Training in progress, step 5030, 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 sha256:6351b9139c5c6abdbe7fa4176b7d2f941cc7bb39dd59cf1ff6e7f324da9039d0
|
| 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 sha256:162d15a7872fd12e51f98caaa32483923336b55eaa263f228b927ee4a6229052
|
| 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:e48e903816d21f5143d70d668e0fe4ce768db5427662356d27e141f3e66510dc
|
| 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": 38.
|
| 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,
|
|
@@ -9044,6 +9044,24 @@
|
|
| 9044 |
"mean_token_accuracy": 0.6582322597503663,
|
| 9045 |
"num_tokens": 18306234.0,
|
| 9046 |
"step": 5020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9047 |
}
|
| 9048 |
],
|
| 9049 |
"logging_steps": 5,
|
|
@@ -9063,7 +9081,7 @@
|
|
| 9063 |
"attributes": {}
|
| 9064 |
}
|
| 9065 |
},
|
| 9066 |
-
"total_flos": 9.
|
| 9067 |
"train_batch_size": 4,
|
| 9068 |
"trial_name": null,
|
| 9069 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9044 |
"mean_token_accuracy": 0.6582322597503663,
|
| 9045 |
"num_tokens": 18306234.0,
|
| 9046 |
"step": 5020
|
| 9047 |
+
},
|
| 9048 |
+
{
|
| 9049 |
+
"epoch": 38.65384615384615,
|
| 9050 |
+
"grad_norm": 0.0,
|
| 9051 |
+
"learning_rate": 2.488e-05,
|
| 9052 |
+
"loss": 1.6772,
|
| 9053 |
+
"mean_token_accuracy": 0.6635013937950134,
|
| 9054 |
+
"num_tokens": 18325571.0,
|
| 9055 |
+
"step": 5025
|
| 9056 |
+
},
|
| 9057 |
+
{
|
| 9058 |
+
"epoch": 38.69230769230769,
|
| 9059 |
+
"grad_norm": 0.0,
|
| 9060 |
+
"learning_rate": 2.4855000000000002e-05,
|
| 9061 |
+
"loss": 1.7387,
|
| 9062 |
+
"mean_token_accuracy": 0.6517604231834412,
|
| 9063 |
+
"num_tokens": 18344113.0,
|
| 9064 |
+
"step": 5030
|
| 9065 |
}
|
| 9066 |
],
|
| 9067 |
"logging_steps": 5,
|
|
|
|
| 9081 |
"attributes": {}
|
| 9082 |
}
|
| 9083 |
},
|
| 9084 |
+
"total_flos": 9.295618734592819e+17,
|
| 9085 |
"train_batch_size": 4,
|
| 9086 |
"trial_name": null,
|
| 9087 |
"trial_params": null
|