Training in progress, step 2440, 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 sha256:4622fb488622416f853db84d59f2d23c5f844d0a63479dfe70fd6dd14af16d22
|
| 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:ec2c1753b695ffbe9245e789531bfe7ba674d96571b9707097ef4a85a66d27e8
|
| 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 sha256:8239855b03501b67fc138b36283bad738aba77d41a43ca0ea9ec5f4e40c268c1
|
| 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,
|
|
@@ -4382,6 +4382,24 @@
|
|
| 4382 |
"mean_token_accuracy": 0.6484656900167465,
|
| 4383 |
"num_tokens": 8860614.0,
|
| 4384 |
"step": 2430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4385 |
}
|
| 4386 |
],
|
| 4387 |
"logging_steps": 5,
|
|
@@ -4401,7 +4419,7 @@
|
|
| 4401 |
"attributes": {}
|
| 4402 |
}
|
| 4403 |
},
|
| 4404 |
-
"total_flos": 4.
|
| 4405 |
"train_batch_size": 4,
|
| 4406 |
"trial_name": null,
|
| 4407 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4382 |
"mean_token_accuracy": 0.6484656900167465,
|
| 4383 |
"num_tokens": 8860614.0,
|
| 4384 |
"step": 2430
|
| 4385 |
+
},
|
| 4386 |
+
{
|
| 4387 |
+
"epoch": 18.73076923076923,
|
| 4388 |
+
"grad_norm": 0.0,
|
| 4389 |
+
"learning_rate": 3.783e-05,
|
| 4390 |
+
"loss": 1.775,
|
| 4391 |
+
"mean_token_accuracy": 0.6378404378890992,
|
| 4392 |
+
"num_tokens": 8879255.0,
|
| 4393 |
+
"step": 2435
|
| 4394 |
+
},
|
| 4395 |
+
{
|
| 4396 |
+
"epoch": 18.76923076923077,
|
| 4397 |
+
"grad_norm": 0.0,
|
| 4398 |
+
"learning_rate": 3.7805e-05,
|
| 4399 |
+
"loss": 1.7502,
|
| 4400 |
+
"mean_token_accuracy": 0.6478937238454818,
|
| 4401 |
+
"num_tokens": 8896994.0,
|
| 4402 |
+
"step": 2440
|
| 4403 |
}
|
| 4404 |
],
|
| 4405 |
"logging_steps": 5,
|
|
|
|
| 4419 |
"attributes": {}
|
| 4420 |
}
|
| 4421 |
},
|
| 4422 |
+
"total_flos": 4.508298864348365e+17,
|
| 4423 |
"train_batch_size": 4,
|
| 4424 |
"trial_name": null,
|
| 4425 |
"trial_params": null
|