Training in progress, step 9430, 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:cccf607f4a177f04d4c9fc176380fc8b52e7cc9d7f101ae8857fa5e03ea94e81
|
| 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:fb7cdfe786eef6beda6e5bc9f389a5e5ffb57e10b52457634726011be69739aa
|
| 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:c1426ebe28bbff18fc25aa990d73388d748d1666d6cd16f17b33507fbcbada78
|
| 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": 72.
|
| 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,
|
|
@@ -16964,6 +16964,24 @@
|
|
| 16964 |
"mean_token_accuracy": 0.6363181412220001,
|
| 16965 |
"num_tokens": 34356326.0,
|
| 16966 |
"step": 9420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16967 |
}
|
| 16968 |
],
|
| 16969 |
"logging_steps": 5,
|
|
@@ -16983,7 +17001,7 @@
|
|
| 16983 |
"attributes": {}
|
| 16984 |
}
|
| 16985 |
},
|
| 16986 |
-
"total_flos": 1.
|
| 16987 |
"train_batch_size": 4,
|
| 16988 |
"trial_name": null,
|
| 16989 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16964 |
"mean_token_accuracy": 0.6363181412220001,
|
| 16965 |
"num_tokens": 34356326.0,
|
| 16966 |
"step": 9420
|
| 16967 |
+
},
|
| 16968 |
+
{
|
| 16969 |
+
"epoch": 72.5,
|
| 16970 |
+
"grad_norm": 0.0,
|
| 16971 |
+
"learning_rate": 2.88e-06,
|
| 16972 |
+
"loss": 1.811,
|
| 16973 |
+
"mean_token_accuracy": 0.6379002064466477,
|
| 16974 |
+
"num_tokens": 34373863.0,
|
| 16975 |
+
"step": 9425
|
| 16976 |
+
},
|
| 16977 |
+
{
|
| 16978 |
+
"epoch": 72.53846153846153,
|
| 16979 |
+
"grad_norm": 0.0,
|
| 16980 |
+
"learning_rate": 2.855e-06,
|
| 16981 |
+
"loss": 1.7939,
|
| 16982 |
+
"mean_token_accuracy": 0.64038887321949,
|
| 16983 |
+
"num_tokens": 34391352.0,
|
| 16984 |
+
"step": 9430
|
| 16985 |
}
|
| 16986 |
],
|
| 16987 |
"logging_steps": 5,
|
|
|
|
| 17001 |
"attributes": {}
|
| 17002 |
}
|
| 17003 |
},
|
| 17004 |
+
"total_flos": 1.74393090533376e+18,
|
| 17005 |
"train_batch_size": 4,
|
| 17006 |
"trial_name": null,
|
| 17007 |
"trial_params": null
|