avichr commited on
Commit
c39a3a2
1 Parent(s): daade66
Files changed (4) hide show
  1. config.json +21 -0
  2. log_history.json +23 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "gradient_checkpointing": false,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "total_flos": 6997313242916978688,
19
+ "type_vocab_size": 2,
20
+ "vocab_size": 30522
21
+ }
log_history.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "loss": 0.31480342864990235,
4
+ "learning_rate": 1e-05,
5
+ "epoch": 3.8461538461538463,
6
+ "total_flos": 625010043468600,
7
+ "step": 100
8
+ },
9
+ {
10
+ "loss": 0.04049484252929687,
11
+ "learning_rate": 2e-05,
12
+ "epoch": 7.6923076923076925,
13
+ "total_flos": 1248147914333400,
14
+ "step": 200
15
+ },
16
+ {
17
+ "loss": 0.009078407287597656,
18
+ "learning_rate": 3e-05,
19
+ "epoch": 11.538461538461538,
20
+ "total_flos": 1871285785198200,
21
+ "step": 300
22
+ }
23
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee12aa7fbf47a7e10133f34b4f7415e643189aec33aebd27eb6545d0d8b3259
3
+ size 438024063
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea538a3d4dddab2f4dc91b7b95b0e7ffa55cb9fe7372783ed970f71a1967f148
3
+ size 1775