Hugging Face's logo

craa
/
100M_low_100_8397

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
craa commited on
Commit
036dab7
·
verified ·
1 Parent(s): f7afdec

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_high_2000_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_high_2000_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: 3.3019
20
+ - Accuracy: 0.3944
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
+ | 5.0633 | 0.1076 | 1000 | 4.9965 | 0.2292 |
54
+ | 4.579 | 0.2153 | 2000 | 4.5043 | 0.2712 |
55
+ | 4.322 | 0.3229 | 3000 | 4.2267 | 0.2992 |
56
+ | 4.1439 | 0.4305 | 4000 | 4.0925 | 0.3122 |
57
+ | 4.043 | 0.5382 | 5000 | 3.9926 | 0.3214 |
58
+ | 3.9759 | 0.6458 | 6000 | 3.9196 | 0.3283 |
59
+ | 3.922 | 0.7534 | 7000 | 3.8611 | 0.3334 |
60
+ | 3.8731 | 0.8610 | 8000 | 3.8146 | 0.3380 |
61
+ | 3.8405 | 0.9687 | 9000 | 3.7791 | 0.3417 |
62
+ | 3.7655 | 1.0763 | 10000 | 3.7489 | 0.3451 |
63
+ | 3.7441 | 1.1839 | 11000 | 3.7200 | 0.3471 |
64
+ | 3.7293 | 1.2916 | 12000 | 3.6987 | 0.3496 |
65
+ | 3.7029 | 1.3992 | 13000 | 3.6745 | 0.3523 |
66
+ | 3.6962 | 1.5068 | 14000 | 3.6557 | 0.3536 |
67
+ | 3.6601 | 1.6145 | 15000 | 3.6367 | 0.3556 |
68
+ | 3.6579 | 1.7221 | 16000 | 3.6183 | 0.3572 |
69
+ | 3.6582 | 1.8297 | 17000 | 3.6050 | 0.3590 |
70
+ | 3.6427 | 1.9374 | 18000 | 3.5893 | 0.3606 |
71
+ | 3.56 | 2.0450 | 19000 | 3.5785 | 0.3617 |
72
+ | 3.5527 | 2.1526 | 20000 | 3.5706 | 0.3627 |
73
+ | 3.5487 | 2.2603 | 21000 | 3.5602 | 0.3639 |
74
+ | 3.5664 | 2.3679 | 22000 | 3.5475 | 0.3650 |
75
+ | 3.5464 | 2.4755 | 23000 | 3.5418 | 0.3655 |
76
+ | 3.5619 | 2.5831 | 24000 | 3.5326 | 0.3666 |
77
+ | 3.5487 | 2.6908 | 25000 | 3.5214 | 0.3681 |
78
+ | 3.5277 | 2.7984 | 26000 | 3.5125 | 0.3686 |
79
+ | 3.5346 | 2.9060 | 27000 | 3.5038 | 0.3695 |
80
+ | 3.4461 | 3.0137 | 28000 | 3.4977 | 0.3707 |
81
+ | 3.4491 | 3.1213 | 29000 | 3.4946 | 0.3712 |
82
+ | 3.4684 | 3.2289 | 30000 | 3.4922 | 0.3713 |
83
+ | 3.4662 | 3.3366 | 31000 | 3.4845 | 0.3721 |
84
+ | 3.4454 | 3.4442 | 32000 | 3.4765 | 0.3731 |
85
+ | 3.4605 | 3.5518 | 33000 | 3.4697 | 0.3741 |
86
+ | 3.4428 | 3.6595 | 34000 | 3.4640 | 0.3745 |
87
+ | 3.458 | 3.7671 | 35000 | 3.4591 | 0.3749 |
88
+ | 3.4501 | 3.8747 | 36000 | 3.4519 | 0.3758 |
89
+ | 3.4582 | 3.9823 | 37000 | 3.4467 | 0.3758 |
90
+ | 3.3691 | 4.0900 | 38000 | 3.4484 | 0.3766 |
91
+ | 3.3847 | 4.1976 | 39000 | 3.4444 | 0.3769 |
92
+ | 3.3714 | 4.3052 | 40000 | 3.4397 | 0.3772 |
93
+ | 3.3768 | 4.4129 | 41000 | 3.4378 | 0.3780 |
94
+ | 3.393 | 4.5205 | 42000 | 3.4299 | 0.3785 |
95
+ | 3.3915 | 4.6281 | 43000 | 3.4237 | 0.3790 |
96
+ | 3.3875 | 4.7358 | 44000 | 3.4192 | 0.3795 |
97
+ | 3.4045 | 4.8434 | 45000 | 3.4141 | 0.3801 |
98
+ | 3.3761 | 4.9510 | 46000 | 3.4095 | 0.3805 |
99
+ | 3.3004 | 5.0587 | 47000 | 3.4123 | 0.3809 |
100
+ | 3.3289 | 5.1663 | 48000 | 3.4115 | 0.3815 |
101
+ | 3.3151 | 5.2739 | 49000 | 3.4057 | 0.3817 |
102
+ | 3.3528 | 5.3816 | 50000 | 3.4026 | 0.3818 |
103
+ | 3.3271 | 5.4892 | 51000 | 3.3986 | 0.3823 |
104
+ | 3.3457 | 5.5968 | 52000 | 3.3944 | 0.3825 |
105
+ | 3.3489 | 5.7044 | 53000 | 3.3893 | 0.3832 |
106
+ | 3.3353 | 5.8121 | 54000 | 3.3865 | 0.3837 |
107
+ | 3.3306 | 5.9197 | 55000 | 3.3798 | 0.3840 |
108
+ | 3.2266 | 6.0273 | 56000 | 3.3825 | 0.3844 |
109
+ | 3.2555 | 6.1350 | 57000 | 3.3847 | 0.3842 |
110
+ | 3.2849 | 6.2426 | 58000 | 3.3810 | 0.3847 |
111
+ | 3.2801 | 6.3502 | 59000 | 3.3766 | 0.3852 |
112
+ | 3.2773 | 6.4579 | 60000 | 3.3726 | 0.3854 |
113
+ | 3.3014 | 6.5655 | 61000 | 3.3667 | 0.3860 |
114
+ | 3.2774 | 6.6731 | 62000 | 3.3637 | 0.3862 |
115
+ | 3.2826 | 6.7808 | 63000 | 3.3598 | 0.3868 |
116
+ | 3.2734 | 6.8884 | 64000 | 3.3552 | 0.3873 |
117
+ | 3.2676 | 6.9960 | 65000 | 3.3523 | 0.3876 |
118
+ | 3.2141 | 7.1036 | 66000 | 3.3576 | 0.3874 |
119
+ | 3.2343 | 7.2113 | 67000 | 3.3561 | 0.3876 |
120
+ | 3.2277 | 7.3189 | 68000 | 3.3523 | 0.3881 |
121
+ | 3.236 | 7.4265 | 69000 | 3.3499 | 0.3886 |
122
+ | 3.2201 | 7.5342 | 70000 | 3.3478 | 0.3887 |
123
+ | 3.2337 | 7.6418 | 71000 | 3.3436 | 0.3891 |
124
+ | 3.2174 | 7.7494 | 72000 | 3.3376 | 0.3896 |
125
+ | 3.2182 | 7.8571 | 73000 | 3.3348 | 0.3899 |
126
+ | 3.2393 | 7.9647 | 74000 | 3.3314 | 0.3900 |
127
+ | 3.1517 | 8.0723 | 75000 | 3.3365 | 0.3900 |
128
+ | 3.1824 | 8.1800 | 76000 | 3.3342 | 0.3904 |
129
+ | 3.1814 | 8.2876 | 77000 | 3.3317 | 0.3906 |
130
+ | 3.1945 | 8.3952 | 78000 | 3.3278 | 0.3912 |
131
+ | 3.1847 | 8.5029 | 79000 | 3.3260 | 0.3915 |
132
+ | 3.1648 | 8.6105 | 80000 | 3.3222 | 0.3918 |
133
+ | 3.179 | 8.7181 | 81000 | 3.3188 | 0.3920 |
134
+ | 3.1809 | 8.8257 | 82000 | 3.3150 | 0.3926 |
135
+ | 3.1939 | 8.9334 | 83000 | 3.3116 | 0.3928 |
136
+ | 3.1185 | 9.0410 | 84000 | 3.3150 | 0.3928 |
137
+ | 3.1242 | 9.1486 | 85000 | 3.3141 | 0.3930 |
138
+ | 3.1324 | 9.2563 | 86000 | 3.3112 | 0.3933 |
139
+ | 3.1224 | 9.3639 | 87000 | 3.3099 | 0.3935 |
140
+ | 3.1341 | 9.4715 | 88000 | 3.3078 | 0.3937 |
141
+ | 3.1354 | 9.5792 | 89000 | 3.3048 | 0.3941 |
142
+ | 3.1262 | 9.6868 | 90000 | 3.3019 | 0.3944 |
143
+ | 3.129 | 9.7944 | 91000 | 3.3006 | 0.3946 |
144
+ | 3.1392 | 9.9021 | 92000 | 3.2992 | 0.3947 |
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": 0.3943953146267105,
4
+ "eval_loss": 3.3019161224365234,
5
+ "eval_runtime": 189.6088,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 94.99,
8
+ "eval_steps_per_second": 5.939,
9
+ "perplexity": 27.164639860580742,
10
+ "total_flos": 7.76821211136e+17,
11
+ "train_loss": 3.4556877505752324,
12
+ "train_runtime": 82552.4271,
13
+ "train_samples": 297300,
14
+ "train_samples_per_second": 36.013,
15
+ "train_steps_per_second": 1.125
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": 0.3943953146267105,
4
+ "eval_loss": 3.3019161224365234,
5
+ "eval_runtime": 189.6088,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 94.99,
8
+ "eval_steps_per_second": 5.939,
9
+ "perplexity": 27.164639860580742
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:c756871f2d48d5c72544986ef95dbfa2839a6b20f26c7fb7a59896c3c3b6ce65
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": 7.76821211136e+17,
4
+ "train_loss": 3.4556877505752324,
5
+ "train_runtime": 82552.4271,
6
+ "train_samples": 297300,
7
+ "train_samples_per_second": 36.013,
8
+ "train_steps_per_second": 1.125
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 sha256:864df47aa7c79fa7fe2697ddeb7c806905271ef1003f9debb489ce744ca931c8
3
+ size 5304