Silicon23 commited on
Commit
90fbc90
·
verified ·
1 Parent(s): 6793279

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3acc66ee228a8fbaec1ea30a8cc721d05dae8b55d25d5c9b87dff31e5fa8b625
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da18c3fa8ea96c13af4d5f98dbf8935021e542534576bc4c153e1976de88f64b
3
  size 437958648
run-4/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-4/checkpoint-46/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298c29a27bea4ed75274a9dad896ba67db1e3b78ba7a0bc42efbe78080deb72f
3
+ size 437958648
run-4/checkpoint-46/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd49be535e94784007798c5162da46871dbfb58bff81eb77cf8e3a288eeb1bd
3
+ size 876038394
run-4/checkpoint-46/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b190ac61b1eecd7eb6b78a6bccf694711c89211ce4044b515f5b81bcd9c64a
3
+ size 14244
run-4/checkpoint-46/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5708018fef3b14dfacc0064218bf41fc67c92462946c220bf66cf233f871b9be
3
+ size 1064
run-4/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-4/checkpoint-46/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-46/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6421117249846532,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-4/checkpoint-46",
4
+ "epoch": 2.0,
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": 0.5979128299570289,
14
+ "eval_loss": 0.678537905216217,
15
+ "eval_runtime": 1.4893,
16
+ "eval_samples_per_second": 1093.811,
17
+ "eval_steps_per_second": 68.489,
18
+ "step": 23
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6421117249846532,
23
+ "eval_loss": 0.6587366461753845,
24
+ "eval_runtime": 1.4751,
25
+ "eval_samples_per_second": 1104.331,
26
+ "eval_steps_per_second": 69.148,
27
+ "step": 46
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 69,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
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": 64,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 2.9236721941091785e-06,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 64,
54
+ "seed": 12
55
+ }
56
+ }
run-4/checkpoint-46/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e5d749933754adfcd491676d87575b65895093b05afc38cb0180cdd1806f56
3
+ size 5176
run-4/checkpoint-46/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-69/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-69/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf7853d4f3c61357d09f38af8d17aa2f513c13cd2f7bd8e73c6961dde48ed90
3
+ size 437958648
run-4/checkpoint-69/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe2bb5b3275b3a38337cc71d7a8178fb06d832c82238678b3c6afeb3393db02
3
+ size 876038394
run-4/checkpoint-69/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7adfd811036d4575382aaed52f6afcb6f1087ba61b09bac36d765927d103a6
3
+ size 14244
run-4/checkpoint-69/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ca9b9d17ea0836d5398bcff217245a50c839abc4b42a1ca31d503150df6528
3
+ size 1064
run-4/checkpoint-69/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-69/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-69/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-69/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6507059545733579,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-4/checkpoint-69",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 69,
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": 0.5979128299570289,
14
+ "eval_loss": 0.678537905216217,
15
+ "eval_runtime": 1.4893,
16
+ "eval_samples_per_second": 1093.811,
17
+ "eval_steps_per_second": 68.489,
18
+ "step": 23
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6421117249846532,
23
+ "eval_loss": 0.6587366461753845,
24
+ "eval_runtime": 1.4751,
25
+ "eval_samples_per_second": 1104.331,
26
+ "eval_steps_per_second": 69.148,
27
+ "step": 46
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.6507059545733579,
32
+ "eval_loss": 0.6499518752098083,
33
+ "eval_runtime": 1.5227,
34
+ "eval_samples_per_second": 1069.784,
35
+ "eval_steps_per_second": 66.985,
36
+ "step": 69
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 69,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
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": true
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 0,
57
+ "train_batch_size": 64,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "learning_rate": 2.9236721941091785e-06,
61
+ "num_train_epochs": 3,
62
+ "per_device_train_batch_size": 64,
63
+ "seed": 12
64
+ }
65
+ }
run-4/checkpoint-69/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e5d749933754adfcd491676d87575b65895093b05afc38cb0180cdd1806f56
3
+ size 5176
run-4/checkpoint-69/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-92/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:975944110fa6326aea232898b2ce384b5fff1af434fd96aa6f0d579b4f875527
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da18c3fa8ea96c13af4d5f98dbf8935021e542534576bc4c153e1976de88f64b
3
  size 437958648
run-5/checkpoint-92/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:057c3ecfbe40bffdf67d0f00daee6e5302a94725bdb19677f2d5cc4ab2b12519
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15fb97122455de4b8961e6e812cef5e6d990e3b0aef0652093098c49f83619b
3
  size 876038394
run-5/checkpoint-92/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86aed83f8da1bd90948eb859a732fc9082b84d5e32bde7d68ef91fd6e85b7b24
3
- size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:929a0a7f9803b35619759b490758b16cc6d9139610faeaece3fb350b2ccea6ad
3
+ size 14244
run-5/checkpoint-92/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4defbf2b46425c82b5df121f300464ec43d6a65e8d8b5e27db5803ec6cd3a013
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9398b58a2b955f56898bc87bf8158fff4f7213ae492c555d57bded8867f7a80
3
  size 1064
run-5/checkpoint-92/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.8164518109269491,
3
- "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-5/checkpoint-46",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 92,
7
  "is_hyper_param_search": true,
@@ -10,27 +10,18 @@
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
- "epoch": 2.0,
22
- "eval_accuracy": 0.8017188459177409,
23
- "eval_loss": 0.4937798082828522,
24
- "eval_runtime": 1.5222,
25
- "eval_samples_per_second": 1070.181,
26
- "eval_steps_per_second": 67.01,
27
  "step": 92
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 138,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 3,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "TrainerControl": {
@@ -45,12 +36,12 @@
45
  }
46
  },
47
  "total_flos": 0,
48
- "train_batch_size": 32,
49
  "trial_name": null,
50
  "trial_params": {
51
- "learning_rate": 4.628285992582947e-05,
52
- "num_train_epochs": 3,
53
- "per_device_train_batch_size": 32,
54
- "seed": 8
55
  }
56
  }
 
1
  {
2
+ "best_metric": 0.8410067526089625,
3
+ "best_model_checkpoint": "BERTForDetectingDepression-Twitter2015/run-5/checkpoint-92",
4
+ "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 92,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.8410067526089625,
14
+ "eval_loss": 0.36238893866539,
15
+ "eval_runtime": 1.458,
16
+ "eval_samples_per_second": 1117.304,
17
+ "eval_steps_per_second": 69.96,
 
 
 
 
 
 
 
 
 
18
  "step": 92
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 184,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
 
36
  }
37
  },
38
  "total_flos": 0,
39
+ "train_batch_size": 16,
40
  "trial_name": null,
41
  "trial_params": {
42
+ "learning_rate": 7.022911988641232e-05,
43
+ "num_train_epochs": 2,
44
+ "per_device_train_batch_size": 16,
45
+ "seed": 15
46
  }
47
  }
run-5/checkpoint-92/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee006133791165a4f0fc0592cf175ac51fbb54421547bf7e28eb59d0544133f8
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11aee48452ba775f2d3bcdbe6ebb37d62ffd3ed7a367e24b16014f0a7e85bb4e
3
  size 5176
runs/Aug02_03-09-56_8953887c6028/events.out.tfevents.1722568742.8953887c6028.1235.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c63c88fbc10603c87272f4f873db66b0b398407d873a878aa62b5dc38e96440d
3
+ size 5917
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20e5d749933754adfcd491676d87575b65895093b05afc38cb0180cdd1806f56
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11aee48452ba775f2d3bcdbe6ebb37d62ffd3ed7a367e24b16014f0a7e85bb4e
3
  size 5176