Ubuntu commited on
Commit
aaa0c06
1 Parent(s): 4f5d5a0

initial upload

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.9469156141314297,
4
+ "eval_loss": 0.37976524233818054,
5
+ "eval_runtime": 24.7324,
6
+ "eval_samples": 5463,
7
+ "eval_samples_per_second": 220.885,
8
+ "eval_steps_per_second": 3.477,
9
+ "train_loss": 0.07572162915498783,
10
+ "train_runtime": 4508.6421,
11
+ "train_samples": 104743,
12
+ "train_samples_per_second": 232.316,
13
+ "train_steps_per_second": 1.211
14
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "qnli",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "transformers_version": "4.7.0.dev0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.9469156141314297,
4
+ "eval_loss": 0.37976524233818054,
5
+ "eval_runtime": 24.7324,
6
+ "eval_samples": 5463,
7
+ "eval_samples_per_second": 220.885,
8
+ "eval_steps_per_second": 3.477
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4470ab1548631d2262e437a592213f60420186c41843c59874df722c7534329a
3
+ size 1421616720
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.07572162915498783,
4
+ "train_runtime": 4508.6421,
5
+ "train_samples": 104743,
6
+ "train_samples_per_second": 232.316,
7
+ "train_steps_per_second": 1.211
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 5460,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.92,
12
+ "learning_rate": 1.816849816849817e-05,
13
+ "loss": 0.2816,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.83,
18
+ "learning_rate": 1.633699633699634e-05,
19
+ "loss": 0.1677,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.75,
24
+ "learning_rate": 1.4505494505494506e-05,
25
+ "loss": 0.114,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 3.66,
30
+ "learning_rate": 1.2673992673992674e-05,
31
+ "loss": 0.0777,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 4.58,
36
+ "learning_rate": 1.0842490842490842e-05,
37
+ "loss": 0.0569,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 5.49,
42
+ "learning_rate": 9.010989010989011e-06,
43
+ "loss": 0.04,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 6.41,
48
+ "learning_rate": 7.17948717948718e-06,
49
+ "loss": 0.0314,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 7.33,
54
+ "learning_rate": 5.347985347985348e-06,
55
+ "loss": 0.0206,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 8.24,
60
+ "learning_rate": 3.516483516483517e-06,
61
+ "loss": 0.0171,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 9.16,
66
+ "learning_rate": 1.6849816849816852e-06,
67
+ "loss": 0.0119,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 10.0,
72
+ "step": 5460,
73
+ "total_flos": 2.8586235178707456e+17,
74
+ "train_loss": 0.07572162915498783,
75
+ "train_runtime": 4508.6421,
76
+ "train_samples_per_second": 232.316,
77
+ "train_steps_per_second": 1.211
78
+ }
79
+ ],
80
+ "max_steps": 5460,
81
+ "num_train_epochs": 10,
82
+ "total_flos": 2.8586235178707456e+17,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d9b2435ca5323e886b58d49d25f95d1eeff6afaedceea081258e4b73e0e3c94
3
+ size 2479
vocab.json ADDED
The diff for this file is too large to render. See raw diff