heruberuto commited on
Commit
3827d7d
1 Parent(s): d3df09f

init commit

Browse files
.gitattributes CHANGED
@@ -25,3 +25,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ fpss.tar.gz filter=lfs diff=lfs merge=lfs -text
29
+ checkpoint-10000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
30
+ checkpoint-10000/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
31
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/merges-checkpoint.txt ADDED
The diff for this file is too large to render. See raw diff
 
.ipynb_checkpoints/vocab-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.13.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd744acd088fe402025746b5d0666a4b072a49e10ffef30fc16386434b4eeaa9
3
+ size 668099842
checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e7c25201d14d2647f2a730ba3476f377b521bedbe5b510cf9bc91eccb24142
3
+ size 334066136
checkpoint-10000/rng_state.pth ADDED
Binary file (14.6 kB). View file
 
checkpoint-10000/scheduler.pt ADDED
Binary file (623 Bytes). View file
 
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6566850538481744,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 4.8358287365379566e-05,
13
+ "loss": 7.8649,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 4.671657473075913e-05,
19
+ "loss": 7.2652,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.1,
24
+ "learning_rate": 4.5074862096138694e-05,
25
+ "loss": 7.0778,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.13,
30
+ "learning_rate": 4.343314946151826e-05,
31
+ "loss": 6.9737,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.16,
36
+ "learning_rate": 4.179143682689782e-05,
37
+ "loss": 6.8729,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.2,
42
+ "learning_rate": 4.0149724192277385e-05,
43
+ "loss": 6.79,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.23,
48
+ "learning_rate": 3.850801155765695e-05,
49
+ "loss": 6.752,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.26,
54
+ "learning_rate": 3.686629892303651e-05,
55
+ "loss": 6.7012,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.3,
60
+ "learning_rate": 3.522458628841608e-05,
61
+ "loss": 6.6312,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.33,
66
+ "learning_rate": 3.358287365379564e-05,
67
+ "loss": 6.5047,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.36,
72
+ "learning_rate": 3.1941161019175205e-05,
73
+ "loss": 6.3916,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.39,
78
+ "learning_rate": 3.029944838455477e-05,
79
+ "loss": 6.24,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.43,
84
+ "learning_rate": 2.8657735749934332e-05,
85
+ "loss": 6.1126,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.46,
90
+ "learning_rate": 2.70160231153139e-05,
91
+ "loss": 5.9892,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.49,
96
+ "learning_rate": 2.5374310480693457e-05,
97
+ "loss": 5.8802,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.53,
102
+ "learning_rate": 2.3732597846073024e-05,
103
+ "loss": 5.7723,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.56,
108
+ "learning_rate": 2.2090885211452588e-05,
109
+ "loss": 5.6834,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.59,
114
+ "learning_rate": 2.0449172576832152e-05,
115
+ "loss": 5.5951,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.62,
120
+ "learning_rate": 1.8807459942211716e-05,
121
+ "loss": 5.5049,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.66,
126
+ "learning_rate": 1.716574730759128e-05,
127
+ "loss": 5.4411,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 15228,
132
+ "num_train_epochs": 1,
133
+ "total_flos": 2.1220159479607296e+16,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
checkpoint-10000/training_args.bin ADDED
Binary file (2.86 kB). View file
 
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.13.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
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 sha256:5fc8c1d9fc7cfc913c50d29003b03b2388deb18ee22adfe1610c889ce70ef316
3
+ size 334066136
runs/Dec17_01-38-42_n32/1639701525.4542303/events.out.tfevents.1639701525.n32.21687.1 ADDED
Binary file (4.51 kB). View file
 
runs/Dec17_01-38-42_n32/events.out.tfevents.1639701525.n32.21687.0 ADDED
Binary file (8.13 kB). View file
 
training_args.bin ADDED
Binary file (2.86 kB). View file
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff