marinone94
commited on
Commit
β’
68a7db5
1
Parent(s):
b91d3fa
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 +1 -1
- {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:fe48dc95f416a61e29c9b384b89669597e505aff37f490432393562fd09a7ebc
|
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 sha256:63e29b0b3051d81c522bbad5fd8008db0773293cc66ac34f89d0bc18968817eb
|
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 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:299f0081a5cbf561a975f939c328f4686396da29b3233cdb8a83cc793fe92137
|
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:dd9adbb7bf7a7b94e5da4d383115b816c16f892b14cb7df333d0775ae0f262ae
|
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:e5e288f5acef38cf681fd34cf5dbd19393d9b7a69196a87d07c084d3bc82290e
|
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": 0.
|
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": 0.798,
|
163 |
"eval_wer": 1.0,
|
164 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
165 |
}
|
166 |
],
|
167 |
"max_steps": 6516,
|
168 |
"num_train_epochs": 3,
|
169 |
-
"total_flos":
|
170 |
"trial_name": null,
|
171 |
"trial_params": null
|
172 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.32217236221378437,
|
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": 0.798,
|
163 |
"eval_wer": 1.0,
|
164 |
"step": 400
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.19,
|
168 |
+
"learning_rate": 7.172278778386843e-05,
|
169 |
+
"loss": 2.9993,
|
170 |
+
"step": 420
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2,
|
174 |
+
"learning_rate": 7.148786217697727e-05,
|
175 |
+
"loss": 3.0555,
|
176 |
+
"step": 440
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.21,
|
180 |
+
"learning_rate": 7.126468285043069e-05,
|
181 |
+
"loss": 3.1879,
|
182 |
+
"step": 460
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.22,
|
186 |
+
"learning_rate": 7.102975724353953e-05,
|
187 |
+
"loss": 2.9861,
|
188 |
+
"step": 480
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.23,
|
192 |
+
"learning_rate": 7.080657791699295e-05,
|
193 |
+
"loss": 3.0833,
|
194 |
+
"step": 500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.23,
|
198 |
+
"eval_loss": 2.9769718647003174,
|
199 |
+
"eval_runtime": 195.2639,
|
200 |
+
"eval_samples_per_second": 24.802,
|
201 |
+
"eval_steps_per_second": 0.778,
|
202 |
+
"eval_wer": 1.0,
|
203 |
+
"step": 500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.24,
|
207 |
+
"learning_rate": 7.05716523101018e-05,
|
208 |
+
"loss": 3.1608,
|
209 |
+
"step": 520
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.25,
|
213 |
+
"learning_rate": 7.033672670321064e-05,
|
214 |
+
"loss": 3.0206,
|
215 |
+
"step": 540
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.26,
|
219 |
+
"learning_rate": 7.01018010963195e-05,
|
220 |
+
"loss": 3.0523,
|
221 |
+
"step": 560
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.27,
|
225 |
+
"learning_rate": 6.986687548942835e-05,
|
226 |
+
"loss": 3.0222,
|
227 |
+
"step": 580
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.28,
|
231 |
+
"learning_rate": 6.964369616288175e-05,
|
232 |
+
"loss": 3.0913,
|
233 |
+
"step": 600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.28,
|
237 |
+
"eval_loss": 3.052091598510742,
|
238 |
+
"eval_runtime": 189.8149,
|
239 |
+
"eval_samples_per_second": 25.514,
|
240 |
+
"eval_steps_per_second": 0.801,
|
241 |
+
"eval_wer": 1.0,
|
242 |
+
"step": 600
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.29,
|
246 |
+
"learning_rate": 6.94087705559906e-05,
|
247 |
+
"loss": 3.1987,
|
248 |
+
"step": 620
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.29,
|
252 |
+
"learning_rate": 6.917384494909944e-05,
|
253 |
+
"loss": 3.1504,
|
254 |
+
"step": 640
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.3,
|
258 |
+
"learning_rate": 6.893891934220829e-05,
|
259 |
+
"loss": 3.2406,
|
260 |
+
"step": 660
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.31,
|
264 |
+
"learning_rate": 6.870399373531715e-05,
|
265 |
+
"loss": 3.0632,
|
266 |
+
"step": 680
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.32,
|
270 |
+
"learning_rate": 6.848081440877055e-05,
|
271 |
+
"loss": 3.1487,
|
272 |
+
"step": 700
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.32,
|
276 |
+
"eval_loss": 3.1951305866241455,
|
277 |
+
"eval_runtime": 196.8636,
|
278 |
+
"eval_samples_per_second": 24.601,
|
279 |
+
"eval_steps_per_second": 0.772,
|
280 |
+
"eval_wer": 1.0,
|
281 |
+
"step": 700
|
282 |
}
|
283 |
],
|
284 |
"max_steps": 6516,
|
285 |
"num_train_epochs": 3,
|
286 |
+
"total_flos": 1.3316117705308692e+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 sha256:63e29b0b3051d81c522bbad5fd8008db0773293cc66ac34f89d0bc18968817eb
|
3 |
size 1262063089
|