Hugging Face's logo

craa
/
100M_high_500_634

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
craa commited on
Commit
8eb331f
·
verified ·
1 Parent(s): f68d353

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_634
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_634
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: 3.3057
20
+ - Accuracy: 0.3939
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: 634
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
+ | 5.0844 | 0.1076 | 1000 | 5.0247 | 0.2263 |
54
+ | 4.6123 | 0.2153 | 2000 | 4.5197 | 0.2695 |
55
+ | 4.3027 | 0.3229 | 3000 | 4.2481 | 0.2971 |
56
+ | 4.1665 | 0.4305 | 4000 | 4.0981 | 0.3118 |
57
+ | 4.0561 | 0.5382 | 5000 | 4.0006 | 0.3206 |
58
+ | 3.9998 | 0.6458 | 6000 | 3.9295 | 0.3267 |
59
+ | 3.9341 | 0.7534 | 7000 | 3.8731 | 0.3322 |
60
+ | 3.8988 | 0.8610 | 8000 | 3.8282 | 0.3368 |
61
+ | 3.8383 | 0.9687 | 9000 | 3.7871 | 0.3409 |
62
+ | 3.7702 | 1.0763 | 10000 | 3.7583 | 0.3431 |
63
+ | 3.7732 | 1.1839 | 11000 | 3.7325 | 0.3460 |
64
+ | 3.7403 | 1.2916 | 12000 | 3.7075 | 0.3485 |
65
+ | 3.7254 | 1.3992 | 13000 | 3.6853 | 0.3507 |
66
+ | 3.6975 | 1.5068 | 14000 | 3.6646 | 0.3530 |
67
+ | 3.6764 | 1.6145 | 15000 | 3.6432 | 0.3544 |
68
+ | 3.6952 | 1.7221 | 16000 | 3.6260 | 0.3563 |
69
+ | 3.6746 | 1.8297 | 17000 | 3.6122 | 0.3581 |
70
+ | 3.6458 | 1.9374 | 18000 | 3.5976 | 0.3595 |
71
+ | 3.5395 | 2.0450 | 19000 | 3.5846 | 0.3609 |
72
+ | 3.5686 | 2.1526 | 20000 | 3.5753 | 0.3624 |
73
+ | 3.573 | 2.2603 | 21000 | 3.5658 | 0.3631 |
74
+ | 3.5423 | 2.3679 | 22000 | 3.5570 | 0.3643 |
75
+ | 3.5649 | 2.4755 | 23000 | 3.5443 | 0.3653 |
76
+ | 3.5461 | 2.5831 | 24000 | 3.5344 | 0.3665 |
77
+ | 3.5449 | 2.6908 | 25000 | 3.5274 | 0.3674 |
78
+ | 3.546 | 2.7984 | 26000 | 3.5184 | 0.3678 |
79
+ | 3.52 | 2.9060 | 27000 | 3.5082 | 0.3692 |
80
+ | 3.4344 | 3.0137 | 28000 | 3.5035 | 0.3703 |
81
+ | 3.4521 | 3.1213 | 29000 | 3.4990 | 0.3704 |
82
+ | 3.4658 | 3.2289 | 30000 | 3.4912 | 0.3711 |
83
+ | 3.4658 | 3.3366 | 31000 | 3.4849 | 0.3716 |
84
+ | 3.442 | 3.4442 | 32000 | 3.4788 | 0.3726 |
85
+ | 3.457 | 3.5518 | 33000 | 3.4739 | 0.3735 |
86
+ | 3.4541 | 3.6595 | 34000 | 3.4669 | 0.3736 |
87
+ | 3.4465 | 3.7671 | 35000 | 3.4592 | 0.3747 |
88
+ | 3.4824 | 3.8747 | 36000 | 3.4528 | 0.3753 |
89
+ | 3.4592 | 3.9823 | 37000 | 3.4477 | 0.3760 |
90
+ | 3.3733 | 4.0900 | 38000 | 3.4510 | 0.3760 |
91
+ | 3.3757 | 4.1976 | 39000 | 3.4470 | 0.3766 |
92
+ | 3.3856 | 4.3052 | 40000 | 3.4405 | 0.3773 |
93
+ | 3.38 | 4.4129 | 41000 | 3.4360 | 0.3777 |
94
+ | 3.383 | 4.5205 | 42000 | 3.4337 | 0.3780 |
95
+ | 3.3931 | 4.6281 | 43000 | 3.4277 | 0.3787 |
96
+ | 3.3908 | 4.7358 | 44000 | 3.4218 | 0.3791 |
97
+ | 3.3978 | 4.8434 | 45000 | 3.4169 | 0.3796 |
98
+ | 3.3973 | 4.9510 | 46000 | 3.4117 | 0.3803 |
99
+ | 3.3238 | 5.0587 | 47000 | 3.4143 | 0.3801 |
100
+ | 3.3105 | 5.1663 | 48000 | 3.4145 | 0.3807 |
101
+ | 3.3373 | 5.2739 | 49000 | 3.4104 | 0.3809 |
102
+ | 3.335 | 5.3816 | 50000 | 3.4058 | 0.3815 |
103
+ | 3.3413 | 5.4892 | 51000 | 3.4003 | 0.3821 |
104
+ | 3.3268 | 5.5968 | 52000 | 3.4002 | 0.3821 |
105
+ | 3.3408 | 5.7044 | 53000 | 3.3912 | 0.3827 |
106
+ | 3.3346 | 5.8121 | 54000 | 3.3863 | 0.3830 |
107
+ | 3.3526 | 5.9197 | 55000 | 3.3859 | 0.3834 |
108
+ | 3.2376 | 6.0273 | 56000 | 3.3877 | 0.3837 |
109
+ | 3.2814 | 6.1350 | 57000 | 3.3864 | 0.3842 |
110
+ | 3.2809 | 6.2426 | 58000 | 3.3834 | 0.3843 |
111
+ | 3.269 | 6.3502 | 59000 | 3.3777 | 0.3850 |
112
+ | 3.2772 | 6.4579 | 60000 | 3.3756 | 0.3854 |
113
+ | 3.2918 | 6.5655 | 61000 | 3.3701 | 0.3855 |
114
+ | 3.301 | 6.6731 | 62000 | 3.3663 | 0.3860 |
115
+ | 3.2825 | 6.7808 | 63000 | 3.3652 | 0.3863 |
116
+ | 3.2985 | 6.8884 | 64000 | 3.3576 | 0.3870 |
117
+ | 3.3025 | 6.9960 | 65000 | 3.3560 | 0.3870 |
118
+ | 3.2197 | 7.1036 | 66000 | 3.3615 | 0.3869 |
119
+ | 3.2388 | 7.2113 | 67000 | 3.3581 | 0.3872 |
120
+ | 3.2305 | 7.3189 | 68000 | 3.3580 | 0.3876 |
121
+ | 3.245 | 7.4265 | 69000 | 3.3548 | 0.3877 |
122
+ | 3.2324 | 7.5342 | 70000 | 3.3472 | 0.3882 |
123
+ | 3.237 | 7.6418 | 71000 | 3.3445 | 0.3888 |
124
+ | 3.2258 | 7.7494 | 72000 | 3.3414 | 0.3892 |
125
+ | 3.2352 | 7.8571 | 73000 | 3.3387 | 0.3894 |
126
+ | 3.2482 | 7.9647 | 74000 | 3.3336 | 0.3901 |
127
+ | 3.1661 | 8.0723 | 75000 | 3.3407 | 0.3896 |
128
+ | 3.175 | 8.1800 | 76000 | 3.3385 | 0.3902 |
129
+ | 3.1716 | 8.2876 | 77000 | 3.3346 | 0.3903 |
130
+ | 3.1953 | 8.3952 | 78000 | 3.3325 | 0.3907 |
131
+ | 3.19 | 8.5029 | 79000 | 3.3307 | 0.3910 |
132
+ | 3.1837 | 8.6105 | 80000 | 3.3249 | 0.3914 |
133
+ | 3.1897 | 8.7181 | 81000 | 3.3213 | 0.3916 |
134
+ | 3.1826 | 8.8257 | 82000 | 3.3188 | 0.3922 |
135
+ | 3.1903 | 8.9334 | 83000 | 3.3148 | 0.3925 |
136
+ | 3.1374 | 9.0410 | 84000 | 3.3184 | 0.3924 |
137
+ | 3.1349 | 9.1486 | 85000 | 3.3172 | 0.3927 |
138
+ | 3.1493 | 9.2563 | 86000 | 3.3150 | 0.3929 |
139
+ | 3.128 | 9.3639 | 87000 | 3.3120 | 0.3932 |
140
+ | 3.1407 | 9.4715 | 88000 | 3.3109 | 0.3933 |
141
+ | 3.1395 | 9.5792 | 89000 | 3.3077 | 0.3937 |
142
+ | 3.14 | 9.6868 | 90000 | 3.3057 | 0.3939 |
143
+ | 3.1288 | 9.7944 | 91000 | 3.3038 | 0.3941 |
144
+ | 3.1303 | 9.9021 | 92000 | 3.3024 | 0.3943 |
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": 0.39387280288921067,
4
+ "eval_loss": 3.305699110031128,
5
+ "eval_runtime": 191.4372,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 94.083,
8
+ "eval_steps_per_second": 5.882,
9
+ "perplexity": 27.26759797803971,
10
+ "total_flos": 7.7681859821568e+17,
11
+ "train_loss": 3.4596829572543557,
12
+ "train_runtime": 82007.5112,
13
+ "train_samples": 297299,
14
+ "train_samples_per_second": 36.253,
15
+ "train_steps_per_second": 1.133
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": 0.39387280288921067,
4
+ "eval_loss": 3.305699110031128,
5
+ "eval_runtime": 191.4372,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 94.083,
8
+ "eval_steps_per_second": 5.882,
9
+ "perplexity": 27.26759797803971
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 sha256:4ddfb70756ac2f764238482b97a9aee5b241de9158bf1b5e130fbb1b7bbb3ba1
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": 3.4596829572543557,
5
+ "train_runtime": 82007.5112,
6
+ "train_samples": 297299,
7
+ "train_samples_per_second": 36.253,
8
+ "train_steps_per_second": 1.133
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 sha256:94c48e1ce517188044a594607ae77f7de45d4d4d049feee984b4aeac25b52d6a
3
+ size 5304