Hugging Face's logo

anamelchor
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
anamelchor commited on
Commit
511305a
·
verified ·
1 Parent(s): 5d48eff

Training in progress, epoch 1

Browse files
Files changed (42) hide show
  1. model.safetensors +1 -1
  2. run-7/checkpoint-28/config.json +25 -0
  3. run-7/checkpoint-28/model.safetensors +3 -0
  4. run-7/checkpoint-28/optimizer.pt +3 -0
  5. run-7/checkpoint-28/rng_state.pth +3 -0
  6. run-7/checkpoint-28/scheduler.pt +3 -0
  7. run-7/checkpoint-28/special_tokens_map.json +7 -0
  8. run-7/checkpoint-28/tokenizer.json +0 -0
  9. run-7/checkpoint-28/tokenizer_config.json +55 -0
  10. run-7/checkpoint-28/trainer_state.json +44 -0
  11. run-7/checkpoint-28/training_args.bin +3 -0
  12. run-7/checkpoint-28/vocab.txt +0 -0
  13. run-7/checkpoint-42/config.json +25 -0
  14. run-7/checkpoint-42/model.safetensors +3 -0
  15. run-7/checkpoint-42/optimizer.pt +3 -0
  16. run-7/checkpoint-42/rng_state.pth +3 -0
  17. run-7/checkpoint-42/scheduler.pt +3 -0
  18. run-7/checkpoint-42/special_tokens_map.json +7 -0
  19. run-7/checkpoint-42/tokenizer.json +0 -0
  20. run-7/checkpoint-42/tokenizer_config.json +55 -0
  21. run-7/checkpoint-42/trainer_state.json +53 -0
  22. run-7/checkpoint-42/training_args.bin +3 -0
  23. run-7/checkpoint-42/vocab.txt +0 -0
  24. run-7/checkpoint-56/config.json +25 -0
  25. run-7/checkpoint-56/model.safetensors +3 -0
  26. run-7/checkpoint-56/optimizer.pt +3 -0
  27. run-7/checkpoint-56/rng_state.pth +3 -0
  28. run-7/checkpoint-56/scheduler.pt +3 -0
  29. run-7/checkpoint-56/special_tokens_map.json +7 -0
  30. run-7/checkpoint-56/tokenizer.json +0 -0
  31. run-7/checkpoint-56/tokenizer_config.json +55 -0
  32. run-7/checkpoint-56/trainer_state.json +62 -0
  33. run-7/checkpoint-56/training_args.bin +3 -0
  34. run-7/checkpoint-56/vocab.txt +0 -0
  35. run-8/checkpoint-14/model.safetensors +1 -1
  36. run-8/checkpoint-14/optimizer.pt +1 -1
  37. run-8/checkpoint-14/rng_state.pth +1 -1
  38. run-8/checkpoint-14/scheduler.pt +1 -1
  39. run-8/checkpoint-14/trainer_state.json +9 -9
  40. run-8/checkpoint-14/training_args.bin +1 -1
  41. runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709145267.5620ed9b2fff.209.10 +3 -0
  42. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee4376a86f672a747e935bc5434d5af0dc7dd70266d7fc82bc2e3b6b08d6117f
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df076509a19e5ddf0b3041acf1185a28a896d931638464aedb3591f0d48539f
3
  size 267832560
run-7/checkpoint-28/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3815606f3e3a5efdd0790f45d98fe2c2471f8bcef6812aa061226c7b408c46fa
3
+ size 267832560
run-7/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d236545d4767e12c5af16f52146ed0c19651a1db52b0f7c553fbd7372d43ba
3
+ size 535727290
run-7/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c232c4796b2d264b7aad27a5607016ef3f38da67930315a629ac0bcfd95ce6
3
+ size 14244
run-7/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0457172d24742c574b96d02422466196d88106ddc3187b55728fd23b98ffa4f7
3
+ size 1064
run-7/checkpoint-28/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-7/checkpoint-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-28/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-7/checkpoint-28/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-14",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
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_loss": 0.6431679129600525,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7348,
16
+ "eval_samples_per_second": 1419.395,
17
+ "eval_steps_per_second": 89.818,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6220545172691345,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7873,
25
+ "eval_samples_per_second": 1324.778,
26
+ "eval_steps_per_second": 83.831,
27
+ "step": 28
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 56,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 4.60411924649496e-06,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 1
43
+ }
44
+ }
run-7/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d52f65fbe73570d4e65781de9eeeae78b2e1bae82a19760059f92848fdfae9
3
+ size 4984
run-7/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-42/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4bc2b151df18c318f487e7fe57266d013f72fc82f316d41bbca42cdc544b34
3
+ size 267832560
run-7/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5689137dbb4a72f4dcabb064a855d1ea57fd408775ac7ecf9e473e004702a27c
3
+ size 535727290
run-7/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c64d3dd20fba39cc8ca1cf59259a3f8ee923e301b78fb95cc511e6b9a30fb8
3
+ size 14244
run-7/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:050c3f9e0d13e220c4a05b8eca932a4ab90f9e0dedf824dc351fef1379c74739
3
+ size 1064
run-7/checkpoint-42/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-7/checkpoint-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-42/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-7/checkpoint-42/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-14",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 42,
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_loss": 0.6431679129600525,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7348,
16
+ "eval_samples_per_second": 1419.395,
17
+ "eval_steps_per_second": 89.818,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6220545172691345,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7873,
25
+ "eval_samples_per_second": 1324.778,
26
+ "eval_steps_per_second": 83.831,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6155515313148499,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8134,
34
+ "eval_samples_per_second": 1282.287,
35
+ "eval_steps_per_second": 81.142,
36
+ "step": 42
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 56,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 4.60411924649496e-06,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 1
52
+ }
53
+ }
run-7/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d52f65fbe73570d4e65781de9eeeae78b2e1bae82a19760059f92848fdfae9
3
+ size 4984
run-7/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-56/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75cb553d2fec5e424b5febe3fc776ccad70dd0e2e1d766c0c91627e4cb68cb05
3
+ size 267832560
run-7/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36271f74d74df8f7e1ea032aa11d494eb43b02957cea03dabda23c3beaae1511
3
+ size 535727290
run-7/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95100a9ec53d47587f2d79046665c2f62bcd5a290639415fa05868e8cb8fad8c
3
+ size 14244
run-7/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b83e9c0b618737276cb05a0e7d6096f0908837c92ca3ec4978a7060ec245438
3
+ size 1064
run-7/checkpoint-56/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-7/checkpoint-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-56/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-7/checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-14",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 56,
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_loss": 0.6431679129600525,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7348,
16
+ "eval_samples_per_second": 1419.395,
17
+ "eval_steps_per_second": 89.818,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6220545172691345,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7873,
25
+ "eval_samples_per_second": 1324.778,
26
+ "eval_steps_per_second": 83.831,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6155515313148499,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8134,
34
+ "eval_samples_per_second": 1282.287,
35
+ "eval_steps_per_second": 81.142,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6144578456878662,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 1.222,
43
+ "eval_samples_per_second": 853.527,
44
+ "eval_steps_per_second": 54.01,
45
+ "step": 56
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 56,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 4.60411924649496e-06,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 1
61
+ }
62
+ }
run-7/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d52f65fbe73570d4e65781de9eeeae78b2e1bae82a19760059f92848fdfae9
3
+ size 4984
run-7/checkpoint-56/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-14/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58c4515a6dc258fe5f4d73b3164f733fe2ed7b1024b07e99d59b0b0cae982ec0
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df076509a19e5ddf0b3041acf1185a28a896d931638464aedb3591f0d48539f
3
  size 267832560
run-8/checkpoint-14/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edf545b2f1a2e83d8d578989f951cb74dc81e3d2a00518d3c7d21a5aa370e7c7
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01dbcb416f107c9bff4e1af606c926dc12f0086aa6b0f875e89f1f1ac31923b
3
  size 535727290
run-8/checkpoint-14/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54386060634095ab08b75b0788eb06bf38e5a94673bec3b776c91c74834da60a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcef7a0a658f5ecd3896e803f963363da26a7ab0ba667fd60ff348d24ce5eb0f
3
  size 14244
run-8/checkpoint-14/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:500c2fdfacd57415c895c82ae1c96f9e510b20ec1433202c328278e18e793458
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5c3aecabe90e33b50c271f07e2f49512f716f7896cb62510cd687183994ab4
3
  size 1064
run-8/checkpoint-14/trainer_state.json CHANGED
@@ -10,26 +10,26 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.617560625076294,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.8519,
16
- "eval_samples_per_second": 1224.309,
17
- "eval_steps_per_second": 77.473,
18
  "step": 14
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 14,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 1,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 64,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 2.5943621120102917e-05,
31
- "num_train_epochs": 1,
32
  "per_device_train_batch_size": 64,
33
- "seed": 5
34
  }
35
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6093547344207764,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7473,
16
+ "eval_samples_per_second": 1395.68,
17
+ "eval_steps_per_second": 88.317,
18
  "step": 14
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 56,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 64,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "learning_rate": 2.8212860094421134e-05,
31
+ "num_train_epochs": 4,
32
  "per_device_train_batch_size": 64,
33
+ "seed": 35
34
  }
35
  }
run-8/checkpoint-14/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbf4ff2827bbc39e224d857630f81897bdfaeeb74595f1c8fb7a831d8d6fc3c2
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74b2c2a15777a9330d9199a2d503860f656f04ef76dcd4b374673cd027f7a10
3
  size 4984
runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709145267.5620ed9b2fff.209.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269fec92e6297b031041f203ffb8ab6ce92bcb6f3b0a78be2696ca91fc5c34ee
3
+ size 6207
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7d52f65fbe73570d4e65781de9eeeae78b2e1bae82a19760059f92848fdfae9
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74b2c2a15777a9330d9199a2d503860f656f04ef76dcd4b374673cd027f7a10
3
  size 4984