Training in progress, step 3000, 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 sha256:16771a8f6dc3231c25a4a4ed51f3c486414f43414e0d8acfff251345166e77c9
|
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:d2a95beec4a16fdb41d57632dd65db748ed341dc3e972c11d9854556a2c49e76
|
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 sha256:63d2c99dbd46a20a48c294132ab2d17f45afe77fd0e7fd574cf93295fea8e744
|
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:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
|
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,
|
@@ -413,13 +413,27 @@
|
|
413 |
"eval_samples_per_second": 30.577,
|
414 |
"eval_steps_per_second": 3.826,
|
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.
|
423 |
"trial_name": null,
|
424 |
"trial_params": null
|
425 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.162501096725464,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3000",
|
4 |
+
"epoch": 2.185792349726776,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
413 |
"eval_samples_per_second": 30.577,
|
414 |
"eval_steps_per_second": 3.826,
|
415 |
"step": 2900
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 2.19,
|
419 |
+
"learning_rate": 0.0002,
|
420 |
+
"loss": 2.1341,
|
421 |
+
"step": 3000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 2.19,
|
425 |
+
"eval_loss": 2.162501096725464,
|
426 |
+
"eval_runtime": 204.9372,
|
427 |
+
"eval_samples_per_second": 30.614,
|
428 |
+
"eval_steps_per_second": 3.83,
|
429 |
+
"step": 3000
|
430 |
}
|
431 |
],
|
432 |
"logging_steps": 100,
|
433 |
"max_steps": 4116,
|
434 |
"num_train_epochs": 3,
|
435 |
"save_steps": 100,
|
436 |
+
"total_flos": 8.542105612314624e+16,
|
437 |
"trial_name": null,
|
438 |
"trial_params": null
|
439 |
}
|