Training in progress, step 50, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:223fe63d07b53941a553ee9b0de4e8a136863e90a8dd13ecffc8fea7ffa0f766
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b981b13444dd9d6e2fc18746793c5ce2f1d4988b2bd30c5bbef2953a26fdb94
|
3 |
size 335922386
|
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 sha256:285d2563a4c378e4ef0a81144d122efbda63f0f056ff3b8ee4ef3fdb7634d194
|
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:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
|
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": 0.
|
5 |
"eval_steps": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -447,6 +447,20 @@
|
|
447 |
"eval_samples_per_second": 8.309,
|
448 |
"eval_steps_per_second": 8.309,
|
449 |
"step": 48
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
450 |
}
|
451 |
],
|
452 |
"logging_steps": 1,
|
@@ -461,12 +475,12 @@
|
|
461 |
"should_evaluate": false,
|
462 |
"should_log": false,
|
463 |
"should_save": true,
|
464 |
-
"should_training_stop":
|
465 |
},
|
466 |
"attributes": {}
|
467 |
}
|
468 |
},
|
469 |
-
"total_flos": 1.
|
470 |
"train_batch_size": 1,
|
471 |
"trial_name": null,
|
472 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.021108179419525065,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
447 |
"eval_samples_per_second": 8.309,
|
448 |
"eval_steps_per_second": 8.309,
|
449 |
"step": 48
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.020686015831134566,
|
453 |
+
"grad_norm": 2.18385910987854,
|
454 |
+
"learning_rate": 3.0826662668720364e-07,
|
455 |
+
"loss": 0.1944,
|
456 |
+
"step": 49
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 0.021108179419525065,
|
460 |
+
"grad_norm": 2.7979819774627686,
|
461 |
+
"learning_rate": 0.0,
|
462 |
+
"loss": 0.3756,
|
463 |
+
"step": 50
|
464 |
}
|
465 |
],
|
466 |
"logging_steps": 1,
|
|
|
475 |
"should_evaluate": false,
|
476 |
"should_log": false,
|
477 |
"should_save": true,
|
478 |
+
"should_training_stop": true
|
479 |
},
|
480 |
"attributes": {}
|
481 |
}
|
482 |
},
|
483 |
+
"total_flos": 1.85471820890112e+16,
|
484 |
"train_batch_size": 1,
|
485 |
"trial_name": null,
|
486 |
"trial_params": null
|