anamelchor commited on
Commit
78a2dd9
1 Parent(s): 8668d22

Training in progress, epoch 1

Browse files
Files changed (49) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-42/config.json +27 -0
  3. run-1/checkpoint-42/model.safetensors +3 -0
  4. run-1/checkpoint-42/optimizer.pt +3 -0
  5. run-1/checkpoint-42/rng_state.pth +3 -0
  6. run-1/checkpoint-42/scheduler.pt +3 -0
  7. run-1/checkpoint-42/special_tokens_map.json +7 -0
  8. run-1/checkpoint-42/tokenizer.json +0 -0
  9. run-1/checkpoint-42/tokenizer_config.json +55 -0
  10. run-1/checkpoint-42/trainer_state.json +53 -0
  11. run-1/checkpoint-42/training_args.bin +3 -0
  12. run-1/checkpoint-42/vocab.txt +0 -0
  13. run-1/checkpoint-56/config.json +27 -0
  14. run-1/checkpoint-56/model.safetensors +3 -0
  15. run-1/checkpoint-56/optimizer.pt +3 -0
  16. run-1/checkpoint-56/rng_state.pth +3 -0
  17. run-1/checkpoint-56/scheduler.pt +3 -0
  18. run-1/checkpoint-56/special_tokens_map.json +7 -0
  19. run-1/checkpoint-56/tokenizer.json +0 -0
  20. run-1/checkpoint-56/tokenizer_config.json +55 -0
  21. run-1/checkpoint-56/trainer_state.json +62 -0
  22. run-1/checkpoint-56/training_args.bin +3 -0
  23. run-1/checkpoint-56/vocab.txt +0 -0
  24. run-2/checkpoint-108/model.safetensors +1 -1
  25. run-2/checkpoint-108/optimizer.pt +1 -1
  26. run-2/checkpoint-108/rng_state.pth +2 -2
  27. run-2/checkpoint-108/scheduler.pt +1 -1
  28. run-2/checkpoint-108/trainer_state.json +17 -17
  29. run-2/checkpoint-108/training_args.bin +1 -1
  30. run-2/checkpoint-162/model.safetensors +1 -1
  31. run-2/checkpoint-162/optimizer.pt +1 -1
  32. run-2/checkpoint-162/rng_state.pth +2 -2
  33. run-2/checkpoint-162/scheduler.pt +1 -1
  34. run-2/checkpoint-162/trainer_state.json +22 -22
  35. run-2/checkpoint-162/training_args.bin +1 -1
  36. run-2/checkpoint-216/model.safetensors +1 -1
  37. run-2/checkpoint-216/optimizer.pt +1 -1
  38. run-2/checkpoint-216/rng_state.pth +2 -2
  39. run-2/checkpoint-216/scheduler.pt +1 -1
  40. run-2/checkpoint-216/trainer_state.json +27 -27
  41. run-2/checkpoint-216/training_args.bin +1 -1
  42. run-2/checkpoint-54/model.safetensors +1 -1
  43. run-2/checkpoint-54/optimizer.pt +1 -1
  44. run-2/checkpoint-54/rng_state.pth +2 -2
  45. run-2/checkpoint-54/scheduler.pt +1 -1
  46. run-2/checkpoint-54/trainer_state.json +11 -11
  47. run-2/checkpoint-54/training_args.bin +1 -1
  48. runs/Mar05_08-21-06_22d65867544c/events.out.tfevents.1709628755.22d65867544c.687.11 +3 -0
  49. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7efe7122d8d10596cdafabb1d47bef92c1ccf3c154c24282338bb6daf4277d41
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5532eacb19539cc92d43257b0ea0db854bae37c452c8278162825aa2bb5f0a
3
  size 437958648
run-1/checkpoint-42/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-1/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b60e9fd79f41a74858f590df6830188625946636d6827c5c33640359d10f0836
3
+ size 437958648
run-1/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b757370b8a59423782560047b4e1460fb9b654f1520e818421fdb7d7f014c087
3
+ size 876038394
run-1/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a856c7294543b8ba9066da1bed1676115d5c4db8d63a9b74ff211403ba9e30
3
+ size 14244
run-1/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b196233250426a497a855379f035a34b745fa235235983b0ee7e5e7a5744660e
3
+ size 1064
run-1/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-1/checkpoint-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-42/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0463559874942472,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-1/checkpoint-28",
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": 0.6474732160568237,
14
+ "eval_matthews_correlation": -0.007887379670285008,
15
+ "eval_runtime": 1.3062,
16
+ "eval_samples_per_second": 798.507,
17
+ "eval_steps_per_second": 50.529,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6341453194618225,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 1.766,
25
+ "eval_samples_per_second": 590.591,
26
+ "eval_steps_per_second": 37.372,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6294084787368774,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 2.4709,
34
+ "eval_samples_per_second": 422.122,
35
+ "eval_steps_per_second": 26.711,
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": 1.8171245560200659e-06,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 9
52
+ }
53
+ }
run-1/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1079efb096bc038fdcb92f41e7f212806b5c803d7f37e767ae5856e16aa0bd
3
+ size 4920
run-1/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-56/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-1/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0784d46ea551f96840a20857fdaca8b89d986eaaf64d8192ac79fdb1663bdac8
3
+ size 437958648
run-1/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd118ef23dfdf0f05c6181aed6531ccfe41aa0d61af91e3dfaf975ebcdda3ffb
3
+ size 876038394
run-1/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd32300895a8e2bd5f0ce818c76198c7e4f814d38ba31eab899de596a8ccb40f
3
+ size 14244
run-1/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23352877d34352c960a86806ce9fbe6ac8606201e162fa76f6abb637ac8a1b30
3
+ size 1064
run-1/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-1/checkpoint-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0463559874942472,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-1/checkpoint-28",
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": 0.6474732160568237,
14
+ "eval_matthews_correlation": -0.007887379670285008,
15
+ "eval_runtime": 1.3062,
16
+ "eval_samples_per_second": 798.507,
17
+ "eval_steps_per_second": 50.529,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6341453194618225,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 1.766,
25
+ "eval_samples_per_second": 590.591,
26
+ "eval_steps_per_second": 37.372,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6294084787368774,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 2.4709,
34
+ "eval_samples_per_second": 422.122,
35
+ "eval_steps_per_second": 26.711,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6282962560653687,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 2.0396,
43
+ "eval_samples_per_second": 511.374,
44
+ "eval_steps_per_second": 32.359,
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": 1.8171245560200659e-06,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 9
61
+ }
62
+ }
run-1/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1079efb096bc038fdcb92f41e7f212806b5c803d7f37e767ae5856e16aa0bd
3
+ size 4920
run-1/checkpoint-56/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-108/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c36df94b40c56fcddc85fdb5d52b6637cfc261a095f0785345dbf0088e1e1a03
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb071d8b215954e266ab2c72b3f9176a0af065c0c3a60c553a9452475a18b8e
3
  size 437958648
run-2/checkpoint-108/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bb8c4cdb72480e1110ecabf43dc7b3337be0a67522f5a8f0351a4ecf70a9dd5
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574195f30b51d6e9b79009171494be2f4b78031570282a4f221706b49be5c212
3
  size 876038394
run-2/checkpoint-108/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87cdd35c87e07c4aeb29b0880036742129084a96ee9fb08bd7175a05681326fe
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9390756cd0ccbb61d29a3cdf4de2e5bd0406795934e6b32bd1a95aa46b3b9e12
3
+ size 14308
run-2/checkpoint-108/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9886f252a006785337b73843fffa1abfbf23b4e444a322b78bd4ae9d7a673e13
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cfe37a938ff63c24005b5bf71f7705b389b43b895550b6de5522929744a0e84
3
  size 1064
run-2/checkpoint-108/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.0463559874942472,
3
- "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-108",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 108,
@@ -10,35 +10,35 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6150018572807312,
14
- "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 1.3372,
16
- "eval_samples_per_second": 779.988,
17
- "eval_steps_per_second": 49.357,
18
  "step": 54
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_loss": 0.6089003086090088,
23
- "eval_matthews_correlation": 0.0463559874942472,
24
- "eval_runtime": 1.4244,
25
- "eval_samples_per_second": 732.255,
26
- "eval_steps_per_second": 46.336,
27
  "step": 108
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 216,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 4,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 16,
37
  "trial_name": null,
38
  "trial_params": {
39
- "learning_rate": 2.7854323243021316e-06,
40
- "num_train_epochs": 4,
41
  "per_device_train_batch_size": 16,
42
- "seed": 5
43
  }
44
  }
 
1
  {
2
+ "best_metric": 0.06479227964096512,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-54",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 108,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6800838708877563,
14
+ "eval_matthews_correlation": 0.06479227964096512,
15
+ "eval_runtime": 1.3179,
16
+ "eval_samples_per_second": 791.421,
17
+ "eval_steps_per_second": 50.08,
18
  "step": 54
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_loss": 0.6333577036857605,
23
+ "eval_matthews_correlation": 0.06354272869611655,
24
+ "eval_runtime": 1.4106,
25
+ "eval_samples_per_second": 739.39,
26
+ "eval_steps_per_second": 46.788,
27
  "step": 108
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 270,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 16,
37
  "trial_name": null,
38
  "trial_params": {
39
+ "learning_rate": 1.420124179212326e-06,
40
+ "num_train_epochs": 5,
41
  "per_device_train_batch_size": 16,
42
+ "seed": 26
43
  }
44
  }
run-2/checkpoint-108/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42783ab338ba78bc9a261fef02bd6d857622f28fcbf5b914d81d574b8f77a67
3
  size 4920
run-2/checkpoint-162/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9b54798c78cf39f05cf50fa788dd021b9ad7add92d0f06c58ba8627e18e74e9
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f527f4be6bb431b494bff778817e946d59530dba60cac9c039dc34cac52be71d
3
  size 437958648
run-2/checkpoint-162/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b6f5dbccc3359308165d8c3b12ffb1342d817b88ba6fab7f876fcf24d758bd1
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930faf1c2d8cc6590edfa3135569270143b5b610ad83f61c22af1f730270efc6
3
  size 876038394
run-2/checkpoint-162/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:483eee96cb3e2c0dacabf009de1e51e32d8a86a481ff239e4d0787086a07e443
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:756bf90f9ef88927b7968a25d2b1e55769006361d21a16660508cf47499ebaf1
3
+ size 14308
run-2/checkpoint-162/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:effdba7a30169524a7267e94b80f18cac6bf5ea76fe466745108823a5678d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21ebb2491306a3cffc780fa623132d0fcbf9bd3d6a002f1afac2acdc3c7bf84
3
  size 1064
run-2/checkpoint-162/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.0463559874942472,
3
- "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-108",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
  "global_step": 162,
@@ -10,44 +10,44 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6150018572807312,
14
- "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 1.3372,
16
- "eval_samples_per_second": 779.988,
17
- "eval_steps_per_second": 49.357,
18
  "step": 54
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_loss": 0.6089003086090088,
23
- "eval_matthews_correlation": 0.0463559874942472,
24
- "eval_runtime": 1.4244,
25
- "eval_samples_per_second": 732.255,
26
- "eval_steps_per_second": 46.336,
27
  "step": 108
28
  },
29
  {
30
  "epoch": 3.0,
31
- "eval_loss": 0.6012548208236694,
32
- "eval_matthews_correlation": 0.0463559874942472,
33
- "eval_runtime": 1.4207,
34
- "eval_samples_per_second": 734.141,
35
- "eval_steps_per_second": 46.456,
36
  "step": 162
37
  }
38
  ],
39
  "logging_steps": 500,
40
- "max_steps": 216,
41
  "num_input_tokens_seen": 0,
42
- "num_train_epochs": 4,
43
  "save_steps": 500,
44
  "total_flos": 0,
45
  "train_batch_size": 16,
46
  "trial_name": null,
47
  "trial_params": {
48
- "learning_rate": 2.7854323243021316e-06,
49
- "num_train_epochs": 4,
50
  "per_device_train_batch_size": 16,
51
- "seed": 5
52
  }
53
  }
 
1
  {
2
+ "best_metric": 0.06479227964096512,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-54",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
  "global_step": 162,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6800838708877563,
14
+ "eval_matthews_correlation": 0.06479227964096512,
15
+ "eval_runtime": 1.3179,
16
+ "eval_samples_per_second": 791.421,
17
+ "eval_steps_per_second": 50.08,
18
  "step": 54
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_loss": 0.6333577036857605,
23
+ "eval_matthews_correlation": 0.06354272869611655,
24
+ "eval_runtime": 1.4106,
25
+ "eval_samples_per_second": 739.39,
26
+ "eval_steps_per_second": 46.788,
27
  "step": 108
28
  },
29
  {
30
  "epoch": 3.0,
31
+ "eval_loss": 0.6208921074867249,
32
+ "eval_matthews_correlation": 0.04129856774209186,
33
+ "eval_runtime": 3.1494,
34
+ "eval_samples_per_second": 331.174,
35
+ "eval_steps_per_second": 20.956,
36
  "step": 162
37
  }
38
  ],
39
  "logging_steps": 500,
40
+ "max_steps": 270,
41
  "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
  "save_steps": 500,
44
  "total_flos": 0,
45
  "train_batch_size": 16,
46
  "trial_name": null,
47
  "trial_params": {
48
+ "learning_rate": 1.420124179212326e-06,
49
+ "num_train_epochs": 5,
50
  "per_device_train_batch_size": 16,
51
+ "seed": 26
52
  }
53
  }
run-2/checkpoint-162/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42783ab338ba78bc9a261fef02bd6d857622f28fcbf5b914d81d574b8f77a67
3
  size 4920
run-2/checkpoint-216/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a241eac726a9a46dd541c1ba75a4402ec03a152257cc3b15e6009a133f4003f3
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96727578366c5c006c2c0a6ac307c8304fccad67c4006fe5c349d0b5c0a0b9ee
3
  size 437958648
run-2/checkpoint-216/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4558c559411b39c5dffa7d56e254210cdf6eaa798024d42aec08da23b49f669
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8355d9bd196205e632ec628b1033bc5c7fcdf346d2ae4ca08d3047c3aa46bd
3
  size 876038394
run-2/checkpoint-216/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a005c9efead36f43708fc69d803c2c0aa9d6e3af34c881adadee9ab7e8f2a5ea
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59492816dfb9dd3d0774f42b3fe91114d6338b0e30e9ac611c459ec6b4679975
3
+ size 14308
run-2/checkpoint-216/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b53cdef3adfe1184711d3a09857577ba9dc6ae63d25476fc50f0f565554a9ba3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6140249d9c23ce9654a982bce239c2da5e21931f48857874efc88af8fd591fb
3
  size 1064
run-2/checkpoint-216/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.0463559874942472,
3
- "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-108",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
6
  "global_step": 216,
@@ -10,53 +10,53 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6150018572807312,
14
- "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 1.3372,
16
- "eval_samples_per_second": 779.988,
17
- "eval_steps_per_second": 49.357,
18
  "step": 54
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_loss": 0.6089003086090088,
23
- "eval_matthews_correlation": 0.0463559874942472,
24
- "eval_runtime": 1.4244,
25
- "eval_samples_per_second": 732.255,
26
- "eval_steps_per_second": 46.336,
27
  "step": 108
28
  },
29
  {
30
  "epoch": 3.0,
31
- "eval_loss": 0.6012548208236694,
32
- "eval_matthews_correlation": 0.0463559874942472,
33
- "eval_runtime": 1.4207,
34
- "eval_samples_per_second": 734.141,
35
- "eval_steps_per_second": 46.456,
36
  "step": 162
37
  },
38
  {
39
  "epoch": 4.0,
40
- "eval_loss": 0.598237156867981,
41
- "eval_matthews_correlation": 0.0463559874942472,
42
- "eval_runtime": 1.4427,
43
- "eval_samples_per_second": 722.941,
44
- "eval_steps_per_second": 45.747,
45
  "step": 216
46
  }
47
  ],
48
  "logging_steps": 500,
49
- "max_steps": 216,
50
  "num_input_tokens_seen": 0,
51
- "num_train_epochs": 4,
52
  "save_steps": 500,
53
  "total_flos": 0,
54
  "train_batch_size": 16,
55
  "trial_name": null,
56
  "trial_params": {
57
- "learning_rate": 2.7854323243021316e-06,
58
- "num_train_epochs": 4,
59
  "per_device_train_batch_size": 16,
60
- "seed": 5
61
  }
62
  }
 
1
  {
2
+ "best_metric": 0.06479227964096512,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-54",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
6
  "global_step": 216,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6800838708877563,
14
+ "eval_matthews_correlation": 0.06479227964096512,
15
+ "eval_runtime": 1.3179,
16
+ "eval_samples_per_second": 791.421,
17
+ "eval_steps_per_second": 50.08,
18
  "step": 54
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_loss": 0.6333577036857605,
23
+ "eval_matthews_correlation": 0.06354272869611655,
24
+ "eval_runtime": 1.4106,
25
+ "eval_samples_per_second": 739.39,
26
+ "eval_steps_per_second": 46.788,
27
  "step": 108
28
  },
29
  {
30
  "epoch": 3.0,
31
+ "eval_loss": 0.6208921074867249,
32
+ "eval_matthews_correlation": 0.04129856774209186,
33
+ "eval_runtime": 3.1494,
34
+ "eval_samples_per_second": 331.174,
35
+ "eval_steps_per_second": 20.956,
36
  "step": 162
37
  },
38
  {
39
  "epoch": 4.0,
40
+ "eval_loss": 0.615740180015564,
41
+ "eval_matthews_correlation": 0.0407377624184135,
42
+ "eval_runtime": 3.8341,
43
+ "eval_samples_per_second": 272.03,
44
+ "eval_steps_per_second": 17.214,
45
  "step": 216
46
  }
47
  ],
48
  "logging_steps": 500,
49
+ "max_steps": 270,
50
  "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
  "save_steps": 500,
53
  "total_flos": 0,
54
  "train_batch_size": 16,
55
  "trial_name": null,
56
  "trial_params": {
57
+ "learning_rate": 1.420124179212326e-06,
58
+ "num_train_epochs": 5,
59
  "per_device_train_batch_size": 16,
60
+ "seed": 26
61
  }
62
  }
run-2/checkpoint-216/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42783ab338ba78bc9a261fef02bd6d857622f28fcbf5b914d81d574b8f77a67
3
  size 4920
run-2/checkpoint-54/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adc24a9b3b529867ce40e8ad3ada784dfb746737eae98fd2a707784a055b17ff
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5532eacb19539cc92d43257b0ea0db854bae37c452c8278162825aa2bb5f0a
3
  size 437958648
run-2/checkpoint-54/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:849a269e7c1f1f0ea944fdef109945ea4172440ec76e3a3d49f00dde896ce2af
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4001d66d39487f1b6526f89239856c78aa7f50085b70ef98e0dd1a189c1e853f
3
  size 876038394
run-2/checkpoint-54/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c669928599861916e5e4a1a4b7492a2b89c91233046dc18d8c050bbbb721648
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63fe2a6b91133a605a54e9b5c6acd65e221b36d5f9f87baaabfe91de668c6e12
3
+ size 14308
run-2/checkpoint-54/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf273518d6510e5eb91476a125aef231c3c428854249c16f24b2d2662b5394b6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eab9ab496e83dffb3a387f1e3e7d35de319c08b33e22f5d3a9c6a43e7158d08
3
  size 1064
run-2/checkpoint-54/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.0,
3
  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-54",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,26 +10,26 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6150018572807312,
14
- "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 1.3372,
16
- "eval_samples_per_second": 779.988,
17
- "eval_steps_per_second": 49.357,
18
  "step": 54
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 216,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 4,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 16,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 2.7854323243021316e-06,
31
- "num_train_epochs": 4,
32
  "per_device_train_batch_size": 16,
33
- "seed": 5
34
  }
35
  }
 
1
  {
2
+ "best_metric": 0.06479227964096512,
3
  "best_model_checkpoint": "bert-base-uncased-finetuned-cola/run-2/checkpoint-54",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6800838708877563,
14
+ "eval_matthews_correlation": 0.06479227964096512,
15
+ "eval_runtime": 1.3179,
16
+ "eval_samples_per_second": 791.421,
17
+ "eval_steps_per_second": 50.08,
18
  "step": 54
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 270,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 16,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "learning_rate": 1.420124179212326e-06,
31
+ "num_train_epochs": 5,
32
  "per_device_train_batch_size": 16,
33
+ "seed": 26
34
  }
35
  }
run-2/checkpoint-54/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fdfb014d588afbdeccbaf5fda2c374059ca48b248507655f1c57246bc4731e1
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42783ab338ba78bc9a261fef02bd6d857622f28fcbf5b914d81d574b8f77a67
3
  size 4920
runs/Mar05_08-21-06_22d65867544c/events.out.tfevents.1709628755.22d65867544c.687.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e6d9c51910deb77af05d850ee9606fccd2c33643d313e19cb96c8896bef223
3
+ size 6653
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee1079efb096bc038fdcb92f41e7f212806b5c803d7f37e767ae5856e16aa0bd
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42783ab338ba78bc9a261fef02bd6d857622f28fcbf5b914d81d574b8f77a67
3
  size 4920