Training in progress, step 5310, 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 sha256:6ca2218b7dd5aecfaf8cc6fb44856f1b02e87d8746e5fe856620278be216b972
|
| 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 sha256:7a654ed9e1d6b3b4d4d24baff954e1634ab53e28c5b5506a8b45214db2e137fb
|
| 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:e895d842aae6c974724c9dcb82e0b22a4076e2ab4cca3ace2edcd65c83ec789b
|
| 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,
|
|
@@ -9548,6 +9548,24 @@
|
|
| 9548 |
"mean_token_accuracy": 0.6503111094236373,
|
| 9549 |
"num_tokens": 19328485.0,
|
| 9550 |
"step": 5300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9551 |
}
|
| 9552 |
],
|
| 9553 |
"logging_steps": 5,
|
|
@@ -9567,7 +9585,7 @@
|
|
| 9567 |
"attributes": {}
|
| 9568 |
}
|
| 9569 |
},
|
| 9570 |
-
"total_flos": 9.
|
| 9571 |
"train_batch_size": 4,
|
| 9572 |
"trial_name": null,
|
| 9573 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9548 |
"mean_token_accuracy": 0.6503111094236373,
|
| 9549 |
"num_tokens": 19328485.0,
|
| 9550 |
"step": 5300
|
| 9551 |
+
},
|
| 9552 |
+
{
|
| 9553 |
+
"epoch": 40.80769230769231,
|
| 9554 |
+
"grad_norm": 0.0,
|
| 9555 |
+
"learning_rate": 2.3480000000000002e-05,
|
| 9556 |
+
"loss": 1.8109,
|
| 9557 |
+
"mean_token_accuracy": 0.6344301998615265,
|
| 9558 |
+
"num_tokens": 19346027.0,
|
| 9559 |
+
"step": 5305
|
| 9560 |
+
},
|
| 9561 |
+
{
|
| 9562 |
+
"epoch": 40.84615384615385,
|
| 9563 |
+
"grad_norm": 0.0,
|
| 9564 |
+
"learning_rate": 2.3455e-05,
|
| 9565 |
+
"loss": 1.7801,
|
| 9566 |
+
"mean_token_accuracy": 0.6480203717947006,
|
| 9567 |
+
"num_tokens": 19364659.0,
|
| 9568 |
+
"step": 5310
|
| 9569 |
}
|
| 9570 |
],
|
| 9571 |
"logging_steps": 5,
|
|
|
|
| 9585 |
"attributes": {}
|
| 9586 |
}
|
| 9587 |
},
|
| 9588 |
+
"total_flos": 9.812733833650176e+17,
|
| 9589 |
"train_batch_size": 4,
|
| 9590 |
"trial_name": null,
|
| 9591 |
"trial_params": null
|