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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b8b5642561b3b9fabfd1aaf1fa969a3044a37fcf5023d5b01a3fdb15d3b2c51
|
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:f545629542c6116b51b84b52b07ca997046ac4e872e65c4ec330241c173db297
|
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:fd1cdd076b217373af7247c4e5586438d32391ac0523ee9c4ea56789d6d16d28
|
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": 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,
|
@@ -441,13 +441,27 @@
|
|
441 |
"eval_samples_per_second": 30.567,
|
442 |
"eval_steps_per_second": 3.825,
|
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":
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
453 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.139963388442993,
|
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": 30.567,
|
442 |
"eval_steps_per_second": 3.825,
|
443 |
"step": 3100
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.33,
|
447 |
+
"learning_rate": 0.0002,
|
448 |
+
"loss": 2.122,
|
449 |
+
"step": 3200
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 2.33,
|
453 |
+
"eval_loss": 2.139963388442993,
|
454 |
+
"eval_runtime": 205.3965,
|
455 |
+
"eval_samples_per_second": 30.546,
|
456 |
+
"eval_steps_per_second": 3.822,
|
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": 9.113803498211328e+16,
|
465 |
"trial_name": null,
|
466 |
"trial_params": null
|
467 |
}
|