Training in progress, step 5340, 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:e480d111cc0e751b3b2286ff235df663cc14df7de32eb7e593a733351b998d4c
|
| 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:f48806f132bf8580f7234d41f304e0d89c00b09f6c7faeb7a02c1800bdf51bc9
|
| 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:afefa60c482faea3a1e77218ffa0bcc6ba5e0f563880eef4122ff561a230009d
|
| 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": 41.
|
| 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,
|
|
@@ -9602,6 +9602,24 @@
|
|
| 9602 |
"mean_token_accuracy": 0.6540407299995422,
|
| 9603 |
"num_tokens": 19438305.0,
|
| 9604 |
"step": 5330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9605 |
}
|
| 9606 |
],
|
| 9607 |
"logging_steps": 5,
|
|
@@ -9621,7 +9639,7 @@
|
|
| 9621 |
"attributes": {}
|
| 9622 |
}
|
| 9623 |
},
|
| 9624 |
-
"total_flos": 9.
|
| 9625 |
"train_batch_size": 4,
|
| 9626 |
"trial_name": null,
|
| 9627 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9602 |
"mean_token_accuracy": 0.6540407299995422,
|
| 9603 |
"num_tokens": 19438305.0,
|
| 9604 |
"step": 5330
|
| 9605 |
+
},
|
| 9606 |
+
{
|
| 9607 |
+
"epoch": 41.03846153846154,
|
| 9608 |
+
"grad_norm": 0.0,
|
| 9609 |
+
"learning_rate": 2.3330000000000002e-05,
|
| 9610 |
+
"loss": 1.7928,
|
| 9611 |
+
"mean_token_accuracy": 0.6409297794103622,
|
| 9612 |
+
"num_tokens": 19456136.0,
|
| 9613 |
+
"step": 5335
|
| 9614 |
+
},
|
| 9615 |
+
{
|
| 9616 |
+
"epoch": 41.07692307692308,
|
| 9617 |
+
"grad_norm": 0.0,
|
| 9618 |
+
"learning_rate": 2.3305e-05,
|
| 9619 |
+
"loss": 1.6898,
|
| 9620 |
+
"mean_token_accuracy": 0.6670808821916581,
|
| 9621 |
+
"num_tokens": 19474660.0,
|
| 9622 |
+
"step": 5340
|
| 9623 |
}
|
| 9624 |
],
|
| 9625 |
"logging_steps": 5,
|
|
|
|
| 9639 |
"attributes": {}
|
| 9640 |
}
|
| 9641 |
},
|
| 9642 |
+
"total_flos": 9.86744912744448e+17,
|
| 9643 |
"train_batch_size": 4,
|
| 9644 |
"trial_name": null,
|
| 9645 |
"trial_params": null
|