UTCtwoNLP commited on
Commit
02bba7d
·
1 Parent(s): b99f134

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +48 -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 +58 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_position_embeddings": 258,
36
+ "model_type": "roberta",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "problem_type": "single_label_classification",
42
+ "tokenizer_class": "PhobertTokenizer",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.27.4",
45
+ "type_vocab_size": 1,
46
+ "use_cache": true,
47
+ "vocab_size": 64001
48
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217d338e5fa65f29e9136e3ad46f01941f4c8cd52c675e6c2e11dbed6c2ef4ac
3
+ size 1080147077
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c8bce1b6863c0016b072b2b53e1cad6b97910c70bb0e879d8e69a0e1a2cfba
3
+ size 540085941
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:356265a9874281eb36d92e31788523af525c71694148cf968e2bde5a55c8344c
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb8bbe9f6e4b8bfd523b11a292c8fadd28ef70f99285c02c6c49c797dabb862
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.679938744257274,
5
+ "global_step": 3500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.38,
12
+ "learning_rate": 5e-05,
13
+ "loss": 1.4269,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.77,
18
+ "learning_rate": 4.268578115857227e-05,
19
+ "loss": 0.8747,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.15,
24
+ "learning_rate": 3.537156231714453e-05,
25
+ "loss": 0.7293,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.53,
30
+ "learning_rate": 2.8057343475716798e-05,
31
+ "loss": 0.6426,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.91,
36
+ "learning_rate": 2.074312463428906e-05,
37
+ "loss": 0.5825,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 2.3,
42
+ "learning_rate": 1.3428905792861324e-05,
43
+ "loss": 0.4312,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 2.68,
48
+ "learning_rate": 6.1146869514335876e-06,
49
+ "loss": 0.3789,
50
+ "step": 3500
51
+ }
52
+ ],
53
+ "max_steps": 3918,
54
+ "num_train_epochs": 3,
55
+ "total_flos": 1309073265973200.0,
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:c4404ef01972e182ce80260d22dc9a1c64cda69edb1bf378972d467b932120bd
3
+ size 3707