Training in progress, step 700, 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:ef8f7a8a9de6050c6ce2bcd7d805cb34bd6a6bda5508cd447c2b666f2a6a1b05
|
| 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 sha256:9bd315720db48bafaef6b59bd5665e0f088d89a0f11427b8e210cb319fe825b2
|
| 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:a14da840877ef6157f153e530e8a1e7f276439a2a2f673c5f773ebe86ac1dcab
|
| 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,
|
|
@@ -1250,6 +1250,24 @@
|
|
| 1250 |
"mean_token_accuracy": 0.655092054605484,
|
| 1251 |
"num_tokens": 2515935.0,
|
| 1252 |
"step": 690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1253 |
}
|
| 1254 |
],
|
| 1255 |
"logging_steps": 5,
|
|
@@ -1269,7 +1287,7 @@
|
|
| 1269 |
"attributes": {}
|
| 1270 |
}
|
| 1271 |
},
|
| 1272 |
-
"total_flos": 1.
|
| 1273 |
"train_batch_size": 4,
|
| 1274 |
"trial_name": null,
|
| 1275 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1250 |
"mean_token_accuracy": 0.655092054605484,
|
| 1251 |
"num_tokens": 2515935.0,
|
| 1252 |
"step": 690
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 5.346153846153846,
|
| 1256 |
+
"grad_norm": 0.0,
|
| 1257 |
+
"learning_rate": 4.6530000000000003e-05,
|
| 1258 |
+
"loss": 1.7177,
|
| 1259 |
+
"mean_token_accuracy": 0.6567189127206803,
|
| 1260 |
+
"num_tokens": 2534143.0,
|
| 1261 |
+
"step": 695
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 5.384615384615385,
|
| 1265 |
+
"grad_norm": 0.0,
|
| 1266 |
+
"learning_rate": 4.6505e-05,
|
| 1267 |
+
"loss": 1.771,
|
| 1268 |
+
"mean_token_accuracy": 0.6448938339948654,
|
| 1269 |
+
"num_tokens": 2552295.0,
|
| 1270 |
+
"step": 700
|
| 1271 |
}
|
| 1272 |
],
|
| 1273 |
"logging_steps": 5,
|
|
|
|
| 1287 |
"attributes": {}
|
| 1288 |
}
|
| 1289 |
},
|
| 1290 |
+
"total_flos": 1.294065919770624e+17,
|
| 1291 |
"train_batch_size": 4,
|
| 1292 |
"trial_name": null,
|
| 1293 |
"trial_params": null
|