Training in progress, step 8510, 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 sha256:64c2bd72da3d546666bbecb767195b5b7438695382c15d8941c18d2a39fa75b2
|
| 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 sha256:6a9026677d811a2c261050b0ba99c123cd6a2bfc7358ce653028db8d55014ef2
|
| 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 sha256:0204237f1d2779d006339f8e69e023be3baf516f040a2524f1e2a90c28b56715
|
| 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": 65.
|
| 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,
|
|
@@ -15308,6 +15308,24 @@
|
|
| 15308 |
"mean_token_accuracy": 0.6562123388051987,
|
| 15309 |
"num_tokens": 31001822.0,
|
| 15310 |
"step": 8500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15311 |
}
|
| 15312 |
],
|
| 15313 |
"logging_steps": 5,
|
|
@@ -15327,7 +15345,7 @@
|
|
| 15327 |
"attributes": {}
|
| 15328 |
}
|
| 15329 |
},
|
| 15330 |
-
"total_flos": 1.
|
| 15331 |
"train_batch_size": 4,
|
| 15332 |
"trial_name": null,
|
| 15333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15308 |
"mean_token_accuracy": 0.6562123388051987,
|
| 15309 |
"num_tokens": 31001822.0,
|
| 15310 |
"step": 8500
|
| 15311 |
+
},
|
| 15312 |
+
{
|
| 15313 |
+
"epoch": 65.42307692307692,
|
| 15314 |
+
"grad_norm": 0.0,
|
| 15315 |
+
"learning_rate": 7.480000000000001e-06,
|
| 15316 |
+
"loss": 1.7202,
|
| 15317 |
+
"mean_token_accuracy": 0.6557656317949295,
|
| 15318 |
+
"num_tokens": 31020258.0,
|
| 15319 |
+
"step": 8505
|
| 15320 |
+
},
|
| 15321 |
+
{
|
| 15322 |
+
"epoch": 65.46153846153847,
|
| 15323 |
+
"grad_norm": 0.0,
|
| 15324 |
+
"learning_rate": 7.455000000000001e-06,
|
| 15325 |
+
"loss": 1.7205,
|
| 15326 |
+
"mean_token_accuracy": 0.6543114900588989,
|
| 15327 |
+
"num_tokens": 31038288.0,
|
| 15328 |
+
"step": 8510
|
| 15329 |
}
|
| 15330 |
],
|
| 15331 |
"logging_steps": 5,
|
|
|
|
| 15345 |
"attributes": {}
|
| 15346 |
}
|
| 15347 |
},
|
| 15348 |
+
"total_flos": 1.5737152147483853e+18,
|
| 15349 |
"train_batch_size": 4,
|
| 15350 |
"trial_name": null,
|
| 15351 |
"trial_params": null
|