Training in progress, step 13500, 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 3424816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e114d1cf986fb612752ba70fb0ea17cb79352616af50e33cfc89ace788d3b72
|
3 |
size 3424816
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3447162
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6163818d4bd20de9be429c12036c9bb1da392b50e19a30f533745961246d38f4
|
3 |
size 3447162
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adbac4581908b419c3039e502a4aacf8ebe77d7c5097a659c9e661f2ab321b78
|
3 |
size 14244
|
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 sha256:7eeb85a3c5947dca7875fa9a54d0371a562d757985dcc841d33c689ef8bd64c7
|
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":
|
5 |
"eval_steps": 900,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -456,6 +456,37 @@
|
|
456 |
"eval_samples_per_second": 1.62,
|
457 |
"eval_steps_per_second": 0.102,
|
458 |
"step": 12600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
459 |
}
|
460 |
],
|
461 |
"logging_steps": 900,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 900,
|
6 |
+
"global_step": 13500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
456 |
"eval_samples_per_second": 1.62,
|
457 |
"eval_steps_per_second": 0.102,
|
458 |
"step": 12600
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 3.0,
|
462 |
+
"grad_norm": 5.375,
|
463 |
+
"learning_rate": 0.0,
|
464 |
+
"logits/chosen": -3.2291133403778076,
|
465 |
+
"logits/rejected": -3.2376110553741455,
|
466 |
+
"logps/chosen": -156.7918701171875,
|
467 |
+
"logps/rejected": -134.85708618164062,
|
468 |
+
"loss": 0.6898,
|
469 |
+
"rewards/accuracies": 0.527222216129303,
|
470 |
+
"rewards/chosen": 0.03252815455198288,
|
471 |
+
"rewards/margins": 0.01564921624958515,
|
472 |
+
"rewards/rejected": 0.016878938302397728,
|
473 |
+
"step": 13500
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 3.0,
|
477 |
+
"eval_logits/chosen": -3.013054370880127,
|
478 |
+
"eval_logits/rejected": -3.0272860527038574,
|
479 |
+
"eval_logps/chosen": -157.42190551757812,
|
480 |
+
"eval_logps/rejected": -135.01458740234375,
|
481 |
+
"eval_loss": 0.6845603585243225,
|
482 |
+
"eval_rewards/accuracies": 0.5476190447807312,
|
483 |
+
"eval_rewards/chosen": 0.04152738302946091,
|
484 |
+
"eval_rewards/margins": 0.026597492396831512,
|
485 |
+
"eval_rewards/rejected": 0.014929892495274544,
|
486 |
+
"eval_runtime": 616.7592,
|
487 |
+
"eval_samples_per_second": 1.621,
|
488 |
+
"eval_steps_per_second": 0.102,
|
489 |
+
"step": 13500
|
490 |
}
|
491 |
],
|
492 |
"logging_steps": 900,
|