Training in progress, step 3300, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc2f2d160bdfb1d0e93ecfc8b7c923f2fc777d1f5743442a22f8f2c4066e9baa
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03c6f77f55e11d319ec955dc81fb8f9d0a93150cdf5dad62fa65c4dd6df9a859
|
3 |
size 18902665
|
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 sha256:03b32db0a2b713dd6b1e7016c32489b8ad860f5a342471d86c52b5af270bb99a
|
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:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
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,
|
@@ -455,13 +455,27 @@
|
|
455 |
"eval_samples_per_second": 30.267,
|
456 |
"eval_steps_per_second": 3.787,
|
457 |
"step": 3200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
458 |
}
|
459 |
],
|
460 |
"logging_steps": 100,
|
461 |
"max_steps": 4116,
|
462 |
"num_train_epochs": 3,
|
463 |
"save_steps": 100,
|
464 |
-
"total_flos": 9.
|
465 |
"trial_name": null,
|
466 |
"trial_params": null
|
467 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.031524896621704,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3300",
|
4 |
+
"epoch": 2.4043715846994536,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
455 |
"eval_samples_per_second": 30.267,
|
456 |
"eval_steps_per_second": 3.787,
|
457 |
"step": 3200
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.4,
|
461 |
+
"learning_rate": 0.0002,
|
462 |
+
"loss": 1.9896,
|
463 |
+
"step": 3300
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 2.4,
|
467 |
+
"eval_loss": 2.031524896621704,
|
468 |
+
"eval_runtime": 254.9126,
|
469 |
+
"eval_samples_per_second": 24.612,
|
470 |
+
"eval_steps_per_second": 3.079,
|
471 |
+
"step": 3300
|
472 |
}
|
473 |
],
|
474 |
"logging_steps": 100,
|
475 |
"max_steps": 4116,
|
476 |
"num_train_epochs": 3,
|
477 |
"save_steps": 100,
|
478 |
+
"total_flos": 9.691971842875392e+16,
|
479 |
"trial_name": null,
|
480 |
"trial_params": null
|
481 |
}
|