fpuentes commited on
Commit
0da3f6f
1 Parent(s): 39cec2d

Training in progress, step 500

Browse files
Files changed (35) hide show
  1. config.json +3 -2
  2. runs/Jan11_16-45-27_turing/1673451933.465075/events.out.tfevents.1673451933.turing.162574.1 → events.out.tfevents.1673814853.turing.327173.0 +2 -2
  3. runs/Jan11_16-45-27_turing/events.out.tfevents.1673451933.turing.162574.0 → events.out.tfevents.1673815130.turing.327344.0 +2 -2
  4. events.out.tfevents.1673815472.turing.327590.0 +3 -0
  5. events.out.tfevents.1673818108.turing.328391.0 +3 -0
  6. events.out.tfevents.1673819239.turing.328732.0 +3 -0
  7. last-checkpoint/config.json +3 -2
  8. last-checkpoint/optimizer.pt +2 -2
  9. last-checkpoint/pytorch_model.bin +1 -1
  10. last-checkpoint/rng_state.pth +2 -2
  11. last-checkpoint/scaler.pt +1 -1
  12. last-checkpoint/scheduler.pt +1 -1
  13. last-checkpoint/trainer_state.json +14 -210
  14. last-checkpoint/training_args.bin +2 -2
  15. log.txt +0 -0
  16. merges.txt +0 -0
  17. pytorch_model.bin +1 -1
  18. runs/Jan15_21-34-13_turing/1673814853.9309754/events.out.tfevents.1673814853.turing.327173.2 +3 -0
  19. runs/Jan15_21-34-13_turing/events.out.tfevents.1673814853.turing.327173.1 +3 -0
  20. runs/Jan15_21-38-50_turing/1673815130.6693852/events.out.tfevents.1673815130.turing.327344.2 +3 -0
  21. runs/Jan15_21-38-50_turing/events.out.tfevents.1673815130.turing.327344.1 +3 -0
  22. runs/Jan15_21-44-32_turing/1673815478.7136974/events.out.tfevents.1673815478.turing.327590.2 +3 -0
  23. runs/Jan15_21-44-32_turing/1673816409.4189365/events.out.tfevents.1673816409.turing.327590.3 +3 -0
  24. runs/Jan15_21-44-32_turing/1673816930.061229/events.out.tfevents.1673816930.turing.327590.4 +3 -0
  25. runs/Jan15_21-44-32_turing/1673817441.0883248/events.out.tfevents.1673817441.turing.327590.5 +3 -0
  26. runs/Jan15_21-44-32_turing/events.out.tfevents.1673815478.turing.327590.1 +3 -0
  27. runs/Jan15_22-28-28_turing/1673818114.7901142/events.out.tfevents.1673818114.turing.328391.2 +3 -0
  28. runs/Jan15_22-28-28_turing/events.out.tfevents.1673818114.turing.328391.1 +3 -0
  29. runs/Jan15_22-47-19_turing/1673819245.5556467/events.out.tfevents.1673819245.turing.328732.2 +3 -0
  30. runs/Jan15_22-47-19_turing/events.out.tfevents.1673819245.turing.328732.1 +3 -0
  31. special_tokens_map.json +0 -51
  32. tokenizer.json +0 -348
  33. tokenizer_config.json +0 -64
  34. training_args.bin +2 -2
  35. vocab.json +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
@@ -7,6 +7,7 @@
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,
@@ -20,7 +21,7 @@
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.24.0",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
  "vocab_size": 31002
 
1
  {
2
+ "_name_or_path": "bert-fromscratch-galician-tiny",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
 
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
  "hidden_size": 768,
 
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.25.1",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 31002
runs/Jan11_16-45-27_turing/1673451933.465075/events.out.tfevents.1673451933.turing.162574.1 → events.out.tfevents.1673814853.turing.327173.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:853f3d8342cbd88d1830b3b8643713bfd6721a824bc6b62817b60974a961aafd
3
- size 5573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4009989b8e0cef7be20aace5fa38745aac5d2ff88c7c166309e08ece60c96a9c
3
+ size 40
runs/Jan11_16-45-27_turing/events.out.tfevents.1673451933.turing.162574.0 → events.out.tfevents.1673815130.turing.327344.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3a47a08f9b6acf844e52711088889527cb14f8118d384474492de659f9e07bd
3
- size 10249
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866be7fc2228533501f5b8b9fa180f7d858ef77a9d50f4e342bd7ea017618bc2
3
+ size 40
events.out.tfevents.1673815472.turing.327590.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39cf25e830b6100fd4e060886441e90908203afe88847298ca10d88e7ca06126
3
+ size 40
events.out.tfevents.1673818108.turing.328391.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a42b6d9bbe66175c42d9b4af1832c8839d77c22a7cd49b4763e082c9936a27
3
+ size 40
events.out.tfevents.1673819239.turing.328732.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689679f8f31b6990b0694391fe5b7f95d3b3f65100b681df78f59dfd5b08b4b2
3
+ size 40
last-checkpoint/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
@@ -7,6 +7,7 @@
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,
@@ -20,7 +21,7 @@
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.24.0",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
  "vocab_size": 31002
 
1
  {
2
+ "_name_or_path": "bert-fromscratch-galician-tiny",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
 
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
  "hidden_size": 768,
 
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.25.1",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 31002
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98e8a5b53b2c4d8733fa58155c862d7ad8c8ac19fc17aa2cdbeeecf969876ede
3
- size 538917701
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801c2271d8c5c89f6b75aad292987eb7be01d92eb95b460208b11f44d1aee93b
3
+ size 538943941
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3e60aee58bb3002247500f1d529cca009a081ea94dc8ec603e656e128eb6897
3
  size 269468281
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0b07c5c7fc85dd0dfb66ea5fe8504c1a41a9ec2a4fb4454228c53a694d2d63
3
  size 269468281
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edb60841f841b5cc624351d65feeef8d0507231bd57b9a057376c854c4c7c2a6
3
- size 16619
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31436e4edb8722805d32541741dbc8dc71acb0518feee9de1bd1f464719d49b
3
+ size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:353f071a8d028751f6795b6568373c69120c80918dec3e3f3e2c2a824ed27644
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31e6790cf08ba99f982bd0658300f9c41c4317f30f220548bfd4220ffd05d922
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420e10273b4c605eace81ed700d0fe1224720131ac4e067633f127c39edc0094
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,226 +1,30 @@
1
  {
2
- "best_metric": 2.7213306427001953,
3
- "best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-750",
4
- "epoch": 4.236765612613406,
5
- "global_step": 750,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 0.28,
12
- "learning_rate": 9.717514124293787e-05,
13
- "loss": 5.0078,
14
- "step": 50
15
- },
16
- {
17
- "epoch": 0.28,
18
- "eval_loss": 3.1328039169311523,
19
- "eval_runtime": 312.4569,
20
- "eval_samples_per_second": 184.566,
21
- "eval_steps_per_second": 7.691,
22
- "step": 50
23
- },
24
- {
25
- "epoch": 0.56,
26
- "learning_rate": 9.43502824858757e-05,
27
- "loss": 3.0128,
28
- "step": 100
29
- },
30
- {
31
- "epoch": 0.56,
32
- "eval_loss": 2.960442304611206,
33
- "eval_runtime": 311.919,
34
- "eval_samples_per_second": 184.885,
35
- "eval_steps_per_second": 7.704,
36
- "step": 100
37
- },
38
- {
39
- "epoch": 0.85,
40
- "learning_rate": 9.152542372881357e-05,
41
- "loss": 2.949,
42
- "step": 150
43
- },
44
- {
45
- "epoch": 0.85,
46
- "eval_loss": 2.9336485862731934,
47
- "eval_runtime": 312.61,
48
- "eval_samples_per_second": 184.476,
49
- "eval_steps_per_second": 7.687,
50
- "step": 150
51
- },
52
- {
53
- "epoch": 1.13,
54
- "learning_rate": 8.870056497175142e-05,
55
- "loss": 2.9548,
56
- "step": 200
57
- },
58
- {
59
- "epoch": 1.13,
60
- "eval_loss": 2.925171375274658,
61
- "eval_runtime": 312.2872,
62
- "eval_samples_per_second": 184.667,
63
- "eval_steps_per_second": 7.695,
64
- "step": 200
65
- },
66
- {
67
- "epoch": 1.41,
68
- "learning_rate": 8.587570621468927e-05,
69
- "loss": 2.9239,
70
- "step": 250
71
- },
72
- {
73
- "epoch": 1.41,
74
- "eval_loss": 2.915585517883301,
75
- "eval_runtime": 310.9982,
76
- "eval_samples_per_second": 185.432,
77
- "eval_steps_per_second": 7.727,
78
- "step": 250
79
- },
80
- {
81
- "epoch": 1.69,
82
- "learning_rate": 8.305084745762712e-05,
83
- "loss": 2.9156,
84
- "step": 300
85
- },
86
- {
87
- "epoch": 1.69,
88
- "eval_loss": 2.9091334342956543,
89
- "eval_runtime": 312.2088,
90
- "eval_samples_per_second": 184.713,
91
- "eval_steps_per_second": 7.697,
92
- "step": 300
93
- },
94
- {
95
- "epoch": 1.98,
96
- "learning_rate": 8.022598870056498e-05,
97
- "loss": 2.9106,
98
- "step": 350
99
- },
100
- {
101
- "epoch": 1.98,
102
- "eval_loss": 2.904860019683838,
103
- "eval_runtime": 311.9526,
104
- "eval_samples_per_second": 184.865,
105
- "eval_steps_per_second": 7.703,
106
- "step": 350
107
- },
108
- {
109
- "epoch": 2.26,
110
- "learning_rate": 7.740112994350283e-05,
111
- "loss": 2.9262,
112
- "step": 400
113
- },
114
- {
115
- "epoch": 2.26,
116
- "eval_loss": 2.898866653442383,
117
- "eval_runtime": 312.7381,
118
- "eval_samples_per_second": 184.4,
119
- "eval_steps_per_second": 7.684,
120
- "step": 400
121
- },
122
- {
123
- "epoch": 2.54,
124
- "learning_rate": 7.457627118644068e-05,
125
- "loss": 2.8997,
126
- "step": 450
127
- },
128
- {
129
- "epoch": 2.54,
130
- "eval_loss": 2.8944928646087646,
131
- "eval_runtime": 312.5703,
132
- "eval_samples_per_second": 184.499,
133
- "eval_steps_per_second": 7.688,
134
- "step": 450
135
- },
136
- {
137
- "epoch": 2.82,
138
- "learning_rate": 7.175141242937854e-05,
139
- "loss": 2.8892,
140
  "step": 500
141
  },
142
  {
143
- "epoch": 2.82,
144
- "eval_loss": 2.8732619285583496,
145
- "eval_runtime": 314.1308,
146
- "eval_samples_per_second": 183.583,
147
- "eval_steps_per_second": 7.65,
148
  "step": 500
149
- },
150
- {
151
- "epoch": 3.11,
152
- "learning_rate": 6.892655367231638e-05,
153
- "loss": 2.8935,
154
- "step": 550
155
- },
156
- {
157
- "epoch": 3.11,
158
- "eval_loss": 2.8509020805358887,
159
- "eval_runtime": 313.6449,
160
- "eval_samples_per_second": 183.867,
161
- "eval_steps_per_second": 7.662,
162
- "step": 550
163
- },
164
- {
165
- "epoch": 3.39,
166
- "learning_rate": 6.610169491525424e-05,
167
- "loss": 2.8514,
168
- "step": 600
169
- },
170
- {
171
- "epoch": 3.39,
172
- "eval_loss": 2.824007034301758,
173
- "eval_runtime": 315.311,
174
- "eval_samples_per_second": 182.896,
175
- "eval_steps_per_second": 7.621,
176
- "step": 600
177
- },
178
- {
179
- "epoch": 3.67,
180
- "learning_rate": 6.327683615819209e-05,
181
- "loss": 2.8312,
182
- "step": 650
183
- },
184
- {
185
- "epoch": 3.67,
186
- "eval_loss": 2.7931814193725586,
187
- "eval_runtime": 312.19,
188
- "eval_samples_per_second": 184.724,
189
- "eval_steps_per_second": 7.697,
190
- "step": 650
191
- },
192
- {
193
- "epoch": 3.95,
194
- "learning_rate": 6.045197740112994e-05,
195
- "loss": 2.8029,
196
- "step": 700
197
- },
198
- {
199
- "epoch": 3.95,
200
- "eval_loss": 2.759551525115967,
201
- "eval_runtime": 311.5689,
202
- "eval_samples_per_second": 185.092,
203
- "eval_steps_per_second": 7.713,
204
- "step": 700
205
- },
206
- {
207
- "epoch": 4.24,
208
- "learning_rate": 5.76271186440678e-05,
209
- "loss": 2.7972,
210
- "step": 750
211
- },
212
- {
213
- "epoch": 4.24,
214
- "eval_loss": 2.7213306427001953,
215
- "eval_runtime": 311.178,
216
- "eval_samples_per_second": 185.325,
217
- "eval_steps_per_second": 7.722,
218
- "step": 750
219
  }
220
  ],
221
- "max_steps": 1770,
222
  "num_train_epochs": 10,
223
- "total_flos": 1.5298122780045043e+17,
224
  "trial_name": null,
225
  "trial_params": null
226
  }
 
1
  {
2
+ "best_metric": 6.109755516052246,
3
+ "best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-500",
4
+ "epoch": 0.4516201874223778,
5
+ "global_step": 500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 0.45,
12
+ "learning_rate": 9.5483288166215e-05,
13
+ "loss": 6.7769,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "step": 500
15
  },
16
  {
17
+ "epoch": 0.45,
18
+ "eval_loss": 6.109755516052246,
19
+ "eval_runtime": 33.0039,
20
+ "eval_samples_per_second": 348.201,
21
+ "eval_steps_per_second": 43.54,
22
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
+ "max_steps": 11070,
26
  "num_train_epochs": 10,
27
+ "total_flos": 7979100086017440.0,
28
  "trial_name": null,
29
  "trial_params": null
30
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2354b21c0eb02b167b9d6057f7fbae73d5ab7eeb327be5d088eb30bf0019608
3
- size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76e096e9f1e6ee51628944ab73e15f97c7ed751c3b13429cf3f135d03e06e71
3
+ size 3515
log.txt CHANGED
The diff for this file is too large to render. See raw diff
 
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3e60aee58bb3002247500f1d529cca009a081ea94dc8ec603e656e128eb6897
3
  size 269468281
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0b07c5c7fc85dd0dfb66ea5fe8504c1a41a9ec2a4fb4454228c53a694d2d63
3
  size 269468281
runs/Jan15_21-34-13_turing/1673814853.9309754/events.out.tfevents.1673814853.turing.327173.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d99bd48e1e69b39e42e7e7a111f5813a2df37a546fb6bacb892b68cfcab9b8
3
+ size 5588
runs/Jan15_21-34-13_turing/events.out.tfevents.1673814853.turing.327173.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a30eb94ec311a4244c985461ab9aa705cdf93050fcec6fcfa2cb9c8110aef5
3
+ size 4006
runs/Jan15_21-38-50_turing/1673815130.6693852/events.out.tfevents.1673815130.turing.327344.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2108c88a320146c9d7c9086b61374f2318936d1e4962ae7c1ead830c839c66e
3
+ size 5588
runs/Jan15_21-38-50_turing/events.out.tfevents.1673815130.turing.327344.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03b63169eea176cdba36f0a377b01059662552d65be602090a9ddc75c4988e7
3
+ size 4006
runs/Jan15_21-44-32_turing/1673815478.7136974/events.out.tfevents.1673815478.turing.327590.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fe18d2ad203a2fca17317161706fe1d48ff0bd3d4aa58ddd3786f66ee732e8d
3
+ size 5614
runs/Jan15_21-44-32_turing/1673816409.4189365/events.out.tfevents.1673816409.turing.327590.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eedfc518d3c9ada6bc4edb1d7acdc69eea238eef562fb5983158bd98891c4f3b
3
+ size 5614
runs/Jan15_21-44-32_turing/1673816930.061229/events.out.tfevents.1673816930.turing.327590.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f199bef9b59b52a88ac347dc0611408be16552cf1407f4e91f9abc3a603155
3
+ size 5614
runs/Jan15_21-44-32_turing/1673817441.0883248/events.out.tfevents.1673817441.turing.327590.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f47aa4ff22fa3c39e19eef3d8d7f74e15eaad70caed3426c8785c3416f7c57
3
+ size 5614
runs/Jan15_21-44-32_turing/events.out.tfevents.1673815478.turing.327590.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0db4d4de36b41c4986a5581bd3f70fad45bcc5a1839d9f07ffe3f2039d230f9
3
+ size 16008
runs/Jan15_22-28-28_turing/1673818114.7901142/events.out.tfevents.1673818114.turing.328391.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d412669f79ed37eb2b3550ed1f61ef5e7ee18755c70f0a0f013d113466f767
3
+ size 5617
runs/Jan15_22-28-28_turing/events.out.tfevents.1673818114.turing.328391.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a4f52c4d22249d42aae1a0c4d851ed9e590be0f45b8596b1978a35272eca20
3
+ size 4030
runs/Jan15_22-47-19_turing/1673819245.5556467/events.out.tfevents.1673819245.turing.328732.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9addc809c33f1ed0e2b6e95fb5f0823429ed6463fd572186b9b8ad02a56e1161
3
+ size 5617
runs/Jan15_22-47-19_turing/events.out.tfevents.1673819245.turing.328732.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbdf618a68f2360da89225b17fe7026187bcdb9635d64cdf9529da8764639fa1
3
+ size 4301
special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
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 DELETED
@@ -1,348 +0,0 @@
1
- {
2
- "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
5
- "added_tokens": [
6
- {
7
- "id": 0,
8
- "special": true,
9
- "content": "<s>",
10
- "single_word": false,
11
- "lstrip": false,
12
- "rstrip": false,
13
- "normalized": true
14
- },
15
- {
16
- "id": 1,
17
- "special": true,
18
- "content": "<pad>",
19
- "single_word": false,
20
- "lstrip": false,
21
- "rstrip": false,
22
- "normalized": true
23
- },
24
- {
25
- "id": 2,
26
- "special": true,
27
- "content": "</s>",
28
- "single_word": false,
29
- "lstrip": false,
30
- "rstrip": false,
31
- "normalized": true
32
- },
33
- {
34
- "id": 3,
35
- "special": true,
36
- "content": "<unk>",
37
- "single_word": false,
38
- "lstrip": false,
39
- "rstrip": false,
40
- "normalized": true
41
- },
42
- {
43
- "id": 4,
44
- "special": true,
45
- "content": "<mask>",
46
- "single_word": false,
47
- "lstrip": true,
48
- "rstrip": false,
49
- "normalized": true
50
- }
51
- ],
52
- "normalizer": null,
53
- "pre_tokenizer": {
54
- "type": "ByteLevel",
55
- "add_prefix_space": false,
56
- "trim_offsets": true
57
- },
58
- "post_processor": {
59
- "type": "RobertaProcessing",
60
- "sep": [
61
- "</s>",
62
- 2
63
- ],
64
- "cls": [
65
- "<s>",
66
- 0
67
- ],
68
- "trim_offsets": true,
69
- "add_prefix_space": false
70
- },
71
- "decoder": {
72
- "type": "ByteLevel",
73
- "add_prefix_space": true,
74
- "trim_offsets": true
75
- },
76
- "model": {
77
- "type": "BPE",
78
- "dropout": null,
79
- "unk_token": null,
80
- "continuing_subword_prefix": "",
81
- "end_of_word_suffix": "",
82
- "fuse_unk": false,
83
- "vocab": {
84
- "<s>": 0,
85
- "<pad>": 1,
86
- "</s>": 2,
87
- "<unk>": 3,
88
- "<mask>": 4,
89
- "!": 5,
90
- "\"": 6,
91
- "#": 7,
92
- "$": 8,
93
- "%": 9,
94
- "&": 10,
95
- "'": 11,
96
- "(": 12,
97
- ")": 13,
98
- "*": 14,
99
- "+": 15,
100
- ",": 16,
101
- "-": 17,
102
- ".": 18,
103
- "/": 19,
104
- "0": 20,
105
- "1": 21,
106
- "2": 22,
107
- "3": 23,
108
- "4": 24,
109
- "5": 25,
110
- "6": 26,
111
- "7": 27,
112
- "8": 28,
113
- "9": 29,
114
- ":": 30,
115
- ";": 31,
116
- "<": 32,
117
- "=": 33,
118
- ">": 34,
119
- "?": 35,
120
- "@": 36,
121
- "A": 37,
122
- "B": 38,
123
- "C": 39,
124
- "D": 40,
125
- "E": 41,
126
- "F": 42,
127
- "G": 43,
128
- "H": 44,
129
- "I": 45,
130
- "J": 46,
131
- "K": 47,
132
- "L": 48,
133
- "M": 49,
134
- "N": 50,
135
- "O": 51,
136
- "P": 52,
137
- "Q": 53,
138
- "R": 54,
139
- "S": 55,
140
- "T": 56,
141
- "U": 57,
142
- "V": 58,
143
- "W": 59,
144
- "X": 60,
145
- "Y": 61,
146
- "Z": 62,
147
- "[": 63,
148
- "\\": 64,
149
- "]": 65,
150
- "^": 66,
151
- "_": 67,
152
- "`": 68,
153
- "a": 69,
154
- "b": 70,
155
- "c": 71,
156
- "d": 72,
157
- "e": 73,
158
- "f": 74,
159
- "g": 75,
160
- "h": 76,
161
- "i": 77,
162
- "j": 78,
163
- "k": 79,
164
- "l": 80,
165
- "m": 81,
166
- "n": 82,
167
- "o": 83,
168
- "p": 84,
169
- "q": 85,
170
- "r": 86,
171
- "s": 87,
172
- "t": 88,
173
- "u": 89,
174
- "v": 90,
175
- "w": 91,
176
- "x": 92,
177
- "y": 93,
178
- "z": 94,
179
- "{": 95,
180
- "|": 96,
181
- "}": 97,
182
- "~": 98,
183
- "¡": 99,
184
- "¢": 100,
185
- "£": 101,
186
- "¤": 102,
187
- "¥": 103,
188
- "¦": 104,
189
- "§": 105,
190
- "¨": 106,
191
- "©": 107,
192
- "ª": 108,
193
- "«": 109,
194
- "¬": 110,
195
- "®": 111,
196
- "¯": 112,
197
- "°": 113,
198
- "±": 114,
199
- "²": 115,
200
- "³": 116,
201
- "´": 117,
202
- "µ": 118,
203
- "¶": 119,
204
- "·": 120,
205
- "¸": 121,
206
- "¹": 122,
207
- "º": 123,
208
- "»": 124,
209
- "¼": 125,
210
- "½": 126,
211
- "¾": 127,
212
- "¿": 128,
213
- "À": 129,
214
- "Á": 130,
215
- "Â": 131,
216
- "Ã": 132,
217
- "Ä": 133,
218
- "Å": 134,
219
- "Æ": 135,
220
- "Ç": 136,
221
- "È": 137,
222
- "É": 138,
223
- "Ê": 139,
224
- "Ë": 140,
225
- "Ì": 141,
226
- "Í": 142,
227
- "Î": 143,
228
- "Ï": 144,
229
- "Ð": 145,
230
- "Ñ": 146,
231
- "Ò": 147,
232
- "Ó": 148,
233
- "Ô": 149,
234
- "Õ": 150,
235
- "Ö": 151,
236
- "×": 152,
237
- "Ø": 153,
238
- "Ù": 154,
239
- "Ú": 155,
240
- "Û": 156,
241
- "Ü": 157,
242
- "Ý": 158,
243
- "Þ": 159,
244
- "ß": 160,
245
- "à": 161,
246
- "á": 162,
247
- "â": 163,
248
- "ã": 164,
249
- "ä": 165,
250
- "å": 166,
251
- "æ": 167,
252
- "ç": 168,
253
- "è": 169,
254
- "é": 170,
255
- "ê": 171,
256
- "ë": 172,
257
- "ì": 173,
258
- "í": 174,
259
- "î": 175,
260
- "ï": 176,
261
- "ð": 177,
262
- "ñ": 178,
263
- "ò": 179,
264
- "ó": 180,
265
- "ô": 181,
266
- "õ": 182,
267
- "ö": 183,
268
- "÷": 184,
269
- "ø": 185,
270
- "ù": 186,
271
- "ú": 187,
272
- "û": 188,
273
- "ü": 189,
274
- "ý": 190,
275
- "þ": 191,
276
- "ÿ": 192,
277
- "Ā": 193,
278
- "ā": 194,
279
- "Ă": 195,
280
- "ă": 196,
281
- "Ą": 197,
282
- "ą": 198,
283
- "Ć": 199,
284
- "ć": 200,
285
- "Ĉ": 201,
286
- "ĉ": 202,
287
- "Ċ": 203,
288
- "ċ": 204,
289
- "Č": 205,
290
- "č": 206,
291
- "Ď": 207,
292
- "ď": 208,
293
- "Đ": 209,
294
- "đ": 210,
295
- "Ē": 211,
296
- "ē": 212,
297
- "Ĕ": 213,
298
- "ĕ": 214,
299
- "Ė": 215,
300
- "ė": 216,
301
- "Ę": 217,
302
- "ę": 218,
303
- "Ě": 219,
304
- "ě": 220,
305
- "Ĝ": 221,
306
- "ĝ": 222,
307
- "Ğ": 223,
308
- "ğ": 224,
309
- "Ġ": 225,
310
- "ġ": 226,
311
- "Ģ": 227,
312
- "ģ": 228,
313
- "Ĥ": 229,
314
- "ĥ": 230,
315
- "Ħ": 231,
316
- "ħ": 232,
317
- "Ĩ": 233,
318
- "ĩ": 234,
319
- "Ī": 235,
320
- "ī": 236,
321
- "Ĭ": 237,
322
- "ĭ": 238,
323
- "Į": 239,
324
- "į": 240,
325
- "İ": 241,
326
- "ı": 242,
327
- "IJ": 243,
328
- "ij": 244,
329
- "Ĵ": 245,
330
- "ĵ": 246,
331
- "Ķ": 247,
332
- "ķ": 248,
333
- "ĸ": 249,
334
- "Ĺ": 250,
335
- "ĺ": 251,
336
- "Ļ": 252,
337
- "ļ": 253,
338
- "Ľ": 254,
339
- "ľ": 255,
340
- "Ŀ": 256,
341
- "ŀ": 257,
342
- "Ł": 258,
343
- "ł": 259,
344
- "Ń": 260
345
- },
346
- "merges": []
347
- }
348
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json DELETED
@@ -1,64 +0,0 @@
1
- {
2
- "add_prefix_space": false,
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
- "name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
37
- "pad_token": {
38
- "__type": "AddedToken",
39
- "content": "<pad>",
40
- "lstrip": false,
41
- "normalized": true,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
- "sep_token": {
46
- "__type": "AddedToken",
47
- "content": "</s>",
48
- "lstrip": false,
49
- "normalized": true,
50
- "rstrip": false,
51
- "single_word": false
52
- },
53
- "special_tokens_map_file": null,
54
- "tokenizer_class": "RobertaTokenizer",
55
- "trim_offsets": true,
56
- "unk_token": {
57
- "__type": "AddedToken",
58
- "content": "<unk>",
59
- "lstrip": false,
60
- "normalized": true,
61
- "rstrip": false,
62
- "single_word": false
63
- }
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2354b21c0eb02b167b9d6057f7fbae73d5ab7eeb327be5d088eb30bf0019608
3
- size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76e096e9f1e6ee51628944ab73e15f97c7ed751c3b13429cf3f135d03e06e71
3
+ size 3515
vocab.json CHANGED
The diff for this file is too large to render. See raw diff