Training in progress, step 2450, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aff48be47b2182d6661fa31e7efb656d401d9aa390550aadc8044c6b07256ded
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:982c5dea2bdeaa67d12571be18c5a64fecbc0eca9e9e6646403ba8775f5298a2
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee2946befca8e13bc4f6f828ebc269da4ba7430a77dfa12617473e92f077af1d
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 18.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4400,6 +4400,24 @@
|
|
| 4400 |
"mean_token_accuracy": 0.6478937238454818,
|
| 4401 |
"num_tokens": 8896994.0,
|
| 4402 |
"step": 2440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4403 |
}
|
| 4404 |
],
|
| 4405 |
"logging_steps": 5,
|
|
@@ -4419,7 +4437,7 @@
|
|
| 4419 |
"attributes": {}
|
| 4420 |
}
|
| 4421 |
},
|
| 4422 |
-
"total_flos": 4.
|
| 4423 |
"train_batch_size": 4,
|
| 4424 |
"trial_name": null,
|
| 4425 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4400 |
"mean_token_accuracy": 0.6478937238454818,
|
| 4401 |
"num_tokens": 8896994.0,
|
| 4402 |
"step": 2440
|
| 4403 |
+
},
|
| 4404 |
+
{
|
| 4405 |
+
"epoch": 18.807692307692307,
|
| 4406 |
+
"grad_norm": 0.0,
|
| 4407 |
+
"learning_rate": 3.778000000000001e-05,
|
| 4408 |
+
"loss": 1.7486,
|
| 4409 |
+
"mean_token_accuracy": 0.6547796040773392,
|
| 4410 |
+
"num_tokens": 8915326.0,
|
| 4411 |
+
"step": 2445
|
| 4412 |
+
},
|
| 4413 |
+
{
|
| 4414 |
+
"epoch": 18.846153846153847,
|
| 4415 |
+
"grad_norm": 0.0,
|
| 4416 |
+
"learning_rate": 3.7755e-05,
|
| 4417 |
+
"loss": 1.6805,
|
| 4418 |
+
"mean_token_accuracy": 0.6655582249164581,
|
| 4419 |
+
"num_tokens": 8933916.0,
|
| 4420 |
+
"step": 2450
|
| 4421 |
}
|
| 4422 |
],
|
| 4423 |
"logging_steps": 5,
|
|
|
|
| 4437 |
"attributes": {}
|
| 4438 |
}
|
| 4439 |
},
|
| 4440 |
+
"total_flos": 4.527171353670451e+17,
|
| 4441 |
"train_batch_size": 4,
|
| 4442 |
"trial_name": null,
|
| 4443 |
"trial_params": null
|