usmiva commited on
Commit
ce1459b
1 Parent(s): 2ddb463

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +26 -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 +91 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/ivamarinova/bg-news-bert/",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.22.0.dev0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30001
26
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993b9cf72dad14dc5045d358035d3852573270e6374e90370368c1078d18f0c7
3
+ size 872785693
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6cefcae1006d177246e3469c115be6bc4bcbdbdeecb4f74d3450a147e7351a
3
+ size 436405613
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1547f55650dd63c4662e18dc52734c102f0d028ec91e87eda18614015b220744
3
+ size 15523
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbcc93d01a13e0c646f5fc8cae7e952c1acffd792acf63d73fd139e87ef49824
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 2500,
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": 4e-05,
13
+ "loss": 0.2585,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.9453883495145631,
19
+ "eval_loss": 0.15823796391487122,
20
+ "eval_runtime": 7.4369,
21
+ "eval_samples_per_second": 110.799,
22
+ "eval_steps_per_second": 6.992,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 3e-05,
28
+ "loss": 0.1304,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.9550970873786407,
34
+ "eval_loss": 0.13580937683582306,
35
+ "eval_runtime": 7.422,
36
+ "eval_samples_per_second": 111.021,
37
+ "eval_steps_per_second": 7.006,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 2e-05,
43
+ "loss": 0.0571,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.9526699029126213,
49
+ "eval_loss": 0.2397720217704773,
50
+ "eval_runtime": 7.3747,
51
+ "eval_samples_per_second": 111.733,
52
+ "eval_steps_per_second": 7.051,
53
+ "step": 1500
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 1e-05,
58
+ "loss": 0.0261,
59
+ "step": 2000
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.9757281553398058,
64
+ "eval_loss": 0.10911418497562408,
65
+ "eval_runtime": 7.4257,
66
+ "eval_samples_per_second": 110.966,
67
+ "eval_steps_per_second": 7.003,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 0.0,
73
+ "loss": 0.008,
74
+ "step": 2500
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_accuracy": 0.9684466019417476,
79
+ "eval_loss": 0.15623603761196136,
80
+ "eval_runtime": 7.4414,
81
+ "eval_samples_per_second": 110.732,
82
+ "eval_steps_per_second": 6.988,
83
+ "step": 2500
84
+ }
85
+ ],
86
+ "max_steps": 2500,
87
+ "num_train_epochs": 5,
88
+ "total_flos": 1.05244422144e+16,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1157799575a37dbb70a6406c3cda0e47c63629b478cddb7ba4b06edc9ec520b
3
+ size 3375