Training in progress, step 53, 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 159967880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea374abe6fb978cbfe50bd66b004bc178c2d942cedb1218237bc13ee258a4873
|
3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 320194002
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efb13cccf1f03b9aa7fdda82cbf4493c9f258c831d7120b6c4c14ca902c078c6
|
3 |
size 320194002
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29dd87d761c1efd84ba4147df74291157ec98edff08dbcacc6a0f0903e651a49
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62186d98e2e1a228b1a77580a02e85af5559d427fe6308d24fc721da049c3720
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -445,6 +445,27 @@
|
|
445 |
"eval_samples_per_second": 7.983,
|
446 |
"eval_steps_per_second": 1.064,
|
447 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
448 |
}
|
449 |
],
|
450 |
"logging_steps": 1,
|
@@ -459,12 +480,12 @@
|
|
459 |
"should_evaluate": false,
|
460 |
"should_log": false,
|
461 |
"should_save": true,
|
462 |
-
"should_training_stop":
|
463 |
},
|
464 |
"attributes": {}
|
465 |
}
|
466 |
},
|
467 |
-
"total_flos": 3.
|
468 |
"train_batch_size": 8,
|
469 |
"trial_name": null,
|
470 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0285714285714285,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 53,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
445 |
"eval_samples_per_second": 7.983,
|
446 |
"eval_steps_per_second": 1.064,
|
447 |
"step": 50
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 2.914285714285714,
|
451 |
+
"grad_norm": 3.3688862323760986,
|
452 |
+
"learning_rate": 5.328315962444874e-07,
|
453 |
+
"loss": 0.3766,
|
454 |
+
"step": 51
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 2.9714285714285715,
|
458 |
+
"grad_norm": 2.4611260890960693,
|
459 |
+
"learning_rate": 1.333858168224178e-07,
|
460 |
+
"loss": 0.0894,
|
461 |
+
"step": 52
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 3.0285714285714285,
|
465 |
+
"grad_norm": 2.989964485168457,
|
466 |
+
"learning_rate": 0.0,
|
467 |
+
"loss": 0.0514,
|
468 |
+
"step": 53
|
469 |
}
|
470 |
],
|
471 |
"logging_steps": 1,
|
|
|
480 |
"should_evaluate": false,
|
481 |
"should_log": false,
|
482 |
"should_save": true,
|
483 |
+
"should_training_stop": true
|
484 |
},
|
485 |
"attributes": {}
|
486 |
}
|
487 |
},
|
488 |
+
"total_flos": 3.4633626150764544e+16,
|
489 |
"train_batch_size": 8,
|
490 |
"trial_name": null,
|
491 |
"trial_params": null
|