Hugging Face's logo

KoNqUeRoR3891
/
HW2-orpo

Text Generation
Transformers
Safetensors
gpt2
trl
orpo
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
KoNqUeRoR3891 commited on
Commit
09ffb66
·
verified ·
1 Parent(s): aefdae1

Model save

Browse files
Files changed (3) hide show
  1. README.md +93 -0
  2. generation_config.json +6 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: openai-community/gpt2
5
+ tags:
6
+ - trl
7
+ - orpo
8
+ - generated_from_trainer
9
+ datasets:
10
+ - piqa
11
+ model-index:
12
+ - name: HW2-orpo
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
+ # HW2-orpo
20
+
21
+ This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the piqa dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 3.8617
24
+ - Rewards/chosen: -0.3716
25
+ - Rewards/rejected: -0.3885
26
+ - Rewards/accuracies: 0.6390
27
+ - Rewards/margins: 0.0170
28
+ - Logps/rejected: -3.8851
29
+ - Logps/chosen: -3.7156
30
+ - Logits/rejected: -3.3968
31
+ - Logits/chosen: -3.5059
32
+ - Nll Loss: 3.7885
33
+ - Log Odds Ratio: -0.7324
34
+ - Log Odds Chosen: 0.1830
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 5e-05
54
+ - train_batch_size: 1
55
+ - eval_batch_size: 1
56
+ - seed: 42
57
+ - gradient_accumulation_steps: 8
58
+ - total_train_batch_size: 8
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 5
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
67
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
68
+ | 3.5511 | 0.2758 | 500 | 3.4162 | -0.3146 | -0.3224 | 0.6303 | 0.0078 | -3.2238 | -3.1457 | -12.1919 | -12.3316 | 3.3464 | -0.6978 | 0.0837 |
69
+ | 3.3852 | 0.5517 | 1000 | 3.3345 | -0.3060 | -0.3152 | 0.6421 | 0.0092 | -3.1517 | -3.0602 | -3.3351 | -3.5024 | 3.2656 | -0.6894 | 0.0984 |
70
+ | 3.2734 | 0.8275 | 1500 | 3.2903 | -0.3011 | -0.3101 | 0.6309 | 0.0090 | -3.1013 | -3.0113 | -5.6602 | -5.7320 | 3.2211 | -0.6920 | 0.0975 |
71
+ | 3.104 | 1.1034 | 2000 | 3.2933 | -0.3021 | -0.3118 | 0.6371 | 0.0097 | -3.1182 | -3.0211 | -0.2253 | -0.3135 | 3.2237 | -0.6956 | 0.1062 |
72
+ | 2.8138 | 1.3792 | 2500 | 3.2816 | -0.3018 | -0.3125 | 0.6464 | 0.0107 | -3.1253 | -3.0179 | 1.3216 | 1.2346 | 3.2125 | -0.6916 | 0.1172 |
73
+ | 2.8178 | 1.6551 | 3000 | 3.2660 | -0.2998 | -0.3108 | 0.6383 | 0.0109 | -3.1080 | -2.9985 | -0.7475 | -0.8064 | 3.1968 | -0.6923 | 0.1204 |
74
+ | 2.8122 | 1.9309 | 3500 | 3.2586 | -0.2992 | -0.3104 | 0.6433 | 0.0112 | -3.1039 | -2.9922 | -2.8285 | -2.9509 | 3.1893 | -0.6925 | 0.1228 |
75
+ | 2.4931 | 2.2067 | 4000 | 3.3765 | -0.3130 | -0.3256 | 0.6427 | 0.0127 | -3.2563 | -3.1296 | 1.6707 | 1.5380 | 3.3063 | -0.7020 | 0.1392 |
76
+ | 2.3999 | 2.4826 | 4500 | 3.4109 | -0.3174 | -0.3298 | 0.6402 | 0.0125 | -3.2982 | -3.1736 | 1.4695 | 1.2634 | 3.3402 | -0.7069 | 0.1373 |
77
+ | 2.4254 | 2.7584 | 5000 | 3.3882 | -0.3150 | -0.3278 | 0.6439 | 0.0128 | -3.2781 | -3.1497 | 2.1282 | 1.9044 | 3.3180 | -0.7018 | 0.1416 |
78
+ | 2.373 | 3.0343 | 5500 | 3.5698 | -0.3370 | -0.3515 | 0.6408 | 0.0145 | -3.5149 | -3.3698 | 3.7150 | 3.6601 | 3.4983 | -0.7147 | 0.1595 |
79
+ | 2.0541 | 3.3101 | 6000 | 3.6256 | -0.3430 | -0.3570 | 0.6284 | 0.0140 | -3.5700 | -3.4302 | 1.1269 | 0.9714 | 3.5532 | -0.7240 | 0.1540 |
80
+ | 2.0641 | 3.5860 | 6500 | 3.6157 | -0.3425 | -0.3577 | 0.6445 | 0.0152 | -3.5771 | -3.4246 | -0.6703 | -0.8165 | 3.5439 | -0.7178 | 0.1665 |
81
+ | 2.0747 | 3.8618 | 7000 | 3.6335 | -0.3447 | -0.3598 | 0.6402 | 0.0151 | -3.5983 | -3.4474 | -0.1967 | -0.3291 | 3.5616 | -0.7193 | 0.1640 |
82
+ | 1.9377 | 4.1376 | 7500 | 3.8286 | -0.3671 | -0.3838 | 0.6445 | 0.0167 | -3.8381 | -3.6712 | -2.6871 | -2.8058 | 3.7557 | -0.7288 | 0.1800 |
83
+ | 1.8001 | 4.4135 | 8000 | 3.8629 | -0.3715 | -0.3882 | 0.6414 | 0.0168 | -3.8822 | -3.7146 | -3.4193 | -3.5370 | 3.7898 | -0.7315 | 0.1810 |
84
+ | 1.81 | 4.6893 | 8500 | 3.8574 | -0.3711 | -0.3879 | 0.6396 | 0.0168 | -3.8789 | -3.7110 | -4.2176 | -4.3406 | 3.7842 | -0.7321 | 0.1814 |
85
+ | 1.8108 | 4.9652 | 9000 | 3.8617 | -0.3716 | -0.3885 | 0.6390 | 0.0170 | -3.8851 | -3.7156 | -3.3968 | -3.5059 | 3.7885 | -0.7324 | 0.1830 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.44.2
91
+ - Pytorch 2.4.0+cu118
92
+ - Datasets 2.21.0
93
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.44.2"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0b0e2f0bc85de08e1043061a6fb0d9154a11d05328b0b3812361e4a540e5ef5
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8559b29b32ba7042153e90f72d46d8be9d367e00df9dc812b45cbf82dfb4bcd1
3
  size 497774208