Hugging Face's logo

alakxender
/
dhivehi-gpt2-base

PyTorch
Safetensors
Divehi
gpt2
Model card Files
xet
Community
alakxender commited on
Commit
b1e2ac9
·
verified ·
1 Parent(s): b2ea6f9

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. added_tokens.json +3 -0
  2. checkpoint-100/config.json +39 -0
  3. checkpoint-100/generation_config.json +6 -0
  4. checkpoint-100/model.safetensors +3 -0
  5. checkpoint-100/optimizer.pt +3 -0
  6. checkpoint-100/rng_state.pth +3 -0
  7. checkpoint-100/scheduler.pt +3 -0
  8. checkpoint-100/trainer_state.json +111 -0
  9. checkpoint-100/training_args.bin +3 -0
  10. checkpoint-123/config.json +39 -0
  11. checkpoint-123/generation_config.json +6 -0
  12. checkpoint-123/model.safetensors +3 -0
  13. checkpoint-123/optimizer.pt +3 -0
  14. checkpoint-123/rng_state.pth +3 -0
  15. checkpoint-123/scheduler.pt +3 -0
  16. checkpoint-123/trainer_state.json +125 -0
  17. checkpoint-123/training_args.bin +3 -0
  18. config.json +39 -0
  19. generation_config.json +6 -0
  20. merges.txt +0 -0
  21. model.safetensors +3 -0
  22. pytorch_model.bin +3 -0
  23. special_tokens_map.json +22 -0
  24. tokenizer.json +0 -0
  25. tokenizer_config.json +32 -0
  26. training_args.bin +3 -0
  27. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|startoftext|>": 50257
3
+ }
checkpoint-100/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-100/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": "4.46.3"
6
+ }
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1256181a39adbe068aa87574a1d09ac9415c0ba76c9cb697990d4de36c71f148
3
+ size 497777280
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478e104bba614a49a6837a2ff7a185b39473b491b02ca126849cf5b547aa0743
3
+ size 995648442
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22204b8ec7253f135580d3475a2867c1ed40c03f554f6e4956370281b08bef33
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84edd34d7d0f0f006b96588fbd196800facfb78577f2aa279cb574a7d9facb10
3
+ size 1064
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.382002830505371,
3
+ "best_model_checkpoint": "dhivehi-gpt2-base/checkpoint-100",
4
+ "epoch": 2.4390243902439024,
5
+ "eval_steps": 100,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.24390243902439024,
13
+ "grad_norm": 83.27034759521484,
14
+ "learning_rate": 2.5000000000000004e-07,
15
+ "loss": 2.4436,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.4878048780487805,
20
+ "grad_norm": 60.58613967895508,
21
+ "learning_rate": 7.5e-07,
22
+ "loss": 2.321,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.7317073170731707,
27
+ "grad_norm": 29.228893280029297,
28
+ "learning_rate": 1.25e-06,
29
+ "loss": 2.0685,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.975609756097561,
34
+ "grad_norm": 18.66552734375,
35
+ "learning_rate": 1.7500000000000002e-06,
36
+ "loss": 1.8913,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.2195121951219512,
41
+ "grad_norm": 10.73972225189209,
42
+ "learning_rate": 2.25e-06,
43
+ "loss": 1.7331,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 1.4634146341463414,
48
+ "grad_norm": 6.437626361846924,
49
+ "learning_rate": 2.7500000000000004e-06,
50
+ "loss": 1.6317,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.7073170731707317,
55
+ "grad_norm": 3.9424028396606445,
56
+ "learning_rate": 3.2500000000000002e-06,
57
+ "loss": 1.5445,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.951219512195122,
62
+ "grad_norm": 2.4789206981658936,
63
+ "learning_rate": 3.75e-06,
64
+ "loss": 1.4638,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 2.1951219512195124,
69
+ "grad_norm": 1.7527034282684326,
70
+ "learning_rate": 4.250000000000001e-06,
71
+ "loss": 1.3972,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 2.4390243902439024,
76
+ "grad_norm": 1.9903717041015625,
77
+ "learning_rate": 4.75e-06,
78
+ "loss": 1.3272,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 2.4390243902439024,
83
+ "eval_loss": 1.382002830505371,
84
+ "eval_runtime": 5.1108,
85
+ "eval_samples_per_second": 56.742,
86
+ "eval_steps_per_second": 1.957,
87
+ "step": 100
88
+ }
89
+ ],
90
+ "logging_steps": 10,
91
+ "max_steps": 123,
92
+ "num_input_tokens_seen": 0,
93
+ "num_train_epochs": 3,
94
+ "save_steps": 100,
95
+ "stateful_callbacks": {
96
+ "TrainerControl": {
97
+ "args": {
98
+ "should_epoch_stop": false,
99
+ "should_evaluate": false,
100
+ "should_log": false,
101
+ "should_save": true,
102
+ "should_training_stop": false
103
+ },
104
+ "attributes": {}
105
+ }
106
+ },
107
+ "total_flos": 3322589478912000.0,
108
+ "train_batch_size": 32,
109
+ "trial_name": null,
110
+ "trial_params": null
111
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33253810238ac5f6e19d65eaf18a7b5652de403635f7f896af35a9b7b932f10a
3
+ size 5240
checkpoint-123/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-123/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": "4.46.3"
6
+ }
checkpoint-123/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf64a93419d4aeb9079da0eb6f33276c930b740d901b4378ae9f11c5aa786d0f
3
+ size 497777280
checkpoint-123/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fe9f7fcec27cf0397fed0aea7d3d4b1d7b7b7d1a8e0ac31f5ed4f19e45be2e
3
+ size 995648442
checkpoint-123/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9c2abd33f8421dbe1f81a265d65c5e9b7976e8c94fcbf0c6fa98d24a1e34d4
3
+ size 14244
checkpoint-123/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4447704abe5a3947412c6e315c46fd7fa1c7b8d0c8048f8a9031f4f62c23812
3
+ size 1064
checkpoint-123/trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.382002830505371,
3
+ "best_model_checkpoint": "dhivehi-gpt2-base/checkpoint-100",
4
+ "epoch": 3.0,
5
+ "eval_steps": 100,
6
+ "global_step": 123,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.24390243902439024,
13
+ "grad_norm": 83.27034759521484,
14
+ "learning_rate": 2.5000000000000004e-07,
15
+ "loss": 2.4436,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.4878048780487805,
20
+ "grad_norm": 60.58613967895508,
21
+ "learning_rate": 7.5e-07,
22
+ "loss": 2.321,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.7317073170731707,
27
+ "grad_norm": 29.228893280029297,
28
+ "learning_rate": 1.25e-06,
29
+ "loss": 2.0685,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.975609756097561,
34
+ "grad_norm": 18.66552734375,
35
+ "learning_rate": 1.7500000000000002e-06,
36
+ "loss": 1.8913,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.2195121951219512,
41
+ "grad_norm": 10.73972225189209,
42
+ "learning_rate": 2.25e-06,
43
+ "loss": 1.7331,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 1.4634146341463414,
48
+ "grad_norm": 6.437626361846924,
49
+ "learning_rate": 2.7500000000000004e-06,
50
+ "loss": 1.6317,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.7073170731707317,
55
+ "grad_norm": 3.9424028396606445,
56
+ "learning_rate": 3.2500000000000002e-06,
57
+ "loss": 1.5445,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.951219512195122,
62
+ "grad_norm": 2.4789206981658936,
63
+ "learning_rate": 3.75e-06,
64
+ "loss": 1.4638,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 2.1951219512195124,
69
+ "grad_norm": 1.7527034282684326,
70
+ "learning_rate": 4.250000000000001e-06,
71
+ "loss": 1.3972,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 2.4390243902439024,
76
+ "grad_norm": 1.9903717041015625,
77
+ "learning_rate": 4.75e-06,
78
+ "loss": 1.3272,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 2.4390243902439024,
83
+ "eval_loss": 1.382002830505371,
84
+ "eval_runtime": 5.1108,
85
+ "eval_samples_per_second": 56.742,
86
+ "eval_steps_per_second": 1.957,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 2.682926829268293,
91
+ "grad_norm": 3.0437378883361816,
92
+ "learning_rate": 5.25e-06,
93
+ "loss": 1.292,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 2.926829268292683,
98
+ "grad_norm": 5.521629810333252,
99
+ "learning_rate": 5.750000000000001e-06,
100
+ "loss": 1.2725,
101
+ "step": 120
102
+ }
103
+ ],
104
+ "logging_steps": 10,
105
+ "max_steps": 123,
106
+ "num_input_tokens_seen": 0,
107
+ "num_train_epochs": 3,
108
+ "save_steps": 100,
109
+ "stateful_callbacks": {
110
+ "TrainerControl": {
111
+ "args": {
112
+ "should_epoch_stop": false,
113
+ "should_evaluate": false,
114
+ "should_log": false,
115
+ "should_save": true,
116
+ "should_training_stop": true
117
+ },
118
+ "attributes": {}
119
+ }
120
+ },
121
+ "total_flos": 4080858955776000.0,
122
+ "train_batch_size": 32,
123
+ "trial_name": null,
124
+ "trial_params": null
125
+ }
checkpoint-123/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33253810238ac5f6e19d65eaf18a7b5652de403635f7f896af35a9b7b932f10a
3
+ size 5240
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
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": "4.46.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1256181a39adbe068aa87574a1d09ac9415c0ba76c9cb697990d4de36c71f148
3
+ size 497777280
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cefc1ca7e5a412a741f84b3a88bcbd1d4b84204bb464de843c221eb346ad022
3
+ size 497818650
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|startoftext|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|endoftext|>",
19
+ "eos_token": "<|endoftext|>",
20
+ "pad_token": "<|endoftext|>",
21
+ "unk_token": "<|endoftext|>"
22
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "additional_special_tokens": [
22
+ "<|endoftext|>",
23
+ "<|startoftext|>"
24
+ ],
25
+ "bos_token": "<|endoftext|>",
26
+ "clean_up_tokenization_spaces": false,
27
+ "eos_token": "<|endoftext|>",
28
+ "model_max_length": 1024,
29
+ "pad_token": "<|endoftext|>",
30
+ "tokenizer_class": "GPT2Tokenizer",
31
+ "unk_token": "<|endoftext|>"
32
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33253810238ac5f6e19d65eaf18a7b5652de403635f7f896af35a9b7b932f10a
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff