rklra commited on
Commit
b554f5e
1 Parent(s): 22ed57b

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +37 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scaler.pt +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +58 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
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": 28996
37
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:314c9fea51c07a31a66a3ad3b5b5e7ab486ecffd217e59ff035f021dd86054a1
3
+ size 1424197
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123294f9606a0a96575881ca426657234b95ebef15c45c5e1a01690ea95982fe
3
+ size 433323125
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49fe540ce12c6b9481c3596116f05d0cfec3f0650c21f7cfc5110623095a3751
3
+ size 14575
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2de9749828adacdf103bf6e9592702bb7067a2c1df27dd62ab38c1eb8c070f
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c306ba04c700d3e7f2d7034d2dc42afc0bff2bfad5f0f234856e49516a97c40
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.6666666666666665,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.67,
12
+ "learning_rate": 3.888888888888889e-05,
13
+ "loss": 1.1251,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.37733333333333335,
19
+ "eval_loss": 1.070645809173584,
20
+ "eval_runtime": 18.1804,
21
+ "eval_samples_per_second": 165.013,
22
+ "eval_steps_per_second": 20.627,
23
+ "step": 750
24
+ },
25
+ {
26
+ "epoch": 1.33,
27
+ "learning_rate": 2.777777777777778e-05,
28
+ "loss": 1.0949,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "learning_rate": 1.6666666666666667e-05,
34
+ "loss": 0.898,
35
+ "step": 1500
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6836666666666666,
40
+ "eval_loss": 0.7851265668869019,
41
+ "eval_runtime": 18.6689,
42
+ "eval_samples_per_second": 160.695,
43
+ "eval_steps_per_second": 20.087,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 2.67,
48
+ "learning_rate": 5.555555555555556e-06,
49
+ "loss": 0.671,
50
+ "step": 2000
51
+ }
52
+ ],
53
+ "max_steps": 2250,
54
+ "num_train_epochs": 3,
55
+ "total_flos": 2104907341824000.0,
56
+ "trial_name": null,
57
+ "trial_params": null
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bddec996b3381160833f13136aefacec8fbb0f32de91ca33e1918505c082c6
3
+ size 3515