Training in progress, step 2600, 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 sha256:3ac93ba84e679b3bfdbed1aa4a511fc2fd7668cb8d73b38aaa9593401908fe44
|
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:de577d967c10e597c8c23b3751a4e00f403786cbf695cd42dc5741fe4de523ad
|
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 sha256:85a355cfb19d81e3463ec580a4d7cbcf7f7cfb13b0254e266e3297bbafa58661
|
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:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
|
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": 1.
|
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,
|
@@ -357,13 +357,27 @@
|
|
357 |
"eval_samples_per_second": 30.499,
|
358 |
"eval_steps_per_second": 3.816,
|
359 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 100,
|
363 |
"max_steps": 4116,
|
364 |
"num_train_epochs": 3,
|
365 |
"save_steps": 100,
|
366 |
-
"total_flos": 7.
|
367 |
"trial_name": null,
|
368 |
"trial_params": null
|
369 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.1318325996398926,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2600",
|
4 |
+
"epoch": 1.8943533697632058,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
357 |
"eval_samples_per_second": 30.499,
|
358 |
"eval_steps_per_second": 3.816,
|
359 |
"step": 2500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.89,
|
363 |
+
"learning_rate": 0.0002,
|
364 |
+
"loss": 2.1232,
|
365 |
+
"step": 2600
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.89,
|
369 |
+
"eval_loss": 2.1318325996398926,
|
370 |
+
"eval_runtime": 205.4314,
|
371 |
+
"eval_samples_per_second": 30.541,
|
372 |
+
"eval_steps_per_second": 3.821,
|
373 |
+
"step": 2600
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 100,
|
377 |
"max_steps": 4116,
|
378 |
"num_train_epochs": 3,
|
379 |
"save_steps": 100,
|
380 |
+
"total_flos": 7.590446666901504e+16,
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
383 |
}
|