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
15e8580
·
verified ·
1 Parent(s): 022e937

Training in progress, epoch 1

Browse files
Files changed (28) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-846/config.json +44 -0
  3. run-2/checkpoint-846/merges.txt +0 -0
  4. run-2/checkpoint-846/model.safetensors +3 -0
  5. run-2/checkpoint-846/optimizer.pt +3 -0
  6. run-2/checkpoint-846/rng_state.pth +3 -0
  7. run-2/checkpoint-846/scheduler.pt +3 -0
  8. run-2/checkpoint-846/special_tokens_map.json +15 -0
  9. run-2/checkpoint-846/tokenizer.json +0 -0
  10. run-2/checkpoint-846/tokenizer_config.json +58 -0
  11. run-2/checkpoint-846/trainer_state.json +72 -0
  12. run-2/checkpoint-846/training_args.bin +3 -0
  13. run-2/checkpoint-846/vocab.json +0 -0
  14. run-3/checkpoint-563/config.json +44 -0
  15. run-3/checkpoint-563/merges.txt +0 -0
  16. run-3/checkpoint-563/model.safetensors +3 -0
  17. run-3/checkpoint-563/optimizer.pt +3 -0
  18. run-3/checkpoint-563/rng_state.pth +3 -0
  19. run-3/checkpoint-563/scheduler.pt +3 -0
  20. run-3/checkpoint-563/special_tokens_map.json +15 -0
  21. run-3/checkpoint-563/tokenizer.json +0 -0
  22. run-3/checkpoint-563/tokenizer_config.json +58 -0
  23. run-3/checkpoint-563/trainer_state.json +54 -0
  24. run-3/checkpoint-563/training_args.bin +3 -0
  25. run-3/checkpoint-563/vocab.json +0 -0
  26. runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733697267.6ff5f1d99a72.23.2 +2 -2
  27. runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733698909.6ff5f1d99a72.23.3 +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 sha256:4e8042e8a66f779111574edb23e8d5c38834f4cacdb9af33887881eabf06c385
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b706b818816f8ff5d97692664f73ab0707eb044b0fc20aa8a2f76241e8abbe
3
  size 498625128
run-2/checkpoint-846/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-846/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-846/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66a0e06b8283907d6cc7a4ac7b8d8238ef3c1acffdf648d6c57d9bfeb25b74a4
3
+ size 498625128
run-2/checkpoint-846/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aef18937120c0a18bf746a08e24c9ac71cce0640363e88007e5e70efe703857
3
+ size 997370106
run-2/checkpoint-846/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:567014f442dfce4d2253735634d216240341f8f6592d2e435770e4b006f66ee2
3
+ size 14244
run-2/checkpoint-846/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:babceaf62efd145829b7eb2052bdfc20496a5ca5fc08ac18f9348e67b7a291a8
3
+ size 1064
run-2/checkpoint-846/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-846/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-846/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-846/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6115783238201965,
3
+ "best_model_checkpoint": "students_scores_model/run-2/checkpoint-846",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 846,
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": 0.5280922046056804,
14
+ "eval_loss": 1.0346653461456299,
15
+ "eval_runtime": 37.6542,
16
+ "eval_samples_per_second": 59.754,
17
+ "eval_steps_per_second": 7.489,
18
+ "step": 282
19
+ },
20
+ {
21
+ "epoch": 1.773049645390071,
22
+ "grad_norm": 15.857311248779297,
23
+ "learning_rate": 4.500003283675112e-06,
24
+ "loss": 1.0255,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_f1": 0.597013961740708,
30
+ "eval_loss": 0.9119309782981873,
31
+ "eval_runtime": 37.6531,
32
+ "eval_samples_per_second": 59.756,
33
+ "eval_steps_per_second": 7.489,
34
+ "step": 564
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_f1": 0.6115783238201965,
39
+ "eval_loss": 0.8967968225479126,
40
+ "eval_runtime": 38.7112,
41
+ "eval_samples_per_second": 58.123,
42
+ "eval_steps_per_second": 7.285,
43
+ "step": 846
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 846,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 3,
50
+ "save_steps": 500,
51
+ "stateful_callbacks": {
52
+ "TrainerControl": {
53
+ "args": {
54
+ "should_epoch_stop": false,
55
+ "should_evaluate": false,
56
+ "should_log": false,
57
+ "should_save": true,
58
+ "should_training_stop": true
59
+ },
60
+ "attributes": {}
61
+ }
62
+ },
63
+ "total_flos": 4203350064691200.0,
64
+ "train_batch_size": 32,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 1.1002898202280765e-05,
68
+ "num_train_epochs": 3,
69
+ "per_device_train_batch_size": 32,
70
+ "weight_decay": 0.008293142825111385
71
+ }
72
+ }
run-2/checkpoint-846/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92eed261d071d88405c0cc7cdc0b8eceb2628d134f07932409e8529a92610828
3
+ size 5368
run-2/checkpoint-846/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-563/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-563/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b706b818816f8ff5d97692664f73ab0707eb044b0fc20aa8a2f76241e8abbe
3
+ size 498625128
run-3/checkpoint-563/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07e5bb47aaed372e309012e00d5140081e1df2736be66c43058c0911863c40b
3
+ size 997370106
run-3/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-3/checkpoint-563/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90229d86d250af3471a4ec6a1a5c45f5c6fd9b2fcb6a28f65c95671640d9b9d5
3
+ size 1064
run-3/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-3/checkpoint-563/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-563/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5742027809107039,
3
+ "best_model_checkpoint": "students_scores_model/run-3/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": 21.45689582824707,
14
+ "learning_rate": 9.694484049714234e-06,
15
+ "loss": 1.0844,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_f1": 0.5742027809107039,
21
+ "eval_loss": 0.9514040946960449,
22
+ "eval_runtime": 37.3512,
23
+ "eval_samples_per_second": 60.239,
24
+ "eval_steps_per_second": 7.55,
25
+ "step": 563
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 1689,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 3,
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": 1.3771222506280354e-05,
50
+ "num_train_epochs": 3,
51
+ "per_device_train_batch_size": 16,
52
+ "weight_decay": 0.0002914894301194684
53
+ }
54
+ }
run-3/checkpoint-563/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cd9f34492133ce5e58fc156e903c1cff1ce7d1d888c589c0adfe36c39998cb
3
+ size 5368
run-3/checkpoint-563/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733697267.6ff5f1d99a72.23.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8652c102ac90b4e7dea4324a91e066e47960d14c67685864f781c9ec2ee6315b
3
- size 6199
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47cd52d1c6a52c41ab41bf200009d1c40c0714fbd0471bdaed7042259fe138a
3
+ size 6870
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733698909.6ff5f1d99a72.23.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24787ecd53a27371e006b61f9ec37256788bd579c54952b6d97a2b9b1bc145c
3
+ size 5883
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92eed261d071d88405c0cc7cdc0b8eceb2628d134f07932409e8529a92610828
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cd9f34492133ce5e58fc156e903c1cff1ce7d1d888c589c0adfe36c39998cb
3
  size 5368