rkumar38 commited on
Commit
cf6f192
·
1 Parent(s): 27f0193

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +27 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +64 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.27.1",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa19db4c4163355e28ef3abf1281c07fcfaf755a9eed3bd4fdc509d084ff1942
3
+ size 875988101
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af537c00eebbec767aeeb3c9bb5f8c5986d7e1c1aa5c923e2a69bed0a51c54c2
3
+ size 438007925
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733cef6cd52cc133a43582bff011fe1aee80e121fc80d6092cfeb79c85b9de91
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732b2ad3a37ae5f8331460bd41e606278e934a6513f42679d4c9a75c3147dc70
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.89086859688196,
5
+ "global_step": 4000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 4.443207126948775e-05,
13
+ "loss": 0.1035,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.22,
18
+ "learning_rate": 3.88641425389755e-05,
19
+ "loss": 0.0611,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.33,
24
+ "learning_rate": 3.329621380846326e-05,
25
+ "loss": 0.0413,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.45,
30
+ "learning_rate": 2.7728285077951005e-05,
31
+ "loss": 0.0259,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.56,
36
+ "learning_rate": 2.2160356347438754e-05,
37
+ "loss": 0.0356,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.67,
42
+ "learning_rate": 1.6592427616926504e-05,
43
+ "loss": 0.0151,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.78,
48
+ "learning_rate": 1.1024498886414254e-05,
49
+ "loss": 0.0163,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.89,
54
+ "learning_rate": 5.456570155902005e-06,
55
+ "loss": 0.0187,
56
+ "step": 4000
57
+ }
58
+ ],
59
+ "max_steps": 4490,
60
+ "num_train_epochs": 1,
61
+ "total_flos": 8419553771520000.0,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8673a136631df6aee605beca72d04584811f17cd71a716a53fb9728d02f96bdf
3
+ size 3515