Hugging Face's logo

craa
/
100M_low_100_634

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
craa commited on
Commit
3f275e6
·
verified ·
1 Parent(s): a4bee03

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_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_high_2000_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: 3.2973
20
+ - Accuracy: 0.3949
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
+ | 5.1238 | 0.1076 | 1000 | 5.0474 | 0.2245 |
54
+ | 4.6101 | 0.2153 | 2000 | 4.5428 | 0.2660 |
55
+ | 4.327 | 0.3229 | 3000 | 4.2513 | 0.2964 |
56
+ | 4.18 | 0.4305 | 4000 | 4.1040 | 0.3112 |
57
+ | 4.0788 | 0.5382 | 5000 | 4.0013 | 0.3209 |
58
+ | 3.9809 | 0.6458 | 6000 | 3.9289 | 0.3274 |
59
+ | 3.9432 | 0.7534 | 7000 | 3.8685 | 0.3328 |
60
+ | 3.8951 | 0.8610 | 8000 | 3.8222 | 0.3374 |
61
+ | 3.8465 | 0.9687 | 9000 | 3.7847 | 0.3411 |
62
+ | 3.7776 | 1.0763 | 10000 | 3.7543 | 0.3437 |
63
+ | 3.7468 | 1.1839 | 11000 | 3.7271 | 0.3463 |
64
+ | 3.7506 | 1.2916 | 12000 | 3.7040 | 0.3491 |
65
+ | 3.7237 | 1.3992 | 13000 | 3.6814 | 0.3514 |
66
+ | 3.7012 | 1.5068 | 14000 | 3.6622 | 0.3531 |
67
+ | 3.7034 | 1.6145 | 15000 | 3.6405 | 0.3549 |
68
+ | 3.6725 | 1.7221 | 16000 | 3.6242 | 0.3569 |
69
+ | 3.672 | 1.8297 | 17000 | 3.6070 | 0.3583 |
70
+ | 3.6299 | 1.9374 | 18000 | 3.5937 | 0.3599 |
71
+ | 3.5547 | 2.0450 | 19000 | 3.5826 | 0.3614 |
72
+ | 3.5597 | 2.1526 | 20000 | 3.5708 | 0.3630 |
73
+ | 3.5548 | 2.2603 | 21000 | 3.5607 | 0.3637 |
74
+ | 3.5652 | 2.3679 | 22000 | 3.5529 | 0.3651 |
75
+ | 3.5598 | 2.4755 | 23000 | 3.5399 | 0.3658 |
76
+ | 3.5437 | 2.5831 | 24000 | 3.5304 | 0.3672 |
77
+ | 3.5538 | 2.6908 | 25000 | 3.5202 | 0.3680 |
78
+ | 3.5305 | 2.7984 | 26000 | 3.5113 | 0.3689 |
79
+ | 3.5247 | 2.9060 | 27000 | 3.5038 | 0.3698 |
80
+ | 3.4459 | 3.0137 | 28000 | 3.4984 | 0.3706 |
81
+ | 3.474 | 3.1213 | 29000 | 3.4933 | 0.3714 |
82
+ | 3.4539 | 3.2289 | 30000 | 3.4909 | 0.3722 |
83
+ | 3.4761 | 3.3366 | 31000 | 3.4805 | 0.3729 |
84
+ | 3.4639 | 3.4442 | 32000 | 3.4724 | 0.3736 |
85
+ | 3.4517 | 3.5518 | 33000 | 3.4675 | 0.3739 |
86
+ | 3.4599 | 3.6595 | 34000 | 3.4607 | 0.3744 |
87
+ | 3.4716 | 3.7671 | 35000 | 3.4529 | 0.3753 |
88
+ | 3.4683 | 3.8747 | 36000 | 3.4506 | 0.3759 |
89
+ | 3.4573 | 3.9823 | 37000 | 3.4418 | 0.3767 |
90
+ | 3.3698 | 4.0900 | 38000 | 3.4448 | 0.3770 |
91
+ | 3.3879 | 4.1976 | 39000 | 3.4373 | 0.3774 |
92
+ | 3.3817 | 4.3052 | 40000 | 3.4343 | 0.3781 |
93
+ | 3.3943 | 4.4129 | 41000 | 3.4277 | 0.3784 |
94
+ | 3.3975 | 4.5205 | 42000 | 3.4233 | 0.3789 |
95
+ | 3.3875 | 4.6281 | 43000 | 3.4212 | 0.3793 |
96
+ | 3.3821 | 4.7358 | 44000 | 3.4130 | 0.3804 |
97
+ | 3.3768 | 4.8434 | 45000 | 3.4080 | 0.3806 |
98
+ | 3.3833 | 4.9510 | 46000 | 3.4057 | 0.3807 |
99
+ | 3.2774 | 5.0587 | 47000 | 3.4080 | 0.3811 |
100
+ | 3.334 | 5.1663 | 48000 | 3.4050 | 0.3818 |
101
+ | 3.3145 | 5.2739 | 49000 | 3.4024 | 0.3823 |
102
+ | 3.3141 | 5.3816 | 50000 | 3.3990 | 0.3824 |
103
+ | 3.3453 | 5.4892 | 51000 | 3.3912 | 0.3831 |
104
+ | 3.3352 | 5.5968 | 52000 | 3.3894 | 0.3829 |
105
+ | 3.3216 | 5.7044 | 53000 | 3.3845 | 0.3838 |
106
+ | 3.3479 | 5.8121 | 54000 | 3.3777 | 0.3841 |
107
+ | 3.3476 | 5.9197 | 55000 | 3.3771 | 0.3847 |
108
+ | 3.2375 | 6.0273 | 56000 | 3.3784 | 0.3848 |
109
+ | 3.2627 | 6.1350 | 57000 | 3.3782 | 0.3847 |
110
+ | 3.2627 | 6.2426 | 58000 | 3.3758 | 0.3850 |
111
+ | 3.2839 | 6.3502 | 59000 | 3.3710 | 0.3857 |
112
+ | 3.2989 | 6.4579 | 60000 | 3.3687 | 0.3857 |
113
+ | 3.2743 | 6.5655 | 61000 | 3.3620 | 0.3866 |
114
+ | 3.2791 | 6.6731 | 62000 | 3.3584 | 0.3868 |
115
+ | 3.2852 | 6.7808 | 63000 | 3.3554 | 0.3874 |
116
+ | 3.2907 | 6.8884 | 64000 | 3.3510 | 0.3876 |
117
+ | 3.2801 | 6.9960 | 65000 | 3.3469 | 0.3881 |
118
+ | 3.2135 | 7.1036 | 66000 | 3.3548 | 0.3879 |
119
+ | 3.2265 | 7.2113 | 67000 | 3.3512 | 0.3881 |
120
+ | 3.2246 | 7.3189 | 68000 | 3.3511 | 0.3881 |
121
+ | 3.238 | 7.4265 | 69000 | 3.3462 | 0.3888 |
122
+ | 3.2426 | 7.5342 | 70000 | 3.3393 | 0.3896 |
123
+ | 3.2285 | 7.6418 | 71000 | 3.3385 | 0.3897 |
124
+ | 3.2196 | 7.7494 | 72000 | 3.3344 | 0.3901 |
125
+ | 3.2332 | 7.8571 | 73000 | 3.3292 | 0.3905 |
126
+ | 3.2324 | 7.9647 | 74000 | 3.3260 | 0.3908 |
127
+ | 3.166 | 8.0723 | 75000 | 3.3311 | 0.3905 |
128
+ | 3.1575 | 8.1800 | 76000 | 3.3304 | 0.3909 |
129
+ | 3.1742 | 8.2876 | 77000 | 3.3261 | 0.3914 |
130
+ | 3.1689 | 8.3952 | 78000 | 3.3249 | 0.3915 |
131
+ | 3.1832 | 8.5029 | 79000 | 3.3202 | 0.3919 |
132
+ | 3.1731 | 8.6105 | 80000 | 3.3172 | 0.3922 |
133
+ | 3.1745 | 8.7181 | 81000 | 3.3136 | 0.3927 |
134
+ | 3.2062 | 8.8257 | 82000 | 3.3107 | 0.3930 |
135
+ | 3.1827 | 8.9334 | 83000 | 3.3073 | 0.3932 |
136
+ | 3.1252 | 9.0410 | 84000 | 3.3080 | 0.3934 |
137
+ | 3.1172 | 9.1486 | 85000 | 3.3087 | 0.3936 |
138
+ | 3.1315 | 9.2563 | 86000 | 3.3066 | 0.3938 |
139
+ | 3.1489 | 9.3639 | 87000 | 3.3037 | 0.3941 |
140
+ | 3.1382 | 9.4715 | 88000 | 3.3020 | 0.3944 |
141
+ | 3.1278 | 9.5792 | 89000 | 3.2999 | 0.3946 |
142
+ | 3.1205 | 9.6868 | 90000 | 3.2973 | 0.3949 |
143
+ | 3.1305 | 9.7944 | 91000 | 3.2960 | 0.3950 |
144
+ | 3.1249 | 9.9021 | 92000 | 3.2941 | 0.3953 |
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": 0.39493445025604595,
4
+ "eval_loss": 3.2973227500915527,
5
+ "eval_runtime": 184.9314,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 97.393,
8
+ "eval_steps_per_second": 6.089,
9
+ "perplexity": 27.040148691118805,
10
+ "total_flos": 7.76821211136e+17,
11
+ "train_loss": 3.45856736887003,
12
+ "train_runtime": 80340.319,
13
+ "train_samples": 297300,
14
+ "train_samples_per_second": 37.005,
15
+ "train_steps_per_second": 1.156
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": 0.39493445025604595,
4
+ "eval_loss": 3.2973227500915527,
5
+ "eval_runtime": 184.9314,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 97.393,
8
+ "eval_steps_per_second": 6.089,
9
+ "perplexity": 27.040148691118805
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 sha256:27bb9fe8996c25b039f88f18d877f81a15ce06b6c32ab014309d3b9a08ba2fdb
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": 3.45856736887003,
5
+ "train_runtime": 80340.319,
6
+ "train_samples": 297300,
7
+ "train_samples_per_second": 37.005,
8
+ "train_steps_per_second": 1.156
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:f357aa2dae49e2327cd5e424592383a9b10f7c43d691eb67bd615efff45fa730
3
+ size 5304