Training in progress, step 3400, 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 sha256:63269f6d2005cad6fe6899aefaad818d47dbb6115cbe9e24a81fa776bf9f8a9d
|
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:ee6ab0ef5a50e0d2e6bad338a0dee1e85da7e4fc023470786fa72fa3e2f06568
|
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 sha256:748f1340fd9b0d57811f59fe041f609e22a6ddf5e0bc7260681bf17e3d449b1b
|
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:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
|
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,
|
@@ -469,13 +469,27 @@
|
|
469 |
"eval_samples_per_second": 30.215,
|
470 |
"eval_steps_per_second": 3.78,
|
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.
|
479 |
"trial_name": null,
|
480 |
"trial_params": null
|
481 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.0520451068878174,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3400",
|
4 |
+
"epoch": 2.477231329690346,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
469 |
"eval_samples_per_second": 30.215,
|
470 |
"eval_steps_per_second": 3.78,
|
471 |
"step": 3300
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.48,
|
475 |
+
"learning_rate": 0.0002,
|
476 |
+
"loss": 2.0034,
|
477 |
+
"step": 3400
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 2.48,
|
481 |
+
"eval_loss": 2.0520451068878174,
|
482 |
+
"eval_runtime": 207.9034,
|
483 |
+
"eval_samples_per_second": 30.177,
|
484 |
+
"eval_steps_per_second": 3.776,
|
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": 9.919903936610304e+16,
|
493 |
"trial_name": null,
|
494 |
"trial_params": null
|
495 |
}
|