Hugging Face's logo

DeskDown
/
MarianMix_en-zh_to_vi-ms-hi-ja

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Inference Endpoints
Model card Files Metrics Community
1
DeskDown commited on
Commit
c804ffb
•
1 Parent(s): 1b1396c

Training in progress, step 20000

Browse files
Files changed (12) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +135 -5
  7. last-checkpoint/training_args.bin +1 -1
  8. pytorch_model.bin +1 -1
  9. runs/Jan12_10-19-43_b9e9bdc6eb9d/1641991038.3060858/events.out.tfevents.1641991038.b9e9bdc6eb9d.34.5 +3 -0
  10. runs/Jan12_10-19-43_b9e9bdc6eb9d/events.out.tfevents.1641982794.b9e9bdc6eb9d.34.2 +2 -2
  11. runs/Jan12_10-19-43_b9e9bdc6eb9d/events.out.tfevents.1641991038.b9e9bdc6eb9d.34.4 +3 -0
  12. training_args.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b82e0d8a25c4e2d10df4f17ff176a4dcab751e1e5f7da8c4ce56bf434c4a19c0
3
  size 768802253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752e784baeb68d1c9923d9d62a3c329e62ab9fdbf22228b7c0f8a318a83627d7
3
  size 768802253
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f0d973f47679db77ad91a94a432ffd8d3c21e58045823622e88099f7b521793
3
  size 384827845
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6573c4bc18e2a61cf0c28bf5a6af6212623b123a90dd3fb773405bbb29c926e3
3
  size 384827845
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:106f38b2915671d1b908c32b3cbf76f01989ec6112a9eb279119ddf4d98c6009
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede870873a7c24c1a0beea75c0401dcac5fdbaa4e62d8623dc8430904d8ed8b0
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2a4914ac33c232452b9952cfe6dce5403de9b2d4a7036f821d3c1ed1060b07a
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c7bbb3bb8d454db6eb177c9b403f0e20a9ed397b38673d4bc0399800f81c3b
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d466bae241df304cf88e4f0d3631f7db64bc42748c26fa5646641cbbad6810e3
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2efd5a45f3a1a3b9155ec0a3c31df929efd109ad68fb16d48d2fa4b605c6b98a
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.5587188612099645,
5
- "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -136,11 +136,141 @@
136
  "eval_samples_per_second": 11.892,
137
  "eval_steps_per_second": 0.373,
138
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
139
  }
140
  ],
141
- "max_steps": 14050,
142
- "num_train_epochs": 5,
143
- "total_flos": 2.169210609126605e+16,
144
  "trial_name": null,
145
  "trial_params": null
146
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 7.117437722419929,
5
+ "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
136
  "eval_samples_per_second": 11.892,
137
  "eval_steps_per_second": 0.373,
138
  "step": 10000
139
+ },
140
+ {
141
+ "epoch": 3.74,
142
+ "learning_rate": 2.5292022792022797e-05,
143
+ "loss": 0.4957,
144
+ "step": 10500
145
+ },
146
+ {
147
+ "epoch": 3.91,
148
+ "learning_rate": 2.173076923076923e-05,
149
+ "loss": 0.4974,
150
+ "step": 11000
151
+ },
152
+ {
153
+ "epoch": 4.09,
154
+ "learning_rate": 1.817663817663818e-05,
155
+ "loss": 0.4834,
156
+ "step": 11500
157
+ },
158
+ {
159
+ "epoch": 4.27,
160
+ "learning_rate": 1.4615384615384617e-05,
161
+ "loss": 0.4756,
162
+ "step": 12000
163
+ },
164
+ {
165
+ "epoch": 4.45,
166
+ "learning_rate": 1.1054131054131055e-05,
167
+ "loss": 0.4713,
168
+ "step": 12500
169
+ },
170
+ {
171
+ "epoch": 4.63,
172
+ "learning_rate": 7.492877492877494e-06,
173
+ "loss": 0.4682,
174
+ "step": 13000
175
+ },
176
+ {
177
+ "epoch": 4.8,
178
+ "learning_rate": 3.9316239316239315e-06,
179
+ "loss": 0.4713,
180
+ "step": 13500
181
+ },
182
+ {
183
+ "epoch": 4.98,
184
+ "learning_rate": 3.7749287749287755e-07,
185
+ "loss": 0.4758,
186
+ "step": 14000
187
+ },
188
+ {
189
+ "epoch": 5.16,
190
+ "learning_rate": 0.0,
191
+ "loss": 0.4562,
192
+ "step": 14500
193
+ },
194
+ {
195
+ "epoch": 5.34,
196
+ "learning_rate": 0.0,
197
+ "loss": 0.457,
198
+ "step": 15000
199
+ },
200
+ {
201
+ "epoch": 5.52,
202
+ "learning_rate": 0.0,
203
+ "loss": 0.4522,
204
+ "step": 15500
205
+ },
206
+ {
207
+ "epoch": 5.69,
208
+ "learning_rate": 0.0,
209
+ "loss": 0.4607,
210
+ "step": 16000
211
+ },
212
+ {
213
+ "epoch": 5.87,
214
+ "learning_rate": 0.0,
215
+ "loss": 0.4508,
216
+ "step": 16500
217
+ },
218
+ {
219
+ "epoch": 6.05,
220
+ "learning_rate": 0.0,
221
+ "loss": 0.4547,
222
+ "step": 17000
223
+ },
224
+ {
225
+ "epoch": 6.23,
226
+ "learning_rate": 0.0,
227
+ "loss": 0.4495,
228
+ "step": 17500
229
+ },
230
+ {
231
+ "epoch": 6.41,
232
+ "learning_rate": 0.0,
233
+ "loss": 0.4565,
234
+ "step": 18000
235
+ },
236
+ {
237
+ "epoch": 6.58,
238
+ "learning_rate": 0.0,
239
+ "loss": 0.4553,
240
+ "step": 18500
241
+ },
242
+ {
243
+ "epoch": 6.76,
244
+ "learning_rate": 0.0,
245
+ "loss": 0.4521,
246
+ "step": 19000
247
+ },
248
+ {
249
+ "epoch": 6.94,
250
+ "learning_rate": 0.0,
251
+ "loss": 0.4621,
252
+ "step": 19500
253
+ },
254
+ {
255
+ "epoch": 7.12,
256
+ "learning_rate": 0.0,
257
+ "loss": 0.4585,
258
+ "step": 20000
259
+ },
260
+ {
261
+ "epoch": 7.12,
262
+ "eval_bleu": 9.9179,
263
+ "eval_gen_len": 36.9039,
264
+ "eval_loss": 0.6802528500556946,
265
+ "eval_runtime": 335.8822,
266
+ "eval_samples_per_second": 11.861,
267
+ "eval_steps_per_second": 0.372,
268
+ "step": 20000
269
  }
270
  ],
271
+ "max_steps": 28100,
272
+ "num_train_epochs": 10,
273
+ "total_flos": 4.338326302831411e+16,
274
  "trial_name": null,
275
  "trial_params": null
276
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a36939be1771359f3b477e541ab1d6ae1de57d2c29ccbf158d1775562e8e679
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6531c9d30a62e077e8076f79d72df2135c5bd907f1406e82761b60b1635897
3
  size 3055
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f0d973f47679db77ad91a94a432ffd8d3c21e58045823622e88099f7b521793
3
  size 384827845
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6573c4bc18e2a61cf0c28bf5a6af6212623b123a90dd3fb773405bbb29c926e3
3
  size 384827845
runs/Jan12_10-19-43_b9e9bdc6eb9d/1641991038.3060858/events.out.tfevents.1641991038.b9e9bdc6eb9d.34.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687c505ed76ce6e2ba175eab373af00ca1f73774da027b4725ec78a7fddeb56a
3
+ size 4783
runs/Jan12_10-19-43_b9e9bdc6eb9d/events.out.tfevents.1641982794.b9e9bdc6eb9d.34.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f51a7a3bdf6998ae2da30f3c398b721caa626cbff8e1e2f7e75879173d8ef841
3
- size 7612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:501c97d2c608ee4facbae265096aeab9e7cd502c540172327ffb755a4627c0ae
3
+ size 9222
runs/Jan12_10-19-43_b9e9bdc6eb9d/events.out.tfevents.1641991038.b9e9bdc6eb9d.34.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0c37d7720ac7b3208368bbb8d98297d7671d3dc692966079a60d44227da9bd
3
+ size 7672
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a36939be1771359f3b477e541ab1d6ae1de57d2c29ccbf158d1775562e8e679
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6531c9d30a62e077e8076f79d72df2135c5bd907f1406e82761b60b1635897
3
  size 3055