yunyus commited on
Commit
2696760
·
verified ·
1 Parent(s): fac6c9d

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 sha256:1764b411aa7222c07ffe81e7c2146ce5d5865aad2f0edddc2cf2d7baaf830015
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d78cab325391021ee719642bbdf50381f04c6d2732a045b119e940c6bf2c659
3
  size 437958648
run-7/checkpoint-156/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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": "4.44.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-7/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd08f199b9ecac6f33381c79e146bf8f92f781026867ec4426fccd572cf45b60
3
+ size 437958648
run-7/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97089eecfc25df7943afe3cd6bce6e82922ae6af61dc683ac2d7b3e46375361
3
+ size 876038394
run-7/checkpoint-156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b06d22713ab0eccf6163f8b0ec7376abad69fdc0b947461e0b301173cdd320
3
+ size 14244
run-7/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df9796af3a82a20c7a2b9409918852b946ebc075075c8380403ea3f3439f264
3
+ size 1064
run-7/checkpoint-156/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-7/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-156/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-7/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6064981949458483,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-7/checkpoint-156",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 156,
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": 0.5812274368231047,
14
+ "eval_loss": 0.6901144981384277,
15
+ "eval_runtime": 0.6674,
16
+ "eval_samples_per_second": 415.066,
17
+ "eval_steps_per_second": 13.486,
18
+ "step": 78
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6064981949458483,
23
+ "eval_loss": 0.6823810935020447,
24
+ "eval_runtime": 0.6842,
25
+ "eval_samples_per_second": 404.827,
26
+ "eval_steps_per_second": 13.153,
27
+ "step": 156
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 156,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
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": true
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 0,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "dropout_rate": 0.14341458699848886,
52
+ "learning_rate": 8.474768574918493e-06,
53
+ "max_seq_length": 128,
54
+ "num_train_epochs": 2,
55
+ "per_device_train_batch_size": 32
56
+ }
57
+ }
run-7/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801b5d5c5e0cdbcffde90e82eff54251ea0c570ab81c1446d0c0b6353aabd6d1
3
+ size 5240
run-7/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-78/config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "BertForSequenceClassification"
4
  ],
@@ -19,7 +20,7 @@
19
  "position_embedding_type": "absolute",
20
  "problem_type": "single_label_classification",
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.50.3",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
25
  "vocab_size": 30522
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 30522
run-9/checkpoint-78/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed052aeed3f11a4b60e7fd22b5a66d76183c967af6b758053670d062cf1203cc
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d78cab325391021ee719642bbdf50381f04c6d2732a045b119e940c6bf2c659
3
  size 437958648
run-9/checkpoint-78/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2946f970582758a623b5eae4e4d41a475dfbe6d5f4c6b25306c59017b95addde
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6860d48aa2bebf5b7c831f4b960b9a5be527a934862cc4e72c73f89c3cfecfe
3
  size 876038394
run-9/checkpoint-78/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2359103b6aecc5a33be9630634e2521d802ca571eca1b4adeac3ec6496c46f19
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd53c5c3dd7d411230f105bda2473d2a3923ae5b6e14f965bb99d91f5a28c9b2
3
  size 14244
run-9/checkpoint-78/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d20ee9edd9925c00e05c85eaa0a21b58f8855178996cba0ba4942c9415b7710c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645ff7660bf29ad45263561a9fb2f69928f570b46ec13d525960e6341412781a
3
  size 1064
run-9/checkpoint-78/tokenizer_config.json CHANGED
@@ -41,10 +41,9 @@
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
- "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
  "pad_token": "[PAD]",
 
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]",
run-9/checkpoint-78/trainer_state.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "best_global_step": 39,
3
- "best_metric": 0.4729241877256318,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-39",
5
- "epoch": 2.0,
6
  "eval_steps": 500,
7
  "global_step": 78,
8
  "is_hyper_param_search": true,
@@ -11,27 +10,18 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.4729241877256318,
15
- "eval_loss": 0.7208108901977539,
16
- "eval_runtime": 2.0113,
17
- "eval_samples_per_second": 137.72,
18
- "eval_steps_per_second": 2.486,
19
- "step": 39
20
- },
21
- {
22
- "epoch": 2.0,
23
- "eval_accuracy": 0.4693140794223827,
24
- "eval_loss": 0.717487633228302,
25
- "eval_runtime": 2.0543,
26
- "eval_samples_per_second": 134.842,
27
- "eval_steps_per_second": 2.434,
28
  "step": 78
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 78,
33
  "num_input_tokens_seen": 0,
34
- "num_train_epochs": 2,
35
  "save_steps": 500,
36
  "stateful_callbacks": {
37
  "TrainerControl": {
@@ -40,19 +30,19 @@
40
  "should_evaluate": false,
41
  "should_log": false,
42
  "should_save": true,
43
- "should_training_stop": true
44
  },
45
  "attributes": {}
46
  }
47
  },
48
  "total_flos": 0,
49
- "train_batch_size": 64,
50
  "trial_name": null,
51
  "trial_params": {
52
- "dropout_rate": 0.2684169145768369,
53
- "learning_rate": 1.481500826666273e-06,
54
  "max_seq_length": 64,
55
- "num_train_epochs": 2,
56
- "per_device_train_batch_size": 64
57
  }
58
  }
 
1
  {
2
+ "best_metric": 0.6064981949458483,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-78",
4
+ "epoch": 1.0,
 
5
  "eval_steps": 500,
6
  "global_step": 78,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6064981949458483,
14
+ "eval_loss": 0.6529371738433838,
15
+ "eval_runtime": 0.696,
16
+ "eval_samples_per_second": 397.999,
17
+ "eval_steps_per_second": 12.931,
 
 
 
 
 
 
 
 
 
18
  "step": 78
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 234,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
 
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
+ "dropout_rate": 0.2892402615402374,
43
+ "learning_rate": 3.773085262586205e-05,
44
  "max_seq_length": 64,
45
+ "num_train_epochs": 3,
46
+ "per_device_train_batch_size": 32
47
  }
48
  }
run-9/checkpoint-78/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44a07a14f8d822acb854025696a4756c71c914ef6c94583f3ef9e20a9ad193e5
3
- size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d194138e61b5f886e352871a7e47275b103df8c119f4a23897fd240d2849d429
3
+ size 5240
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:801b5d5c5e0cdbcffde90e82eff54251ea0c570ab81c1446d0c0b6353aabd6d1
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d194138e61b5f886e352871a7e47275b103df8c119f4a23897fd240d2849d429
3
  size 5240