Training in progress, step 5320, 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 sha256:0cf9c477b9376db82f16468adb01b3e870408e7fb628f625a4f41e2196c3cbcc
|
| 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:b5f930aa88dc3f4883b361a2a570ad70cc8776c0da927473b246cdb612d8f6bc
|
| 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 sha256:00f74fe8fabf165023fc094430a3241002bc65110dfc088679202a3ea4238b0f
|
| 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": 40.
|
| 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,
|
|
@@ -9566,6 +9566,24 @@
|
|
| 9566 |
"mean_token_accuracy": 0.6480203717947006,
|
| 9567 |
"num_tokens": 19364659.0,
|
| 9568 |
"step": 5310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9569 |
}
|
| 9570 |
],
|
| 9571 |
"logging_steps": 5,
|
|
@@ -9585,7 +9603,7 @@
|
|
| 9585 |
"attributes": {}
|
| 9586 |
}
|
| 9587 |
},
|
| 9588 |
-
"total_flos": 9.
|
| 9589 |
"train_batch_size": 4,
|
| 9590 |
"trial_name": null,
|
| 9591 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9566 |
"mean_token_accuracy": 0.6480203717947006,
|
| 9567 |
"num_tokens": 19364659.0,
|
| 9568 |
"step": 5310
|
| 9569 |
+
},
|
| 9570 |
+
{
|
| 9571 |
+
"epoch": 40.88461538461539,
|
| 9572 |
+
"grad_norm": 0.0,
|
| 9573 |
+
"learning_rate": 2.343e-05,
|
| 9574 |
+
"loss": 1.7486,
|
| 9575 |
+
"mean_token_accuracy": 0.6470009624958039,
|
| 9576 |
+
"num_tokens": 19383460.0,
|
| 9577 |
+
"step": 5315
|
| 9578 |
+
},
|
| 9579 |
+
{
|
| 9580 |
+
"epoch": 40.92307692307692,
|
| 9581 |
+
"grad_norm": 0.0,
|
| 9582 |
+
"learning_rate": 2.3405e-05,
|
| 9583 |
+
"loss": 1.6961,
|
| 9584 |
+
"mean_token_accuracy": 0.6605125904083252,
|
| 9585 |
+
"num_tokens": 19401413.0,
|
| 9586 |
+
"step": 5320
|
| 9587 |
}
|
| 9588 |
],
|
| 9589 |
"logging_steps": 5,
|
|
|
|
| 9603 |
"attributes": {}
|
| 9604 |
}
|
| 9605 |
},
|
| 9606 |
+
"total_flos": 9.831230016395674e+17,
|
| 9607 |
"train_batch_size": 4,
|
| 9608 |
"trial_name": null,
|
| 9609 |
"trial_params": null
|