Training in progress, step 9760, 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 sha256:92f91baee00f745e65f2a46ff7ba03cc1c456a0ed035a7b6f1417d9220b7c311
|
| 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:a3466ea8cb862e704024e8fb0dc53051224f544550fb6f8428e258d8fb8b4399
|
| 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 sha256:00686b10e6f4dd9c20e8665c66f4785848aed19449c6012d2c07cc9f61e71c03
|
| 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": 75.
|
| 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,
|
|
@@ -17558,6 +17558,24 @@
|
|
| 17558 |
"mean_token_accuracy": 0.6401764988899231,
|
| 17559 |
"num_tokens": 35557875.0,
|
| 17560 |
"step": 9750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17561 |
}
|
| 17562 |
],
|
| 17563 |
"logging_steps": 5,
|
|
@@ -17577,7 +17595,7 @@
|
|
| 17577 |
"attributes": {}
|
| 17578 |
}
|
| 17579 |
},
|
| 17580 |
-
"total_flos": 1.
|
| 17581 |
"train_batch_size": 4,
|
| 17582 |
"trial_name": null,
|
| 17583 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17558 |
"mean_token_accuracy": 0.6401764988899231,
|
| 17559 |
"num_tokens": 35557875.0,
|
| 17560 |
"step": 9750
|
| 17561 |
+
},
|
| 17562 |
+
{
|
| 17563 |
+
"epoch": 75.03846153846153,
|
| 17564 |
+
"grad_norm": 0.0,
|
| 17565 |
+
"learning_rate": 1.23e-06,
|
| 17566 |
+
"loss": 1.7148,
|
| 17567 |
+
"mean_token_accuracy": 0.6562530130147934,
|
| 17568 |
+
"num_tokens": 35576356.0,
|
| 17569 |
+
"step": 9755
|
| 17570 |
+
},
|
| 17571 |
+
{
|
| 17572 |
+
"epoch": 75.07692307692308,
|
| 17573 |
+
"grad_norm": 0.0,
|
| 17574 |
+
"learning_rate": 1.2050000000000001e-06,
|
| 17575 |
+
"loss": 1.6865,
|
| 17576 |
+
"mean_token_accuracy": 0.6659580796957016,
|
| 17577 |
+
"num_tokens": 35594809.0,
|
| 17578 |
+
"step": 9760
|
| 17579 |
}
|
| 17580 |
],
|
| 17581 |
"logging_steps": 5,
|
|
|
|
| 17595 |
"attributes": {}
|
| 17596 |
}
|
| 17597 |
},
|
| 17598 |
+
"total_flos": 1.8050777072256614e+18,
|
| 17599 |
"train_batch_size": 4,
|
| 17600 |
"trial_name": null,
|
| 17601 |
"trial_params": null
|