marinone94
commited on
Commit
β’
cbb2361
1
Parent(s):
68a7db5
Training in progress, step 800
Browse files- {checkpoint-500 β checkpoint-800}/config.json +0 -0
- {checkpoint-500 β checkpoint-800}/optimizer.pt +1 -1
- {checkpoint-500 β checkpoint-800}/preprocessor_config.json +0 -0
- {checkpoint-500 β checkpoint-800}/pytorch_model.bin +1 -1
- {checkpoint-500 β checkpoint-800}/rng_state.pth +2 -2
- {checkpoint-500 β checkpoint-800}/scaler.pt +1 -1
- {checkpoint-500 β checkpoint-800}/scheduler.pt +1 -1
- {checkpoint-500 β checkpoint-800}/trainer_state.json +120 -3
- {checkpoint-500 β checkpoint-800}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-500 β checkpoint-800}/config.json
RENAMED
File without changes
|
{checkpoint-500 β checkpoint-800}/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 sha256:58d40f21a27bc7f1923c7d04f34f438f664d524cd4a03d73ddd945feffa415cb
|
3 |
size 2490337809
|
{checkpoint-500 β checkpoint-800}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-500 β checkpoint-800}/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 sha256:4cfc19f8f8b247c6b5050f32c8b2bf68b9bdc2656dafb45faf51286ab02eec5e
|
3 |
size 1262063089
|
{checkpoint-500 β checkpoint-800}/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 sha256:8e1a22fa0fe527ae7807404dd534e45dc9526c41b4d88efd52d4ea3de5ea2d81
|
3 |
+
size 14567
|
{checkpoint-500 β checkpoint-800}/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 sha256:60c51dda6298af7ed612d10ff39b3f233c2bf5ffd32d965c0c08263e14858ea9
|
3 |
size 559
|
{checkpoint-500 β checkpoint-800}/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 sha256:179d0711ab8fef56ecf9a9aea25248daf43634aa94dfc5cfe7a4eb224c90b32e
|
3 |
size 623
|
{checkpoint-500 β checkpoint-800}/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,
|
@@ -201,11 +201,128 @@
|
|
201 |
"eval_steps_per_second": 0.778,
|
202 |
"eval_wer": 1.0,
|
203 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
204 |
}
|
205 |
],
|
206 |
"max_steps": 6516,
|
207 |
"num_train_epochs": 3,
|
208 |
-
"total_flos":
|
209 |
"trial_name": null,
|
210 |
"trial_params": null
|
211 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.36819698538718215,
|
5 |
+
"global_step": 800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
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 |
+
"epoch": 0.33,
|
285 |
+
"learning_rate": 6.824588880187941e-05,
|
286 |
+
"loss": 3.298,
|
287 |
+
"step": 720
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.34,
|
291 |
+
"learning_rate": 6.801096319498825e-05,
|
292 |
+
"loss": 3.1669,
|
293 |
+
"step": 740
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.35,
|
297 |
+
"learning_rate": 6.778778386844165e-05,
|
298 |
+
"loss": 3.2651,
|
299 |
+
"step": 760
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.36,
|
303 |
+
"learning_rate": 6.75528582615505e-05,
|
304 |
+
"loss": 3.1562,
|
305 |
+
"step": 780
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.37,
|
309 |
+
"learning_rate": 6.732967893500391e-05,
|
310 |
+
"loss": 3.3254,
|
311 |
+
"step": 800
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.37,
|
315 |
+
"eval_loss": 3.0070509910583496,
|
316 |
+
"eval_runtime": 192.0978,
|
317 |
+
"eval_samples_per_second": 25.211,
|
318 |
+
"eval_steps_per_second": 0.791,
|
319 |
+
"eval_wer": 1.0,
|
320 |
+
"step": 800
|
321 |
}
|
322 |
],
|
323 |
"max_steps": 6516,
|
324 |
"num_train_epochs": 3,
|
325 |
+
"total_flos": 1.5225400497310126e+19,
|
326 |
"trial_name": null,
|
327 |
"trial_params": null
|
328 |
}
|
{checkpoint-500 β checkpoint-800}/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 sha256:4cfc19f8f8b247c6b5050f32c8b2bf68b9bdc2656dafb45faf51286ab02eec5e
|
3 |
size 1262063089
|