Training in progress, step 710, 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:ce5fd3059fd77e59390e4263e6d8ffa823fa4864b31da01152d2b3d08c89d95e
|
| 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 sha256:6b21bf9e4211cdec9f91d1ecb5ebaaef5dbb1e91453d77651212fa7f70f780a7
|
| 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:b74a6e1ed1d2f259172bb6310e2808f6435ed5018a5cf3424628ad90eb56793e
|
| 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": 5.
|
| 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,
|
|
@@ -1268,6 +1268,24 @@
|
|
| 1268 |
"mean_token_accuracy": 0.6448938339948654,
|
| 1269 |
"num_tokens": 2552295.0,
|
| 1270 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1271 |
}
|
| 1272 |
],
|
| 1273 |
"logging_steps": 5,
|
|
@@ -1287,7 +1305,7 @@
|
|
| 1287 |
"attributes": {}
|
| 1288 |
}
|
| 1289 |
},
|
| 1290 |
-
"total_flos": 1.
|
| 1291 |
"train_batch_size": 4,
|
| 1292 |
"trial_name": null,
|
| 1293 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1268 |
"mean_token_accuracy": 0.6448938339948654,
|
| 1269 |
"num_tokens": 2552295.0,
|
| 1270 |
"step": 700
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 5.423076923076923,
|
| 1274 |
+
"grad_norm": 0.0,
|
| 1275 |
+
"learning_rate": 4.648e-05,
|
| 1276 |
+
"loss": 1.7079,
|
| 1277 |
+
"mean_token_accuracy": 0.6543023705482482,
|
| 1278 |
+
"num_tokens": 2571330.0,
|
| 1279 |
+
"step": 705
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 5.461538461538462,
|
| 1283 |
+
"grad_norm": 0.0,
|
| 1284 |
+
"learning_rate": 4.6455e-05,
|
| 1285 |
+
"loss": 1.6662,
|
| 1286 |
+
"mean_token_accuracy": 0.6654859989881515,
|
| 1287 |
+
"num_tokens": 2590405.0,
|
| 1288 |
+
"step": 710
|
| 1289 |
}
|
| 1290 |
],
|
| 1291 |
"logging_steps": 5,
|
|
|
|
| 1305 |
"attributes": {}
|
| 1306 |
}
|
| 1307 |
},
|
| 1308 |
+
"total_flos": 1.313754533904384e+17,
|
| 1309 |
"train_batch_size": 4,
|
| 1310 |
"trial_name": null,
|
| 1311 |
"trial_params": null
|