Hugging Face's logo

Narrativa
/
legal-longformer-base-4096-spanish

Fill-Mask
Transformers
PyTorch
TensorBoard
Spanish
roberta
Long documents
longformer
robertalex
spanish
legal
Inference Endpoints
Model card Files Metrics Community
2
mrm8488 commited on
Commit
0ab1b15
•
1 Parent(s): 9a51c41

Upload the model

Browse files
Files changed (16) hide show
  1. config.json +42 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. runs/Nov08_15-58-36_21ac1a3e56da/1667923123.5426064/events.out.tfevents.1667923123.21ac1a3e56da.1471.1 +3 -0
  7. runs/Nov08_15-58-36_21ac1a3e56da/events.out.tfevents.1667923123.21ac1a3e56da.1471.0 +3 -0
  8. runs/Nov09_18-18-38_644ec4f2e0f6/1668017927.686863/events.out.tfevents.1668017927.644ec4f2e0f6.722.1 +3 -0
  9. runs/Nov09_18-18-38_644ec4f2e0f6/events.out.tfevents.1668017927.644ec4f2e0f6.722.0 +3 -0
  10. scheduler.pt +3 -0
  11. special_tokens_map.json +51 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +66 -0
  14. trainer_state.json +1186 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/longformer-legal-es/train/checkpoint-1200",
3
+ "architectures": [
4
+ "RobertaLongForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 512,
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "bos_token_id": 0,
22
+ "classifier_dropout": null,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "layer_norm_eps": 1e-05,
31
+ "max_position_embeddings": 4098,
32
+ "model_type": "roberta",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.25.0.dev0",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 52000
42
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454ebb4d9f26de58719aabf070974b947f32e8789480e749246e5ed3ae75064b
3
+ size 1030390553
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9400883a2dc0f278f1f999a11d5d83018fa0b1fab069c77c6eef6603371f76
3
+ size 600307611
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84315f16d96152131c6e93edeea1895cbcc08bd44f4702a0cf0e24c9203d024c
3
+ size 14503
runs/Nov08_15-58-36_21ac1a3e56da/1667923123.5426064/events.out.tfevents.1667923123.21ac1a3e56da.1471.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f2d4de71df26fd3bf9af498504bc1bf6a23166847b4b801285240afd856588
3
+ size 5555
runs/Nov08_15-58-36_21ac1a3e56da/events.out.tfevents.1667923123.21ac1a3e56da.1471.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d7975fa61b111ffc39fee1524be3c7d03bfa5d86d00395f8cb5b03c56b0046a
3
+ size 23310
runs/Nov09_18-18-38_644ec4f2e0f6/1668017927.686863/events.out.tfevents.1668017927.644ec4f2e0f6.722.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9785e0f410c1693395bf01ee47e82b928f7a6b8421bc9e4487febc2252532a
3
+ size 5555
runs/Nov09_18-18-38_644ec4f2e0f6/events.out.tfevents.1668017927.644ec4f2e0f6.722.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb5781b268385637ce6fd6bd77788b545f06d91ccae4aba86847c687c895296
3
+ size 16302
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c7499b05eee78aea71e38c7a66605a6f64989ed71f56e6499d7183992400e4
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "max_len": 512,
37
+ "model_max_length": 4096,
38
+ "name_or_path": "/content/drive/MyDrive/longformer-legal-es-4096",
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "special_tokens_map_file": null,
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": {
59
+ "__type": "AddedToken",
60
+ "content": "<unk>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ }
66
+ }
trainer_state.json ADDED
@@ -0,0 +1,1186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2910379888528719,
5
+ "global_step": 1950,
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": 6.000000000000001e-07,
13
+ "loss": 2.9477,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 1.2000000000000002e-06,
19
+ "loss": 2.9437,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 1.8e-06,
25
+ "loss": 2.8391,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 2.4000000000000003e-06,
31
+ "loss": 2.7878,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 3e-06,
37
+ "loss": 2.7033,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 3.6e-06,
43
+ "loss": 2.5839,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 4.2000000000000004e-06,
49
+ "loss": 2.5077,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 4.800000000000001e-06,
55
+ "loss": 2.3937,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 5.4e-06,
61
+ "loss": 2.2994,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.01,
66
+ "learning_rate": 6e-06,
67
+ "loss": 2.3544,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.02,
72
+ "learning_rate": 6.6e-06,
73
+ "loss": 2.2563,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.02,
78
+ "learning_rate": 7.2e-06,
79
+ "loss": 2.1624,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "learning_rate": 7.8e-06,
85
+ "loss": 2.1635,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.02,
90
+ "learning_rate": 8.400000000000001e-06,
91
+ "loss": 2.1196,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.02,
96
+ "learning_rate": 9e-06,
97
+ "loss": 2.0701,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.02,
102
+ "learning_rate": 9.600000000000001e-06,
103
+ "loss": 2.0222,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.03,
108
+ "learning_rate": 1.02e-05,
109
+ "loss": 2.0375,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.03,
114
+ "learning_rate": 1.08e-05,
115
+ "loss": 1.9524,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.03,
120
+ "learning_rate": 1.1400000000000001e-05,
121
+ "loss": 1.9589,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "learning_rate": 1.2e-05,
127
+ "loss": 1.9512,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.03,
132
+ "learning_rate": 1.26e-05,
133
+ "loss": 1.8844,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.03,
138
+ "learning_rate": 1.32e-05,
139
+ "loss": 1.8968,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.03,
144
+ "learning_rate": 1.3800000000000002e-05,
145
+ "loss": 1.8407,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.04,
150
+ "learning_rate": 1.44e-05,
151
+ "loss": 1.8488,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.04,
156
+ "learning_rate": 1.5e-05,
157
+ "loss": 1.8461,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.04,
162
+ "learning_rate": 1.56e-05,
163
+ "loss": 1.8473,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.04,
168
+ "learning_rate": 1.62e-05,
169
+ "loss": 1.8165,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.04,
174
+ "learning_rate": 1.6800000000000002e-05,
175
+ "loss": 1.8255,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.04,
180
+ "learning_rate": 1.74e-05,
181
+ "loss": 1.8499,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.04,
186
+ "learning_rate": 1.8e-05,
187
+ "loss": 1.8384,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.05,
192
+ "learning_rate": 1.86e-05,
193
+ "loss": 1.8069,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.05,
198
+ "learning_rate": 1.9200000000000003e-05,
199
+ "loss": 1.7542,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.05,
204
+ "learning_rate": 1.98e-05,
205
+ "loss": 1.8121,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.05,
210
+ "learning_rate": 2.04e-05,
211
+ "loss": 1.7528,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.05,
216
+ "learning_rate": 2.1e-05,
217
+ "loss": 1.7386,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.05,
222
+ "learning_rate": 2.16e-05,
223
+ "loss": 1.7411,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.06,
228
+ "learning_rate": 2.22e-05,
229
+ "loss": 1.7301,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.06,
234
+ "learning_rate": 2.2800000000000002e-05,
235
+ "loss": 1.7389,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.06,
240
+ "learning_rate": 2.3400000000000003e-05,
241
+ "loss": 1.7339,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.06,
246
+ "learning_rate": 2.4e-05,
247
+ "loss": 1.7242,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.06,
252
+ "learning_rate": 2.4599999999999998e-05,
253
+ "loss": 1.7381,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.06,
258
+ "learning_rate": 2.52e-05,
259
+ "loss": 1.7049,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.06,
264
+ "learning_rate": 2.58e-05,
265
+ "loss": 1.699,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.07,
270
+ "learning_rate": 2.64e-05,
271
+ "loss": 1.7059,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.07,
276
+ "learning_rate": 2.7000000000000002e-05,
277
+ "loss": 1.7285,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.07,
282
+ "learning_rate": 2.7600000000000003e-05,
283
+ "loss": 1.6645,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.07,
288
+ "learning_rate": 2.8199999999999998e-05,
289
+ "loss": 1.6943,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.07,
294
+ "learning_rate": 2.88e-05,
295
+ "loss": 1.6647,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.07,
300
+ "learning_rate": 2.94e-05,
301
+ "loss": 1.6977,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.07,
306
+ "learning_rate": 3e-05,
307
+ "loss": 1.672,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.08,
312
+ "learning_rate": 2.9880000000000002e-05,
313
+ "loss": 1.6515,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.08,
318
+ "learning_rate": 2.976e-05,
319
+ "loss": 1.7002,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.08,
324
+ "learning_rate": 2.964e-05,
325
+ "loss": 1.6703,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.08,
330
+ "learning_rate": 2.9520000000000002e-05,
331
+ "loss": 1.6593,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.08,
336
+ "learning_rate": 2.94e-05,
337
+ "loss": 1.6481,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.08,
342
+ "learning_rate": 2.928e-05,
343
+ "loss": 1.618,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.09,
348
+ "learning_rate": 2.916e-05,
349
+ "loss": 1.6649,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 0.09,
354
+ "learning_rate": 2.904e-05,
355
+ "loss": 1.6145,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 0.09,
360
+ "learning_rate": 2.892e-05,
361
+ "loss": 1.6316,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 0.09,
366
+ "learning_rate": 2.88e-05,
367
+ "loss": 1.6236,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 0.09,
372
+ "learning_rate": 2.868e-05,
373
+ "loss": 1.6178,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 0.09,
378
+ "learning_rate": 2.856e-05,
379
+ "loss": 1.5701,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 0.09,
384
+ "learning_rate": 2.844e-05,
385
+ "loss": 1.6125,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 0.1,
390
+ "learning_rate": 2.832e-05,
391
+ "loss": 1.5994,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 0.1,
396
+ "learning_rate": 2.8199999999999998e-05,
397
+ "loss": 1.5694,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 0.1,
402
+ "learning_rate": 2.8080000000000002e-05,
403
+ "loss": 1.5835,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 0.1,
408
+ "learning_rate": 2.7960000000000003e-05,
409
+ "loss": 1.5758,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 0.1,
414
+ "learning_rate": 2.784e-05,
415
+ "loss": 1.6216,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 0.1,
420
+ "learning_rate": 2.7720000000000002e-05,
421
+ "loss": 1.5372,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 0.1,
426
+ "learning_rate": 2.7600000000000003e-05,
427
+ "loss": 1.5672,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 0.11,
432
+ "learning_rate": 2.748e-05,
433
+ "loss": 1.5815,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 0.11,
438
+ "learning_rate": 2.7360000000000002e-05,
439
+ "loss": 1.5739,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 0.11,
444
+ "learning_rate": 2.724e-05,
445
+ "loss": 1.5802,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 0.11,
450
+ "learning_rate": 2.712e-05,
451
+ "loss": 1.5669,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 0.11,
456
+ "learning_rate": 2.7000000000000002e-05,
457
+ "loss": 1.5571,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 0.11,
462
+ "learning_rate": 2.688e-05,
463
+ "loss": 1.5661,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 0.11,
468
+ "learning_rate": 2.676e-05,
469
+ "loss": 1.5643,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 0.12,
474
+ "learning_rate": 2.6640000000000002e-05,
475
+ "loss": 1.5446,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 0.12,
480
+ "learning_rate": 2.652e-05,
481
+ "loss": 1.5343,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 0.12,
486
+ "learning_rate": 2.64e-05,
487
+ "loss": 1.5592,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 0.12,
492
+ "learning_rate": 2.628e-05,
493
+ "loss": 1.5131,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 0.12,
498
+ "learning_rate": 2.616e-05,
499
+ "loss": 1.5568,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 0.12,
504
+ "learning_rate": 2.604e-05,
505
+ "loss": 1.5287,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 0.13,
510
+ "learning_rate": 2.592e-05,
511
+ "loss": 1.5364,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 0.13,
516
+ "learning_rate": 2.58e-05,
517
+ "loss": 1.5537,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 0.13,
522
+ "learning_rate": 2.568e-05,
523
+ "loss": 1.5066,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 0.13,
528
+ "learning_rate": 2.556e-05,
529
+ "loss": 1.5276,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 0.13,
534
+ "learning_rate": 2.544e-05,
535
+ "loss": 1.5165,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 0.13,
540
+ "learning_rate": 2.5319999999999998e-05,
541
+ "loss": 1.518,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 0.13,
546
+ "learning_rate": 2.52e-05,
547
+ "loss": 1.5238,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 0.14,
552
+ "learning_rate": 2.508e-05,
553
+ "loss": 1.5033,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 0.14,
558
+ "learning_rate": 2.4959999999999998e-05,
559
+ "loss": 1.5505,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 0.14,
564
+ "learning_rate": 2.484e-05,
565
+ "loss": 1.5228,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 0.14,
570
+ "learning_rate": 2.472e-05,
571
+ "loss": 1.5207,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 0.14,
576
+ "learning_rate": 2.4599999999999998e-05,
577
+ "loss": 1.5547,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 0.14,
582
+ "learning_rate": 2.448e-05,
583
+ "loss": 1.5234,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 0.14,
588
+ "learning_rate": 2.4360000000000004e-05,
589
+ "loss": 1.5325,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 0.15,
594
+ "learning_rate": 2.4240000000000002e-05,
595
+ "loss": 1.5049,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 0.15,
600
+ "learning_rate": 2.4120000000000003e-05,
601
+ "loss": 1.5138,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 0.15,
606
+ "learning_rate": 2.4e-05,
607
+ "loss": 1.503,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 0.15,
612
+ "learning_rate": 2.3880000000000002e-05,
613
+ "loss": 1.5241,
614
+ "step": 1010
615
+ },
616
+ {
617
+ "epoch": 0.15,
618
+ "learning_rate": 2.3760000000000003e-05,
619
+ "loss": 1.5353,
620
+ "step": 1020
621
+ },
622
+ {
623
+ "epoch": 0.15,
624
+ "learning_rate": 2.364e-05,
625
+ "loss": 1.489,
626
+ "step": 1030
627
+ },
628
+ {
629
+ "epoch": 0.16,
630
+ "learning_rate": 2.3520000000000002e-05,
631
+ "loss": 1.4958,
632
+ "step": 1040
633
+ },
634
+ {
635
+ "epoch": 0.16,
636
+ "learning_rate": 2.3400000000000003e-05,
637
+ "loss": 1.5068,
638
+ "step": 1050
639
+ },
640
+ {
641
+ "epoch": 0.16,
642
+ "learning_rate": 2.328e-05,
643
+ "loss": 1.4988,
644
+ "step": 1060
645
+ },
646
+ {
647
+ "epoch": 0.16,
648
+ "learning_rate": 2.3160000000000002e-05,
649
+ "loss": 1.5311,
650
+ "step": 1070
651
+ },
652
+ {
653
+ "epoch": 0.16,
654
+ "learning_rate": 2.304e-05,
655
+ "loss": 1.4811,
656
+ "step": 1080
657
+ },
658
+ {
659
+ "epoch": 0.16,
660
+ "learning_rate": 2.292e-05,
661
+ "loss": 1.5139,
662
+ "step": 1090
663
+ },
664
+ {
665
+ "epoch": 0.16,
666
+ "learning_rate": 2.2800000000000002e-05,
667
+ "loss": 1.5403,
668
+ "step": 1100
669
+ },
670
+ {
671
+ "epoch": 0.17,
672
+ "learning_rate": 2.268e-05,
673
+ "loss": 1.4928,
674
+ "step": 1110
675
+ },
676
+ {
677
+ "epoch": 0.17,
678
+ "learning_rate": 2.256e-05,
679
+ "loss": 1.4635,
680
+ "step": 1120
681
+ },
682
+ {
683
+ "epoch": 0.17,
684
+ "learning_rate": 2.2440000000000002e-05,
685
+ "loss": 1.5088,
686
+ "step": 1130
687
+ },
688
+ {
689
+ "epoch": 0.17,
690
+ "learning_rate": 2.232e-05,
691
+ "loss": 1.5081,
692
+ "step": 1140
693
+ },
694
+ {
695
+ "epoch": 0.17,
696
+ "learning_rate": 2.22e-05,
697
+ "loss": 1.4923,
698
+ "step": 1150
699
+ },
700
+ {
701
+ "epoch": 0.17,
702
+ "learning_rate": 2.208e-05,
703
+ "loss": 1.4836,
704
+ "step": 1160
705
+ },
706
+ {
707
+ "epoch": 0.17,
708
+ "learning_rate": 2.196e-05,
709
+ "loss": 1.4861,
710
+ "step": 1170
711
+ },
712
+ {
713
+ "epoch": 0.18,
714
+ "learning_rate": 2.184e-05,
715
+ "loss": 1.4594,
716
+ "step": 1180
717
+ },
718
+ {
719
+ "epoch": 0.18,
720
+ "learning_rate": 2.172e-05,
721
+ "loss": 1.4895,
722
+ "step": 1190
723
+ },
724
+ {
725
+ "epoch": 0.18,
726
+ "learning_rate": 2.16e-05,
727
+ "loss": 1.4775,
728
+ "step": 1200
729
+ },
730
+ {
731
+ "epoch": 0.18,
732
+ "learning_rate": 2.148e-05,
733
+ "loss": 1.4682,
734
+ "step": 1210
735
+ },
736
+ {
737
+ "epoch": 0.18,
738
+ "learning_rate": 2.136e-05,
739
+ "loss": 1.5022,
740
+ "step": 1220
741
+ },
742
+ {
743
+ "epoch": 0.18,
744
+ "learning_rate": 2.124e-05,
745
+ "loss": 1.4594,
746
+ "step": 1230
747
+ },
748
+ {
749
+ "epoch": 0.19,
750
+ "learning_rate": 2.1119999999999998e-05,
751
+ "loss": 1.453,
752
+ "step": 1240
753
+ },
754
+ {
755
+ "epoch": 0.19,
756
+ "learning_rate": 2.1e-05,
757
+ "loss": 1.4665,
758
+ "step": 1250
759
+ },
760
+ {
761
+ "epoch": 0.19,
762
+ "learning_rate": 2.088e-05,
763
+ "loss": 1.489,
764
+ "step": 1260
765
+ },
766
+ {
767
+ "epoch": 0.19,
768
+ "learning_rate": 2.0759999999999998e-05,
769
+ "loss": 1.4959,
770
+ "step": 1270
771
+ },
772
+ {
773
+ "epoch": 0.19,
774
+ "learning_rate": 2.064e-05,
775
+ "loss": 1.4831,
776
+ "step": 1280
777
+ },
778
+ {
779
+ "epoch": 0.19,
780
+ "learning_rate": 2.0520000000000003e-05,
781
+ "loss": 1.4488,
782
+ "step": 1290
783
+ },
784
+ {
785
+ "epoch": 0.19,
786
+ "learning_rate": 2.04e-05,
787
+ "loss": 1.4885,
788
+ "step": 1300
789
+ },
790
+ {
791
+ "epoch": 0.2,
792
+ "learning_rate": 2.0280000000000002e-05,
793
+ "loss": 1.4756,
794
+ "step": 1310
795
+ },
796
+ {
797
+ "epoch": 0.2,
798
+ "learning_rate": 2.016e-05,
799
+ "loss": 1.4813,
800
+ "step": 1320
801
+ },
802
+ {
803
+ "epoch": 0.2,
804
+ "learning_rate": 2.004e-05,
805
+ "loss": 1.4878,
806
+ "step": 1330
807
+ },
808
+ {
809
+ "epoch": 0.2,
810
+ "learning_rate": 1.9920000000000002e-05,
811
+ "loss": 1.4756,
812
+ "step": 1340
813
+ },
814
+ {
815
+ "epoch": 0.2,
816
+ "learning_rate": 1.98e-05,
817
+ "loss": 1.4759,
818
+ "step": 1350
819
+ },
820
+ {
821
+ "epoch": 0.2,
822
+ "learning_rate": 1.968e-05,
823
+ "loss": 1.4541,
824
+ "step": 1360
825
+ },
826
+ {
827
+ "epoch": 0.2,
828
+ "learning_rate": 1.9560000000000002e-05,
829
+ "loss": 1.4533,
830
+ "step": 1370
831
+ },
832
+ {
833
+ "epoch": 0.21,
834
+ "learning_rate": 1.944e-05,
835
+ "loss": 1.4842,
836
+ "step": 1380
837
+ },
838
+ {
839
+ "epoch": 0.21,
840
+ "learning_rate": 1.932e-05,
841
+ "loss": 1.4585,
842
+ "step": 1390
843
+ },
844
+ {
845
+ "epoch": 0.21,
846
+ "learning_rate": 1.9200000000000003e-05,
847
+ "loss": 1.4781,
848
+ "step": 1400
849
+ },
850
+ {
851
+ "epoch": 0.21,
852
+ "learning_rate": 1.908e-05,
853
+ "loss": 1.4637,
854
+ "step": 1410
855
+ },
856
+ {
857
+ "epoch": 0.21,
858
+ "learning_rate": 1.896e-05,
859
+ "loss": 1.4691,
860
+ "step": 1420
861
+ },
862
+ {
863
+ "epoch": 0.21,
864
+ "learning_rate": 1.884e-05,
865
+ "loss": 1.4782,
866
+ "step": 1430
867
+ },
868
+ {
869
+ "epoch": 0.21,
870
+ "learning_rate": 1.872e-05,
871
+ "loss": 1.4689,
872
+ "step": 1440
873
+ },
874
+ {
875
+ "epoch": 0.22,
876
+ "learning_rate": 1.86e-05,
877
+ "loss": 1.4603,
878
+ "step": 1450
879
+ },
880
+ {
881
+ "epoch": 0.22,
882
+ "learning_rate": 1.848e-05,
883
+ "loss": 1.4666,
884
+ "step": 1460
885
+ },
886
+ {
887
+ "epoch": 0.22,
888
+ "learning_rate": 1.836e-05,
889
+ "loss": 1.4694,
890
+ "step": 1470
891
+ },
892
+ {
893
+ "epoch": 0.22,
894
+ "learning_rate": 1.824e-05,
895
+ "loss": 1.4499,
896
+ "step": 1480
897
+ },
898
+ {
899
+ "epoch": 0.22,
900
+ "learning_rate": 1.812e-05,
901
+ "loss": 1.4794,
902
+ "step": 1490
903
+ },
904
+ {
905
+ "epoch": 0.22,
906
+ "learning_rate": 1.8e-05,
907
+ "loss": 1.475,
908
+ "step": 1500
909
+ },
910
+ {
911
+ "epoch": 0.23,
912
+ "learning_rate": 1.7879999999999998e-05,
913
+ "loss": 1.4431,
914
+ "step": 1510
915
+ },
916
+ {
917
+ "epoch": 0.23,
918
+ "learning_rate": 1.776e-05,
919
+ "loss": 1.4492,
920
+ "step": 1520
921
+ },
922
+ {
923
+ "epoch": 0.23,
924
+ "learning_rate": 1.764e-05,
925
+ "loss": 1.4656,
926
+ "step": 1530
927
+ },
928
+ {
929
+ "epoch": 0.23,
930
+ "learning_rate": 1.7519999999999998e-05,
931
+ "loss": 1.4524,
932
+ "step": 1540
933
+ },
934
+ {
935
+ "epoch": 0.23,
936
+ "learning_rate": 1.74e-05,
937
+ "loss": 1.4611,
938
+ "step": 1550
939
+ },
940
+ {
941
+ "epoch": 0.23,
942
+ "learning_rate": 1.728e-05,
943
+ "loss": 1.4602,
944
+ "step": 1560
945
+ },
946
+ {
947
+ "epoch": 0.23,
948
+ "learning_rate": 1.716e-05,
949
+ "loss": 1.4603,
950
+ "step": 1570
951
+ },
952
+ {
953
+ "epoch": 0.24,
954
+ "learning_rate": 1.704e-05,
955
+ "loss": 1.4334,
956
+ "step": 1580
957
+ },
958
+ {
959
+ "epoch": 0.24,
960
+ "learning_rate": 1.6919999999999997e-05,
961
+ "loss": 1.4761,
962
+ "step": 1590
963
+ },
964
+ {
965
+ "epoch": 0.24,
966
+ "learning_rate": 1.6800000000000002e-05,
967
+ "loss": 1.4193,
968
+ "step": 1600
969
+ },
970
+ {
971
+ "epoch": 0.24,
972
+ "learning_rate": 1.6680000000000003e-05,
973
+ "loss": 1.4209,
974
+ "step": 1610
975
+ },
976
+ {
977
+ "epoch": 0.24,
978
+ "learning_rate": 1.656e-05,
979
+ "loss": 1.4473,
980
+ "step": 1620
981
+ },
982
+ {
983
+ "epoch": 0.24,
984
+ "learning_rate": 1.6440000000000002e-05,
985
+ "loss": 1.4451,
986
+ "step": 1630
987
+ },
988
+ {
989
+ "epoch": 0.24,
990
+ "learning_rate": 1.6320000000000003e-05,
991
+ "loss": 1.4428,
992
+ "step": 1640
993
+ },
994
+ {
995
+ "epoch": 0.25,
996
+ "learning_rate": 1.62e-05,
997
+ "loss": 1.444,
998
+ "step": 1650
999
+ },
1000
+ {
1001
+ "epoch": 0.25,
1002
+ "learning_rate": 1.6080000000000002e-05,
1003
+ "loss": 1.4677,
1004
+ "step": 1660
1005
+ },
1006
+ {
1007
+ "epoch": 0.25,
1008
+ "learning_rate": 1.596e-05,
1009
+ "loss": 1.4483,
1010
+ "step": 1670
1011
+ },
1012
+ {
1013
+ "epoch": 0.25,
1014
+ "learning_rate": 1.584e-05,
1015
+ "loss": 1.4536,
1016
+ "step": 1680
1017
+ },
1018
+ {
1019
+ "epoch": 0.25,
1020
+ "learning_rate": 1.5720000000000002e-05,
1021
+ "loss": 1.4515,
1022
+ "step": 1690
1023
+ },
1024
+ {
1025
+ "epoch": 0.25,
1026
+ "learning_rate": 1.56e-05,
1027
+ "loss": 1.436,
1028
+ "step": 1700
1029
+ },
1030
+ {
1031
+ "epoch": 0.26,
1032
+ "learning_rate": 1.548e-05,
1033
+ "loss": 1.4277,
1034
+ "step": 1710
1035
+ },
1036
+ {
1037
+ "epoch": 0.26,
1038
+ "learning_rate": 1.5360000000000002e-05,
1039
+ "loss": 1.4434,
1040
+ "step": 1720
1041
+ },
1042
+ {
1043
+ "epoch": 0.26,
1044
+ "learning_rate": 1.524e-05,
1045
+ "loss": 1.4312,
1046
+ "step": 1730
1047
+ },
1048
+ {
1049
+ "epoch": 0.26,
1050
+ "learning_rate": 1.5120000000000001e-05,
1051
+ "loss": 1.4457,
1052
+ "step": 1740
1053
+ },
1054
+ {
1055
+ "epoch": 0.26,
1056
+ "learning_rate": 1.5e-05,
1057
+ "loss": 1.4404,
1058
+ "step": 1750
1059
+ },
1060
+ {
1061
+ "epoch": 0.26,
1062
+ "learning_rate": 1.488e-05,
1063
+ "loss": 1.4684,
1064
+ "step": 1760
1065
+ },
1066
+ {
1067
+ "epoch": 0.26,
1068
+ "learning_rate": 1.4760000000000001e-05,
1069
+ "loss": 1.4449,
1070
+ "step": 1770
1071
+ },
1072
+ {
1073
+ "epoch": 0.27,
1074
+ "learning_rate": 1.464e-05,
1075
+ "loss": 1.4354,
1076
+ "step": 1780
1077
+ },
1078
+ {
1079
+ "epoch": 0.27,
1080
+ "learning_rate": 1.452e-05,
1081
+ "loss": 1.4303,
1082
+ "step": 1790
1083
+ },
1084
+ {
1085
+ "epoch": 0.27,
1086
+ "learning_rate": 1.44e-05,
1087
+ "loss": 1.4215,
1088
+ "step": 1800
1089
+ },
1090
+ {
1091
+ "epoch": 0.27,
1092
+ "learning_rate": 1.428e-05,
1093
+ "loss": 1.4385,
1094
+ "step": 1810
1095
+ },
1096
+ {
1097
+ "epoch": 0.27,
1098
+ "learning_rate": 1.416e-05,
1099
+ "loss": 1.4239,
1100
+ "step": 1820
1101
+ },
1102
+ {
1103
+ "epoch": 0.27,
1104
+ "learning_rate": 1.4040000000000001e-05,
1105
+ "loss": 1.4431,
1106
+ "step": 1830
1107
+ },
1108
+ {
1109
+ "epoch": 0.27,
1110
+ "learning_rate": 1.392e-05,
1111
+ "loss": 1.4354,
1112
+ "step": 1840
1113
+ },
1114
+ {
1115
+ "epoch": 0.28,
1116
+ "learning_rate": 1.3800000000000002e-05,
1117
+ "loss": 1.4428,
1118
+ "step": 1850
1119
+ },
1120
+ {
1121
+ "epoch": 0.28,
1122
+ "learning_rate": 1.3680000000000001e-05,
1123
+ "loss": 1.4062,
1124
+ "step": 1860
1125
+ },
1126
+ {
1127
+ "epoch": 0.28,
1128
+ "learning_rate": 1.356e-05,
1129
+ "loss": 1.4423,
1130
+ "step": 1870
1131
+ },
1132
+ {
1133
+ "epoch": 0.28,
1134
+ "learning_rate": 1.344e-05,
1135
+ "loss": 1.4218,
1136
+ "step": 1880
1137
+ },
1138
+ {
1139
+ "epoch": 0.28,
1140
+ "learning_rate": 1.3320000000000001e-05,
1141
+ "loss": 1.4131,
1142
+ "step": 1890
1143
+ },
1144
+ {
1145
+ "epoch": 0.28,
1146
+ "learning_rate": 1.32e-05,
1147
+ "loss": 1.4536,
1148
+ "step": 1900
1149
+ },
1150
+ {
1151
+ "epoch": 0.29,
1152
+ "learning_rate": 1.308e-05,
1153
+ "loss": 1.3985,
1154
+ "step": 1910
1155
+ },
1156
+ {
1157
+ "epoch": 0.29,
1158
+ "learning_rate": 1.296e-05,
1159
+ "loss": 1.4204,
1160
+ "step": 1920
1161
+ },
1162
+ {
1163
+ "epoch": 0.29,
1164
+ "learning_rate": 1.284e-05,
1165
+ "loss": 1.4266,
1166
+ "step": 1930
1167
+ },
1168
+ {
1169
+ "epoch": 0.29,
1170
+ "learning_rate": 1.272e-05,
1171
+ "loss": 1.4255,
1172
+ "step": 1940
1173
+ },
1174
+ {
1175
+ "epoch": 0.29,
1176
+ "learning_rate": 1.26e-05,
1177
+ "loss": 1.4357,
1178
+ "step": 1950
1179
+ }
1180
+ ],
1181
+ "max_steps": 3000,
1182
+ "num_train_epochs": 1,
1183
+ "total_flos": 3.28059806810112e+17,
1184
+ "trial_name": null,
1185
+ "trial_params": null
1186
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a13ba7d5f7d2c3e31206c9e8bc0bb49c53ce226686b5e47cf82629efdcb8a33e
3
+ size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff