Hugging Face's logo

adity12345
/
chakma-gpt2

Transformers
TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
adity12345 commited on
Commit
5d19cd4
·
verified ·
1 Parent(s): 653324a

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. checkpoint-500/config.json +33 -0
  2. checkpoint-500/generation_config.json +5 -0
  3. checkpoint-500/model.safetensors +3 -0
  4. checkpoint-500/optimizer.pt +3 -0
  5. checkpoint-500/rng_state.pth +3 -0
  6. checkpoint-500/scheduler.pt +3 -0
  7. checkpoint-500/special_tokens_map.json +37 -0
  8. checkpoint-500/tokenizer.json +0 -0
  9. checkpoint-500/tokenizer_config.json +53 -0
  10. checkpoint-500/trainer_state.json +69 -0
  11. checkpoint-500/training_args.bin +3 -0
  12. checkpoint-580/config.json +33 -0
  13. checkpoint-580/generation_config.json +5 -0
  14. checkpoint-580/model.safetensors +3 -0
  15. checkpoint-580/optimizer.pt +3 -0
  16. checkpoint-580/rng_state.pth +3 -0
  17. checkpoint-580/scheduler.pt +3 -0
  18. checkpoint-580/special_tokens_map.json +37 -0
  19. checkpoint-580/tokenizer.json +0 -0
  20. checkpoint-580/tokenizer_config.json +53 -0
  21. checkpoint-580/trainer_state.json +69 -0
  22. checkpoint-580/training_args.bin +3 -0
  23. runs/Aug17_11-26-56_b9dde2d71266/events.out.tfevents.1755430029.b9dde2d71266.1253.0 +3 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": null,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": null,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 512,
14
+ "n_embd": 256,
15
+ "n_head": 4,
16
+ "n_inner": null,
17
+ "n_layer": 4,
18
+ "n_positions": 512,
19
+ "pad_token_id": 3,
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
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.1",
31
+ "use_cache": true,
32
+ "vocab_size": 3286
33
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 3,
4
+ "transformers_version": "4.55.1"
5
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422feb66e1e6eb44a134cc5e8efa69e77bb085f4e2de61e40b33353aa29f0319
3
+ size 16532464
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998138b111e8d22596a694e475888a90b16cee5d39d60c2b0223c9eadb48eaa8
3
+ size 33097146
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e19877f6c88d1d03dee0be605ce51a0d9604f16a96be3be67d3460d02764d1b
3
+ size 13990
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5106ad7432e731ec736173193caa5ea1ad532e66e19de02c143eaf74bf4f8be6
3
+ size 1064
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
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
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
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
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "extra_special_tokens": {},
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "unk_token": "[UNK]"
53
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.310344827586207,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8620689655172413,
14
+ "grad_norm": 1.8119763135910034,
15
+ "learning_rate": 4.1465517241379316e-05,
16
+ "loss": 7.0608,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 1.7241379310344827,
21
+ "grad_norm": 1.487192988395691,
22
+ "learning_rate": 3.28448275862069e-05,
23
+ "loss": 6.642,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 2.586206896551724,
28
+ "grad_norm": 2.240494966506958,
29
+ "learning_rate": 2.4224137931034484e-05,
30
+ "loss": 6.4743,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 3.4482758620689653,
35
+ "grad_norm": 1.6817247867584229,
36
+ "learning_rate": 1.560344827586207e-05,
37
+ "loss": 6.3882,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 4.310344827586207,
42
+ "grad_norm": 2.3927712440490723,
43
+ "learning_rate": 6.982758620689656e-06,
44
+ "loss": 6.3381,
45
+ "step": 500
46
+ }
47
+ ],
48
+ "logging_steps": 100,
49
+ "max_steps": 580,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": false
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 4400409176064.0,
66
+ "train_batch_size": 8,
67
+ "trial_name": null,
68
+ "trial_params": null
69
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d5f20a861dba76d72af3ab3fee8b2b55e3716e784f1bf71e429b45d1942972
3
+ size 5304
checkpoint-580/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": null,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": null,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 512,
14
+ "n_embd": 256,
15
+ "n_head": 4,
16
+ "n_inner": null,
17
+ "n_layer": 4,
18
+ "n_positions": 512,
19
+ "pad_token_id": 3,
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
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.1",
31
+ "use_cache": true,
32
+ "vocab_size": 3286
33
+ }
checkpoint-580/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 3,
4
+ "transformers_version": "4.55.1"
5
+ }
checkpoint-580/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f68a53ba750666453ab5f9cb2196ac96e2867c961a91980fc97d5a36d9e8fe8
3
+ size 16532464
checkpoint-580/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa2a42d089dafdd0a559a1923107912a604dd28459fa8966e1b934372b07211
3
+ size 33097146
checkpoint-580/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7ecb532e639c77b884f45b20d17b622fd8c47320e6bf08cf92727250f89458
3
+ size 13990
checkpoint-580/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eacdca6c0c8a87735f5b27cd1c463766950676365df65e4b9f8d06152e2084ae
3
+ size 1064
checkpoint-580/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
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
+ }
checkpoint-580/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-580/tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
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
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "extra_special_tokens": {},
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "unk_token": "[UNK]"
53
+ }
checkpoint-580/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 580,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8620689655172413,
14
+ "grad_norm": 1.8119763135910034,
15
+ "learning_rate": 4.1465517241379316e-05,
16
+ "loss": 7.0608,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 1.7241379310344827,
21
+ "grad_norm": 1.487192988395691,
22
+ "learning_rate": 3.28448275862069e-05,
23
+ "loss": 6.642,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 2.586206896551724,
28
+ "grad_norm": 2.240494966506958,
29
+ "learning_rate": 2.4224137931034484e-05,
30
+ "loss": 6.4743,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 3.4482758620689653,
35
+ "grad_norm": 1.6817247867584229,
36
+ "learning_rate": 1.560344827586207e-05,
37
+ "loss": 6.3882,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 4.310344827586207,
42
+ "grad_norm": 2.3927712440490723,
43
+ "learning_rate": 6.982758620689656e-06,
44
+ "loss": 6.3381,
45
+ "step": 500
46
+ }
47
+ ],
48
+ "logging_steps": 100,
49
+ "max_steps": 580,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": true
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 5039877224448.0,
66
+ "train_batch_size": 8,
67
+ "trial_name": null,
68
+ "trial_params": null
69
+ }
checkpoint-580/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d5f20a861dba76d72af3ab3fee8b2b55e3716e784f1bf71e429b45d1942972
3
+ size 5304
runs/Aug17_11-26-56_b9dde2d71266/events.out.tfevents.1755430029.b9dde2d71266.1253.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879c52778708d5f827515abc3c6813f9d098f8f72707a1d28ad790c7751814c7
3
+ size 6424