gchhablani commited on
Commit
584157c
1 Parent(s): 306e9cc

Training in progress, epoch 5

Browse files
checkpoint-1150/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-1150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f254c5404d3833932a4004b03dfd35dc1dc07ebd0413060508e7912873fca8
3
+ size 866610973
checkpoint-1150/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa5d9dd2528952def71f866b05166fdbc8f697f69e0c0ce1b99429b369149bb
3
+ size 433331373
checkpoint-1150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2441cff2d79c2f95778be91088706e3936e5f0ade6204f40fbae3cc614dac5d3
3
+ size 14503
checkpoint-1150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d59441f08c42483b29933513683055a9830b6b0f5f682588da8f3b8a6e40bc9
3
+ size 623
checkpoint-1150/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-1150/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1150/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-1150/trainer_state.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 1150,
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
+ "epoch": 4.0,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 0.1286,
65
+ "step": 920
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.8529411764705882,
70
+ "eval_combined_score": 0.8757949125596185,
71
+ "eval_f1": 0.8986486486486487,
72
+ "eval_loss": 0.6342187523841858,
73
+ "eval_runtime": 4.165,
74
+ "eval_samples_per_second": 97.959,
75
+ "eval_steps_per_second": 12.245,
76
+ "step": 920
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "learning_rate": 0.0,
81
+ "loss": 0.0812,
82
+ "step": 1150
83
+ },
84
+ {
85
+ "epoch": 5.0,
86
+ "eval_accuracy": 0.8602941176470589,
87
+ "eval_combined_score": 0.8814291101055808,
88
+ "eval_f1": 0.9025641025641027,
89
+ "eval_loss": 0.7132137417793274,
90
+ "eval_runtime": 4.1564,
91
+ "eval_samples_per_second": 98.161,
92
+ "eval_steps_per_second": 12.27,
93
+ "step": 1150
94
+ }
95
+ ],
96
+ "max_steps": 1150,
97
+ "num_train_epochs": 5,
98
+ "total_flos": 4825456755302400.0,
99
+ "trial_name": null,
100
+ "trial_params": null
101
+ }
checkpoint-1150/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-1150/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:ffc0e9faca4eef0d93b0e47c10f4ccd967150c7f0974c64dace7265c554bf767
3
  size 433331373
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa5d9dd2528952def71f866b05166fdbc8f697f69e0c0ce1b99429b369149bb
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 sha256:1570720fe1bebd27a5dab278309a24fd10d7e0275157509748a4b43fa082c7c2
3
- size 5582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a12084a94ab8c6c0ce3e6c8493208c9c5f8e2d395018b431b36193d968fddc
3
+ size 6166