Training in progress, step 6560, 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 sha256:1491d329e39476ec45aa7a4631fb08c29530eac9b768e5da9f424e47526d694e
|
| 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:f0473555db420c2d00d3f4cf5c5b843580ae80faa95f52de7ff6788931e12967
|
| 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 sha256:0ca3d30c4312c12b153f82967adcf3074b390330970ee3481f73563acbe741eb
|
| 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": 50.
|
| 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,
|
|
@@ -11798,6 +11798,24 @@
|
|
| 11798 |
"mean_token_accuracy": 0.6558305144309997,
|
| 11799 |
"num_tokens": 23887966.0,
|
| 11800 |
"step": 6550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11801 |
}
|
| 11802 |
],
|
| 11803 |
"logging_steps": 5,
|
|
@@ -11817,7 +11835,7 @@
|
|
| 11817 |
"attributes": {}
|
| 11818 |
}
|
| 11819 |
},
|
| 11820 |
-
"total_flos": 1.
|
| 11821 |
"train_batch_size": 4,
|
| 11822 |
"trial_name": null,
|
| 11823 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11798 |
"mean_token_accuracy": 0.6558305144309997,
|
| 11799 |
"num_tokens": 23887966.0,
|
| 11800 |
"step": 6550
|
| 11801 |
+
},
|
| 11802 |
+
{
|
| 11803 |
+
"epoch": 50.42307692307692,
|
| 11804 |
+
"grad_norm": 0.0,
|
| 11805 |
+
"learning_rate": 1.7230000000000003e-05,
|
| 11806 |
+
"loss": 1.703,
|
| 11807 |
+
"mean_token_accuracy": 0.6580185920000077,
|
| 11808 |
+
"num_tokens": 23906795.0,
|
| 11809 |
+
"step": 6555
|
| 11810 |
+
},
|
| 11811 |
+
{
|
| 11812 |
+
"epoch": 50.46153846153846,
|
| 11813 |
+
"grad_norm": 0.0,
|
| 11814 |
+
"learning_rate": 1.7205000000000002e-05,
|
| 11815 |
+
"loss": 1.7364,
|
| 11816 |
+
"mean_token_accuracy": 0.6480530560016632,
|
| 11817 |
+
"num_tokens": 23925538.0,
|
| 11818 |
+
"step": 6560
|
| 11819 |
}
|
| 11820 |
],
|
| 11821 |
"logging_steps": 5,
|
|
|
|
| 11835 |
"attributes": {}
|
| 11836 |
}
|
| 11837 |
},
|
| 11838 |
+
"total_flos": 1.213013770210345e+18,
|
| 11839 |
"train_batch_size": 4,
|
| 11840 |
"trial_name": null,
|
| 11841 |
"trial_params": null
|