Hugging Face's logo

thainq107
/
gpt-small-c4

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
thainq107 commited on
Commit
0b0661c
·
verified ·
1 Parent(s): 2f560e8

End of training

Browse files
Files changed (8) hide show
  1. README.md +105 -0
  2. config.json +32 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +53 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt-small-c4
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # gpt-small-c4
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.4497
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 32
38
+ - eval_batch_size: 32
39
+ - seed: 42
40
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 20
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-------:|:-----:|:---------------:|
49
+ | 7.0256 | 0.4005 | 1000 | 6.4298 |
50
+ | 6.264 | 0.8010 | 2000 | 6.0446 |
51
+ | 5.9635 | 1.2014 | 3000 | 5.7924 |
52
+ | 5.7506 | 1.6019 | 4000 | 5.6125 |
53
+ | 5.6108 | 2.0024 | 5000 | 5.4753 |
54
+ | 5.4654 | 2.4029 | 6000 | 5.3627 |
55
+ | 5.3748 | 2.8034 | 7000 | 5.2686 |
56
+ | 5.2775 | 3.2038 | 8000 | 5.1859 |
57
+ | 5.1925 | 3.6043 | 9000 | 5.1097 |
58
+ | 5.1347 | 4.0048 | 10000 | 5.0354 |
59
+ | 5.0484 | 4.4053 | 11000 | 4.9773 |
60
+ | 4.9933 | 4.8058 | 12000 | 4.9212 |
61
+ | 4.9351 | 5.2062 | 13000 | 4.8743 |
62
+ | 4.8865 | 5.6067 | 14000 | 4.8315 |
63
+ | 4.8497 | 6.0072 | 15000 | 4.7960 |
64
+ | 4.793 | 6.4077 | 16000 | 4.7648 |
65
+ | 4.7707 | 6.8082 | 17000 | 4.7354 |
66
+ | 4.7275 | 7.2087 | 18000 | 4.7083 |
67
+ | 4.702 | 7.6091 | 19000 | 4.6839 |
68
+ | 4.6871 | 8.0096 | 20000 | 4.6641 |
69
+ | 4.6432 | 8.4101 | 21000 | 4.6458 |
70
+ | 4.6269 | 8.8106 | 22000 | 4.6268 |
71
+ | 4.6021 | 9.2111 | 23000 | 4.6126 |
72
+ | 4.5857 | 9.6115 | 24000 | 4.5965 |
73
+ | 4.5755 | 10.0120 | 25000 | 4.5830 |
74
+ | 4.5421 | 10.4125 | 26000 | 4.5738 |
75
+ | 4.5401 | 10.8130 | 27000 | 4.5622 |
76
+ | 4.5149 | 11.2135 | 28000 | 4.5539 |
77
+ | 4.5035 | 11.6139 | 29000 | 4.5425 |
78
+ | 4.4957 | 12.0144 | 30000 | 4.5350 |
79
+ | 4.47 | 12.4149 | 31000 | 4.5258 |
80
+ | 4.4736 | 12.8154 | 32000 | 4.5191 |
81
+ | 4.4503 | 13.2159 | 33000 | 4.5091 |
82
+ | 4.4474 | 13.6163 | 34000 | 4.5037 |
83
+ | 4.4405 | 14.0168 | 35000 | 4.4968 |
84
+ | 4.4225 | 14.4173 | 36000 | 4.4937 |
85
+ | 4.4167 | 14.8178 | 37000 | 4.4876 |
86
+ | 4.4138 | 15.2183 | 38000 | 4.4808 |
87
+ | 4.4023 | 15.6187 | 39000 | 4.4764 |
88
+ | 4.3988 | 16.0192 | 40000 | 4.4723 |
89
+ | 4.3839 | 16.4197 | 41000 | 4.4702 |
90
+ | 4.3865 | 16.8202 | 42000 | 4.4652 |
91
+ | 4.3782 | 17.2207 | 43000 | 4.4615 |
92
+ | 4.3732 | 17.6211 | 44000 | 4.4601 |
93
+ | 4.3711 | 18.0216 | 45000 | 4.4561 |
94
+ | 4.3628 | 18.4221 | 46000 | 4.4542 |
95
+ | 4.362 | 18.8226 | 47000 | 4.4522 |
96
+ | 4.3554 | 19.2231 | 48000 | 4.4509 |
97
+ | 4.3549 | 19.6235 | 49000 | 4.4497 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.49.0
103
+ - Pytorch 2.6.0+cu124
104
+ - Datasets 2.20.0
105
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 0,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 2,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 512,
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 6,
18
+ "n_positions": 512,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.49.0",
30
+ "use_cache": true,
31
+ "vocab_size": 50257
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.49.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af78708fbac15d0c7d63b5367995e782394281a682b4346beffc11b9853e2b43
3
+ size 179643784
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "eos_token": "</s>",
47
+ "extra_special_tokens": {},
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "tokenizer_class": "PreTrainedTokenizer",
52
+ "unk_token": "<unk>"
53
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f91c3ffba48bbc717441c50ab12d5a8f0b2e5860d2cf801444b599209e9d30a
3
+ size 5304