Training in progress, step 720, 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:dd65d69552ea8f951323f37526ff3f9b3a9ab879b55c641bd668f7e90be23a0c
|
| 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 sha256:568ae088b7a389be72b6a549e8dc59b5d65d005ba38bb3b292c4aaf213414c7d
|
| 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:ef2d16fb6e0e427143f08c28e75ae1b8fb238f5d8a95ac57e3df485c45c19028
|
| 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,
|
|
@@ -1286,6 +1286,24 @@
|
|
| 1286 |
"mean_token_accuracy": 0.6654859989881515,
|
| 1287 |
"num_tokens": 2590405.0,
|
| 1288 |
"step": 710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1289 |
}
|
| 1290 |
],
|
| 1291 |
"logging_steps": 5,
|
|
@@ -1305,7 +1323,7 @@
|
|
| 1305 |
"attributes": {}
|
| 1306 |
}
|
| 1307 |
},
|
| 1308 |
-
"total_flos": 1.
|
| 1309 |
"train_batch_size": 4,
|
| 1310 |
"trial_name": null,
|
| 1311 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1286 |
"mean_token_accuracy": 0.6654859989881515,
|
| 1287 |
"num_tokens": 2590405.0,
|
| 1288 |
"step": 710
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 5.5,
|
| 1292 |
+
"grad_norm": 0.0,
|
| 1293 |
+
"learning_rate": 4.643e-05,
|
| 1294 |
+
"loss": 1.7794,
|
| 1295 |
+
"mean_token_accuracy": 0.6464732140302658,
|
| 1296 |
+
"num_tokens": 2607594.0,
|
| 1297 |
+
"step": 715
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 5.538461538461538,
|
| 1301 |
+
"grad_norm": 0.0,
|
| 1302 |
+
"learning_rate": 4.640500000000001e-05,
|
| 1303 |
+
"loss": 1.7341,
|
| 1304 |
+
"mean_token_accuracy": 0.6509989589452744,
|
| 1305 |
+
"num_tokens": 2625915.0,
|
| 1306 |
+
"step": 720
|
| 1307 |
}
|
| 1308 |
],
|
| 1309 |
"logging_steps": 5,
|
|
|
|
| 1323 |
"attributes": {}
|
| 1324 |
}
|
| 1325 |
},
|
| 1326 |
+
"total_flos": 1.331696577429504e+17,
|
| 1327 |
"train_batch_size": 4,
|
| 1328 |
"trial_name": null,
|
| 1329 |
"trial_params": null
|