Commit
β’
0c23640
1
Parent(s):
b91a3a8
Training in progress, step 500
Browse files- {checkpoint-200 β checkpoint-500}/config.json +0 -0
- {checkpoint-200 β checkpoint-500}/optimizer.pt +2 -2
- {checkpoint-200 β checkpoint-500}/preprocessor_config.json +0 -0
- {checkpoint-200 β checkpoint-500}/pytorch_model.bin +1 -1
- {checkpoint-200 β checkpoint-500}/rng_state.pth +1 -1
- {checkpoint-200 β checkpoint-500}/scaler.pt +1 -1
- {checkpoint-200 β checkpoint-500}/scheduler.pt +1 -1
- {checkpoint-200 β checkpoint-500}/trainer_state.json +210 -3
- {checkpoint-200 β checkpoint-500}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-200 β checkpoint-500}/config.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-500}/optimizer.pt
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:e1851d90640fae1429c8bc6e2baa16e7ce7bcbc2c9e0360292b57c63705f63c3
|
3 |
+
size 2490346001
|
{checkpoint-200 β checkpoint-500}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-500}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262067185
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d37d8b46fff81cb7c0632707f6755c972760efacc89d90558f854dc54bd880e
|
3 |
size 1262067185
|
{checkpoint-200 β checkpoint-500}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba1dab228290b3826ffb1f6e748f9ca7c766ef71c09288a7f28a9b4fc91edd7
|
3 |
size 14567
|
{checkpoint-200 β checkpoint-500}/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 sha256:1c304e72bfea7592d4ddcc6e3b3b1a9bcab2965ed75957d798b3560c75dbe7d8
|
3 |
size 559
|
{checkpoint-200 β checkpoint-500}/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:d329f7de106210c9b555181c590d8fd032215809ecb1e289ee83b0ce08346df0
|
3 |
size 623
|
{checkpoint-200 β checkpoint-500}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -144,11 +144,218 @@
|
|
144 |
"eval_steps_per_second": 1.114,
|
145 |
"eval_wer": 1.0,
|
146 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
147 |
}
|
148 |
],
|
149 |
"max_steps": 6501,
|
150 |
"num_train_epochs": 3,
|
151 |
-
"total_flos":
|
152 |
"trial_name": null,
|
153 |
"trial_params": null
|
154 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2306805074971165,
|
5 |
+
"global_step": 500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
144 |
"eval_steps_per_second": 1.114,
|
145 |
"eval_wer": 1.0,
|
146 |
"step": 200
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.1,
|
150 |
+
"learning_rate": 7.414050235478806e-05,
|
151 |
+
"loss": 3.1612,
|
152 |
+
"step": 210
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.1,
|
156 |
+
"learning_rate": 7.402276295133437e-05,
|
157 |
+
"loss": 3.0375,
|
158 |
+
"step": 220
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.11,
|
162 |
+
"learning_rate": 7.390502354788069e-05,
|
163 |
+
"loss": 3.08,
|
164 |
+
"step": 230
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.11,
|
168 |
+
"learning_rate": 7.3787284144427e-05,
|
169 |
+
"loss": 3.2809,
|
170 |
+
"step": 240
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.12,
|
174 |
+
"learning_rate": 7.368131868131867e-05,
|
175 |
+
"loss": 3.5351,
|
176 |
+
"step": 250
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.12,
|
180 |
+
"learning_rate": 7.356357927786499e-05,
|
181 |
+
"loss": 3.01,
|
182 |
+
"step": 260
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.12,
|
186 |
+
"learning_rate": 7.34458398744113e-05,
|
187 |
+
"loss": 3.0006,
|
188 |
+
"step": 270
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.13,
|
192 |
+
"learning_rate": 7.33281004709576e-05,
|
193 |
+
"loss": 3.0397,
|
194 |
+
"step": 280
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.13,
|
198 |
+
"learning_rate": 7.321036106750392e-05,
|
199 |
+
"loss": 3.1733,
|
200 |
+
"step": 290
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.14,
|
204 |
+
"learning_rate": 7.310439560439559e-05,
|
205 |
+
"loss": 3.5007,
|
206 |
+
"step": 300
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.14,
|
210 |
+
"eval_loss": 3.068483591079712,
|
211 |
+
"eval_runtime": 129.9806,
|
212 |
+
"eval_samples_per_second": 35.544,
|
213 |
+
"eval_steps_per_second": 1.116,
|
214 |
+
"eval_wer": 1.0,
|
215 |
+
"step": 300
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.14,
|
219 |
+
"learning_rate": 7.29866562009419e-05,
|
220 |
+
"loss": 2.9984,
|
221 |
+
"step": 310
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.15,
|
225 |
+
"learning_rate": 7.286891679748822e-05,
|
226 |
+
"loss": 3.0006,
|
227 |
+
"step": 320
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.15,
|
231 |
+
"learning_rate": 7.275117739403453e-05,
|
232 |
+
"loss": 3.029,
|
233 |
+
"step": 330
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.16,
|
237 |
+
"learning_rate": 7.263343799058085e-05,
|
238 |
+
"loss": 3.158,
|
239 |
+
"step": 340
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.16,
|
243 |
+
"learning_rate": 7.252747252747252e-05,
|
244 |
+
"loss": 3.4909,
|
245 |
+
"step": 350
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.17,
|
249 |
+
"learning_rate": 7.240973312401883e-05,
|
250 |
+
"loss": 3.001,
|
251 |
+
"step": 360
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.17,
|
255 |
+
"learning_rate": 7.229199372056515e-05,
|
256 |
+
"loss": 2.9925,
|
257 |
+
"step": 370
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.18,
|
261 |
+
"learning_rate": 7.217425431711145e-05,
|
262 |
+
"loss": 3.0009,
|
263 |
+
"step": 380
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.18,
|
267 |
+
"learning_rate": 7.205651491365776e-05,
|
268 |
+
"loss": 3.1263,
|
269 |
+
"step": 390
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.18,
|
273 |
+
"learning_rate": 7.195054945054944e-05,
|
274 |
+
"loss": 3.421,
|
275 |
+
"step": 400
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.18,
|
279 |
+
"eval_loss": 3.0357792377471924,
|
280 |
+
"eval_runtime": 130.0328,
|
281 |
+
"eval_samples_per_second": 35.529,
|
282 |
+
"eval_steps_per_second": 1.115,
|
283 |
+
"eval_wer": 1.0,
|
284 |
+
"step": 400
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.19,
|
288 |
+
"learning_rate": 7.183281004709575e-05,
|
289 |
+
"loss": 3.0018,
|
290 |
+
"step": 410
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.19,
|
294 |
+
"learning_rate": 7.171507064364207e-05,
|
295 |
+
"loss": 2.9947,
|
296 |
+
"step": 420
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.2,
|
300 |
+
"learning_rate": 7.159733124018838e-05,
|
301 |
+
"loss": 2.9935,
|
302 |
+
"step": 430
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.2,
|
306 |
+
"learning_rate": 7.147959183673469e-05,
|
307 |
+
"loss": 3.0818,
|
308 |
+
"step": 440
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.21,
|
312 |
+
"learning_rate": 7.137362637362637e-05,
|
313 |
+
"loss": 3.3386,
|
314 |
+
"step": 450
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.21,
|
318 |
+
"learning_rate": 7.125588697017268e-05,
|
319 |
+
"loss": 3.0803,
|
320 |
+
"step": 460
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.22,
|
324 |
+
"learning_rate": 7.1138147566719e-05,
|
325 |
+
"loss": 3.1655,
|
326 |
+
"step": 470
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.22,
|
330 |
+
"learning_rate": 7.10204081632653e-05,
|
331 |
+
"loss": 3.0899,
|
332 |
+
"step": 480
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.23,
|
336 |
+
"learning_rate": 7.090266875981161e-05,
|
337 |
+
"loss": 3.1638,
|
338 |
+
"step": 490
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.23,
|
342 |
+
"learning_rate": 7.079670329670328e-05,
|
343 |
+
"loss": 3.3518,
|
344 |
+
"step": 500
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.23,
|
348 |
+
"eval_loss": 2.9412434101104736,
|
349 |
+
"eval_runtime": 130.1575,
|
350 |
+
"eval_samples_per_second": 35.495,
|
351 |
+
"eval_steps_per_second": 1.114,
|
352 |
+
"eval_wer": 1.0,
|
353 |
+
"step": 500
|
354 |
}
|
355 |
],
|
356 |
"max_steps": 6501,
|
357 |
"num_train_epochs": 3,
|
358 |
+
"total_flos": 9.466107317116815e+18,
|
359 |
"trial_name": null,
|
360 |
"trial_params": null
|
361 |
}
|
{checkpoint-200 β checkpoint-500}/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 1262067185
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d37d8b46fff81cb7c0632707f6755c972760efacc89d90558f854dc54bd880e
|
3 |
size 1262067185
|