gchhablani commited on
Commit
f9bbdcf
1 Parent(s): e8df8de

Training in progress, epoch 3

Browse files
checkpoint-1869/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "rte",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "entailment",
16
+ "1": "not_entailment"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "entailment": 0,
22
+ "not_entailment": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.11.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-1869/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fd092b3dbba7392b7d3dec48c211de62c9250ed29845b707ae5badee1f348db
3
+ size 2668879261
checkpoint-1869/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd98ab7c062cf6d09ae971f775ce1954052e4fec65fd550594865dfe958a038
3
+ size 1334486957
checkpoint-1869/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005059942f55550ca2fdcc705756874455cd1f0e23815e0ec180051275d0278b
3
+ size 14503
checkpoint-1869/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2780fd14be91c71e9874620e45e474625b70b5f31dd07192fac262b87276483d
3
+ size 623
checkpoint-1869/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-1869/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1869/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-large-cased", "tokenizer_class": "BertTokenizer"}
checkpoint-1869/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 1869,
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": 1.3333333333333333e-05,
13
+ "loss": 0.6969,
14
+ "step": 623
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5342960288808665,
19
+ "eval_loss": 0.7039318680763245,
20
+ "eval_runtime": 9.0213,
21
+ "eval_samples_per_second": 30.705,
22
+ "eval_steps_per_second": 3.88,
23
+ "step": 623
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.5903,
29
+ "step": 1246
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.7184115523465704,
34
+ "eval_loss": 0.6461479663848877,
35
+ "eval_runtime": 8.9942,
36
+ "eval_samples_per_second": 30.798,
37
+ "eval_steps_per_second": 3.891,
38
+ "step": 1246
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.4557,
44
+ "step": 1869
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.6642599277978339,
49
+ "eval_loss": 1.5187355279922485,
50
+ "eval_runtime": 9.0028,
51
+ "eval_samples_per_second": 30.768,
52
+ "eval_steps_per_second": 3.888,
53
+ "step": 1869
54
+ }
55
+ ],
56
+ "max_steps": 1869,
57
+ "num_train_epochs": 3,
58
+ "total_flos": 6961527284060160.0,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-1869/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7d10d8668d1f1967ef4c4281a48895971354bd8101c64a0769eb783535687a
3
+ size 2799
checkpoint-1869/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:bf5f082d4c30792a01ac8c08f5cd852ec7b6e0571778d04dcd17e6d63e00020f
3
  size 1334486957
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd98ab7c062cf6d09ae971f775ce1954052e4fec65fd550594865dfe958a038
3
  size 1334486957
runs/Oct09_13-52-41_patrick-general-gpu/events.out.tfevents.1633787594.patrick-general-gpu.50676.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cf50ec445c0fbfaefb98643bf59132248df3767a7d95661e56b61227757d618
3
- size 4397
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c8993d0d6043c0a05392b7383e0c8af4d4d2ce5d2d3b0aaf32d8f1b8200016
3
+ size 4877