gchhablani commited on
Commit
4d453c2
1 Parent(s): 4e87dde

Training in progress, epoch 3

Browse files
checkpoint-690/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "mrpc",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "not_equivalent",
15
+ "1": "equivalent"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "equivalent": 1,
21
+ "not_equivalent": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.11.0.dev0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 28996
36
+ }
checkpoint-690/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44333210a41f8f722a14c634c132a6971c7505fded43615215c51b68d423ca20
3
+ size 866610973
checkpoint-690/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fabae069113093bf77363be8d61ecf606460e2e1aad081ad6a4d49e997ec672
3
+ size 433331373
checkpoint-690/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f0fbfcf3d17fc9addecbbd47e7c29d55cdda8c9cff807dc50dcddef421176d8
3
+ size 14503
checkpoint-690/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0cf3ce8e7365e59eba2550cf0339839704f78b96897c1e66c20f680f3730989
3
+ size 623
checkpoint-690/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-690/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-690/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
checkpoint-690/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 690,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.6000000000000003e-05,
13
+ "loss": 0.5981,
14
+ "step": 230
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7892156862745098,
19
+ "eval_combined_score": 0.8227014886222047,
20
+ "eval_f1": 0.8561872909698997,
21
+ "eval_loss": 0.45800894498825073,
22
+ "eval_runtime": 4.1966,
23
+ "eval_samples_per_second": 97.221,
24
+ "eval_steps_per_second": 12.153,
25
+ "step": 230
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 1.2e-05,
30
+ "loss": 0.3739,
31
+ "step": 460
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.8480392156862745,
36
+ "eval_combined_score": 0.8711185839523523,
37
+ "eval_f1": 0.89419795221843,
38
+ "eval_loss": 0.38060691952705383,
39
+ "eval_runtime": 4.1663,
40
+ "eval_samples_per_second": 97.928,
41
+ "eval_steps_per_second": 12.241,
42
+ "step": 460
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 8.000000000000001e-06,
47
+ "loss": 0.1991,
48
+ "step": 690
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8529411764705882,
53
+ "eval_combined_score": 0.8743872549019608,
54
+ "eval_f1": 0.8958333333333334,
55
+ "eval_loss": 0.4879474937915802,
56
+ "eval_runtime": 4.1609,
57
+ "eval_samples_per_second": 98.056,
58
+ "eval_steps_per_second": 12.257,
59
+ "step": 690
60
+ }
61
+ ],
62
+ "max_steps": 1150,
63
+ "num_train_epochs": 5,
64
+ "total_flos": 2895274053181440.0,
65
+ "trial_name": null,
66
+ "trial_params": null
67
+ }
checkpoint-690/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8281bedb20092f0f04f54b17beca2ef4df4174a4f98ca39b9bf37f14eac3ae9
3
+ size 2799
checkpoint-690/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:965d23effd7512f42278b810a84a409210dd8e32d685053be959c109af316e2e
3
  size 433331373
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fabae069113093bf77363be8d61ecf606460e2e1aad081ad6a4d49e997ec672
3
  size 433331373
runs/Sep16_16-48-11_patrick-general-gpu/events.out.tfevents.1631810908.patrick-general-gpu.172718.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb3b565cba8d5deb5daf3ef1fa0ef067e1b9e32dadd7e958f5013ae9eb76e3a9
3
- size 4414
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ff62853c23f71bb9ec7bbc8f8b73704f7e6dd5089af01b7a620a147287aff9
3
+ size 4998