Training in progress, step 9580, 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:eab5e50a44a11a6ba710dda68328c57586182174c92127a76f7909ff49ffdb99
|
| 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 sha256:6abcd8c9cf9aa07e74f3b14c9cdc5b8c335ed8f332a564ed66bc2f809b6b2a56
|
| 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 sha256:9ac8467f7ee13a19835e6ca3d5b8cde196df9da66a089aa4fcab09172f681d50
|
| 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": 73.
|
| 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,
|
|
@@ -17234,6 +17234,24 @@
|
|
| 17234 |
"mean_token_accuracy": 0.646284231543541,
|
| 17235 |
"num_tokens": 34900082.0,
|
| 17236 |
"step": 9570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17237 |
}
|
| 17238 |
],
|
| 17239 |
"logging_steps": 5,
|
|
@@ -17253,7 +17271,7 @@
|
|
| 17253 |
"attributes": {}
|
| 17254 |
}
|
| 17255 |
},
|
| 17256 |
-
"total_flos": 1.
|
| 17257 |
"train_batch_size": 4,
|
| 17258 |
"trial_name": null,
|
| 17259 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17234 |
"mean_token_accuracy": 0.646284231543541,
|
| 17235 |
"num_tokens": 34900082.0,
|
| 17236 |
"step": 9570
|
| 17237 |
+
},
|
| 17238 |
+
{
|
| 17239 |
+
"epoch": 73.65384615384616,
|
| 17240 |
+
"grad_norm": 0.0,
|
| 17241 |
+
"learning_rate": 2.13e-06,
|
| 17242 |
+
"loss": 1.7086,
|
| 17243 |
+
"mean_token_accuracy": 0.6528146833181381,
|
| 17244 |
+
"num_tokens": 34919228.0,
|
| 17245 |
+
"step": 9575
|
| 17246 |
+
},
|
| 17247 |
+
{
|
| 17248 |
+
"epoch": 73.6923076923077,
|
| 17249 |
+
"grad_norm": 0.0,
|
| 17250 |
+
"learning_rate": 2.105e-06,
|
| 17251 |
+
"loss": 1.7914,
|
| 17252 |
+
"mean_token_accuracy": 0.6391745179891586,
|
| 17253 |
+
"num_tokens": 34936386.0,
|
| 17254 |
+
"step": 9580
|
| 17255 |
}
|
| 17256 |
],
|
| 17257 |
"logging_steps": 5,
|
|
|
|
| 17271 |
"attributes": {}
|
| 17272 |
}
|
| 17273 |
},
|
| 17274 |
+
"total_flos": 1.771643741181051e+18,
|
| 17275 |
"train_batch_size": 4,
|
| 17276 |
"trial_name": null,
|
| 17277 |
"trial_params": null
|