Training in progress, step 9650, 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:a1e4bcfdc6819babe08883ce4101e765cb6091c0d74b4c76b02b3b94de08a6ea
|
| 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 sha256:9a545707580ef987bfad7fc3b1ab32b3ea2393a2395619a1a21a0cab8f81b48e
|
| 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 sha256:69e413638d66ad248170b508b60942d253028a61bc98f8b78c9b53d43eaabd07
|
| 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": 74.
|
| 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,
|
|
@@ -17360,6 +17360,24 @@
|
|
| 17360 |
"mean_token_accuracy": 0.6392817258834839,
|
| 17361 |
"num_tokens": 35155463.0,
|
| 17362 |
"step": 9640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17363 |
}
|
| 17364 |
],
|
| 17365 |
"logging_steps": 5,
|
|
@@ -17379,7 +17397,7 @@
|
|
| 17379 |
"attributes": {}
|
| 17380 |
}
|
| 17381 |
},
|
| 17382 |
-
"total_flos": 1.
|
| 17383 |
"train_batch_size": 4,
|
| 17384 |
"trial_name": null,
|
| 17385 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17360 |
"mean_token_accuracy": 0.6392817258834839,
|
| 17361 |
"num_tokens": 35155463.0,
|
| 17362 |
"step": 9640
|
| 17363 |
+
},
|
| 17364 |
+
{
|
| 17365 |
+
"epoch": 74.1923076923077,
|
| 17366 |
+
"grad_norm": 0.0,
|
| 17367 |
+
"learning_rate": 1.7800000000000001e-06,
|
| 17368 |
+
"loss": 1.7609,
|
| 17369 |
+
"mean_token_accuracy": 0.6492180019617081,
|
| 17370 |
+
"num_tokens": 35173695.0,
|
| 17371 |
+
"step": 9645
|
| 17372 |
+
},
|
| 17373 |
+
{
|
| 17374 |
+
"epoch": 74.23076923076923,
|
| 17375 |
+
"grad_norm": 0.0,
|
| 17376 |
+
"learning_rate": 1.7550000000000001e-06,
|
| 17377 |
+
"loss": 1.7774,
|
| 17378 |
+
"mean_token_accuracy": 0.6455636918544769,
|
| 17379 |
+
"num_tokens": 35191312.0,
|
| 17380 |
+
"step": 9650
|
| 17381 |
}
|
| 17382 |
],
|
| 17383 |
"logging_steps": 5,
|
|
|
|
| 17397 |
"attributes": {}
|
| 17398 |
}
|
| 17399 |
},
|
| 17400 |
+
"total_flos": 1.7845726507219354e+18,
|
| 17401 |
"train_batch_size": 4,
|
| 17402 |
"trial_name": null,
|
| 17403 |
"trial_params": null
|