jaimin commited on
Commit
c09b423
·
1 Parent(s): afdc7c3

Update from $USER

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 +52 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "asafaya/bert-base-arabic",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
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
+ "output_past": true,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.9.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b49d4e673905a23b0e1bfeda891b7b4b27cf015bb6dab79fb6c020fd88b592e
3
+ size 885067549
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd6ffcaaf98677b2317f700b4be4e0b33f3fbc577a66161409cd5b1679f1d84
3
+ size 442559661
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8114b7e0a0aac95e7cd590781366c27aa66079faa55fcbea59911f7a793bd09e
3
+ size 14439
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ffd0c4b96e41079c6001d827a8e9afcba808242858d2b1d92ac94ca6313c63
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.06682556300536832,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.98143734360962e-05,
13
+ "loss": 0.0,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 4.96287468721924e-05,
19
+ "loss": 0.0,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 4.94431203082886e-05,
25
+ "loss": 0.0,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 4.92574937443848e-05,
31
+ "loss": 0.0,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 4.907186718048099e-05,
37
+ "loss": 0.0,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.07,
42
+ "learning_rate": 4.888624061657719e-05,
43
+ "loss": 0.0,
44
+ "step": 3000
45
+ }
46
+ ],
47
+ "max_steps": 134679,
48
+ "num_train_epochs": 3,
49
+ "total_flos": 6314665328640000.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f5d7f5a49d1dcb6cdf44ccb2677022c5b57c59e765f50872daf6741c0ef725
3
+ size 2671