Hugging Face's logo

Silicon23
/
BERTForDetectingDepression-Twitter2020

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
Silicon23 commited on
Commit
e7fd5a3
·
verified ·
1 Parent(s): 83b2dc2

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-113/config.json +27 -0
  3. run-0/checkpoint-113/model.safetensors +3 -0
  4. run-0/checkpoint-113/optimizer.pt +3 -0
  5. run-0/checkpoint-113/rng_state.pth +3 -0
  6. run-0/checkpoint-113/scheduler.pt +3 -0
  7. run-0/checkpoint-113/special_tokens_map.json +37 -0
  8. run-0/checkpoint-113/tokenizer.json +0 -0
  9. run-0/checkpoint-113/tokenizer_config.json +59 -0
  10. run-0/checkpoint-113/trainer_state.json +47 -0
  11. run-0/checkpoint-113/training_args.bin +3 -0
  12. run-0/checkpoint-113/vocab.txt +0 -0
  13. run-1/checkpoint-113/model.safetensors +1 -1
  14. run-1/checkpoint-113/optimizer.pt +1 -1
  15. run-1/checkpoint-113/rng_state.pth +2 -2
  16. run-1/checkpoint-113/scheduler.pt +1 -1
  17. run-1/checkpoint-113/trainer_state.json +11 -11
  18. run-1/checkpoint-113/training_args.bin +1 -1
  19. run-1/checkpoint-226/model.safetensors +1 -1
  20. run-1/checkpoint-226/optimizer.pt +1 -1
  21. run-1/checkpoint-226/rng_state.pth +2 -2
  22. run-1/checkpoint-226/scheduler.pt +1 -1
  23. run-1/checkpoint-226/trainer_state.json +16 -16
  24. run-1/checkpoint-226/training_args.bin +1 -1
  25. run-1/checkpoint-339/model.safetensors +1 -1
  26. run-1/checkpoint-339/optimizer.pt +1 -1
  27. run-1/checkpoint-339/rng_state.pth +2 -2
  28. run-1/checkpoint-339/scheduler.pt +1 -1
  29. run-1/checkpoint-339/trainer_state.json +21 -21
  30. run-1/checkpoint-339/training_args.bin +1 -1
  31. run-1/checkpoint-452/model.safetensors +1 -1
  32. run-1/checkpoint-452/optimizer.pt +1 -1
  33. run-1/checkpoint-452/rng_state.pth +2 -2
  34. run-1/checkpoint-452/scheduler.pt +1 -1
  35. run-1/checkpoint-452/trainer_state.json +27 -27
  36. run-1/checkpoint-452/training_args.bin +1 -1
  37. runs/Aug01_13-43-54_1d376fbba8fb/events.out.tfevents.1722519987.1d376fbba8fb.194.3 +3 -0
  38. runs/Aug01_13-47-28_1d376fbba8fb/events.out.tfevents.1722520055.1d376fbba8fb.194.4 +3 -0
  39. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aec5cc494e807df52fdcc90d7b4001bc07af0eb0579e01f5697f6b86e18d154
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4d143b5f97e100392dff4ff2aecad133b5b40858872418dd3d5f7892a4635b
3
  size 433270768
run-0/checkpoint-113/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AIMH/mental-bert-base-cased",
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": 28996
27
+ }
run-0/checkpoint-113/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4d143b5f97e100392dff4ff2aecad133b5b40858872418dd3d5f7892a4635b
3
+ size 433270768
run-0/checkpoint-113/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34480b2d94e413ec6f36dce9de5be1092442970cf81802cab6c9b11eb64e766d
3
+ size 866662650
run-0/checkpoint-113/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951da6c244441227dfd03875600893dfc4c09564afc01dde9286ecd3f67641fe
3
+ size 14244
run-0/checkpoint-113/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1825dc2ffff6dd60d79ef229d2905598e4880ed5a85df6e28411fca3745e93b4
3
+ size 1064
run-0/checkpoint-113/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-0/checkpoint-113/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-113/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 512,
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "stride": 0,
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "truncation_side": "right",
57
+ "truncation_strategy": "longest_first",
58
+ "unk_token": "[UNK]"
59
+ }
run-0/checkpoint-113/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.53,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-0/checkpoint-113",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 113,
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": 0.53,
14
+ "eval_loss": 0.6914214491844177,
15
+ "eval_runtime": 3.1734,
16
+ "eval_samples_per_second": 630.24,
17
+ "eval_steps_per_second": 39.39,
18
+ "step": 113
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 113,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
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": true
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 16,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 2.2361264251827005e-06,
43
+ "num_train_epochs": 1,
44
+ "per_device_train_batch_size": 16,
45
+ "seed": 39
46
+ }
47
+ }
run-0/checkpoint-113/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e7886cec37e6d7adf3d7a1ca71b01930e812265faaa75a7daaaaac101d4154
3
+ size 5176
run-0/checkpoint-113/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-113/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ef512dc333e02dd50a0fbeeaa10cf86a89145edfa2bc6bbbb15e688362592bc
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f2b492a33229cc295e578f8876cfcb94b1b9407e722e41bb5f4a1741f37afe0
3
  size 433270768
run-1/checkpoint-113/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e55d402f5cb660682f0fa717747bacc14ee39183732b604b9bb149c181501ce6
3
  size 866662650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee62648bf57a9472dcfa38c6bd16777e2608b37027ffbfb8dc7cff75f4c9104
3
  size 866662650
run-1/checkpoint-113/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df79dd5bba777654c58009215bdcca11b3db6c3ed63fbd2ae632bd87f7802be0
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47699f1e70fae69639d282116d434321f3d1cd7f81cae74d8fd73fe47a6ebb1d
3
+ size 14244
run-1/checkpoint-113/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f14a8aa7de27c23773b80f4eeba81aed83cbcd2b982f4d91b76fa456f56f643d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33882787a2f8e4f5f3246a6bc6d4daf1168f9e144d0f3bc3dec0b05e0804b4dd
3
  size 1064
run-1/checkpoint-113/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.5945,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-113",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,18 +10,18 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5945,
14
- "eval_loss": 0.6746140718460083,
15
- "eval_runtime": 3.0608,
16
- "eval_samples_per_second": 653.432,
17
- "eval_steps_per_second": 40.84,
18
  "step": 113
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 565,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 5,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
@@ -39,9 +39,9 @@
39
  "train_batch_size": 16,
40
  "trial_name": null,
41
  "trial_params": {
42
- "learning_rate": 5.117087338208196e-05,
43
- "num_train_epochs": 5,
44
  "per_device_train_batch_size": 16,
45
- "seed": 26
46
  }
47
  }
 
1
  {
2
+ "best_metric": 0.5365,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-113",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5365,
14
+ "eval_loss": 0.6904081106185913,
15
+ "eval_runtime": 3.0555,
16
+ "eval_samples_per_second": 654.568,
17
+ "eval_steps_per_second": 40.911,
18
  "step": 113
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 452,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
 
39
  "train_batch_size": 16,
40
  "trial_name": null,
41
  "trial_params": {
42
+ "learning_rate": 1.02690913847536e-06,
43
+ "num_train_epochs": 4,
44
  "per_device_train_batch_size": 16,
45
+ "seed": 23
46
  }
47
  }
run-1/checkpoint-113/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c6cf6d62bd96276ddb153ee4c0dd1056bc0032dc430c2a812d2ddb559048838
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7521cb30664a0c20ab156d8ccb08d3894654e486488a3d8c1ca49fd6c3bb6cce
3
  size 5176
run-1/checkpoint-226/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e67a267eddbffecc8700a903c68b6a8cbcf69c98cb51fbf7893727fb229951f
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:434459f2b9611bc7196ea398a951b828dd4c54a05f2cd271b4cd7fc41966492d
3
  size 433270768
run-1/checkpoint-226/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1feb33dc6240a6dbabad9a74f85b5ec3fb898c8f09d665d75efc364051034f1f
3
  size 866662650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f600edac7b21b20307f5513fcc65cb9e5d5c52b0b39aae6f3ec2d6567385f2
3
  size 866662650
run-1/checkpoint-226/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d742293d5ef02f8d3a9f2c5daca9bdc09ab35d7b595b13ed9e011ee755b1a19
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76eb78e52a83da373ca5ab83ad2f5050f82f26131a5facbd32da52aee3bb6968
3
+ size 14244
run-1/checkpoint-226/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45eadcbcbc12bf532f47f28684ef101f54fee5af336e181965964754d23f9b41
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75bb5dbc4af33b636365d97902be8a9e2cf2279962b171fc089c5dbdd229fae0
3
  size 1064
run-1/checkpoint-226/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.5985,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-226",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,27 +10,27 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5945,
14
- "eval_loss": 0.6746140718460083,
15
- "eval_runtime": 3.0608,
16
- "eval_samples_per_second": 653.432,
17
- "eval_steps_per_second": 40.84,
18
  "step": 113
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 0.5985,
23
- "eval_loss": 0.7479358315467834,
24
- "eval_runtime": 3.0745,
25
- "eval_samples_per_second": 650.511,
26
- "eval_steps_per_second": 40.657,
27
  "step": 226
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 565,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 5,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "TrainerControl": {
@@ -48,9 +48,9 @@
48
  "train_batch_size": 16,
49
  "trial_name": null,
50
  "trial_params": {
51
- "learning_rate": 5.117087338208196e-05,
52
- "num_train_epochs": 5,
53
  "per_device_train_batch_size": 16,
54
- "seed": 26
55
  }
56
  }
 
1
  {
2
+ "best_metric": 0.5585,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-226",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5365,
14
+ "eval_loss": 0.6904081106185913,
15
+ "eval_runtime": 3.0555,
16
+ "eval_samples_per_second": 654.568,
17
+ "eval_steps_per_second": 40.911,
18
  "step": 113
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.5585,
23
+ "eval_loss": 0.6850683093070984,
24
+ "eval_runtime": 3.0686,
25
+ "eval_samples_per_second": 651.768,
26
+ "eval_steps_per_second": 40.736,
27
  "step": 226
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 452,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "TrainerControl": {
 
48
  "train_batch_size": 16,
49
  "trial_name": null,
50
  "trial_params": {
51
+ "learning_rate": 1.02690913847536e-06,
52
+ "num_train_epochs": 4,
53
  "per_device_train_batch_size": 16,
54
+ "seed": 23
55
  }
56
  }
run-1/checkpoint-226/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c6cf6d62bd96276ddb153ee4c0dd1056bc0032dc430c2a812d2ddb559048838
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7521cb30664a0c20ab156d8ccb08d3894654e486488a3d8c1ca49fd6c3bb6cce
3
  size 5176
run-1/checkpoint-339/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1492e387b1e68d5afd175557f585dceeb238575ecbf81f6e4ef1a63940dad61
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e2e11a64a98d0086b8f472cc7debf841fae14be938076e7c9a5902278e190c
3
  size 433270768
run-1/checkpoint-339/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20f37ef3eb189e71f99258446616895a9805bbd3c41cdb756fbc771f773c8b80
3
  size 866662650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db7e9a2d59c22b210750d1f9361198d246c4a19a18598dffdd3581862208c64
3
  size 866662650
run-1/checkpoint-339/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9def8259c00a645f5ee40a2e593024b3c6f8b5c4088c34c87e626a715a9cc800
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17dd5c8e6f694a840d4d084d327adcc0e5dd80255cd4fe39aacd8c767d51e2b9
3
+ size 14244
run-1/checkpoint-339/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:472f031528426f4385200755d71bdff1d4a548fbd9538f1de209aab73817ec66
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40d3b79b8b6c1247051a512a3f137762ab52d907bf840c50c5acdd48cea6b99
3
  size 1064
run-1/checkpoint-339/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.602,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-339",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
@@ -10,36 +10,36 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5945,
14
- "eval_loss": 0.6746140718460083,
15
- "eval_runtime": 3.0608,
16
- "eval_samples_per_second": 653.432,
17
- "eval_steps_per_second": 40.84,
18
  "step": 113
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 0.5985,
23
- "eval_loss": 0.7479358315467834,
24
- "eval_runtime": 3.0745,
25
- "eval_samples_per_second": 650.511,
26
- "eval_steps_per_second": 40.657,
27
  "step": 226
28
  },
29
  {
30
  "epoch": 3.0,
31
- "eval_accuracy": 0.602,
32
- "eval_loss": 1.183725118637085,
33
- "eval_runtime": 3.1173,
34
- "eval_samples_per_second": 641.587,
35
- "eval_steps_per_second": 40.099,
36
  "step": 339
37
  }
38
  ],
39
  "logging_steps": 500,
40
- "max_steps": 565,
41
  "num_input_tokens_seen": 0,
42
- "num_train_epochs": 5,
43
  "save_steps": 500,
44
  "stateful_callbacks": {
45
  "TrainerControl": {
@@ -57,9 +57,9 @@
57
  "train_batch_size": 16,
58
  "trial_name": null,
59
  "trial_params": {
60
- "learning_rate": 5.117087338208196e-05,
61
- "num_train_epochs": 5,
62
  "per_device_train_batch_size": 16,
63
- "seed": 26
64
  }
65
  }
 
1
  {
2
+ "best_metric": 0.566,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-339",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5365,
14
+ "eval_loss": 0.6904081106185913,
15
+ "eval_runtime": 3.0555,
16
+ "eval_samples_per_second": 654.568,
17
+ "eval_steps_per_second": 40.911,
18
  "step": 113
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.5585,
23
+ "eval_loss": 0.6850683093070984,
24
+ "eval_runtime": 3.0686,
25
+ "eval_samples_per_second": 651.768,
26
+ "eval_steps_per_second": 40.736,
27
  "step": 226
28
  },
29
  {
30
  "epoch": 3.0,
31
+ "eval_accuracy": 0.566,
32
+ "eval_loss": 0.682464063167572,
33
+ "eval_runtime": 3.0696,
34
+ "eval_samples_per_second": 651.554,
35
+ "eval_steps_per_second": 40.722,
36
  "step": 339
37
  }
38
  ],
39
  "logging_steps": 500,
40
+ "max_steps": 452,
41
  "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
  "save_steps": 500,
44
  "stateful_callbacks": {
45
  "TrainerControl": {
 
57
  "train_batch_size": 16,
58
  "trial_name": null,
59
  "trial_params": {
60
+ "learning_rate": 1.02690913847536e-06,
61
+ "num_train_epochs": 4,
62
  "per_device_train_batch_size": 16,
63
+ "seed": 23
64
  }
65
  }
run-1/checkpoint-339/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c6cf6d62bd96276ddb153ee4c0dd1056bc0032dc430c2a812d2ddb559048838
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7521cb30664a0c20ab156d8ccb08d3894654e486488a3d8c1ca49fd6c3bb6cce
3
  size 5176
run-1/checkpoint-452/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:154f2101c856cbccfb878e5f3eacbf08836da49b72378256ca3a9750883c5f62
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0870a31707754bfeac7e3e8d04e99d49224029253e2174a88116bc80819f131
3
  size 433270768
run-1/checkpoint-452/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86f91a8bf6553db4ec3882722e929a6c46e4e715c4bf5235aa6d4dbec1d82c02
3
  size 866662650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d646f3ddfe62ab7efac66a9f87f2804809003b0360021825be8aa633a53a42d6
3
  size 866662650
run-1/checkpoint-452/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f881909abb23b2e3099c9e0661acd6821399279975a799a34d8332720a30e47
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c659cd779773853332b8e7d66e43cf0ed0a642262acb8cc747e9a6b40d95df4b
3
+ size 14244
run-1/checkpoint-452/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69ef9502aa958ebe24d637901acde06b87ace8757300727d422bd10689eed585
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ad936618aeadf9bc4263aa78c2ccb902a38e048e9c1b6647846fa46e1bee1e
3
  size 1064
run-1/checkpoint-452/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6075,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-452",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
@@ -10,45 +10,45 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5945,
14
- "eval_loss": 0.6746140718460083,
15
- "eval_runtime": 3.0608,
16
- "eval_samples_per_second": 653.432,
17
- "eval_steps_per_second": 40.84,
18
  "step": 113
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 0.5985,
23
- "eval_loss": 0.7479358315467834,
24
- "eval_runtime": 3.0745,
25
- "eval_samples_per_second": 650.511,
26
- "eval_steps_per_second": 40.657,
27
  "step": 226
28
  },
29
  {
30
  "epoch": 3.0,
31
- "eval_accuracy": 0.602,
32
- "eval_loss": 1.183725118637085,
33
- "eval_runtime": 3.1173,
34
- "eval_samples_per_second": 641.587,
35
- "eval_steps_per_second": 40.099,
36
  "step": 339
37
  },
38
  {
39
  "epoch": 4.0,
40
- "eval_accuracy": 0.6075,
41
- "eval_loss": 1.88389253616333,
42
- "eval_runtime": 3.1299,
43
- "eval_samples_per_second": 638.99,
44
- "eval_steps_per_second": 39.937,
45
  "step": 452
46
  }
47
  ],
48
  "logging_steps": 500,
49
- "max_steps": 565,
50
  "num_input_tokens_seen": 0,
51
- "num_train_epochs": 5,
52
  "save_steps": 500,
53
  "stateful_callbacks": {
54
  "TrainerControl": {
@@ -57,7 +57,7 @@
57
  "should_evaluate": false,
58
  "should_log": false,
59
  "should_save": true,
60
- "should_training_stop": false
61
  },
62
  "attributes": {}
63
  }
@@ -66,9 +66,9 @@
66
  "train_batch_size": 16,
67
  "trial_name": null,
68
  "trial_params": {
69
- "learning_rate": 5.117087338208196e-05,
70
- "num_train_epochs": 5,
71
  "per_device_train_batch_size": 16,
72
- "seed": 26
73
  }
74
  }
 
1
  {
2
+ "best_metric": 0.567,
3
  "best_model_checkpoint": "BERTForDetectingDepression-Twitter2020/run-1/checkpoint-452",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5365,
14
+ "eval_loss": 0.6904081106185913,
15
+ "eval_runtime": 3.0555,
16
+ "eval_samples_per_second": 654.568,
17
+ "eval_steps_per_second": 40.911,
18
  "step": 113
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.5585,
23
+ "eval_loss": 0.6850683093070984,
24
+ "eval_runtime": 3.0686,
25
+ "eval_samples_per_second": 651.768,
26
+ "eval_steps_per_second": 40.736,
27
  "step": 226
28
  },
29
  {
30
  "epoch": 3.0,
31
+ "eval_accuracy": 0.566,
32
+ "eval_loss": 0.682464063167572,
33
+ "eval_runtime": 3.0696,
34
+ "eval_samples_per_second": 651.554,
35
+ "eval_steps_per_second": 40.722,
36
  "step": 339
37
  },
38
  {
39
  "epoch": 4.0,
40
+ "eval_accuracy": 0.567,
41
+ "eval_loss": 0.6815997362136841,
42
+ "eval_runtime": 3.8675,
43
+ "eval_samples_per_second": 517.133,
44
+ "eval_steps_per_second": 32.321,
45
  "step": 452
46
  }
47
  ],
48
  "logging_steps": 500,
49
+ "max_steps": 452,
50
  "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
  "save_steps": 500,
53
  "stateful_callbacks": {
54
  "TrainerControl": {
 
57
  "should_evaluate": false,
58
  "should_log": false,
59
  "should_save": true,
60
+ "should_training_stop": true
61
  },
62
  "attributes": {}
63
  }
 
66
  "train_batch_size": 16,
67
  "trial_name": null,
68
  "trial_params": {
69
+ "learning_rate": 1.02690913847536e-06,
70
+ "num_train_epochs": 4,
71
  "per_device_train_batch_size": 16,
72
+ "seed": 23
73
  }
74
  }
run-1/checkpoint-452/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c6cf6d62bd96276ddb153ee4c0dd1056bc0032dc430c2a812d2ddb559048838
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7521cb30664a0c20ab156d8ccb08d3894654e486488a3d8c1ca49fd6c3bb6cce
3
  size 5176
runs/Aug01_13-43-54_1d376fbba8fb/events.out.tfevents.1722519987.1d376fbba8fb.194.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc4b66097638e14f8f243718197f2597e769023741421957fc78ffdc5b03425
3
+ size 6588
runs/Aug01_13-47-28_1d376fbba8fb/events.out.tfevents.1722520055.1d376fbba8fb.194.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2243461c027dec4399fcef4104be9ce3c227fac5e7a7d0a087ab611281f3030e
3
+ size 5614
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d38c6d6ebdd0f678d78aa49abbd1aaddd569cfb3e35dad0222aced730dc5d871
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e7886cec37e6d7adf3d7a1ca71b01930e812265faaa75a7daaaaac101d4154
3
  size 5176