yunyus commited on
Commit
e8ec60a
·
verified ·
1 Parent(s): c3d3d11

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 sha256:4f9c5f4a099dfe9bc24db55b3a5ffe4c296f2f622fbe1f0c399e39a628ab0020
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8cb536bf79e94bea82e47c05257188d34ffa06a1d51188e7eaae013758e6d3
3
  size 437958648
run-8/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-8/checkpoint-78/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a835fc0e7ef159c1df113e13db93c9f54edf4f9a8e065bd55f369bcce0af1c7d
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8cb536bf79e94bea82e47c05257188d34ffa06a1d51188e7eaae013758e6d3
3
  size 437958648
run-8/checkpoint-78/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cf0a9f1477f66e21943110f49acca41926b475c84133cc24f661ef3ca6b2215
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dcfd3084b46d450349d859be2bc9939179e3bf7832d9c6dbeba21421a15d7bf
3
  size 876038394
run-8/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-8/checkpoint-78/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:665dedd5c3c2ebb68b64755541413fd3fb9fa477e0601f424cdd6be6a02a3db0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8815e09eebf590843da918ef4f4b9e162efdb053b9368fd69733b16433437f9
3
  size 1064
run-8/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-8/checkpoint-78/trainer_state.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "best_global_step": 39,
3
- "best_metric": 0.5342960288808665,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-8/checkpoint-39",
5
- "epoch": 2.0,
6
  "eval_steps": 500,
7
  "global_step": 78,
8
  "is_hyper_param_search": true,
@@ -11,25 +10,16 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.5342960288808665,
15
- "eval_loss": 0.6908717751502991,
16
- "eval_runtime": 1.9685,
17
- "eval_samples_per_second": 140.717,
18
- "eval_steps_per_second": 2.54,
19
- "step": 39
20
- },
21
- {
22
- "epoch": 2.0,
23
- "eval_accuracy": 0.5270758122743683,
24
- "eval_loss": 0.6904876232147217,
25
- "eval_runtime": 1.9797,
26
- "eval_samples_per_second": 139.92,
27
- "eval_steps_per_second": 2.526,
28
  "step": 78
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 117,
33
  "num_input_tokens_seen": 0,
34
  "num_train_epochs": 3,
35
  "save_steps": 500,
@@ -46,13 +36,13 @@
46
  }
47
  },
48
  "total_flos": 0,
49
- "train_batch_size": 64,
50
  "trial_name": null,
51
  "trial_params": {
52
- "dropout_rate": 0.34293444726782196,
53
- "learning_rate": 9.002340084037376e-06,
54
- "max_seq_length": 256,
55
  "num_train_epochs": 3,
56
- "per_device_train_batch_size": 64
57
  }
58
  }
 
1
  {
2
+ "best_metric": 0.5415162454873647,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-8/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": 0.5415162454873647,
14
+ "eval_loss": 0.6883169412612915,
15
+ "eval_runtime": 0.7604,
16
+ "eval_samples_per_second": 364.306,
17
+ "eval_steps_per_second": 11.837,
 
 
 
 
 
 
 
 
 
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,
 
36
  }
37
  },
38
  "total_flos": 0,
39
+ "train_batch_size": 32,
40
  "trial_name": null,
41
  "trial_params": {
42
+ "dropout_rate": 0.3667117294878569,
43
+ "learning_rate": 1.2518263409353602e-05,
44
+ "max_seq_length": 32,
45
  "num_train_epochs": 3,
46
+ "per_device_train_batch_size": 32
47
  }
48
  }
run-8/checkpoint-78/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0700a167b6e74e336c767640e8ddec156e025d797cb99c1bdd6c0819e5b0d1f1
3
- size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f34a4ba9d363996796172c4079d7b53234858e152885ed794144295366d369
3
+ size 5240
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08e2a2a4d379d09164306b95a4c3d156e6b668af97fc2d5e808d2935986cbf97
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f34a4ba9d363996796172c4079d7b53234858e152885ed794144295366d369
3
  size 5240