Hugging Face's logo

withmartian
/
roberta-bcbToppers-perf-15epochs

TensorBoard
Safetensors
roberta
Model card Files Metrics Community
wlg1 commited on
Commit
ada6914
·
verified ·
1 Parent(s): ba10cd6

Upload folder using huggingface_hub

Browse files
Files changed (34) hide show
  1. checkpoint-500/config.json +41 -0
  2. checkpoint-500/merges.txt +0 -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 +15 -0
  8. checkpoint-500/tokenizer.json +0 -0
  9. checkpoint-500/tokenizer_config.json +58 -0
  10. checkpoint-500/trainer_state.json +41 -0
  11. checkpoint-500/training_args.bin +3 -0
  12. checkpoint-500/vocab.json +0 -0
  13. checkpoint-750/config.json +41 -0
  14. checkpoint-750/merges.txt +0 -0
  15. checkpoint-750/model.safetensors +3 -0
  16. checkpoint-750/optimizer.pt +3 -0
  17. checkpoint-750/rng_state.pth +3 -0
  18. checkpoint-750/scheduler.pt +3 -0
  19. checkpoint-750/special_tokens_map.json +15 -0
  20. checkpoint-750/tokenizer.json +0 -0
  21. checkpoint-750/tokenizer_config.json +58 -0
  22. checkpoint-750/trainer_state.json +41 -0
  23. checkpoint-750/training_args.bin +3 -0
  24. checkpoint-750/vocab.json +0 -0
  25. config.json +41 -0
  26. merges.txt +0 -0
  27. model.safetensors +3 -0
  28. runs/Aug03_20-12-43_209-20-159-47/events.out.tfevents.1754251964.209-20-159-47.12391.0 +3 -0
  29. runs/Aug03_20-37-10_209-20-159-47/events.out.tfevents.1754253431.209-20-159-47.14093.0 +3 -0
  30. special_tokens_map.json +15 -0
  31. tokenizer.json +0 -0
  32. tokenizer_config.json +58 -0
  33. training_args.bin +3 -0
  34. vocab.json +0 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3,
26
+ "LABEL_4": 4
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "multi_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.54.1",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 50265
41
+ }
checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe772940c6b15ca18b09f771c6995f75bfcd7a04f89b8df964c055b95945fe50
3
+ size 498622052
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0104e7b506588ad47c878f559d4d647669b2d6d95335e97260899a4b03e85d10
3
+ size 997364363
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdf334999f1d86f4c0fd2e34b526bcf6e963460ef83fb4772827539c8698bf5
3
+ size 14645
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267992721569133f63f838405eeb7a3e04d86426f97ca08526318c3b65f71b3a
3
+ size 1465
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
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": 10.0,
14
+ "grad_norm": 1.2768138647079468,
15
+ "learning_rate": 1.004e-05,
16
+ "loss": 0.6921,
17
+ "step": 500
18
+ }
19
+ ],
20
+ "logging_steps": 500,
21
+ "max_steps": 750,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 15,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": false
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 2099682776862720.0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1639c95820714f517832c4ffd514567b527b73858c7414514e89c4a9e1817b9a
3
+ size 5777
checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-750/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3,
26
+ "LABEL_4": 4
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "multi_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.54.1",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 50265
41
+ }
checkpoint-750/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3098c3c53a8fb2c64c7a66ea7c6ee1571806468fb3393e8616a01e45125e5c6f
3
+ size 498622052
checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d3bafde61f67529e1f8b91eda1d4cfcdd4fbbf789fb534cdaf0416ed762cb0
3
+ size 997364363
checkpoint-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e0010af467776d3204bfbd7c0fc927685434bb4a505b960e8496c8ef10616b
3
+ size 14645
checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c4040f93924ed51ed2027bb7a6b8d5f928d223b18915138ee2309d3a7286b3b
3
+ size 1465
checkpoint-750/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-750/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-750/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 15.0,
6
+ "eval_steps": 500,
7
+ "global_step": 750,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 10.0,
14
+ "grad_norm": 1.2768138647079468,
15
+ "learning_rate": 1.004e-05,
16
+ "loss": 0.6921,
17
+ "step": 500
18
+ }
19
+ ],
20
+ "logging_steps": 500,
21
+ "max_steps": 750,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 15,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": true
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 3149524165294080.0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
checkpoint-750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1639c95820714f517832c4ffd514567b527b73858c7414514e89c4a9e1817b9a
3
+ size 5777
checkpoint-750/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3,
26
+ "LABEL_4": 4
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "multi_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.54.1",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 50265
41
+ }
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 sha256:3098c3c53a8fb2c64c7a66ea7c6ee1571806468fb3393e8616a01e45125e5c6f
3
+ size 498622052
runs/Aug03_20-12-43_209-20-159-47/events.out.tfevents.1754251964.209-20-159-47.12391.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa9a4d07eb816801c95126b295b05d5725b663aab91c4cdfd17ad9e1733eed5
3
+ size 5834
runs/Aug03_20-37-10_209-20-159-47/events.out.tfevents.1754253431.209-20-159-47.14093.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69505e6263f96c92af7bc67c0fdd6e4a8a651e96ea10a7dd8b974ecb130d680f
3
+ size 5834
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1639c95820714f517832c4ffd514567b527b73858c7414514e89c4a9e1817b9a
3
+ size 5777
vocab.json ADDED
The diff for this file is too large to render. See raw diff