Training in progress, step 2900, 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:da2e87ad67863518d5ced7d76001d0a52f2bf719897ca25fdeda24caecaf8666
|
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 sha256:1812f3546006f87a8e3660d593982345bb664173a3973bfd1e05394d12e7a9f6
|
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:a16dbd92b02a89cf372eb0be8faed673d0065b4c507cdb24698df320c511fb2f
|
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 sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
|
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,
|
@@ -399,13 +399,27 @@
|
|
399 |
"eval_samples_per_second": 30.646,
|
400 |
"eval_steps_per_second": 3.834,
|
401 |
"step": 2800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
402 |
}
|
403 |
],
|
404 |
"logging_steps": 100,
|
405 |
"max_steps": 4116,
|
406 |
"num_train_epochs": 3,
|
407 |
"save_steps": 100,
|
408 |
-
"total_flos":
|
409 |
"trial_name": null,
|
410 |
"trial_params": null
|
411 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.1633405685424805,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2900",
|
4 |
+
"epoch": 2.1129326047358834,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
399 |
"eval_samples_per_second": 30.646,
|
400 |
"eval_steps_per_second": 3.834,
|
401 |
"step": 2800
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.11,
|
405 |
+
"learning_rate": 0.0002,
|
406 |
+
"loss": 2.1076,
|
407 |
+
"step": 2900
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 2.11,
|
411 |
+
"eval_loss": 2.1633405685424805,
|
412 |
+
"eval_runtime": 205.0465,
|
413 |
+
"eval_samples_per_second": 30.598,
|
414 |
+
"eval_steps_per_second": 3.828,
|
415 |
+
"step": 2900
|
416 |
}
|
417 |
],
|
418 |
"logging_steps": 100,
|
419 |
"max_steps": 4116,
|
420 |
"num_train_epochs": 3,
|
421 |
"save_steps": 100,
|
422 |
+
"total_flos": 8.255440339421184e+16,
|
423 |
"trial_name": null,
|
424 |
"trial_params": null
|
425 |
}
|