Hugging Face's logo

craa
/
100M_low_2000_8397

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
craa commited on
Commit
b9dd874
·
verified ·
1 Parent(s): 0681e79

Training in progress, step 10000

Browse files
Files changed (12) hide show
  1. README.md +152 -0
  2. all_results.json +16 -0
  3. config.json +31 -0
  4. eval_results.json +10 -0
  5. generation_config.json +6 -0
  6. model.safetensors +3 -0
  7. special_tokens_map.json +1 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +0 -0
  10. train_results.json +9 -0
  11. trainer_state.json +0 -0
  12. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: 100M_low_1000_8397
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # 100M_low_1000_8397
16
+
17
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 3.3076
20
+ - Accuracy: 0.3938
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0006
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 16
42
+ - seed: 8397
43
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 100
46
+ - num_epochs: 10
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|
53
+ | 5.1052 | 0.1076 | 1000 | 5.0340 | 0.2255 |
54
+ | 4.6124 | 0.2153 | 2000 | 4.5219 | 0.2690 |
55
+ | 4.3286 | 0.3229 | 3000 | 4.2415 | 0.2979 |
56
+ | 4.1493 | 0.4305 | 4000 | 4.0979 | 0.3121 |
57
+ | 4.0522 | 0.5382 | 5000 | 4.0021 | 0.3199 |
58
+ | 3.9857 | 0.6458 | 6000 | 3.9259 | 0.3272 |
59
+ | 3.932 | 0.7534 | 7000 | 3.8695 | 0.3327 |
60
+ | 3.8959 | 0.8610 | 8000 | 3.8262 | 0.3368 |
61
+ | 3.8478 | 0.9687 | 9000 | 3.7854 | 0.3404 |
62
+ | 3.7833 | 1.0763 | 10000 | 3.7528 | 0.3440 |
63
+ | 3.7495 | 1.1839 | 11000 | 3.7281 | 0.3466 |
64
+ | 3.7503 | 1.2916 | 12000 | 3.7012 | 0.3487 |
65
+ | 3.7205 | 1.3992 | 13000 | 3.6827 | 0.3512 |
66
+ | 3.6956 | 1.5068 | 14000 | 3.6613 | 0.3528 |
67
+ | 3.6897 | 1.6145 | 15000 | 3.6417 | 0.3548 |
68
+ | 3.6712 | 1.7221 | 16000 | 3.6251 | 0.3569 |
69
+ | 3.6428 | 1.8297 | 17000 | 3.6106 | 0.3578 |
70
+ | 3.6477 | 1.9374 | 18000 | 3.5920 | 0.3597 |
71
+ | 3.5527 | 2.0450 | 19000 | 3.5835 | 0.3614 |
72
+ | 3.5691 | 2.1526 | 20000 | 3.5730 | 0.3623 |
73
+ | 3.5718 | 2.2603 | 21000 | 3.5646 | 0.3635 |
74
+ | 3.5632 | 2.3679 | 22000 | 3.5524 | 0.3642 |
75
+ | 3.5554 | 2.4755 | 23000 | 3.5433 | 0.3653 |
76
+ | 3.5367 | 2.5831 | 24000 | 3.5345 | 0.3661 |
77
+ | 3.543 | 2.6908 | 25000 | 3.5265 | 0.3671 |
78
+ | 3.542 | 2.7984 | 26000 | 3.5208 | 0.3677 |
79
+ | 3.5247 | 2.9060 | 27000 | 3.5082 | 0.3691 |
80
+ | 3.4332 | 3.0137 | 28000 | 3.5029 | 0.3699 |
81
+ | 3.444 | 3.1213 | 29000 | 3.4993 | 0.3706 |
82
+ | 3.4617 | 3.2289 | 30000 | 3.4922 | 0.3714 |
83
+ | 3.4675 | 3.3366 | 31000 | 3.4855 | 0.3718 |
84
+ | 3.4746 | 3.4442 | 32000 | 3.4805 | 0.3727 |
85
+ | 3.468 | 3.5518 | 33000 | 3.4732 | 0.3729 |
86
+ | 3.4691 | 3.6595 | 34000 | 3.4665 | 0.3735 |
87
+ | 3.4681 | 3.7671 | 35000 | 3.4601 | 0.3743 |
88
+ | 3.4485 | 3.8747 | 36000 | 3.4551 | 0.3752 |
89
+ | 3.4428 | 3.9823 | 37000 | 3.4494 | 0.3755 |
90
+ | 3.3682 | 4.0900 | 38000 | 3.4523 | 0.3757 |
91
+ | 3.3809 | 4.1976 | 39000 | 3.4480 | 0.3764 |
92
+ | 3.3874 | 4.3052 | 40000 | 3.4424 | 0.3769 |
93
+ | 3.4029 | 4.4129 | 41000 | 3.4402 | 0.3773 |
94
+ | 3.4236 | 4.5205 | 42000 | 3.4332 | 0.3778 |
95
+ | 3.3834 | 4.6281 | 43000 | 3.4282 | 0.3786 |
96
+ | 3.3957 | 4.7358 | 44000 | 3.4234 | 0.3787 |
97
+ | 3.3904 | 4.8434 | 45000 | 3.4175 | 0.3794 |
98
+ | 3.3921 | 4.9510 | 46000 | 3.4129 | 0.3798 |
99
+ | 3.3313 | 5.0587 | 47000 | 3.4170 | 0.3800 |
100
+ | 3.333 | 5.1663 | 48000 | 3.4167 | 0.3802 |
101
+ | 3.3374 | 5.2739 | 49000 | 3.4130 | 0.3809 |
102
+ | 3.3217 | 5.3816 | 50000 | 3.4041 | 0.3814 |
103
+ | 3.3285 | 5.4892 | 51000 | 3.4027 | 0.3818 |
104
+ | 3.3538 | 5.5968 | 52000 | 3.3965 | 0.3823 |
105
+ | 3.3236 | 5.7044 | 53000 | 3.3931 | 0.3825 |
106
+ | 3.3326 | 5.8121 | 54000 | 3.3880 | 0.3831 |
107
+ | 3.3383 | 5.9197 | 55000 | 3.3847 | 0.3835 |
108
+ | 3.2422 | 6.0273 | 56000 | 3.3883 | 0.3834 |
109
+ | 3.2646 | 6.1350 | 57000 | 3.3881 | 0.3836 |
110
+ | 3.2708 | 6.2426 | 58000 | 3.3843 | 0.3841 |
111
+ | 3.2901 | 6.3502 | 59000 | 3.3813 | 0.3844 |
112
+ | 3.3013 | 6.4579 | 60000 | 3.3755 | 0.3848 |
113
+ | 3.2954 | 6.5655 | 61000 | 3.3737 | 0.3855 |
114
+ | 3.2993 | 6.6731 | 62000 | 3.3672 | 0.3857 |
115
+ | 3.2894 | 6.7808 | 63000 | 3.3641 | 0.3862 |
116
+ | 3.294 | 6.8884 | 64000 | 3.3613 | 0.3865 |
117
+ | 3.2997 | 6.9960 | 65000 | 3.3577 | 0.3869 |
118
+ | 3.238 | 7.1036 | 66000 | 3.3638 | 0.3870 |
119
+ | 3.2202 | 7.2113 | 67000 | 3.3612 | 0.3873 |
120
+ | 3.2489 | 7.3189 | 68000 | 3.3569 | 0.3874 |
121
+ | 3.2278 | 7.4265 | 69000 | 3.3534 | 0.3878 |
122
+ | 3.2375 | 7.5342 | 70000 | 3.3498 | 0.3880 |
123
+ | 3.247 | 7.6418 | 71000 | 3.3458 | 0.3885 |
124
+ | 3.2471 | 7.7494 | 72000 | 3.3430 | 0.3891 |
125
+ | 3.2406 | 7.8571 | 73000 | 3.3387 | 0.3894 |
126
+ | 3.2495 | 7.9647 | 74000 | 3.3350 | 0.3897 |
127
+ | 3.191 | 8.0723 | 75000 | 3.3415 | 0.3899 |
128
+ | 3.1735 | 8.1800 | 76000 | 3.3391 | 0.3899 |
129
+ | 3.1844 | 8.2876 | 77000 | 3.3362 | 0.3902 |
130
+ | 3.1819 | 8.3952 | 78000 | 3.3330 | 0.3905 |
131
+ | 3.1854 | 8.5029 | 79000 | 3.3297 | 0.3911 |
132
+ | 3.1847 | 8.6105 | 80000 | 3.3275 | 0.3913 |
133
+ | 3.1935 | 8.7181 | 81000 | 3.3237 | 0.3916 |
134
+ | 3.1881 | 8.8257 | 82000 | 3.3191 | 0.3919 |
135
+ | 3.1831 | 8.9334 | 83000 | 3.3174 | 0.3924 |
136
+ | 3.126 | 9.0410 | 84000 | 3.3203 | 0.3923 |
137
+ | 3.1376 | 9.1486 | 85000 | 3.3189 | 0.3924 |
138
+ | 3.1377 | 9.2563 | 86000 | 3.3168 | 0.3927 |
139
+ | 3.1389 | 9.3639 | 87000 | 3.3138 | 0.3930 |
140
+ | 3.1323 | 9.4715 | 88000 | 3.3127 | 0.3932 |
141
+ | 3.1385 | 9.5792 | 89000 | 3.3093 | 0.3936 |
142
+ | 3.1358 | 9.6868 | 90000 | 3.3076 | 0.3938 |
143
+ | 3.1303 | 9.7944 | 91000 | 3.3053 | 0.3940 |
144
+ | 3.1412 | 9.9021 | 92000 | 3.3038 | 0.3942 |
145
+
146
+
147
+ ### Framework versions
148
+
149
+ - Transformers 4.47.0.dev0
150
+ - Pytorch 2.5.0+cu124
151
+ - Datasets 3.0.2
152
+ - Tokenizers 0.20.1
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.3937655624889378,
4
+ "eval_loss": 3.3076210021972656,
5
+ "eval_runtime": 185.9043,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 96.883,
8
+ "eval_steps_per_second": 6.057,
9
+ "perplexity": 27.320053752007436,
10
+ "total_flos": 7.7681859821568e+17,
11
+ "train_loss": 3.460850506426251,
12
+ "train_runtime": 80822.0047,
13
+ "train_samples": 297299,
14
+ "train_samples_per_second": 36.784,
15
+ "train_steps_per_second": 1.15
16
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 1024,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.47.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 52000
31
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.3937655624889378,
4
+ "eval_loss": 3.3076210021972656,
5
+ "eval_runtime": 185.9043,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 96.883,
8
+ "eval_steps_per_second": 6.057,
9
+ "perplexity": 27.320053752007436
10
+ }
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": "4.47.0.dev0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad96b9c160abbb286c9901f6668f5c89fb035af44adc8dec20a236ee5a73aac9
3
+ size 503128704
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 7.7681859821568e+17,
4
+ "train_loss": 3.460850506426251,
5
+ "train_runtime": 80822.0047,
6
+ "train_samples": 297299,
7
+ "train_samples_per_second": 36.784,
8
+ "train_steps_per_second": 1.15
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097b2f4878fa458807831f34b125c9126dbb86ed90dd7b8414ba94f45393ff0f
3
+ size 5304