Hugging Face's logo

NightMachinery
/
lang_adapter_fa_twitter_multilingual_base_cased2

TensorBoard
Generated from Trainer
Model card Files
xet
 Metrics Community
NightMachinery commited on
Commit
878494c
·
1 Parent(s): c437119

Model save

Browse files
Files changed (14) hide show
  1. last-checkpoint/optimizer.pt +0 -3
  2. last-checkpoint/rng_state.pth +0 -3
  3. last-checkpoint/scheduler.pt +0 -3
  4. last-checkpoint/special_tokens_map.json +0 -7
  5. last-checkpoint/tokenizer.json +0 -0
  6. last-checkpoint/tokenizer_config.json +0 -14
  7. last-checkpoint/trainer_state.json +0 -256
  8. last-checkpoint/training_args.bin +0 -3
  9. last-checkpoint/vocab.txt +0 -0
  10. {last-checkpoint/mlm → mlm}/adapter_config.json +0 -0
  11. {last-checkpoint/mlm → mlm}/head_config.json +0 -0
  12. {last-checkpoint/mlm → mlm}/pytorch_adapter.bin +0 -0
  13. {last-checkpoint/mlm → mlm}/pytorch_model_head.bin +0 -0
  14. runs/Mar03_03-30-32_9cd65751e33a/events.out.tfevents.1677814395.9cd65751e33a.1322.0 +2 -2
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3c2b8bbf43b349af3969daa737c97f381bf05fe2579a5c89afefb6ba5b69a6b
3
- size 15254021
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e8fcd7f56e38ec6c23074a812939da90f1adfbec39e4984dcc0d6f23e38abd9
3
- size 14575
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa2995201bca0a6269b8d04d7cc21810ee2748251f6ff31dec5602126bf4c67b
3
- size 627
 
 
 
 
last-checkpoint/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
last-checkpoint/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "do_lower_case": false,
4
- "mask_token": "[MASK]",
5
- "model_max_length": 512,
6
- "name_or_path": "bert-base-multilingual-cased",
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "special_tokens_map_file": null,
10
- "strip_accents": null,
11
- "tokenize_chinese_chars": true,
12
- "tokenizer_class": "BertTokenizer",
13
- "unk_token": "[UNK]"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,256 +0,0 @@
1
- {
2
- "best_metric": 1.691104769706726,
3
- "best_model_checkpoint": "./test-mlm/checkpoint-8000",
4
- "epoch": 9.501187648456057,
5
- "global_step": 8000,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.59,
12
- "learning_rate": 0.00047030878859857485,
13
- "loss": 2.5064,
14
- "step": 500
15
- },
16
- {
17
- "epoch": 0.59,
18
- "eval_accuracy": 0.5923440629322982,
19
- "eval_loss": 2.000737190246582,
20
- "eval_runtime": 40.8995,
21
- "eval_samples_per_second": 15.99,
22
- "eval_steps_per_second": 2.005,
23
- "step": 500
24
- },
25
- {
26
- "epoch": 1.19,
27
- "learning_rate": 0.0004406175771971497,
28
- "loss": 2.3261,
29
- "step": 1000
30
- },
31
- {
32
- "epoch": 1.19,
33
- "eval_accuracy": 0.6004155844155844,
34
- "eval_loss": 1.9369549751281738,
35
- "eval_runtime": 40.9751,
36
- "eval_samples_per_second": 15.961,
37
- "eval_steps_per_second": 2.001,
38
- "step": 1000
39
- },
40
- {
41
- "epoch": 1.78,
42
- "learning_rate": 0.00041092636579572443,
43
- "loss": 2.2689,
44
- "step": 1500
45
- },
46
- {
47
- "epoch": 1.78,
48
- "eval_accuracy": 0.6049467180826803,
49
- "eval_loss": 1.9199129343032837,
50
- "eval_runtime": 40.8894,
51
- "eval_samples_per_second": 15.994,
52
- "eval_steps_per_second": 2.005,
53
- "step": 1500
54
- },
55
- {
56
- "epoch": 2.38,
57
- "learning_rate": 0.00038123515439429927,
58
- "loss": 2.2101,
59
- "step": 2000
60
- },
61
- {
62
- "epoch": 2.38,
63
- "eval_accuracy": 0.6167493796526055,
64
- "eval_loss": 1.8502798080444336,
65
- "eval_runtime": 41.0954,
66
- "eval_samples_per_second": 15.914,
67
- "eval_steps_per_second": 1.995,
68
- "step": 2000
69
- },
70
- {
71
- "epoch": 2.97,
72
- "learning_rate": 0.0003515439429928741,
73
- "loss": 2.2015,
74
- "step": 2500
75
- },
76
- {
77
- "epoch": 2.97,
78
- "eval_accuracy": 0.6148145072557039,
79
- "eval_loss": 1.858150601387024,
80
- "eval_runtime": 40.9285,
81
- "eval_samples_per_second": 15.979,
82
- "eval_steps_per_second": 2.003,
83
- "step": 2500
84
- },
85
- {
86
- "epoch": 3.56,
87
- "learning_rate": 0.00032185273159144896,
88
- "loss": 2.1468,
89
- "step": 3000
90
- },
91
- {
92
- "epoch": 3.56,
93
- "eval_accuracy": 0.6186465352300141,
94
- "eval_loss": 1.8364105224609375,
95
- "eval_runtime": 40.9793,
96
- "eval_samples_per_second": 15.959,
97
- "eval_steps_per_second": 2.001,
98
- "step": 3000
99
- },
100
- {
101
- "epoch": 4.16,
102
- "learning_rate": 0.00029216152019002374,
103
- "loss": 2.1213,
104
- "step": 3500
105
- },
106
- {
107
- "epoch": 4.16,
108
- "eval_accuracy": 0.6203441651000888,
109
- "eval_loss": 1.8127774000167847,
110
- "eval_runtime": 40.94,
111
- "eval_samples_per_second": 15.975,
112
- "eval_steps_per_second": 2.003,
113
- "step": 3500
114
- },
115
- {
116
- "epoch": 4.75,
117
- "learning_rate": 0.0002624703087885986,
118
- "loss": 2.0938,
119
- "step": 4000
120
- },
121
- {
122
- "epoch": 4.75,
123
- "eval_accuracy": 0.6253609489581818,
124
- "eval_loss": 1.788784384727478,
125
- "eval_runtime": 41.0869,
126
- "eval_samples_per_second": 15.917,
127
- "eval_steps_per_second": 1.996,
128
- "step": 4000
129
- },
130
- {
131
- "epoch": 5.34,
132
- "learning_rate": 0.0002327790973871734,
133
- "loss": 2.0888,
134
- "step": 4500
135
- },
136
- {
137
- "epoch": 5.34,
138
- "eval_accuracy": 0.628534333525678,
139
- "eval_loss": 1.7835372686386108,
140
- "eval_runtime": 41.0712,
141
- "eval_samples_per_second": 15.924,
142
- "eval_steps_per_second": 1.997,
143
- "step": 4500
144
- },
145
- {
146
- "epoch": 5.94,
147
- "learning_rate": 0.00020308788598574824,
148
- "loss": 2.0619,
149
- "step": 5000
150
- },
151
- {
152
- "epoch": 5.94,
153
- "eval_accuracy": 0.6320160722422434,
154
- "eval_loss": 1.7468773126602173,
155
- "eval_runtime": 41.0197,
156
- "eval_samples_per_second": 15.944,
157
- "eval_steps_per_second": 1.999,
158
- "step": 5000
159
- },
160
- {
161
- "epoch": 6.53,
162
- "learning_rate": 0.00017339667458432303,
163
- "loss": 2.045,
164
- "step": 5500
165
- },
166
- {
167
- "epoch": 6.53,
168
- "eval_accuracy": 0.6350336264873254,
169
- "eval_loss": 1.7321710586547852,
170
- "eval_runtime": 41.1615,
171
- "eval_samples_per_second": 15.889,
172
- "eval_steps_per_second": 1.992,
173
- "step": 5500
174
- },
175
- {
176
- "epoch": 7.13,
177
- "learning_rate": 0.00014370546318289787,
178
- "loss": 2.032,
179
- "step": 6000
180
- },
181
- {
182
- "epoch": 7.13,
183
- "eval_accuracy": 0.6363391096814361,
184
- "eval_loss": 1.7278571128845215,
185
- "eval_runtime": 41.1852,
186
- "eval_samples_per_second": 15.88,
187
- "eval_steps_per_second": 1.991,
188
- "step": 6000
189
- },
190
- {
191
- "epoch": 7.72,
192
- "learning_rate": 0.00011401425178147269,
193
- "loss": 2.012,
194
- "step": 6500
195
- },
196
- {
197
- "epoch": 7.72,
198
- "eval_accuracy": 0.6403126628452319,
199
- "eval_loss": 1.7044711112976074,
200
- "eval_runtime": 41.1592,
201
- "eval_samples_per_second": 15.89,
202
- "eval_steps_per_second": 1.992,
203
- "step": 6500
204
- },
205
- {
206
- "epoch": 8.31,
207
- "learning_rate": 8.432304038004752e-05,
208
- "loss": 1.9992,
209
- "step": 7000
210
- },
211
- {
212
- "epoch": 8.31,
213
- "eval_accuracy": 0.6397965988662888,
214
- "eval_loss": 1.7062609195709229,
215
- "eval_runtime": 40.9227,
216
- "eval_samples_per_second": 15.981,
217
- "eval_steps_per_second": 2.004,
218
- "step": 7000
219
- },
220
- {
221
- "epoch": 8.91,
222
- "learning_rate": 5.463182897862233e-05,
223
- "loss": 1.993,
224
- "step": 7500
225
- },
226
- {
227
- "epoch": 8.91,
228
- "eval_accuracy": 0.640505019145193,
229
- "eval_loss": 1.7070534229278564,
230
- "eval_runtime": 41.0391,
231
- "eval_samples_per_second": 15.936,
232
- "eval_steps_per_second": 1.998,
233
- "step": 7500
234
- },
235
- {
236
- "epoch": 9.5,
237
- "learning_rate": 2.494061757719715e-05,
238
- "loss": 1.9774,
239
- "step": 8000
240
- },
241
- {
242
- "epoch": 9.5,
243
- "eval_accuracy": 0.6419018087855297,
244
- "eval_loss": 1.691104769706726,
245
- "eval_runtime": 41.0068,
246
- "eval_samples_per_second": 15.949,
247
- "eval_steps_per_second": 2.0,
248
- "step": 8000
249
- }
250
- ],
251
- "max_steps": 8420,
252
- "num_train_epochs": 10,
253
- "total_flos": 1.708466984750592e+16,
254
- "trial_name": null,
255
- "trial_params": null
256
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:875c2cee79b69d7b43584d5fe462ea6c4bffb20a43dd76d238ec3c7ad6f0f180
3
- size 3515
 
 
 
 
last-checkpoint/vocab.txt DELETED
The diff for this file is too large to render. See raw diff
 
{last-checkpoint/mlm → mlm}/adapter_config.json RENAMED
File without changes
{last-checkpoint/mlm → mlm}/head_config.json RENAMED
File without changes
{last-checkpoint/mlm → mlm}/pytorch_adapter.bin RENAMED
File without changes
{last-checkpoint/mlm → mlm}/pytorch_model_head.bin RENAMED
File without changes
runs/Mar03_03-30-32_9cd65751e33a/events.out.tfevents.1677814395.9cd65751e33a.1322.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa5e9f6e923798b0bf47cce16fa53b5b3d64f0ec0a5d5d7387b4a1ec94b973d1
3
- size 12828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef68060ef47ad1d3ce68523a7faa1b14dc1d7ce04919b91116ab4a87616638d
3
+ size 13182