jjkozlow commited on
Commit
a214db8
1 Parent(s): a4644a4

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-108/config.json +25 -0
  3. run-6/checkpoint-108/model.safetensors +3 -0
  4. run-6/checkpoint-108/optimizer.pt +3 -0
  5. run-6/checkpoint-108/rng_state.pth +3 -0
  6. run-6/checkpoint-108/scheduler.pt +3 -0
  7. run-6/checkpoint-108/special_tokens_map.json +7 -0
  8. run-6/checkpoint-108/tokenizer.json +0 -0
  9. run-6/checkpoint-108/tokenizer_config.json +55 -0
  10. run-6/checkpoint-108/trainer_state.json +62 -0
  11. run-6/checkpoint-108/training_args.bin +3 -0
  12. run-6/checkpoint-108/vocab.txt +0 -0
  13. run-6/checkpoint-135/config.json +25 -0
  14. run-6/checkpoint-135/model.safetensors +3 -0
  15. run-6/checkpoint-135/optimizer.pt +3 -0
  16. run-6/checkpoint-135/rng_state.pth +3 -0
  17. run-6/checkpoint-135/scheduler.pt +3 -0
  18. run-6/checkpoint-135/special_tokens_map.json +7 -0
  19. run-6/checkpoint-135/tokenizer.json +0 -0
  20. run-6/checkpoint-135/tokenizer_config.json +55 -0
  21. run-6/checkpoint-135/trainer_state.json +71 -0
  22. run-6/checkpoint-135/training_args.bin +3 -0
  23. run-6/checkpoint-135/vocab.txt +0 -0
  24. run-6/checkpoint-54/config.json +25 -0
  25. run-6/checkpoint-54/model.safetensors +3 -0
  26. run-6/checkpoint-54/optimizer.pt +3 -0
  27. run-6/checkpoint-54/rng_state.pth +3 -0
  28. run-6/checkpoint-54/scheduler.pt +3 -0
  29. run-6/checkpoint-54/special_tokens_map.json +7 -0
  30. run-6/checkpoint-54/tokenizer.json +0 -0
  31. run-6/checkpoint-54/tokenizer_config.json +55 -0
  32. run-6/checkpoint-54/trainer_state.json +44 -0
  33. run-6/checkpoint-54/training_args.bin +3 -0
  34. run-6/checkpoint-54/vocab.txt +0 -0
  35. run-6/checkpoint-81/config.json +25 -0
  36. run-6/checkpoint-81/model.safetensors +3 -0
  37. run-6/checkpoint-81/optimizer.pt +3 -0
  38. run-6/checkpoint-81/rng_state.pth +3 -0
  39. run-6/checkpoint-81/scheduler.pt +3 -0
  40. run-6/checkpoint-81/special_tokens_map.json +7 -0
  41. run-6/checkpoint-81/tokenizer.json +0 -0
  42. run-6/checkpoint-81/tokenizer_config.json +55 -0
  43. run-6/checkpoint-81/trainer_state.json +53 -0
  44. run-6/checkpoint-81/training_args.bin +3 -0
  45. run-6/checkpoint-81/vocab.txt +0 -0
  46. run-8/checkpoint-214/config.json +25 -0
  47. run-8/checkpoint-214/model.safetensors +3 -0
  48. run-8/checkpoint-214/optimizer.pt +3 -0
  49. run-8/checkpoint-214/rng_state.pth +3 -0
  50. run-8/checkpoint-214/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a344b57655b8bca213d5cfa687cecdb5897e4a015cb742dd436cd70abb4c5b09
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a28a1f7a5bd912e06dd15455ce08a9bad56f205c155f331d0ee5c6ed365375
3
  size 267832560
run-6/checkpoint-108/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b0423c6aefb991ed79ffde091fc0a01d6e86b8e93a38c76cf2043d9c08493f
3
+ size 267832560
run-6/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03e5532509a986544f62cb00505b8e90c9d19f6aec02e6e0ece0e5ba9f3ebc9
3
+ size 535727290
run-6/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4538ff8225b5138bde619440ab115d209ef4fed768c04bd95ce09f95947fb70a
3
+ size 14308
run-6/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6253b4502d68a445cd9c15beb216a43d3c125215a0b03c21a12dd56cc707cd3c
3
+ size 1064
run-6/checkpoint-108/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-6/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-108/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": 1000000000000000019884624838656,
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-6/checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3232069502334773,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-54",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
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": 0.5676701664924622,
14
+ "eval_matthews_correlation": 0.11198943089800718,
15
+ "eval_runtime": 0.7056,
16
+ "eval_samples_per_second": 1478.106,
17
+ "eval_steps_per_second": 93.533,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5832672715187073,
23
+ "eval_matthews_correlation": 0.3232069502334773,
24
+ "eval_runtime": 0.8176,
25
+ "eval_samples_per_second": 1275.761,
26
+ "eval_steps_per_second": 80.729,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.8335629105567932,
32
+ "eval_matthews_correlation": 0.3143422201638131,
33
+ "eval_runtime": 0.7965,
34
+ "eval_samples_per_second": 1309.503,
35
+ "eval_steps_per_second": 82.864,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 1.0557090044021606,
41
+ "eval_matthews_correlation": 0.3137796724464509,
42
+ "eval_runtime": 0.8072,
43
+ "eval_samples_per_second": 1292.198,
44
+ "eval_steps_per_second": 81.769,
45
+ "step": 108
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 135,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 32,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 5.7581529130698136e-05,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 32,
60
+ "seed": 31
61
+ }
62
+ }
run-6/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11129d0c3baf9e6486411cf92d7321b2694158ebcca886ea0c2626c877f17dff
3
+ size 5048
run-6/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-135/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-135/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253a2318dbe5c7f2ea5be780e9b19779209babfb8dbfc1b0c6813cadabfd0fe9
3
+ size 267832560
run-6/checkpoint-135/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65366a92e43745c7d7ddc639e5dd44710af55fa47a900da53d8d8c5cb9db4d12
3
+ size 535727290
run-6/checkpoint-135/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e3aee4dd247ef23b08a103f1ef9b55a13c46f6957c5b0981d0306f4945d4f44
3
+ size 14308
run-6/checkpoint-135/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b7ece35c2a51d101a8e5f634d5c3ecf34758bfd6649667391a6c5db7e61e78d
3
+ size 1064
run-6/checkpoint-135/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-6/checkpoint-135/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-135/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": 1000000000000000019884624838656,
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-6/checkpoint-135/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3244584980129879,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-135",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 135,
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": 0.5676701664924622,
14
+ "eval_matthews_correlation": 0.11198943089800718,
15
+ "eval_runtime": 0.7056,
16
+ "eval_samples_per_second": 1478.106,
17
+ "eval_steps_per_second": 93.533,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5832672715187073,
23
+ "eval_matthews_correlation": 0.3232069502334773,
24
+ "eval_runtime": 0.8176,
25
+ "eval_samples_per_second": 1275.761,
26
+ "eval_steps_per_second": 80.729,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.8335629105567932,
32
+ "eval_matthews_correlation": 0.3143422201638131,
33
+ "eval_runtime": 0.7965,
34
+ "eval_samples_per_second": 1309.503,
35
+ "eval_steps_per_second": 82.864,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 1.0557090044021606,
41
+ "eval_matthews_correlation": 0.3137796724464509,
42
+ "eval_runtime": 0.8072,
43
+ "eval_samples_per_second": 1292.198,
44
+ "eval_steps_per_second": 81.769,
45
+ "step": 108
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 1.0779355764389038,
50
+ "eval_matthews_correlation": 0.3244584980129879,
51
+ "eval_runtime": 0.7908,
52
+ "eval_samples_per_second": 1318.869,
53
+ "eval_steps_per_second": 83.457,
54
+ "step": 135
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 135,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 0,
63
+ "train_batch_size": 32,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 5.7581529130698136e-05,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 32,
69
+ "seed": 31
70
+ }
71
+ }
run-6/checkpoint-135/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11129d0c3baf9e6486411cf92d7321b2694158ebcca886ea0c2626c877f17dff
3
+ size 5048
run-6/checkpoint-135/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-54/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9c3a3e8204f7e2042f3b9f44605ca8dec5508bd3dfa6dc334c91203c654fa3
3
+ size 267832560
run-6/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70903b2abb6ecca4db73b326a9bfaef6877429dac45edf0c6c7318b6361e433
3
+ size 535727290
run-6/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f267c462b34d7e20e04e1c93f3eae702cb928043baa4bbe468e81a5969b969bf
3
+ size 14308
run-6/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4faf9946201bb1b72445173917adceb9b7a800b45112977d544bd9744066eef9
3
+ size 1064
run-6/checkpoint-54/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-6/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-54/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": 1000000000000000019884624838656,
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-6/checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3232069502334773,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-54",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.5676701664924622,
14
+ "eval_matthews_correlation": 0.11198943089800718,
15
+ "eval_runtime": 0.7056,
16
+ "eval_samples_per_second": 1478.106,
17
+ "eval_steps_per_second": 93.533,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5832672715187073,
23
+ "eval_matthews_correlation": 0.3232069502334773,
24
+ "eval_runtime": 0.8176,
25
+ "eval_samples_per_second": 1275.761,
26
+ "eval_steps_per_second": 80.729,
27
+ "step": 54
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 135,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 5.7581529130698136e-05,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 31
43
+ }
44
+ }
run-6/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11129d0c3baf9e6486411cf92d7321b2694158ebcca886ea0c2626c877f17dff
3
+ size 5048
run-6/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-81/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc8c0cc1fcb29018638c08dfecd2093314619126e5da2208be931689e2e3b21
3
+ size 267832560
run-6/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f43a200c2d3f11935e747367c05d0741f32d8ee7ab5427e4a276ff615f556e
3
+ size 535727290
run-6/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e602cacc04b4487c218076e78ea84e93ce2d9cd1316caeae5ec7ed603464a2
3
+ size 14308
run-6/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aea1b2ac5822158757b83f866ad5cde1dd0e3fd110a9e627503b9028228ceea
3
+ size 1064
run-6/checkpoint-81/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-6/checkpoint-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-81/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": 1000000000000000019884624838656,
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-6/checkpoint-81/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3232069502334773,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-54",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
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": 0.5676701664924622,
14
+ "eval_matthews_correlation": 0.11198943089800718,
15
+ "eval_runtime": 0.7056,
16
+ "eval_samples_per_second": 1478.106,
17
+ "eval_steps_per_second": 93.533,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5832672715187073,
23
+ "eval_matthews_correlation": 0.3232069502334773,
24
+ "eval_runtime": 0.8176,
25
+ "eval_samples_per_second": 1275.761,
26
+ "eval_steps_per_second": 80.729,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.8335629105567932,
32
+ "eval_matthews_correlation": 0.3143422201638131,
33
+ "eval_runtime": 0.7965,
34
+ "eval_samples_per_second": 1309.503,
35
+ "eval_steps_per_second": 82.864,
36
+ "step": 81
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 135,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 5.7581529130698136e-05,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 31
52
+ }
53
+ }
run-6/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11129d0c3baf9e6486411cf92d7321b2694158ebcca886ea0c2626c877f17dff
3
+ size 5048
run-6/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-214/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a28a1f7a5bd912e06dd15455ce08a9bad56f205c155f331d0ee5c6ed365375
3
+ size 267832560
run-8/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ba9732e83f979f94b4228ee957115be4232fc29bfd3cb4565ef76ce9a53c07
3
+ size 535727290
run-8/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6642b66e64e0b7ca68e0c6a1ce3642e5ff680df66b6e523921454a079ed214ed
3
+ size 14244
run-8/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20cef685cf1e9669a6ec93d59836759e69cced5a0e02c013134299ca06d9d0e
3
+ size 1064