Hugging Face's logo

berkayaltntas
/
bert-base-uncased-finetuned-rte-run_3

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
berkayaltntas commited on
Commit
424ef78
·
verified ·
1 Parent(s): 2cc7f0b

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-10/checkpoint-156/config.json +26 -0
  3. run-10/checkpoint-156/model.safetensors +3 -0
  4. run-10/checkpoint-156/optimizer.pt +3 -0
  5. run-10/checkpoint-156/rng_state.pth +3 -0
  6. run-10/checkpoint-156/scheduler.pt +3 -0
  7. run-10/checkpoint-156/special_tokens_map.json +7 -0
  8. run-10/checkpoint-156/tokenizer.json +0 -0
  9. run-10/checkpoint-156/tokenizer_config.json +56 -0
  10. run-10/checkpoint-156/trainer_state.json +49 -0
  11. run-10/checkpoint-156/training_args.bin +3 -0
  12. run-10/checkpoint-156/vocab.txt +0 -0
  13. run-9/checkpoint-156/config.json +26 -0
  14. run-9/checkpoint-156/model.safetensors +3 -0
  15. run-9/checkpoint-156/optimizer.pt +3 -0
  16. run-9/checkpoint-156/rng_state.pth +3 -0
  17. run-9/checkpoint-156/scheduler.pt +3 -0
  18. run-9/checkpoint-156/special_tokens_map.json +7 -0
  19. run-9/checkpoint-156/tokenizer.json +0 -0
  20. run-9/checkpoint-156/tokenizer_config.json +56 -0
  21. run-9/checkpoint-156/trainer_state.json +49 -0
  22. run-9/checkpoint-156/training_args.bin +3 -0
  23. run-9/checkpoint-156/vocab.txt +0 -0
  24. run-9/checkpoint-312/config.json +26 -0
  25. run-9/checkpoint-312/model.safetensors +3 -0
  26. run-9/checkpoint-312/optimizer.pt +3 -0
  27. run-9/checkpoint-312/rng_state.pth +3 -0
  28. run-9/checkpoint-312/scheduler.pt +3 -0
  29. run-9/checkpoint-312/special_tokens_map.json +7 -0
  30. run-9/checkpoint-312/tokenizer.json +0 -0
  31. run-9/checkpoint-312/tokenizer_config.json +56 -0
  32. run-9/checkpoint-312/trainer_state.json +58 -0
  33. run-9/checkpoint-312/training_args.bin +3 -0
  34. run-9/checkpoint-312/vocab.txt +0 -0
  35. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744024489.d0bdfe9fd409.3962.11 +3 -0
  36. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744024644.d0bdfe9fd409.3962.12 +3 -0
  37. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c33de66df47b89a59c9acc83dac020e6af8316fa90e5e9b533ae16b375f62ad0
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c39f3acefc9f3fc13aa3fb720fa818ac2691837d7509630b9e5db6ebfad352
3
  size 437958648
run-10/checkpoint-156/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-10/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c39f3acefc9f3fc13aa3fb720fa818ac2691837d7509630b9e5db6ebfad352
3
+ size 437958648
run-10/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c612b850fd6577f094c5b417ccca9923c35eae64af75e9237e3506676770c2e5
3
+ size 876038394
run-10/checkpoint-156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0bd0ecbea6accdf7a51551feef7c19310fde6287eee32a3f2a6d63776d2405c
3
+ size 14244
run-10/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839cec0815a8c76e032eb4daba33315daf0356081d1ba586931e202047391600
3
+ size 1064
run-10/checkpoint-156/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-10/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-156/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-10/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.6606498194945848,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-10/checkpoint-156",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 156,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.6606498194945848,
15
+ "eval_loss": 0.6351022124290466,
16
+ "eval_runtime": 0.6544,
17
+ "eval_samples_per_second": 423.274,
18
+ "eval_steps_per_second": 7.64,
19
+ "step": 156
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 468,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 3,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 16,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "classifier_dropout": 0.19880893323294635,
44
+ "learning_rate": 4.813710106555415e-05,
45
+ "max_length": 256,
46
+ "num_train_epochs": 3,
47
+ "per_device_train_batch_size": 16
48
+ }
49
+ }
run-10/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb6ae6e9d06392983d91c812e9818db80ae9e396cf6d7bedcffaffaf9fc0381
3
+ size 5432
run-10/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-156/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-9/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50031850748551bdbaac37cbb897aa5ecc4c644583f4d0015b04804619a9864
3
+ size 437958648
run-9/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29c08c8c8bbb1a5c02e58dc366a612794bb73e67123573e00ae3e29bdd8ae79
3
+ size 876038394
run-9/checkpoint-156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0bd0ecbea6accdf7a51551feef7c19310fde6287eee32a3f2a6d63776d2405c
3
+ size 14244
run-9/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf073e2ce0e165a8a46c1b29bfb744279d37e2acfb812346fc867da2341f271
3
+ size 1064
run-9/checkpoint-156/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-9/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-156/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-9/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.5740072202166066,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-9/checkpoint-156",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 156,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.5740072202166066,
15
+ "eval_loss": 0.6890994906425476,
16
+ "eval_runtime": 0.654,
17
+ "eval_samples_per_second": 423.573,
18
+ "eval_steps_per_second": 7.646,
19
+ "step": 156
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 312,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 2,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 16,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "classifier_dropout": 0.33282255094216256,
44
+ "learning_rate": 6.3406321145340925e-06,
45
+ "max_length": 512,
46
+ "num_train_epochs": 2,
47
+ "per_device_train_batch_size": 16
48
+ }
49
+ }
run-9/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44af718b2dbe3f140c090dd1b60a0986318751448b120eba30c61259e63deb13
3
+ size 5432
run-9/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-312/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-9/checkpoint-312/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3864cb261ea187692dc90d82d4a91ffdd36904002db1288a9d4e0ca3fb544b
3
+ size 437958648
run-9/checkpoint-312/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d424a931149069b5ea396d1d2f2d48389191f4417f73b96ff0daa537beaf011
3
+ size 876038394
run-9/checkpoint-312/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a69fbc11d3f7bdd194c4f6febc68ff9beadd46e45ba247e1b80b7871f6f7be0
3
+ size 14244
run-9/checkpoint-312/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96365ed9d3f5065042a83b79308fac398d228aeef4d99b34d74e523d1641876b
3
+ size 1064
run-9/checkpoint-312/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-9/checkpoint-312/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-312/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-9/checkpoint-312/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 312,
3
+ "best_metric": 0.5776173285198556,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-9/checkpoint-312",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 312,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.5740072202166066,
15
+ "eval_loss": 0.6890994906425476,
16
+ "eval_runtime": 0.654,
17
+ "eval_samples_per_second": 423.573,
18
+ "eval_steps_per_second": 7.646,
19
+ "step": 156
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5776173285198556,
24
+ "eval_loss": 0.6779555678367615,
25
+ "eval_runtime": 0.6562,
26
+ "eval_samples_per_second": 422.133,
27
+ "eval_steps_per_second": 7.62,
28
+ "step": 312
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 312,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 2,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": true
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 16,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "classifier_dropout": 0.33282255094216256,
53
+ "learning_rate": 6.3406321145340925e-06,
54
+ "max_length": 512,
55
+ "num_train_epochs": 2,
56
+ "per_device_train_batch_size": 16
57
+ }
58
+ }
run-9/checkpoint-312/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44af718b2dbe3f140c090dd1b60a0986318751448b120eba30c61259e63deb13
3
+ size 5432
run-9/checkpoint-312/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744024489.d0bdfe9fd409.3962.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf564e14c70568707f18619cd8646453e7cb3aa61a6ff6d7b09cb47f8841647
3
+ size 6102
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744024644.d0bdfe9fd409.3962.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b83e9c1b0072906f81aa440c215a9df5dad4ae7c29987589a6aee173ab2379a
3
+ size 6424
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531460a5e6a46a6be5016d26066192a4d9b5aec325fca2f3ead68fd2e84685b3
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb6ae6e9d06392983d91c812e9818db80ae9e396cf6d7bedcffaffaf9fc0381
3
  size 5432