Training in progress, step 690, 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 sha256:04fa77d0b5dd281a77ebd2bbd0a974ef86f82a80e2cdc32d2160afbcd64cf918
|
| 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 sha256:3ad2336cf69ec237b919c245119287dd85c6d73b3896a83f4e2651cbedc96c2b
|
| 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 sha256:49d42ed7ae549c23160b0e20537773fe320709fe0c6b21f4449360dea1319904
|
| 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,
|
|
@@ -1232,6 +1232,24 @@
|
|
| 1232 |
"mean_token_accuracy": 0.642570036649704,
|
| 1233 |
"num_tokens": 2480028.0,
|
| 1234 |
"step": 680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1235 |
}
|
| 1236 |
],
|
| 1237 |
"logging_steps": 5,
|
|
@@ -1251,7 +1269,7 @@
|
|
| 1251 |
"attributes": {}
|
| 1252 |
}
|
| 1253 |
},
|
| 1254 |
-
"total_flos": 1.
|
| 1255 |
"train_batch_size": 4,
|
| 1256 |
"trial_name": null,
|
| 1257 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.3076923076923075,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1232 |
"mean_token_accuracy": 0.642570036649704,
|
| 1233 |
"num_tokens": 2480028.0,
|
| 1234 |
"step": 680
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 5.269230769230769,
|
| 1238 |
+
"grad_norm": 0.0,
|
| 1239 |
+
"learning_rate": 4.6580000000000005e-05,
|
| 1240 |
+
"loss": 1.7696,
|
| 1241 |
+
"mean_token_accuracy": 0.6482695400714874,
|
| 1242 |
+
"num_tokens": 2497710.0,
|
| 1243 |
+
"step": 685
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 5.3076923076923075,
|
| 1247 |
+
"grad_norm": 0.0,
|
| 1248 |
+
"learning_rate": 4.6555000000000004e-05,
|
| 1249 |
+
"loss": 1.7291,
|
| 1250 |
+
"mean_token_accuracy": 0.655092054605484,
|
| 1251 |
+
"num_tokens": 2515935.0,
|
| 1252 |
+
"step": 690
|
| 1253 |
}
|
| 1254 |
],
|
| 1255 |
"logging_steps": 5,
|
|
|
|
| 1269 |
"attributes": {}
|
| 1270 |
}
|
| 1271 |
},
|
| 1272 |
+
"total_flos": 1.2756348364750848e+17,
|
| 1273 |
"train_batch_size": 4,
|
| 1274 |
"trial_name": null,
|
| 1275 |
"trial_params": null
|