polejowska
commited on
Commit
•
7447b89
1
Parent(s):
3554a84
End of training
Browse files- trainer_state.json +84 -14
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd\\checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -288,18 +288,88 @@
|
|
288 |
"step": 92120
|
289 |
},
|
290 |
{
|
291 |
-
"epoch":
|
292 |
-
"
|
293 |
-
"
|
294 |
-
"
|
295 |
-
|
296 |
-
|
297 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
298 |
}
|
299 |
],
|
300 |
-
"max_steps":
|
301 |
-
"num_train_epochs":
|
302 |
-
"total_flos": 3.
|
303 |
"trial_name": null,
|
304 |
"trial_params": null
|
305 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.5818963050842285,
|
3 |
+
"best_model_checkpoint": "detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd\\checkpoint-115150",
|
4 |
+
"epoch": 25.0,
|
5 |
+
"global_step": 115150,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
288 |
"step": 92120
|
289 |
},
|
290 |
{
|
291 |
+
"epoch": 21.0,
|
292 |
+
"learning_rate": 1.603821102909249e-06,
|
293 |
+
"loss": 2.0165,
|
294 |
+
"step": 96726
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 21.0,
|
298 |
+
"eval_loss": 1.6092338562011719,
|
299 |
+
"eval_runtime": 906.9743,
|
300 |
+
"eval_samples_per_second": 1.964,
|
301 |
+
"eval_steps_per_second": 0.246,
|
302 |
+
"step": 96726
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 22.0,
|
306 |
+
"learning_rate": 1.2039079461571863e-06,
|
307 |
+
"loss": 2.007,
|
308 |
+
"step": 101332
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 22.0,
|
312 |
+
"eval_loss": 1.5986328125,
|
313 |
+
"eval_runtime": 1255.6495,
|
314 |
+
"eval_samples_per_second": 1.418,
|
315 |
+
"eval_steps_per_second": 0.178,
|
316 |
+
"step": 101332
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 23.0,
|
320 |
+
"learning_rate": 8.039947894051238e-07,
|
321 |
+
"loss": 2.0009,
|
322 |
+
"step": 105938
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 23.0,
|
326 |
+
"eval_loss": 1.5931391716003418,
|
327 |
+
"eval_runtime": 1400.4232,
|
328 |
+
"eval_samples_per_second": 1.272,
|
329 |
+
"eval_steps_per_second": 0.159,
|
330 |
+
"step": 105938
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 24.0,
|
334 |
+
"learning_rate": 4.041684759009987e-07,
|
335 |
+
"loss": 1.992,
|
336 |
+
"step": 110544
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 24.0,
|
340 |
+
"eval_loss": 1.5898462533950806,
|
341 |
+
"eval_runtime": 1322.312,
|
342 |
+
"eval_samples_per_second": 1.347,
|
343 |
+
"eval_steps_per_second": 0.169,
|
344 |
+
"step": 110544
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 25.0,
|
348 |
+
"learning_rate": 4.342162396873643e-09,
|
349 |
+
"loss": 1.9769,
|
350 |
+
"step": 115150
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 25.0,
|
354 |
+
"eval_loss": 1.5818963050842285,
|
355 |
+
"eval_runtime": 1441.7733,
|
356 |
+
"eval_samples_per_second": 1.235,
|
357 |
+
"eval_steps_per_second": 0.155,
|
358 |
+
"step": 115150
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 25.0,
|
362 |
+
"step": 115150,
|
363 |
+
"total_flos": 3.874481502652799e+20,
|
364 |
+
"train_loss": 0.3997329824549501,
|
365 |
+
"train_runtime": 88532.2397,
|
366 |
+
"train_samples_per_second": 5.202,
|
367 |
+
"train_steps_per_second": 1.301
|
368 |
}
|
369 |
],
|
370 |
+
"max_steps": 115150,
|
371 |
+
"num_train_epochs": 25,
|
372 |
+
"total_flos": 3.874481502652799e+20,
|
373 |
"trial_name": null,
|
374 |
"trial_params": null
|
375 |
}
|