Training in progress, step 9180, 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:dfedea075221310ee4349d2c55f599d5c8f8e985b7018ca1fc3094d74ca1385a
|
| 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 sha256:19f2850e8cb759785eb7521044a8a2f7c52d80e17516625e215ea1f84c742c27
|
| 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 sha256:60206c7b442e2134c380aee0f923d6e2a71cc3cc3b3dc8f224ce378f6c0261ba
|
| 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": 70.
|
| 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,
|
|
@@ -16514,6 +16514,24 @@
|
|
| 16514 |
"mean_token_accuracy": 0.6361591160297394,
|
| 16515 |
"num_tokens": 33443218.0,
|
| 16516 |
"step": 9170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16517 |
}
|
| 16518 |
],
|
| 16519 |
"logging_steps": 5,
|
|
@@ -16533,7 +16551,7 @@
|
|
| 16533 |
"attributes": {}
|
| 16534 |
}
|
| 16535 |
},
|
| 16536 |
-
"total_flos": 1.
|
| 16537 |
"train_batch_size": 4,
|
| 16538 |
"trial_name": null,
|
| 16539 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16514 |
"mean_token_accuracy": 0.6361591160297394,
|
| 16515 |
"num_tokens": 33443218.0,
|
| 16516 |
"step": 9170
|
| 16517 |
+
},
|
| 16518 |
+
{
|
| 16519 |
+
"epoch": 70.57692307692308,
|
| 16520 |
+
"grad_norm": 0.0,
|
| 16521 |
+
"learning_rate": 4.13e-06,
|
| 16522 |
+
"loss": 1.7396,
|
| 16523 |
+
"mean_token_accuracy": 0.6503497928380966,
|
| 16524 |
+
"num_tokens": 33462100.0,
|
| 16525 |
+
"step": 9175
|
| 16526 |
+
},
|
| 16527 |
+
{
|
| 16528 |
+
"epoch": 70.61538461538461,
|
| 16529 |
+
"grad_norm": 0.0,
|
| 16530 |
+
"learning_rate": 4.1050000000000005e-06,
|
| 16531 |
+
"loss": 1.7632,
|
| 16532 |
+
"mean_token_accuracy": 0.6452891588211059,
|
| 16533 |
+
"num_tokens": 33479921.0,
|
| 16534 |
+
"step": 9180
|
| 16535 |
}
|
| 16536 |
],
|
| 16537 |
"logging_steps": 5,
|
|
|
|
| 16551 |
"attributes": {}
|
| 16552 |
}
|
| 16553 |
},
|
| 16554 |
+
"total_flos": 1.6976161398295757e+18,
|
| 16555 |
"train_batch_size": 4,
|
| 16556 |
"trial_name": null,
|
| 16557 |
"trial_params": null
|