Training in progress, step 2390, 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:fbba8f1e7b0f62de1423b05eadf0efcd7069bea232139c875eb3ad426d1af74c
|
| 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 sha256:883790ea1167655a21a0d567182ef9136d474697577137fcd9021d6781b8ec42
|
| 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:bc2f2955e41274807ab42514825226bed3fe95f90978775c1f62656701a84695
|
| 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": 18.
|
| 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,
|
|
@@ -4292,6 +4292,24 @@
|
|
| 4292 |
"mean_token_accuracy": 0.6460558891296386,
|
| 4293 |
"num_tokens": 8678813.0,
|
| 4294 |
"step": 2380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4295 |
}
|
| 4296 |
],
|
| 4297 |
"logging_steps": 5,
|
|
@@ -4311,7 +4329,7 @@
|
|
| 4311 |
"attributes": {}
|
| 4312 |
}
|
| 4313 |
},
|
| 4314 |
-
"total_flos": 4.
|
| 4315 |
"train_batch_size": 4,
|
| 4316 |
"trial_name": null,
|
| 4317 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4292 |
"mean_token_accuracy": 0.6460558891296386,
|
| 4293 |
"num_tokens": 8678813.0,
|
| 4294 |
"step": 2380
|
| 4295 |
+
},
|
| 4296 |
+
{
|
| 4297 |
+
"epoch": 18.346153846153847,
|
| 4298 |
+
"grad_norm": 0.0,
|
| 4299 |
+
"learning_rate": 3.808e-05,
|
| 4300 |
+
"loss": 1.7844,
|
| 4301 |
+
"mean_token_accuracy": 0.6402776807546615,
|
| 4302 |
+
"num_tokens": 8696912.0,
|
| 4303 |
+
"step": 2385
|
| 4304 |
+
},
|
| 4305 |
+
{
|
| 4306 |
+
"epoch": 18.384615384615383,
|
| 4307 |
+
"grad_norm": 0.0,
|
| 4308 |
+
"learning_rate": 3.8055e-05,
|
| 4309 |
+
"loss": 1.8192,
|
| 4310 |
+
"mean_token_accuracy": 0.6349106699228286,
|
| 4311 |
+
"num_tokens": 8714150.0,
|
| 4312 |
+
"step": 2390
|
| 4313 |
}
|
| 4314 |
],
|
| 4315 |
"logging_steps": 5,
|
|
|
|
| 4329 |
"attributes": {}
|
| 4330 |
}
|
| 4331 |
},
|
| 4332 |
+
"total_flos": 4.415219353239552e+17,
|
| 4333 |
"train_batch_size": 4,
|
| 4334 |
"trial_name": null,
|
| 4335 |
"trial_params": null
|