Training in progress, step 3200, 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 31466288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ab1e2f153115c0b81e34cb30fc04a2deaf180ad56935e03ef83dc2c7a81965e
|
3 |
size 31466288
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 62950917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1e1c1c9515e39380f709a1b9e0b3f4772ebb9571a391da56d27f1b4f55f3fa1
|
3 |
size 62950917
|
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 sha256:4332f3d7a2ef1a6e323b3a53feacd865832e52ec9d6a70a488368d19a65795d4
|
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 sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
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,
|
@@ -441,13 +441,27 @@
|
|
441 |
"eval_samples_per_second": 11.287,
|
442 |
"eval_steps_per_second": 1.412,
|
443 |
"step": 3100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
444 |
}
|
445 |
],
|
446 |
"logging_steps": 100,
|
447 |
"max_steps": 4116,
|
448 |
"num_train_epochs": 3,
|
449 |
"save_steps": 100,
|
450 |
-
"total_flos": 8.
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
453 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2733838558197021,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3200",
|
4 |
+
"epoch": 2.3315118397085612,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
441 |
"eval_samples_per_second": 11.287,
|
442 |
"eval_steps_per_second": 1.412,
|
443 |
"step": 3100
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.33,
|
447 |
+
"learning_rate": 0.0002,
|
448 |
+
"loss": 1.2078,
|
449 |
+
"step": 3200
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 2.33,
|
453 |
+
"eval_loss": 1.2733838558197021,
|
454 |
+
"eval_runtime": 556.0489,
|
455 |
+
"eval_samples_per_second": 11.283,
|
456 |
+
"eval_steps_per_second": 1.412,
|
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": 8.332718824760279e+17,
|
465 |
"trial_name": null,
|
466 |
"trial_params": null
|
467 |
}
|