Hugging Face's logo

itsanastasiaminina
/
students_scores_model

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
itsanastasiaminina commited on
Commit
ef549c0
·
verified ·
1 Parent(s): 6aee8fa

Training in progress, epoch 1

Browse files
Files changed (28) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-1410/config.json +44 -0
  3. run-1/checkpoint-1410/merges.txt +0 -0
  4. run-1/checkpoint-1410/model.safetensors +3 -0
  5. run-1/checkpoint-1410/optimizer.pt +3 -0
  6. run-1/checkpoint-1410/rng_state.pth +3 -0
  7. run-1/checkpoint-1410/scheduler.pt +3 -0
  8. run-1/checkpoint-1410/special_tokens_map.json +15 -0
  9. run-1/checkpoint-1410/tokenizer.json +0 -0
  10. run-1/checkpoint-1410/tokenizer_config.json +58 -0
  11. run-1/checkpoint-1410/trainer_state.json +97 -0
  12. run-1/checkpoint-1410/training_args.bin +3 -0
  13. run-1/checkpoint-1410/vocab.json +0 -0
  14. run-2/checkpoint-563/config.json +44 -0
  15. run-2/checkpoint-563/merges.txt +0 -0
  16. run-2/checkpoint-563/model.safetensors +3 -0
  17. run-2/checkpoint-563/optimizer.pt +3 -0
  18. run-2/checkpoint-563/rng_state.pth +3 -0
  19. run-2/checkpoint-563/scheduler.pt +3 -0
  20. run-2/checkpoint-563/special_tokens_map.json +15 -0
  21. run-2/checkpoint-563/tokenizer.json +0 -0
  22. run-2/checkpoint-563/tokenizer_config.json +58 -0
  23. run-2/checkpoint-563/trainer_state.json +54 -0
  24. run-2/checkpoint-563/training_args.bin +3 -0
  25. run-2/checkpoint-563/vocab.json +0 -0
  26. runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733666403.3b937233628b.23.1 +2 -2
  27. runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733669115.3b937233628b.23.2 +3 -0
  28. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7990e33fa8b696609893e535a2f57fb904b216de13b4775c66d8ed0932dc14c
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a179bdc6645e371c1c6c54d65c472ae37780358419b2d43cda9745925698e3d
3
  size 498625128
run-1/checkpoint-1410/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 1,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.47.0",
41
+ "type_vocab_size": 1,
42
+ "use_cache": true,
43
+ "vocab_size": 50265
44
+ }
run-1/checkpoint-1410/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1410/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990205f242b0ec2efe39dbc3eb01f20f27d4e8e5f2fac9bd31e6196f3777bab8
3
+ size 498625128
run-1/checkpoint-1410/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3845a8d67428319e44a880d5e03f4185aca323658755031fab87ba7904b6d17a
3
+ size 997370106
run-1/checkpoint-1410/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fcbae34d469657b5d0c79b5675615c71134bf171f73d10deae62819e085a38e
3
+ size 14244
run-1/checkpoint-1410/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3699141451f13435bbff84239896053f36e79abab9b017911318554f619a55
3
+ size 1064
run-1/checkpoint-1410/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
+ }
run-1/checkpoint-1410/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1410/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
+ }
run-1/checkpoint-1410/trainer_state.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6285243252934658,
3
+ "best_model_checkpoint": "students_scores_model/run-1/checkpoint-1128",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1410,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_f1": 0.5135559583730447,
14
+ "eval_loss": 1.0615456104278564,
15
+ "eval_runtime": 37.678,
16
+ "eval_samples_per_second": 59.716,
17
+ "eval_steps_per_second": 7.484,
18
+ "step": 282
19
+ },
20
+ {
21
+ "epoch": 1.773049645390071,
22
+ "grad_norm": 11.819360733032227,
23
+ "learning_rate": 8.537794225405964e-06,
24
+ "loss": 1.0289,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_f1": 0.5853742204012189,
30
+ "eval_loss": 0.9459031224250793,
31
+ "eval_runtime": 37.7163,
32
+ "eval_samples_per_second": 59.656,
33
+ "eval_steps_per_second": 7.477,
34
+ "step": 564
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_f1": 0.6179112498233506,
39
+ "eval_loss": 0.8894566893577576,
40
+ "eval_runtime": 37.6552,
41
+ "eval_samples_per_second": 59.753,
42
+ "eval_steps_per_second": 7.489,
43
+ "step": 846
44
+ },
45
+ {
46
+ "epoch": 3.546099290780142,
47
+ "grad_norm": 19.25679588317871,
48
+ "learning_rate": 3.8466984971609285e-06,
49
+ "loss": 0.8051,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_f1": 0.6285243252934658,
55
+ "eval_loss": 0.8603602647781372,
56
+ "eval_runtime": 37.769,
57
+ "eval_samples_per_second": 59.573,
58
+ "eval_steps_per_second": 7.466,
59
+ "step": 1128
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_f1": 0.6176495736574765,
64
+ "eval_loss": 0.893376886844635,
65
+ "eval_runtime": 38.2772,
66
+ "eval_samples_per_second": 58.782,
67
+ "eval_steps_per_second": 7.367,
68
+ "step": 1410
69
+ }
70
+ ],
71
+ "logging_steps": 500,
72
+ "max_steps": 1410,
73
+ "num_input_tokens_seen": 0,
74
+ "num_train_epochs": 5,
75
+ "save_steps": 500,
76
+ "stateful_callbacks": {
77
+ "TrainerControl": {
78
+ "args": {
79
+ "should_epoch_stop": false,
80
+ "should_evaluate": false,
81
+ "should_log": false,
82
+ "should_save": true,
83
+ "should_training_stop": true
84
+ },
85
+ "attributes": {}
86
+ }
87
+ },
88
+ "total_flos": 8400122116761600.0,
89
+ "train_batch_size": 32,
90
+ "trial_name": null,
91
+ "trial_params": {
92
+ "learning_rate": 1.3228889953650998e-05,
93
+ "num_train_epochs": 5,
94
+ "per_device_train_batch_size": 32,
95
+ "weight_decay": 0.0004860339799795757
96
+ }
97
+ }
run-1/checkpoint-1410/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6c0e80228b83305d52c2ecaa5e9378ae485930e09ca765409ad7f4e4465fdb
3
+ size 5368
run-1/checkpoint-1410/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-563/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 1,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.47.0",
41
+ "type_vocab_size": 1,
42
+ "use_cache": true,
43
+ "vocab_size": 50265
44
+ }
run-2/checkpoint-563/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-563/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a179bdc6645e371c1c6c54d65c472ae37780358419b2d43cda9745925698e3d
3
+ size 498625128
run-2/checkpoint-563/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa642b23f35be33602ecc98cb1a714f93d29959d58acb3cc143e603100637fc
3
+ size 997370106
run-2/checkpoint-563/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49348fa43bd53147898b45d0b95d766e80d34cb0478edbfadb78cb95f3ed5edb
3
+ size 14244
run-2/checkpoint-563/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f7ca0ceb804c0de096d04e5c1434196e22ebc3fdf0d6a2ed9bc4bd0d427cc8
3
+ size 1064
run-2/checkpoint-563/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
+ }
run-2/checkpoint-563/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-563/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
+ }
run-2/checkpoint-563/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5011171601790574,
3
+ "best_model_checkpoint": "students_scores_model/run-2/checkpoint-563",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 563,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.8880994671403197,
13
+ "grad_norm": 7.292171478271484,
14
+ "learning_rate": 3.526354733861817e-05,
15
+ "loss": 1.0895,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_f1": 0.5011171601790574,
21
+ "eval_loss": 1.1365867853164673,
22
+ "eval_runtime": 37.7018,
23
+ "eval_samples_per_second": 59.679,
24
+ "eval_steps_per_second": 7.48,
25
+ "step": 563
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 2815,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 5,
32
+ "save_steps": 500,
33
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 2104964038656000.0,
46
+ "train_batch_size": 16,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "learning_rate": 4.2879864258406114e-05,
50
+ "num_train_epochs": 5,
51
+ "per_device_train_batch_size": 16,
52
+ "weight_decay": 0.060543241151812754
53
+ }
54
+ }
run-2/checkpoint-563/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07844380fb9421e367e0fe8c8cfeb6356de89708d1d3002c9565a87a48709fa1
3
+ size 5368
run-2/checkpoint-563/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733666403.3b937233628b.23.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6c060003c03fac1eda412c178b7f9917436d7fd9bc32116fede3618fdcf3bc8
3
- size 7045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33acc9e2be0e64aacefb07d8bdf6031ea93dd5b3f208f7dd2fa556839c28dca
3
+ size 7716
runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733669115.3b937233628b.23.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:707864b352d5b133aea76ad75c4aa3b350a52d021e17b73fbc0af06e20eadade
3
+ size 5882
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b6c0e80228b83305d52c2ecaa5e9378ae485930e09ca765409ad7f4e4465fdb
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07844380fb9421e367e0fe8c8cfeb6356de89708d1d3002c9565a87a48709fa1
3
  size 5368