Training in progress, step 8780, 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 sha256:63446f40107a1e6d82003ee7f8a5242ea3e4b68d5e7544528da73c4203b2d3f2
|
| 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:c5cd8cc2758ebc71ec25995b7af7f62c41d75d04f0a3721ce75d037cb957b653
|
| 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 sha256:9006012608f1adab17047916dce8f5354abf6679ca440bc14b80c8114ea304e0
|
| 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": 67.
|
| 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,
|
|
@@ -15794,6 +15794,24 @@
|
|
| 15794 |
"mean_token_accuracy": 0.6392051458358765,
|
| 15795 |
"num_tokens": 31982476.0,
|
| 15796 |
"step": 8770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15797 |
}
|
| 15798 |
],
|
| 15799 |
"logging_steps": 5,
|
|
@@ -15813,7 +15831,7 @@
|
|
| 15813 |
"attributes": {}
|
| 15814 |
}
|
| 15815 |
},
|
| 15816 |
-
"total_flos": 1.
|
| 15817 |
"train_batch_size": 4,
|
| 15818 |
"trial_name": null,
|
| 15819 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15794 |
"mean_token_accuracy": 0.6392051458358765,
|
| 15795 |
"num_tokens": 31982476.0,
|
| 15796 |
"step": 8770
|
| 15797 |
+
},
|
| 15798 |
+
{
|
| 15799 |
+
"epoch": 67.5,
|
| 15800 |
+
"grad_norm": 0.0,
|
| 15801 |
+
"learning_rate": 6.130000000000001e-06,
|
| 15802 |
+
"loss": 1.7112,
|
| 15803 |
+
"mean_token_accuracy": 0.6520894914865494,
|
| 15804 |
+
"num_tokens": 32001093.0,
|
| 15805 |
+
"step": 8775
|
| 15806 |
+
},
|
| 15807 |
+
{
|
| 15808 |
+
"epoch": 67.53846153846153,
|
| 15809 |
+
"grad_norm": 0.0,
|
| 15810 |
+
"learning_rate": 6.105e-06,
|
| 15811 |
+
"loss": 1.7363,
|
| 15812 |
+
"mean_token_accuracy": 0.651617681980133,
|
| 15813 |
+
"num_tokens": 32019131.0,
|
| 15814 |
+
"step": 8780
|
| 15815 |
}
|
| 15816 |
],
|
| 15817 |
"logging_steps": 5,
|
|
|
|
| 15831 |
"attributes": {}
|
| 15832 |
}
|
| 15833 |
},
|
| 15834 |
+
"total_flos": 1.6235813934165197e+18,
|
| 15835 |
"train_batch_size": 4,
|
| 15836 |
"trial_name": null,
|
| 15837 |
"trial_params": null
|