Training in progress, step 8880, 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:e834f60fb9108c24f077da8ac517c9d717ab2d8ffc1b4e3c0808f3296bbadc11
|
| 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 sha256:8210f16f4b5eca17995b1c204cdc5ee898f7bcd2b79536384868ddcf0ecdda66
|
| 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 sha256:5f1baf4528f28a7b0d4c3330419db466287a61ddd60ccdd84b6e2166b00bab2a
|
| 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": 68.
|
| 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,
|
|
@@ -15974,6 +15974,24 @@
|
|
| 15974 |
"mean_token_accuracy": 0.6429946154356003,
|
| 15975 |
"num_tokens": 32346455.0,
|
| 15976 |
"step": 8870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15977 |
}
|
| 15978 |
],
|
| 15979 |
"logging_steps": 5,
|
|
@@ -15993,7 +16011,7 @@
|
|
| 15993 |
"attributes": {}
|
| 15994 |
}
|
| 15995 |
},
|
| 15996 |
-
"total_flos": 1.
|
| 15997 |
"train_batch_size": 4,
|
| 15998 |
"trial_name": null,
|
| 15999 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15974 |
"mean_token_accuracy": 0.6429946154356003,
|
| 15975 |
"num_tokens": 32346455.0,
|
| 15976 |
"step": 8870
|
| 15977 |
+
},
|
| 15978 |
+
{
|
| 15979 |
+
"epoch": 68.26923076923077,
|
| 15980 |
+
"grad_norm": 0.0,
|
| 15981 |
+
"learning_rate": 5.63e-06,
|
| 15982 |
+
"loss": 1.7832,
|
| 15983 |
+
"mean_token_accuracy": 0.6436864167451859,
|
| 15984 |
+
"num_tokens": 32364893.0,
|
| 15985 |
+
"step": 8875
|
| 15986 |
+
},
|
| 15987 |
+
{
|
| 15988 |
+
"epoch": 68.3076923076923,
|
| 15989 |
+
"grad_norm": 0.0,
|
| 15990 |
+
"learning_rate": 5.6050000000000005e-06,
|
| 15991 |
+
"loss": 1.6646,
|
| 15992 |
+
"mean_token_accuracy": 0.66810921728611,
|
| 15993 |
+
"num_tokens": 32383625.0,
|
| 15994 |
+
"step": 8880
|
| 15995 |
}
|
| 15996 |
],
|
| 15997 |
"logging_steps": 5,
|
|
|
|
| 16011 |
"attributes": {}
|
| 16012 |
}
|
| 16013 |
},
|
| 16014 |
+
"total_flos": 1.6420401042835046e+18,
|
| 16015 |
"train_batch_size": 4,
|
| 16016 |
"trial_name": null,
|
| 16017 |
"trial_params": null
|