Hugging Face's logo

craa
/
100M_high_1000_6910

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
craa commited on
Commit
18407fe
·
verified ·
1 Parent(s): 6d701ec

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_6910
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_6910
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: 3.3092
20
+ - Accuracy: 0.3933
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: 6910
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
+ | 5.0801 | 0.1076 | 1000 | 5.0232 | 0.2271 |
54
+ | 4.596 | 0.2153 | 2000 | 4.5306 | 0.2679 |
55
+ | 4.3232 | 0.3229 | 3000 | 4.2456 | 0.2974 |
56
+ | 4.1553 | 0.4305 | 4000 | 4.1002 | 0.3118 |
57
+ | 4.0665 | 0.5382 | 5000 | 4.0021 | 0.3199 |
58
+ | 3.9882 | 0.6458 | 6000 | 3.9310 | 0.3272 |
59
+ | 3.9394 | 0.7534 | 7000 | 3.8736 | 0.3320 |
60
+ | 3.8898 | 0.8610 | 8000 | 3.8263 | 0.3365 |
61
+ | 3.8549 | 0.9687 | 9000 | 3.7866 | 0.3402 |
62
+ | 3.7728 | 1.0763 | 10000 | 3.7558 | 0.3437 |
63
+ | 3.756 | 1.1839 | 11000 | 3.7326 | 0.3459 |
64
+ | 3.7433 | 1.2916 | 12000 | 3.7075 | 0.3482 |
65
+ | 3.6954 | 1.3992 | 13000 | 3.6850 | 0.3507 |
66
+ | 3.7046 | 1.5068 | 14000 | 3.6652 | 0.3524 |
67
+ | 3.6836 | 1.6145 | 15000 | 3.6443 | 0.3549 |
68
+ | 3.6705 | 1.7221 | 16000 | 3.6317 | 0.3563 |
69
+ | 3.6766 | 1.8297 | 17000 | 3.6120 | 0.3582 |
70
+ | 3.6642 | 1.9374 | 18000 | 3.5988 | 0.3593 |
71
+ | 3.574 | 2.0450 | 19000 | 3.5869 | 0.3607 |
72
+ | 3.586 | 2.1526 | 20000 | 3.5799 | 0.3617 |
73
+ | 3.579 | 2.2603 | 21000 | 3.5687 | 0.3628 |
74
+ | 3.5842 | 2.3679 | 22000 | 3.5584 | 0.3636 |
75
+ | 3.5734 | 2.4755 | 23000 | 3.5507 | 0.3647 |
76
+ | 3.5581 | 2.5831 | 24000 | 3.5391 | 0.3659 |
77
+ | 3.5515 | 2.6908 | 25000 | 3.5315 | 0.3668 |
78
+ | 3.5423 | 2.7984 | 26000 | 3.5233 | 0.3680 |
79
+ | 3.5243 | 2.9060 | 27000 | 3.5113 | 0.3684 |
80
+ | 3.4538 | 3.0137 | 28000 | 3.5069 | 0.3696 |
81
+ | 3.4722 | 3.1213 | 29000 | 3.5049 | 0.3697 |
82
+ | 3.4524 | 3.2289 | 30000 | 3.4978 | 0.3707 |
83
+ | 3.4688 | 3.3366 | 31000 | 3.4941 | 0.3712 |
84
+ | 3.4785 | 3.4442 | 32000 | 3.4841 | 0.3719 |
85
+ | 3.4753 | 3.5518 | 33000 | 3.4780 | 0.3729 |
86
+ | 3.4545 | 3.6595 | 34000 | 3.4730 | 0.3732 |
87
+ | 3.4517 | 3.7671 | 35000 | 3.4651 | 0.3737 |
88
+ | 3.4909 | 3.8747 | 36000 | 3.4599 | 0.3745 |
89
+ | 3.4628 | 3.9823 | 37000 | 3.4547 | 0.3749 |
90
+ | 3.3911 | 4.0900 | 38000 | 3.4564 | 0.3753 |
91
+ | 3.3895 | 4.1976 | 39000 | 3.4516 | 0.3759 |
92
+ | 3.4174 | 4.3052 | 40000 | 3.4474 | 0.3762 |
93
+ | 3.4022 | 4.4129 | 41000 | 3.4428 | 0.3768 |
94
+ | 3.4035 | 4.5205 | 42000 | 3.4386 | 0.3773 |
95
+ | 3.4213 | 4.6281 | 43000 | 3.4306 | 0.3780 |
96
+ | 3.3859 | 4.7358 | 44000 | 3.4266 | 0.3786 |
97
+ | 3.3887 | 4.8434 | 45000 | 3.4216 | 0.3788 |
98
+ | 3.4066 | 4.9510 | 46000 | 3.4164 | 0.3793 |
99
+ | 3.3124 | 5.0587 | 47000 | 3.4212 | 0.3794 |
100
+ | 3.3621 | 5.1663 | 48000 | 3.4188 | 0.3800 |
101
+ | 3.3335 | 5.2739 | 49000 | 3.4140 | 0.3802 |
102
+ | 3.3529 | 5.3816 | 50000 | 3.4105 | 0.3805 |
103
+ | 3.3445 | 5.4892 | 51000 | 3.4076 | 0.3811 |
104
+ | 3.3472 | 5.5968 | 52000 | 3.4007 | 0.3814 |
105
+ | 3.3447 | 5.7044 | 53000 | 3.3967 | 0.3822 |
106
+ | 3.3548 | 5.8121 | 54000 | 3.3929 | 0.3826 |
107
+ | 3.3568 | 5.9197 | 55000 | 3.3891 | 0.3831 |
108
+ | 3.2596 | 6.0273 | 56000 | 3.3910 | 0.3830 |
109
+ | 3.28 | 6.1350 | 57000 | 3.3911 | 0.3833 |
110
+ | 3.2973 | 6.2426 | 58000 | 3.3869 | 0.3838 |
111
+ | 3.2905 | 6.3502 | 59000 | 3.3843 | 0.3839 |
112
+ | 3.2984 | 6.4579 | 60000 | 3.3795 | 0.3844 |
113
+ | 3.2829 | 6.5655 | 61000 | 3.3760 | 0.3846 |
114
+ | 3.2952 | 6.6731 | 62000 | 3.3733 | 0.3853 |
115
+ | 3.2994 | 6.7808 | 63000 | 3.3677 | 0.3857 |
116
+ | 3.2935 | 6.8884 | 64000 | 3.3649 | 0.3858 |
117
+ | 3.3002 | 6.9960 | 65000 | 3.3595 | 0.3865 |
118
+ | 3.2116 | 7.1036 | 66000 | 3.3664 | 0.3865 |
119
+ | 3.2481 | 7.2113 | 67000 | 3.3638 | 0.3866 |
120
+ | 3.2384 | 7.3189 | 68000 | 3.3612 | 0.3867 |
121
+ | 3.2446 | 7.4265 | 69000 | 3.3570 | 0.3874 |
122
+ | 3.2569 | 7.5342 | 70000 | 3.3543 | 0.3877 |
123
+ | 3.2258 | 7.6418 | 71000 | 3.3509 | 0.3879 |
124
+ | 3.258 | 7.7494 | 72000 | 3.3453 | 0.3886 |
125
+ | 3.2484 | 7.8571 | 73000 | 3.3418 | 0.3889 |
126
+ | 3.252 | 7.9647 | 74000 | 3.3382 | 0.3892 |
127
+ | 3.1996 | 8.0723 | 75000 | 3.3451 | 0.3889 |
128
+ | 3.1725 | 8.1800 | 76000 | 3.3427 | 0.3895 |
129
+ | 3.2013 | 8.2876 | 77000 | 3.3404 | 0.3896 |
130
+ | 3.1951 | 8.3952 | 78000 | 3.3374 | 0.3900 |
131
+ | 3.1936 | 8.5029 | 79000 | 3.3332 | 0.3901 |
132
+ | 3.2063 | 8.6105 | 80000 | 3.3296 | 0.3908 |
133
+ | 3.2116 | 8.7181 | 81000 | 3.3260 | 0.3910 |
134
+ | 3.1955 | 8.8257 | 82000 | 3.3253 | 0.3912 |
135
+ | 3.1902 | 8.9334 | 83000 | 3.3195 | 0.3917 |
136
+ | 3.1168 | 9.0410 | 84000 | 3.3231 | 0.3916 |
137
+ | 3.1455 | 9.1486 | 85000 | 3.3208 | 0.3920 |
138
+ | 3.1348 | 9.2563 | 86000 | 3.3196 | 0.3921 |
139
+ | 3.1499 | 9.3639 | 87000 | 3.3164 | 0.3925 |
140
+ | 3.1286 | 9.4715 | 88000 | 3.3146 | 0.3928 |
141
+ | 3.1561 | 9.5792 | 89000 | 3.3114 | 0.3931 |
142
+ | 3.1599 | 9.6868 | 90000 | 3.3092 | 0.3933 |
143
+ | 3.1425 | 9.7944 | 91000 | 3.3074 | 0.3935 |
144
+ | 3.1375 | 9.9021 | 92000 | 3.3063 | 0.3937 |
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": 0.3932824917497146,
4
+ "eval_loss": 3.3091650009155273,
5
+ "eval_runtime": 184.8493,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 97.436,
8
+ "eval_steps_per_second": 6.091,
9
+ "perplexity": 27.3622684613255,
10
+ "total_flos": 7.7681859821568e+17,
11
+ "train_loss": 3.468291573590681,
12
+ "train_runtime": 80362.6457,
13
+ "train_samples": 297299,
14
+ "train_samples_per_second": 36.995,
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": 0.3932824917497146,
4
+ "eval_loss": 3.3091650009155273,
5
+ "eval_runtime": 184.8493,
6
+ "eval_samples": 18011,
7
+ "eval_samples_per_second": 97.436,
8
+ "eval_steps_per_second": 6.091,
9
+ "perplexity": 27.3622684613255
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 sha256:323728d4ed0ec66f10b825568155add8a6cff28ea98f55f18ce734b850b4629d
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": 3.468291573590681,
5
+ "train_runtime": 80362.6457,
6
+ "train_samples": 297299,
7
+ "train_samples_per_second": 36.995,
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 sha256:0517a4c3ffc9997b66b76e1384f703bfe769ddfda9447aed74aa1950cd4f5e29
3
+ size 5304