SjardiWillems commited on
Commit
384e934
·
verified ·
1 Parent(s): 773b166

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-144/config.json +31 -0
  3. run-0/checkpoint-144/model.safetensors +3 -0
  4. run-0/checkpoint-144/optimizer.pt +3 -0
  5. run-0/checkpoint-144/rng_state.pth +3 -0
  6. run-0/checkpoint-144/scheduler.pt +3 -0
  7. run-0/checkpoint-144/special_tokens_map.json +7 -0
  8. run-0/checkpoint-144/tokenizer.json +0 -0
  9. run-0/checkpoint-144/tokenizer_config.json +55 -0
  10. run-0/checkpoint-144/trainer_state.json +46 -0
  11. run-0/checkpoint-144/training_args.bin +3 -0
  12. run-0/checkpoint-144/vocab.txt +0 -0
  13. run-0/checkpoint-216/config.json +31 -0
  14. run-0/checkpoint-216/model.safetensors +3 -0
  15. run-0/checkpoint-216/optimizer.pt +3 -0
  16. run-0/checkpoint-216/rng_state.pth +3 -0
  17. run-0/checkpoint-216/scheduler.pt +3 -0
  18. run-0/checkpoint-216/special_tokens_map.json +7 -0
  19. run-0/checkpoint-216/tokenizer.json +0 -0
  20. run-0/checkpoint-216/tokenizer_config.json +55 -0
  21. run-0/checkpoint-216/trainer_state.json +56 -0
  22. run-0/checkpoint-216/training_args.bin +3 -0
  23. run-0/checkpoint-216/vocab.txt +0 -0
  24. run-0/checkpoint-288/config.json +31 -0
  25. run-0/checkpoint-288/model.safetensors +3 -0
  26. run-0/checkpoint-288/optimizer.pt +3 -0
  27. run-0/checkpoint-288/rng_state.pth +3 -0
  28. run-0/checkpoint-288/scheduler.pt +3 -0
  29. run-0/checkpoint-288/special_tokens_map.json +7 -0
  30. run-0/checkpoint-288/tokenizer.json +0 -0
  31. run-0/checkpoint-288/tokenizer_config.json +55 -0
  32. run-0/checkpoint-288/trainer_state.json +66 -0
  33. run-0/checkpoint-288/training_args.bin +3 -0
  34. run-0/checkpoint-288/vocab.txt +0 -0
  35. run-1/checkpoint-72/config.json +31 -0
  36. run-1/checkpoint-72/model.safetensors +3 -0
  37. run-1/checkpoint-72/optimizer.pt +3 -0
  38. run-1/checkpoint-72/rng_state.pth +3 -0
  39. run-1/checkpoint-72/scheduler.pt +3 -0
  40. run-1/checkpoint-72/special_tokens_map.json +7 -0
  41. run-1/checkpoint-72/tokenizer.json +0 -0
  42. run-1/checkpoint-72/tokenizer_config.json +55 -0
  43. run-1/checkpoint-72/trainer_state.json +36 -0
  44. run-1/checkpoint-72/training_args.bin +3 -0
  45. run-1/checkpoint-72/vocab.txt +0 -0
  46. runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709675915.fe13c9557656.828.2 +2 -2
  47. runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709675978.fe13c9557656.828.3 +3 -0
  48. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:193eafc1a8a054e2125b9000585ca1e9ef912e9070ea24787555b3596dd2f1c6
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3ebf954bf47e16b3867b4027c95e69abd7b1d6aa47363214e7d3508b762595
3
  size 267829484
run-0/checkpoint-144/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-0/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ac0c2f35d425f333ba67d099e88cb795e65504bbc2231759b07595aec73394
3
+ size 267829484
run-0/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43200add0c200a1dbeb3f7f34ebe2ff794e7cd6e2999784144ef645bc563fd13
3
+ size 535721146
run-0/checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4ef1c5e753a9401f18db6dd0e9badc9fb4e3e4956aafa5bbed209ec8cba9e0
3
+ size 14244
run-0/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec20383411992cd3429d55d5d2e0d917be81ead609cf212a32ad3ed0745d2424
3
+ size 1064
run-0/checkpoint-144/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-0/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-144/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-0/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8253446259273143,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-144",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
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": 1.0813779830932617,
14
+ "eval_pearson": 0.7567095621264116,
15
+ "eval_runtime": 0.9163,
16
+ "eval_samples_per_second": 1637.038,
17
+ "eval_spearmanr": 0.7572162649891061,
18
+ "eval_steps_per_second": 102.588,
19
+ "step": 72
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.8653174042701721,
24
+ "eval_pearson": 0.8253446259273143,
25
+ "eval_runtime": 1.0205,
26
+ "eval_samples_per_second": 1469.804,
27
+ "eval_spearmanr": 0.8213518482816455,
28
+ "eval_steps_per_second": 92.108,
29
+ "step": 144
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 288,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 4,
36
+ "save_steps": 500,
37
+ "total_flos": 0,
38
+ "train_batch_size": 8,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "learning_rate": 3.8584811748752325e-05,
42
+ "num_train_epochs": 4,
43
+ "per_device_train_batch_size": 8,
44
+ "seed": 40
45
+ }
46
+ }
run-0/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9a09d3e6d841ee4f64161d2a8c27492f996273463a537d8f3f6e05968d37fe
3
+ size 4920
run-0/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-216/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-0/checkpoint-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5418acaf01f7db94af0b54792b6d4d366668bbd0a5d0b667448131120c5418
3
+ size 267829484
run-0/checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8e9f3709f2d455f24f61a19d17d420e4f680e5bc3fb8b0655be37df65a418b
3
+ size 535721146
run-0/checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038e71594f5547a63cb7e467f33b50c0377a188cf2dc5dbbab756833f58c85c4
3
+ size 14244
run-0/checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe1117b504cf6be0206f1a8b7f9b6d990c0681fd1da4c1855e91c3864469c71
3
+ size 1064
run-0/checkpoint-216/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-0/checkpoint-216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-216/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-0/checkpoint-216/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8284186695774568,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-216",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 216,
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": 1.0813779830932617,
14
+ "eval_pearson": 0.7567095621264116,
15
+ "eval_runtime": 0.9163,
16
+ "eval_samples_per_second": 1637.038,
17
+ "eval_spearmanr": 0.7572162649891061,
18
+ "eval_steps_per_second": 102.588,
19
+ "step": 72
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.8653174042701721,
24
+ "eval_pearson": 0.8253446259273143,
25
+ "eval_runtime": 1.0205,
26
+ "eval_samples_per_second": 1469.804,
27
+ "eval_spearmanr": 0.8213518482816455,
28
+ "eval_steps_per_second": 92.108,
29
+ "step": 144
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 0.7286169528961182,
34
+ "eval_pearson": 0.8284186695774568,
35
+ "eval_runtime": 0.9489,
36
+ "eval_samples_per_second": 1580.844,
37
+ "eval_spearmanr": 0.8248712386045135,
38
+ "eval_steps_per_second": 99.066,
39
+ "step": 216
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 288,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 3.8584811748752325e-05,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 8,
54
+ "seed": 40
55
+ }
56
+ }
run-0/checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9a09d3e6d841ee4f64161d2a8c27492f996273463a537d8f3f6e05968d37fe
3
+ size 4920
run-0/checkpoint-216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-288/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-0/checkpoint-288/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a7e69db21e42d412939d1e36d85c5cce94cf888a48d410cdcebba133954961
3
+ size 267829484
run-0/checkpoint-288/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db29bdcba8691d7355db2d4b2efb03d2fc57abcb4241e331aadec87069aab9d0
3
+ size 535721146
run-0/checkpoint-288/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f626927ff09c9fc535421ec8dad43c9dbeb3494a6f853f65416b0df7692c7c0
3
+ size 14244
run-0/checkpoint-288/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c84e36f5d86b2d14c61e406755bf7b1e2f465ae07eeff109e65a79476ac0d4a
3
+ size 1064
run-0/checkpoint-288/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-0/checkpoint-288/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-288/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-0/checkpoint-288/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8324083319363956,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-288",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 288,
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": 1.0813779830932617,
14
+ "eval_pearson": 0.7567095621264116,
15
+ "eval_runtime": 0.9163,
16
+ "eval_samples_per_second": 1637.038,
17
+ "eval_spearmanr": 0.7572162649891061,
18
+ "eval_steps_per_second": 102.588,
19
+ "step": 72
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.8653174042701721,
24
+ "eval_pearson": 0.8253446259273143,
25
+ "eval_runtime": 1.0205,
26
+ "eval_samples_per_second": 1469.804,
27
+ "eval_spearmanr": 0.8213518482816455,
28
+ "eval_steps_per_second": 92.108,
29
+ "step": 144
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 0.7286169528961182,
34
+ "eval_pearson": 0.8284186695774568,
35
+ "eval_runtime": 0.9489,
36
+ "eval_samples_per_second": 1580.844,
37
+ "eval_spearmanr": 0.8248712386045135,
38
+ "eval_steps_per_second": 99.066,
39
+ "step": 216
40
+ },
41
+ {
42
+ "epoch": 4.0,
43
+ "eval_loss": 0.7232770323753357,
44
+ "eval_pearson": 0.8324083319363956,
45
+ "eval_runtime": 0.9594,
46
+ "eval_samples_per_second": 1563.435,
47
+ "eval_spearmanr": 0.8281963049502055,
48
+ "eval_steps_per_second": 97.975,
49
+ "step": 288
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 288,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 4,
56
+ "save_steps": 500,
57
+ "total_flos": 0,
58
+ "train_batch_size": 8,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "learning_rate": 3.8584811748752325e-05,
62
+ "num_train_epochs": 4,
63
+ "per_device_train_batch_size": 8,
64
+ "seed": 40
65
+ }
66
+ }
run-0/checkpoint-288/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9a09d3e6d841ee4f64161d2a8c27492f996273463a537d8f3f6e05968d37fe
3
+ size 4920
run-0/checkpoint-288/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-72/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-1/checkpoint-72/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3ebf954bf47e16b3867b4027c95e69abd7b1d6aa47363214e7d3508b762595
3
+ size 267829484
run-1/checkpoint-72/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3288c168f52ade9bbf48b57c6f41bd6a4f8774d498772e531b8129a96a5a0569
3
+ size 535721146
run-1/checkpoint-72/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76dea30ed468799ad519f8a8381a4853bdbb56668807cb8c42f49e744c8d98e4
3
+ size 14244
run-1/checkpoint-72/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ad13b028cee0d7e8e337970c903165f898dcedd240a415c23cca94504d89e5
3
+ size 1064
run-1/checkpoint-72/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-72/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-72/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-1/checkpoint-72/trainer_state.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.49554442333740484,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-72",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 72,
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": 2.2141971588134766,
14
+ "eval_pearson": 0.49554442333740484,
15
+ "eval_runtime": 0.9304,
16
+ "eval_samples_per_second": 1612.164,
17
+ "eval_spearmanr": 0.5246897691009283,
18
+ "eval_steps_per_second": 101.029,
19
+ "step": 72
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 216,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 3,
26
+ "save_steps": 500,
27
+ "total_flos": 0,
28
+ "train_batch_size": 8,
29
+ "trial_name": null,
30
+ "trial_params": {
31
+ "learning_rate": 1.2713760898858066e-05,
32
+ "num_train_epochs": 3,
33
+ "per_device_train_batch_size": 8,
34
+ "seed": 30
35
+ }
36
+ }
run-1/checkpoint-72/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e19ef0ddd5d554387252f8727f426e5c782e9c195b5e4538a0a61f48d78d6d
3
+ size 4920
run-1/checkpoint-72/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709675915.fe13c9557656.828.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:440f684f615e35018cce413c625605e335a7ec3f5f47344931a3f83fde63aacd
3
- size 4975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf872dc9c6121fc431eda6d623da648d27026ccbac2fd75763901ae60a8c7275
3
+ size 6454
runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709675978.fe13c9557656.828.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788e2cc3c752c09c18861403d12be3707ab22e3df71ed127169b39883683867c
3
+ size 6079
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd9a09d3e6d841ee4f64161d2a8c27492f996273463a537d8f3f6e05968d37fe
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e19ef0ddd5d554387252f8727f426e5c782e9c195b5e4538a0a61f48d78d6d
3
  size 4920