Ubuntu commited on
Commit
1503cf4
1 Parent(s): bf1aba6

initial upload

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.9655963302752294,
4
+ "eval_loss": 0.16654755175113678,
5
+ "eval_runtime": 4.0649,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 214.521,
8
+ "eval_steps_per_second": 3.444,
9
+ "train_loss": 0.09133690474209961,
10
+ "train_runtime": 2940.2636,
11
+ "train_samples": 67349,
12
+ "train_samples_per_second": 229.058,
13
+ "train_steps_per_second": 1.194
14
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/electra-large-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "embedding_size": 1024,
8
+ "finetuning_task": "sst2",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "electra",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "summary_activation": "gelu",
23
+ "summary_last_dropout": 0.1,
24
+ "summary_type": "first",
25
+ "summary_use_proj": true,
26
+ "transformers_version": "4.7.0.dev0",
27
+ "type_vocab_size": 2,
28
+ "vocab_size": 30522
29
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.9655963302752294,
4
+ "eval_loss": 0.16654755175113678,
5
+ "eval_runtime": 4.0649,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 214.521,
8
+ "eval_steps_per_second": 3.444
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fd91dd37bb6403778e2affc37a884a7c0ad2977d42e174f81d2dcb63f6fea2
3
+ size 1340745303
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-large-discriminator"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.09133690474209961,
4
+ "train_runtime": 2940.2636,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 229.058,
7
+ "train_steps_per_second": 1.194
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 3510,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.42,
12
+ "learning_rate": 1.7150997150997152e-05,
13
+ "loss": 0.287,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 2.85,
18
+ "learning_rate": 1.4301994301994305e-05,
19
+ "loss": 0.157,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 4.27,
24
+ "learning_rate": 1.1452991452991454e-05,
25
+ "loss": 0.0685,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 5.7,
30
+ "learning_rate": 8.603988603988605e-06,
31
+ "loss": 0.0477,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 7.12,
36
+ "learning_rate": 5.7549857549857555e-06,
37
+ "loss": 0.0332,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 8.55,
42
+ "learning_rate": 2.9059829059829063e-06,
43
+ "loss": 0.0257,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 9.97,
48
+ "learning_rate": 5.6980056980056986e-08,
49
+ "loss": 0.0215,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 10.0,
54
+ "step": 3510,
55
+ "total_flos": 1.7334995773718016e+17,
56
+ "train_loss": 0.09133690474209961,
57
+ "train_runtime": 2940.2636,
58
+ "train_samples_per_second": 229.058,
59
+ "train_steps_per_second": 1.194
60
+ }
61
+ ],
62
+ "max_steps": 3510,
63
+ "num_train_epochs": 10,
64
+ "total_flos": 1.7334995773718016e+17,
65
+ "trial_name": null,
66
+ "trial_params": null
67
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83170ad5d7c040b8504983bbc10a4919b9c660a14e9155380147868ab013bf1
3
+ size 2479
vocab.txt ADDED
The diff for this file is too large to render. See raw diff