Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 26008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eea02a42e3c436a9d9ca773b10f834e7afb91e0f46930df7e9f9e294ebf95f54
|
3 |
size 26008
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61926
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9b55d55ff6e805a3e78a7c97d51ebd215c85fb8543012712355f01aa220618f
|
3 |
size 61926
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3531fd590b8fd6fcbddb61e6b46ac1b997cf7cef5113053fb7f5015848c30f35
|
3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29bc15d430c252c1243d6e8d1875dc4c35f8e88790da8d78ff009203f04072e9
|
3 |
size 14512
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -312,6 +312,83 @@
|
|
312 |
"eval_samples_per_second": 121.464,
|
313 |
"eval_steps_per_second": 30.509,
|
314 |
"step": 39
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
315 |
}
|
316 |
],
|
317 |
"logging_steps": 1,
|
@@ -326,12 +403,12 @@
|
|
326 |
"should_evaluate": false,
|
327 |
"should_log": false,
|
328 |
"should_save": true,
|
329 |
-
"should_training_stop":
|
330 |
},
|
331 |
"attributes": {}
|
332 |
}
|
333 |
},
|
334 |
-
"total_flos":
|
335 |
"train_batch_size": 2,
|
336 |
"trial_name": null,
|
337 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7916872835230084,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
312 |
"eval_samples_per_second": 121.464,
|
313 |
"eval_steps_per_second": 30.509,
|
314 |
"step": 39
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.6333498268184067,
|
318 |
+
"grad_norm": 0.008273452520370483,
|
319 |
+
"learning_rate": 1.0332332985438248e-05,
|
320 |
+
"loss": 11.9306,
|
321 |
+
"step": 40
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.6491835724888669,
|
325 |
+
"grad_norm": 0.0072366236709058285,
|
326 |
+
"learning_rate": 8.426519384872733e-06,
|
327 |
+
"loss": 11.9315,
|
328 |
+
"step": 41
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.6650173181593271,
|
332 |
+
"grad_norm": 0.007517676800489426,
|
333 |
+
"learning_rate": 6.698729810778065e-06,
|
334 |
+
"loss": 11.9309,
|
335 |
+
"step": 42
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.6808510638297872,
|
339 |
+
"grad_norm": 0.00758866872638464,
|
340 |
+
"learning_rate": 5.156362923365588e-06,
|
341 |
+
"loss": 11.9314,
|
342 |
+
"step": 43
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.6966848095002474,
|
346 |
+
"grad_norm": 0.006661114748567343,
|
347 |
+
"learning_rate": 3.8060233744356633e-06,
|
348 |
+
"loss": 11.9313,
|
349 |
+
"step": 44
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.7125185551707076,
|
353 |
+
"grad_norm": 0.007711367215961218,
|
354 |
+
"learning_rate": 2.653493525244721e-06,
|
355 |
+
"loss": 11.9301,
|
356 |
+
"step": 45
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.7283523008411678,
|
360 |
+
"grad_norm": 0.005763665772974491,
|
361 |
+
"learning_rate": 1.70370868554659e-06,
|
362 |
+
"loss": 11.9307,
|
363 |
+
"step": 46
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.7441860465116279,
|
367 |
+
"grad_norm": 0.006471547763794661,
|
368 |
+
"learning_rate": 9.607359798384785e-07,
|
369 |
+
"loss": 11.9307,
|
370 |
+
"step": 47
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.760019792182088,
|
374 |
+
"grad_norm": 0.00781251024454832,
|
375 |
+
"learning_rate": 4.277569313094809e-07,
|
376 |
+
"loss": 11.9312,
|
377 |
+
"step": 48
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.7758535378525483,
|
381 |
+
"grad_norm": 0.0064762914553284645,
|
382 |
+
"learning_rate": 1.0705383806982606e-07,
|
383 |
+
"loss": 11.931,
|
384 |
+
"step": 49
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.7916872835230084,
|
388 |
+
"grad_norm": 0.00732074398547411,
|
389 |
+
"learning_rate": 0.0,
|
390 |
+
"loss": 11.9304,
|
391 |
+
"step": 50
|
392 |
}
|
393 |
],
|
394 |
"logging_steps": 1,
|
|
|
403 |
"should_evaluate": false,
|
404 |
"should_log": false,
|
405 |
"should_save": true,
|
406 |
+
"should_training_stop": true
|
407 |
},
|
408 |
"attributes": {}
|
409 |
}
|
410 |
},
|
411 |
+
"total_flos": 1208519884800.0,
|
412 |
"train_batch_size": 2,
|
413 |
"trial_name": null,
|
414 |
"trial_params": null
|