Training in progress, step 6790, 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 sha256:9941aa863ab9de02a0c98d43d1b8a2fa746c8690dcdd5d9759ed9f6ed07b612a
|
| 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 sha256:50479042b4bd58fa7178e86545cd07086b4768b529bbed0fee144cf3b4189b1f
|
| 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 sha256:815d60ac4ad9357be1b4e5a8cd8149118e558cded711fa42b21a8b915566e48e
|
| 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": 52.
|
| 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,
|
|
@@ -12212,6 +12212,24 @@
|
|
| 12212 |
"mean_token_accuracy": 0.6377092868089675,
|
| 12213 |
"num_tokens": 24726980.0,
|
| 12214 |
"step": 6780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12215 |
}
|
| 12216 |
],
|
| 12217 |
"logging_steps": 5,
|
|
@@ -12231,7 +12249,7 @@
|
|
| 12231 |
"attributes": {}
|
| 12232 |
}
|
| 12233 |
},
|
| 12234 |
-
"total_flos": 1.
|
| 12235 |
"train_batch_size": 4,
|
| 12236 |
"trial_name": null,
|
| 12237 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12212 |
"mean_token_accuracy": 0.6377092868089675,
|
| 12213 |
"num_tokens": 24726980.0,
|
| 12214 |
"step": 6780
|
| 12215 |
+
},
|
| 12216 |
+
{
|
| 12217 |
+
"epoch": 52.19230769230769,
|
| 12218 |
+
"grad_norm": 0.0,
|
| 12219 |
+
"learning_rate": 1.6080000000000002e-05,
|
| 12220 |
+
"loss": 1.758,
|
| 12221 |
+
"mean_token_accuracy": 0.6477128326892853,
|
| 12222 |
+
"num_tokens": 24744869.0,
|
| 12223 |
+
"step": 6785
|
| 12224 |
+
},
|
| 12225 |
+
{
|
| 12226 |
+
"epoch": 52.23076923076923,
|
| 12227 |
+
"grad_norm": 0.0,
|
| 12228 |
+
"learning_rate": 1.6055e-05,
|
| 12229 |
+
"loss": 1.74,
|
| 12230 |
+
"mean_token_accuracy": 0.6518424063920975,
|
| 12231 |
+
"num_tokens": 24763369.0,
|
| 12232 |
+
"step": 6790
|
| 12233 |
}
|
| 12234 |
],
|
| 12235 |
"logging_steps": 5,
|
|
|
|
| 12249 |
"attributes": {}
|
| 12250 |
}
|
| 12251 |
},
|
| 12252 |
+
"total_flos": 1.2555575309913293e+18,
|
| 12253 |
"train_batch_size": 4,
|
| 12254 |
"trial_name": null,
|
| 12255 |
"trial_params": null
|