1.53 | 13750 | 0.5990 | 0.6733 |
112
+ | 0.606 | 1.56 | 14000 | 0.6024 | 0.6733 |
113
+ | 0.5985 | 1.59 | 14250 | 0.6079 | 0.6716 |
114
+ | 0.664 | 1.61 | 14500 | 0.6019 | 0.6748 |
115
+ | 0.5859 | 1.64 | 14750 | 0.6039 | 0.6743 |
116
+ | 0.6231 | 1.67 | 15000 | 0.6002 | 0.6733 |
117
+ | 0.5984 | 1.7 | 15250 | 0.6020 | 0.6741 |
118
+ | 0.602 | 1.73 | 15500 | 0.6037 | 0.6741 |
119
+ | 0.5817 | 1.75 | 15750 | 0.6031 | 0.6748 |
120
+ | 0.6128 | 1.78 | 16000 | 0.6040 | 0.6743 |
121
+ | 0.6415 | 1.81 | 16250 | 0.6047 | 0.6748 |
122
+ | 0.6084 | 1.84 | 16500 | 0.6041 | 0.6743 |
123
+ | 0.6103 | 1.87 | 16750 | 0.6040 | 0.6746 |
124
+ | 0.6289 | 1.89 | 17000 | 0.6033 | 0.6746 |
125
+ | 0.5948 | 1.92 | 17250 | 0.6030 | 0.6759 |
126
+ | 0.5655 | 1.95 | 17500 | 0.6033 | 0.6748 |
127
+ | 0.6125 | 1.98 | 17750 | 0.6036 | 0.6751 |
128
+
129
+
130
+ ### Framework versions
131
+
132
+ - PEFT 0.9.0
133
+ - Transformers 4.38.2
134
+ - Pytorch 2.1.2
135
+ - Datasets 2.18.0
136
+ - 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 sha256:4cd7908049d5d77487cb3804777717da15cad0386f269da6505ab2f88860472b
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:b7414bcd54732166aab7786f25fc380aa933c7f69de326a5b9e723ebfe67b991
3
+ size 4984
vocab.json ADDED
The diff for this file is too large to render. See raw diff