Reza-Madani commited on
Commit
0dc714e
1 Parent(s): fcf7137

Training in progress, step 250

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
13
+ "0": "contradiction",
14
+ "1": "neutral",
15
+ "2": "entailment"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "contradiction": 0,
21
+ "entailment": 2,
22
+ "neutral": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.26.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
13
+ "0": "contradiction",
14
+ "1": "neutral",
15
+ "2": "entailment"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "contradiction": 0,
21
+ "entailment": 2,
22
+ "neutral": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.26.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5709e00dbd611de2274256964cc8798ad8e667a0e75c8530471d74375051e416
3
+ size 875994053
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d254a40d39c6a2146bb0841f9f5353c9d0d62cc0e6d1c95efecb9844d091f6b5
3
+ size 438010997
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7727806566005e936df3d19f11e78de8eaab1e83bb6e2e2c737e1c433f57c152
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0eb9c791cb4d366715877384e7b69911a7cb3bffde3499695e200a1433d2ac0
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.33003470301628113,
3
+ "best_model_checkpoint": "./esnli-label-predictor-bert-based/checkpoint-250",
4
+ "epoch": 0.4921259842519685,
5
+ "global_step": 250,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.49,
12
+ "learning_rate": 4.1797900262467194e-05,
13
+ "loss": 0.3644,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 0.49,
18
+ "eval_Accuracy": {
19
+ "accuracy": 0.8712660028449503
20
+ },
21
+ "eval_loss": 0.33003470301628113,
22
+ "eval_runtime": 5.1931,
23
+ "eval_samples_per_second": 1895.21,
24
+ "eval_steps_per_second": 3.851,
25
+ "step": 250
26
+ }
27
+ ],
28
+ "max_steps": 1524,
29
+ "num_train_epochs": 3,
30
+ "total_flos": 526226835456000.0,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087c5320a9b036f646ef9d81c37507472ec22b7dd399e1ff17d0b645c3a9e2f5
3
+ size 3515
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d254a40d39c6a2146bb0841f9f5353c9d0d62cc0e6d1c95efecb9844d091f6b5
3
+ size 438010997
runs/Feb05_22-59-29_7b2c5a261d79/1675637989.5853822/events.out.tfevents.1675637989.7b2c5a261d79.156.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b2dfd4bf9a3829a8522778410d590c846c1c59ae0e87bf3239f4bf2a69fe44
3
+ size 5734
runs/Feb05_22-59-29_7b2c5a261d79/events.out.tfevents.1675637989.7b2c5a261d79.156.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25007658bd97fbc404b0ce5d3806552c6f94b7a5d10afae30e7bf50b86263b65
3
+ size 4046
runs/Feb05_23-03-01_7b2c5a261d79/1675638314.814115/events.out.tfevents.1675638314.7b2c5a261d79.156.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a94e2c1350b13a977f0ecd157b192402e6a45bac66b0cba803bcf6d6e7cb1fe8
3
+ size 5734
runs/Feb05_23-03-01_7b2c5a261d79/events.out.tfevents.1675638314.7b2c5a261d79.156.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d1e8f9111108b0ceec57f1ca020f30a473e276bec621090b73fe0b2dca38f88
3
+ size 4095
runs/Feb05_23-05-35_7b2c5a261d79/1675638339.6712217/events.out.tfevents.1675638339.7b2c5a261d79.156.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73544436ab4f4146ca9f220b94fc9d8d36ab1899acc09cdabc78c2327f6be66
3
+ size 5734
runs/Feb05_23-05-35_7b2c5a261d79/events.out.tfevents.1675638339.7b2c5a261d79.156.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0396e33cb53f25dfd28802e274696abcce169ffd84e01742b20f61a6adca58
3
+ size 4523
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087c5320a9b036f646ef9d81c37507472ec22b7dd399e1ff17d0b645c3a9e2f5
3
+ size 3515