rdemorais commited on
Commit
4915498
1 Parent(s): d93239f

Training in progress, step 200

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.23.1",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.23.1",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74dfb9364229615096571a292f21c6238b9534a9f5941a31ee85196c3a4f9e6c
3
+ size 2226478361
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840383f0d1b889fd1fd61960659e6c832adc71ac9791115694aef6c90b17380c
3
+ size 1113252715
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4c2fd9ccc6ce0ddeb7868906fe4ab7de21d77c1aa69c1c1120746a681305f0
3
+ size 17563
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb6982c29cd162f49aeb531674acf574eccd46a8f556bec596040d7c3b95200a
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc11e0e0fe9189b24400e9296623f6835d166bd001211aeab59a7cfc3f1fe7c
3
+ size 623
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "max_len": 512,
15
+ "model_max_length": 512,
16
+ "name_or_path": "xlm-roberta-base",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.01638387417184636,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.0000000000000002e-06,
13
+ "loss": 1.4445,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 2.0000000000000003e-06,
19
+ "loss": 1.4332,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 3e-06,
25
+ "loss": 1.4346,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 4.000000000000001e-06,
31
+ "loss": 1.4213,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 5e-06,
37
+ "loss": 1.4162,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 6e-06,
43
+ "loss": 1.4093,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 7.000000000000001e-06,
49
+ "loss": 1.4005,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 8.000000000000001e-06,
55
+ "loss": 1.405,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 9e-06,
61
+ "loss": 1.4112,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.01,
66
+ "learning_rate": 1e-05,
67
+ "loss": 1.4123,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.01,
72
+ "learning_rate": 1.1000000000000001e-05,
73
+ "loss": 1.4037,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.01,
78
+ "learning_rate": 1.2e-05,
79
+ "loss": 1.402,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.01,
84
+ "learning_rate": 1.3000000000000001e-05,
85
+ "loss": 1.3856,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "learning_rate": 1.4000000000000001e-05,
91
+ "loss": 1.392,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.01,
96
+ "learning_rate": 1.5e-05,
97
+ "loss": 1.3968,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.01,
102
+ "learning_rate": 1.6000000000000003e-05,
103
+ "loss": 1.393,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.01,
108
+ "learning_rate": 1.7000000000000003e-05,
109
+ "loss": 1.3897,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.01,
114
+ "learning_rate": 1.8e-05,
115
+ "loss": 1.388,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.02,
120
+ "learning_rate": 1.9e-05,
121
+ "loss": 1.3885,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.02,
126
+ "learning_rate": 2e-05,
127
+ "loss": 1.3883,
128
+ "step": 200
129
+ }
130
+ ],
131
+ "max_steps": 24414,
132
+ "num_train_epochs": 2,
133
+ "total_flos": 2.7021215268864e+16,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3402e851b005f28eb338ec0b3971c54372c57683892e0b0d8111120f28da456f
3
+ size 3439
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840383f0d1b889fd1fd61960659e6c832adc71ac9791115694aef6c90b17380c
3
+ size 1113252715
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "max_len": 512,
15
+ "model_max_length": 512,
16
+ "name_or_path": "xlm-roberta-base",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3402e851b005f28eb338ec0b3971c54372c57683892e0b0d8111120f28da456f
3
+ size 3439