Silicon23 commited on
Commit
e6536aa
·
verified ·
1 Parent(s): c9b863b

Training in progress, epoch 1

Browse files
Files changed (47) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-184/config.json +27 -0
  3. run-4/checkpoint-184/model.safetensors +3 -0
  4. run-4/checkpoint-184/optimizer.pt +3 -0
  5. run-4/checkpoint-184/rng_state.pth +3 -0
  6. run-4/checkpoint-184/scheduler.pt +3 -0
  7. run-4/checkpoint-184/special_tokens_map.json +7 -0
  8. run-4/checkpoint-184/tokenizer.json +0 -0
  9. run-4/checkpoint-184/tokenizer_config.json +55 -0
  10. run-4/checkpoint-184/trainer_state.json +56 -0
  11. run-4/checkpoint-184/training_args.bin +3 -0
  12. run-4/checkpoint-184/vocab.txt +0 -0
  13. run-4/checkpoint-276/config.json +27 -0
  14. run-4/checkpoint-276/model.safetensors +3 -0
  15. run-4/checkpoint-276/optimizer.pt +3 -0
  16. run-4/checkpoint-276/rng_state.pth +3 -0
  17. run-4/checkpoint-276/scheduler.pt +3 -0
  18. run-4/checkpoint-276/special_tokens_map.json +7 -0
  19. run-4/checkpoint-276/tokenizer.json +0 -0
  20. run-4/checkpoint-276/tokenizer_config.json +55 -0
  21. run-4/checkpoint-276/trainer_state.json +65 -0
  22. run-4/checkpoint-276/training_args.bin +3 -0
  23. run-4/checkpoint-276/vocab.txt +0 -0
  24. run-4/checkpoint-368/config.json +27 -0
  25. run-4/checkpoint-368/model.safetensors +3 -0
  26. run-4/checkpoint-368/optimizer.pt +3 -0
  27. run-4/checkpoint-368/rng_state.pth +3 -0
  28. run-4/checkpoint-368/scheduler.pt +3 -0
  29. run-4/checkpoint-368/special_tokens_map.json +7 -0
  30. run-4/checkpoint-368/tokenizer.json +0 -0
  31. run-4/checkpoint-368/tokenizer_config.json +55 -0
  32. run-4/checkpoint-368/trainer_state.json +74 -0
  33. run-4/checkpoint-368/training_args.bin +3 -0
  34. run-4/checkpoint-368/vocab.txt +0 -0
  35. run-5/checkpoint-46/config.json +27 -0
  36. run-5/checkpoint-46/model.safetensors +3 -0
  37. run-5/checkpoint-46/optimizer.pt +3 -0
  38. run-5/checkpoint-46/rng_state.pth +3 -0
  39. run-5/checkpoint-46/scheduler.pt +3 -0
  40. run-5/checkpoint-46/special_tokens_map.json +7 -0
  41. run-5/checkpoint-46/tokenizer.json +0 -0
  42. run-5/checkpoint-46/tokenizer_config.json +55 -0
  43. run-5/checkpoint-46/trainer_state.json +47 -0
  44. run-5/checkpoint-46/training_args.bin +3 -0
  45. run-5/checkpoint-46/vocab.txt +0 -0
  46. runs/Jul31_19-18-04_20e4e50bc3c6/events.out.tfevents.1722454169.20e4e50bc3c6.1187.5 +3 -0
  47. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e6a27adaac0bbe2b5312f4f381977654281a67946bcc88757d4a1c1634bae36
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aded855ec43ea0179e934bfa3f3b024737c9d6156fd3dfb98b20e81ae3b4b0a6
3
  size 437958648
run-4/checkpoint-184/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/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": "4.42.4",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-4/checkpoint-184/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8032ac4c62c540c92550b17939d79e0bd650716fd78d134224afbb47d0a4dad5
3
+ size 437958648
run-4/checkpoint-184/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5392d22cc160251105972d88bd7acf48f72891ef679522b54c40ab39981059f1
3
+ size 876038394
run-4/checkpoint-184/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1127bd117b8693570befc1cf65cb99b9708f9cd34b6f299beba14fdf508dc045
3
+ size 14244
run-4/checkpoint-184/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce47302dad0314f370577b753791579861b167a672c866a0edf29701ec7a45c
3
+ size 1064
run-4/checkpoint-184/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-4/checkpoint-184/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-184/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-4/checkpoint-184/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8029465930018416,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-4/checkpoint-184",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 184,
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_accuracy": 0.7599754450583179,
14
+ "eval_loss": 0.5310371518135071,
15
+ "eval_runtime": 1.5228,
16
+ "eval_samples_per_second": 1069.729,
17
+ "eval_steps_per_second": 66.981,
18
+ "step": 92
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8029465930018416,
23
+ "eval_loss": 0.4333054721355438,
24
+ "eval_runtime": 1.5219,
25
+ "eval_samples_per_second": 1070.365,
26
+ "eval_steps_per_second": 67.021,
27
+ "step": 184
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 368,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": false
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 8.172683454042364e-06,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 5
55
+ }
56
+ }
run-4/checkpoint-184/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbcf13295d62195686db12523e4a631a6ccda6cd83f27f82b79770ea78c26499
3
+ size 5176
run-4/checkpoint-184/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-276/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/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": "4.42.4",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-4/checkpoint-276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335207bef4e6f87c0315864addcefcff28aff99a11bbeef3be34d28e9009c364
3
+ size 437958648
run-4/checkpoint-276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6695b5bb7e06ba10f8bf0a837f6cdd32962b3a4a1c078c2538d99cae27eb08e4
3
+ size 876038394
run-4/checkpoint-276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db7a070f2ead7ee0bbe009dc6889ed092d36d9beb7cdb6e8824e7381066b99ae
3
+ size 14244
run-4/checkpoint-276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31f04373b0babdafe49b523b44c8dda05424ee4a172b6b95036efd9c1b55d2d
3
+ size 1064
run-4/checkpoint-276/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-4/checkpoint-276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-276/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-4/checkpoint-276/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8158379373848987,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-4/checkpoint-276",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 276,
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_accuracy": 0.7599754450583179,
14
+ "eval_loss": 0.5310371518135071,
15
+ "eval_runtime": 1.5228,
16
+ "eval_samples_per_second": 1069.729,
17
+ "eval_steps_per_second": 66.981,
18
+ "step": 92
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8029465930018416,
23
+ "eval_loss": 0.4333054721355438,
24
+ "eval_runtime": 1.5219,
25
+ "eval_samples_per_second": 1070.365,
26
+ "eval_steps_per_second": 67.021,
27
+ "step": 184
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8158379373848987,
32
+ "eval_loss": 0.4052351415157318,
33
+ "eval_runtime": 1.5302,
34
+ "eval_samples_per_second": 1064.578,
35
+ "eval_steps_per_second": 66.659,
36
+ "step": 276
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 368,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "stateful_callbacks": {
45
+ "TrainerControl": {
46
+ "args": {
47
+ "should_epoch_stop": false,
48
+ "should_evaluate": false,
49
+ "should_log": false,
50
+ "should_save": true,
51
+ "should_training_stop": false
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 0,
57
+ "train_batch_size": 16,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "learning_rate": 8.172683454042364e-06,
61
+ "num_train_epochs": 4,
62
+ "per_device_train_batch_size": 16,
63
+ "seed": 5
64
+ }
65
+ }
run-4/checkpoint-276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbcf13295d62195686db12523e4a631a6ccda6cd83f27f82b79770ea78c26499
3
+ size 5176
run-4/checkpoint-276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-368/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/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": "4.42.4",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-4/checkpoint-368/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf287d6150184d0d665d067c3f6a0a836773e1960223761db3c83782a5e12500
3
+ size 437958648
run-4/checkpoint-368/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c150a43af551a1e24ab7cb0602548ec8cc59e92cb2c74273f7e62175000a54c9
3
+ size 876038394
run-4/checkpoint-368/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8faeb3cc529d91fffff115518eb84d4c1c7bf9a8e03f558e8aa6e46165686d39
3
+ size 14244
run-4/checkpoint-368/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5020f7d89d12ca9ca98fd21c5cac8001eee7dc2e447231c80bda17d5c3bfb62
3
+ size 1064
run-4/checkpoint-368/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-4/checkpoint-368/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-368/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-4/checkpoint-368/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8158379373848987,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-4/checkpoint-276",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 368,
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_accuracy": 0.7599754450583179,
14
+ "eval_loss": 0.5310371518135071,
15
+ "eval_runtime": 1.5228,
16
+ "eval_samples_per_second": 1069.729,
17
+ "eval_steps_per_second": 66.981,
18
+ "step": 92
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8029465930018416,
23
+ "eval_loss": 0.4333054721355438,
24
+ "eval_runtime": 1.5219,
25
+ "eval_samples_per_second": 1070.365,
26
+ "eval_steps_per_second": 67.021,
27
+ "step": 184
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8158379373848987,
32
+ "eval_loss": 0.4052351415157318,
33
+ "eval_runtime": 1.5302,
34
+ "eval_samples_per_second": 1064.578,
35
+ "eval_steps_per_second": 66.659,
36
+ "step": 276
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.8121546961325967,
41
+ "eval_loss": 0.40069225430488586,
42
+ "eval_runtime": 1.5674,
43
+ "eval_samples_per_second": 1039.321,
44
+ "eval_steps_per_second": 65.077,
45
+ "step": 368
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 368,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": true
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 8.172683454042364e-06,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 16,
72
+ "seed": 5
73
+ }
74
+ }
run-4/checkpoint-368/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbcf13295d62195686db12523e4a631a6ccda6cd83f27f82b79770ea78c26499
3
+ size 5176
run-4/checkpoint-368/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-46/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/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": "4.42.4",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-5/checkpoint-46/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aded855ec43ea0179e934bfa3f3b024737c9d6156fd3dfb98b20e81ae3b4b0a6
3
+ size 437958648
run-5/checkpoint-46/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e9c82fa9670a5451fba2199a5d61bb8d3fc96383db885b0f122bb05a98be2e
3
+ size 876038394
run-5/checkpoint-46/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f6e940e973616e9af04659471b24885e6ca775730d36bd3c9a6ea79ef681dd
3
+ size 14308
run-5/checkpoint-46/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ee3bfbe826ce314a70107fc4430472b5b54cf17ea20a48fe4dcbae21a2609b
3
+ size 1064
run-5/checkpoint-46/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-5/checkpoint-46/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-46/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-5/checkpoint-46/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8164518109269491,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-5/checkpoint-46",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 46,
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_accuracy": 0.8164518109269491,
14
+ "eval_loss": 0.4110926389694214,
15
+ "eval_runtime": 1.5153,
16
+ "eval_samples_per_second": 1075.006,
17
+ "eval_steps_per_second": 67.312,
18
+ "step": 46
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 138,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "stateful_callbacks": {
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": false
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 32,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 4.628285992582947e-05,
43
+ "num_train_epochs": 3,
44
+ "per_device_train_batch_size": 32,
45
+ "seed": 8
46
+ }
47
+ }
run-5/checkpoint-46/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee006133791165a4f0fc0592cf175ac51fbb54421547bf7e28eb59d0544133f8
3
+ size 5176
run-5/checkpoint-46/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul31_19-18-04_20e4e50bc3c6/events.out.tfevents.1722454169.20e4e50bc3c6.1187.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac831f38fa826358041442a5ccbb35ade49b96ed16aebc3e9b5e19ba5ddbe06
3
+ size 6236
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbcf13295d62195686db12523e4a631a6ccda6cd83f27f82b79770ea78c26499
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee006133791165a4f0fc0592cf175ac51fbb54421547bf7e28eb59d0544133f8
3
  size 5176