Commit
•
690d196
1
Parent(s):
624e6b4
Training in progress, step 3500, 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 75507072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:027649fdc9bb39375f7877e818837eec9151d245c636ff7645c95d33d3a52732
|
3 |
size 75507072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151034501
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ff7270ada9cf8cf5634d4915d2aa34fa7bf7f529feeec57587911f95fff17cb
|
3 |
size 151034501
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5111e44aa3c7fb3d2679f29ed14de9b378a43fa023e1e3c7c0e2bac399b6ea6f
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -483,13 +483,27 @@
|
|
483 |
"eval_samples_per_second": 14.984,
|
484 |
"eval_steps_per_second": 1.875,
|
485 |
"step": 3400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
486 |
}
|
487 |
],
|
488 |
"logging_steps": 100,
|
489 |
"max_steps": 4116,
|
490 |
"num_train_epochs": 3,
|
491 |
"save_steps": 100,
|
492 |
-
"total_flos": 1.
|
493 |
"trial_name": null,
|
494 |
"trial_params": null
|
495 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.128933310508728,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3500",
|
4 |
+
"epoch": 2.5500910746812386,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
483 |
"eval_samples_per_second": 14.984,
|
484 |
"eval_steps_per_second": 1.875,
|
485 |
"step": 3400
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.55,
|
489 |
+
"learning_rate": 0.0002,
|
490 |
+
"loss": 1.1112,
|
491 |
+
"step": 3500
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 2.55,
|
495 |
+
"eval_loss": 1.128933310508728,
|
496 |
+
"eval_runtime": 418.5353,
|
497 |
+
"eval_samples_per_second": 14.99,
|
498 |
+
"eval_steps_per_second": 1.876,
|
499 |
+
"step": 3500
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 100,
|
503 |
"max_steps": 4116,
|
504 |
"num_train_epochs": 3,
|
505 |
"save_steps": 100,
|
506 |
+
"total_flos": 1.134669408060162e+18,
|
507 |
"trial_name": null,
|
508 |
"trial_params": null
|
509 |
}
|