marinone94
commited on
Commit
β’
fdf3f3d
1
Parent(s):
ac1c759
Training in progress, step 700
Browse files- {checkpoint-400 β checkpoint-700}/config.json +0 -0
- {checkpoint-400 β checkpoint-700}/optimizer.pt +1 -1
- {checkpoint-400 β checkpoint-700}/preprocessor_config.json +0 -0
- {checkpoint-400 β checkpoint-700}/pytorch_model.bin +1 -1
- {checkpoint-400 β checkpoint-700}/rng_state.pth +2 -2
- {checkpoint-400 β checkpoint-700}/scaler.pt +1 -1
- {checkpoint-400 β checkpoint-700}/scheduler.pt +1 -1
- {checkpoint-400 β checkpoint-700}/trainer_state.json +120 -3
- {checkpoint-400 β checkpoint-700}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-400 β checkpoint-700}/config.json
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-700}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490337809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2734597abb10a2a590cf139e66decfdf1bc18e26d32aa5f4749a68f74109f763
|
3 |
size 2490337809
|
{checkpoint-400 β checkpoint-700}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-400 β checkpoint-700}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:866e0246bd78706b1bfb6c07818d34662e459927e54718460f8a950f5fc33ae8
|
3 |
size 1262063089
|
{checkpoint-400 β checkpoint-700}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21798b4aee64ae056ff3e0e6a64832942beff047fe94bbbddb9d06dcf74d9125
|
3 |
+
size 14567
|
{checkpoint-400 β checkpoint-700}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fb213daf5cce18a5f92167ca14da9df084d907f2b9796efc4666630f312b58c
|
3 |
size 559
|
{checkpoint-400 β checkpoint-700}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcdecc30328ffcc8e9b8e7d7b6cfb5d7c85a8e3d5e777d680eff74cf60f2dc24
|
3 |
size 623
|
{checkpoint-400 β checkpoint-700}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -162,11 +162,128 @@
|
|
162 |
"eval_steps_per_second": 0.766,
|
163 |
"eval_wer": 1.0,
|
164 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
165 |
}
|
166 |
],
|
167 |
"max_steps": 4550,
|
168 |
"num_train_epochs": 50,
|
169 |
-
"total_flos":
|
170 |
"trial_name": null,
|
171 |
"trial_params": null
|
172 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.688524590163935,
|
5 |
+
"global_step": 700,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
162 |
"eval_steps_per_second": 0.766,
|
163 |
"eval_wer": 1.0,
|
164 |
"step": 400
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 4.61,
|
168 |
+
"learning_rate": 5.25e-05,
|
169 |
+
"loss": 3.0309,
|
170 |
+
"step": 420
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.83,
|
174 |
+
"learning_rate": 5.5e-05,
|
175 |
+
"loss": 3.0259,
|
176 |
+
"step": 440
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 5.05,
|
180 |
+
"learning_rate": 5.75e-05,
|
181 |
+
"loss": 3.0998,
|
182 |
+
"step": 460
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 5.27,
|
186 |
+
"learning_rate": 6e-05,
|
187 |
+
"loss": 3.0152,
|
188 |
+
"step": 480
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 5.49,
|
192 |
+
"learning_rate": 6.25e-05,
|
193 |
+
"loss": 3.0129,
|
194 |
+
"step": 500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 5.49,
|
198 |
+
"eval_loss": 3.039973497390747,
|
199 |
+
"eval_runtime": 190.8567,
|
200 |
+
"eval_samples_per_second": 25.375,
|
201 |
+
"eval_steps_per_second": 0.796,
|
202 |
+
"eval_wer": 1.0,
|
203 |
+
"step": 500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 5.71,
|
207 |
+
"learning_rate": 6.500000000000001e-05,
|
208 |
+
"loss": 3.0088,
|
209 |
+
"step": 520
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 5.93,
|
213 |
+
"learning_rate": 6.75e-05,
|
214 |
+
"loss": 3.0051,
|
215 |
+
"step": 540
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 6.15,
|
219 |
+
"learning_rate": 7.000000000000001e-05,
|
220 |
+
"loss": 3.073,
|
221 |
+
"step": 560
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 6.37,
|
225 |
+
"learning_rate": 7.25e-05,
|
226 |
+
"loss": 3.0031,
|
227 |
+
"step": 580
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 6.59,
|
231 |
+
"learning_rate": 7.5e-05,
|
232 |
+
"loss": 2.9964,
|
233 |
+
"step": 600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.59,
|
237 |
+
"eval_loss": 2.998962640762329,
|
238 |
+
"eval_runtime": 193.5213,
|
239 |
+
"eval_samples_per_second": 25.026,
|
240 |
+
"eval_steps_per_second": 0.785,
|
241 |
+
"eval_wer": 1.0,
|
242 |
+
"step": 600
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.81,
|
246 |
+
"learning_rate": 7.75e-05,
|
247 |
+
"loss": 2.9921,
|
248 |
+
"step": 620
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 7.03,
|
252 |
+
"learning_rate": 8e-05,
|
253 |
+
"loss": 3.0665,
|
254 |
+
"step": 640
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.25,
|
258 |
+
"learning_rate": 8.25e-05,
|
259 |
+
"loss": 2.9826,
|
260 |
+
"step": 660
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 7.47,
|
264 |
+
"learning_rate": 8.5e-05,
|
265 |
+
"loss": 2.9689,
|
266 |
+
"step": 680
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 7.69,
|
270 |
+
"learning_rate": 8.75e-05,
|
271 |
+
"loss": 2.9602,
|
272 |
+
"step": 700
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 7.69,
|
276 |
+
"eval_loss": 2.9620397090911865,
|
277 |
+
"eval_runtime": 193.5851,
|
278 |
+
"eval_samples_per_second": 25.017,
|
279 |
+
"eval_steps_per_second": 0.785,
|
280 |
+
"eval_wer": 1.0,
|
281 |
+
"step": 700
|
282 |
}
|
283 |
],
|
284 |
"max_steps": 4550,
|
285 |
"num_train_epochs": 50,
|
286 |
+
"total_flos": 1.0835835827730653e+19,
|
287 |
"trial_name": null,
|
288 |
"trial_params": null
|
289 |
}
|
{checkpoint-400 β checkpoint-700}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:866e0246bd78706b1bfb6c07818d34662e459927e54718460f8a950f5fc33ae8
|
3 |
size 1262063089
|