Training in progress, step 3780, 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:fe1102628acc30e65de062f8569893719afd190aae2947b4e976dfd89c527ece
|
| 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:f753eb6a9ba4e62d4524c40fa23975892f5e9305f39a7c6a4cddd2c51d2c6120
|
| 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:c4286a69347942cc46a395040b53110c6d712bc8abbee8f0dee55ca9073185e4
|
| 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": 29.
|
| 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,
|
|
@@ -6794,6 +6794,24 @@
|
|
| 6794 |
"mean_token_accuracy": 0.6510610312223435,
|
| 6795 |
"num_tokens": 13749045.0,
|
| 6796 |
"step": 3770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6797 |
}
|
| 6798 |
],
|
| 6799 |
"logging_steps": 5,
|
|
@@ -6813,7 +6831,7 @@
|
|
| 6813 |
"attributes": {}
|
| 6814 |
}
|
| 6815 |
},
|
| 6816 |
-
"total_flos": 6.
|
| 6817 |
"train_batch_size": 4,
|
| 6818 |
"trial_name": null,
|
| 6819 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6794 |
"mean_token_accuracy": 0.6510610312223435,
|
| 6795 |
"num_tokens": 13749045.0,
|
| 6796 |
"step": 3770
|
| 6797 |
+
},
|
| 6798 |
+
{
|
| 6799 |
+
"epoch": 29.03846153846154,
|
| 6800 |
+
"grad_norm": 0.0,
|
| 6801 |
+
"learning_rate": 3.113e-05,
|
| 6802 |
+
"loss": 1.6943,
|
| 6803 |
+
"mean_token_accuracy": 0.658639770746231,
|
| 6804 |
+
"num_tokens": 13767612.0,
|
| 6805 |
+
"step": 3775
|
| 6806 |
+
},
|
| 6807 |
+
{
|
| 6808 |
+
"epoch": 29.076923076923077,
|
| 6809 |
+
"grad_norm": 0.0,
|
| 6810 |
+
"learning_rate": 3.1105e-05,
|
| 6811 |
+
"loss": 1.7511,
|
| 6812 |
+
"mean_token_accuracy": 0.645610973238945,
|
| 6813 |
+
"num_tokens": 13785732.0,
|
| 6814 |
+
"step": 3780
|
| 6815 |
}
|
| 6816 |
],
|
| 6817 |
"logging_steps": 5,
|
|
|
|
| 6831 |
"attributes": {}
|
| 6832 |
}
|
| 6833 |
},
|
| 6834 |
+
"total_flos": 6.986177640323482e+17,
|
| 6835 |
"train_batch_size": 4,
|
| 6836 |
"trial_name": null,
|
| 6837 |
"trial_params": null
|