Training in progress, step 24, 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 590925768
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:821c41d055ae43f59583b224aef0fe6ca8460f3f504843f558ed73ec4187c4ec
|
3 |
size 590925768
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 296481140
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15de9aec4da225a8f0e059686a990002242615ab62bd169ea8cf051f430d8003
|
3 |
size 296481140
|
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:b1f07cfba84b1c996956e2762438ed7721853a912845f8535ca55de1e28dc131
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -367,6 +367,78 @@
|
|
367 |
"rewards/margins": 0.0006919947918504477,
|
368 |
"rewards/rejected": -0.1387580782175064,
|
369 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
370 |
}
|
371 |
],
|
372 |
"logging_steps": 1.0,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.03506609136360523,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 24,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
367 |
"rewards/margins": 0.0006919947918504477,
|
368 |
"rewards/rejected": -0.1387580782175064,
|
369 |
"step": 20
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.030682829943154577,
|
373 |
+
"grad_norm": 0.5434465408325195,
|
374 |
+
"learning_rate": 9.989452106587406e-06,
|
375 |
+
"log_odds_chosen": 0.012862562201917171,
|
376 |
+
"log_odds_ratio": -0.7206666469573975,
|
377 |
+
"logits/chosen": -2.1785006523132324,
|
378 |
+
"logits/rejected": -2.181265354156494,
|
379 |
+
"logps/chosen": -1.2523807287216187,
|
380 |
+
"logps/rejected": -1.2531023025512695,
|
381 |
+
"loss": 1.5781,
|
382 |
+
"nll_loss": 1.5060465335845947,
|
383 |
+
"rewards/accuracies": 0.421875,
|
384 |
+
"rewards/chosen": -0.1252380609512329,
|
385 |
+
"rewards/margins": 7.216550875455141e-05,
|
386 |
+
"rewards/rejected": -0.1253102421760559,
|
387 |
+
"step": 21
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.032143917083304795,
|
391 |
+
"grad_norm": 0.6211642026901245,
|
392 |
+
"learning_rate": 9.987892079051531e-06,
|
393 |
+
"log_odds_chosen": 0.012624351307749748,
|
394 |
+
"log_odds_ratio": -0.7291357517242432,
|
395 |
+
"logits/chosen": -2.179482936859131,
|
396 |
+
"logits/rejected": -2.176547050476074,
|
397 |
+
"logps/chosen": -1.3581693172454834,
|
398 |
+
"logps/rejected": -1.3609216213226318,
|
399 |
+
"loss": 1.6565,
|
400 |
+
"nll_loss": 1.5835901498794556,
|
401 |
+
"rewards/accuracies": 0.359375,
|
402 |
+
"rewards/chosen": -0.13581693172454834,
|
403 |
+
"rewards/margins": 0.0002752433065325022,
|
404 |
+
"rewards/rejected": -0.1360921710729599,
|
405 |
+
"step": 22
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.03360500422345501,
|
409 |
+
"grad_norm": 0.769701361656189,
|
410 |
+
"learning_rate": 9.986224643009375e-06,
|
411 |
+
"log_odds_chosen": 0.03776140883564949,
|
412 |
+
"log_odds_ratio": -0.6954489946365356,
|
413 |
+
"logits/chosen": -2.1131434440612793,
|
414 |
+
"logits/rejected": -2.1170055866241455,
|
415 |
+
"logps/chosen": -1.2192529439926147,
|
416 |
+
"logps/rejected": -1.2428308725357056,
|
417 |
+
"loss": 1.519,
|
418 |
+
"nll_loss": 1.4494192600250244,
|
419 |
+
"rewards/accuracies": 0.453125,
|
420 |
+
"rewards/chosen": -0.12192529439926147,
|
421 |
+
"rewards/margins": 0.0023577904794365168,
|
422 |
+
"rewards/rejected": -0.1242830902338028,
|
423 |
+
"step": 23
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.03506609136360523,
|
427 |
+
"grad_norm": 0.6579698324203491,
|
428 |
+
"learning_rate": 9.984449834367251e-06,
|
429 |
+
"log_odds_chosen": -0.08287765085697174,
|
430 |
+
"log_odds_ratio": -0.7655948400497437,
|
431 |
+
"logits/chosen": -2.117600440979004,
|
432 |
+
"logits/rejected": -2.118288993835449,
|
433 |
+
"logps/chosen": -1.3066436052322388,
|
434 |
+
"logps/rejected": -1.2814935445785522,
|
435 |
+
"loss": 1.5987,
|
436 |
+
"nll_loss": 1.5221776962280273,
|
437 |
+
"rewards/accuracies": 0.46875,
|
438 |
+
"rewards/chosen": -0.13066436350345612,
|
439 |
+
"rewards/margins": -0.0025150016881525517,
|
440 |
+
"rewards/rejected": -0.1281493604183197,
|
441 |
+
"step": 24
|
442 |
}
|
443 |
],
|
444 |
"logging_steps": 1.0,
|