Training in progress, step 2770, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54e2729dffa47f57b0e97815a39ff4cfe6e89557c225ec403f1303080d08d1a9
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c106f011eae8cfa1c82f5a91006818475d849c254c20cdbd51e7151eb9ae749
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a9f2bc54a4079fbe4b8ad27b6a7352f3974915ff142a573bf979cb035c512c5
|
| 3 |
size 14645
|
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:e357470dc57fe0b1eeda492e3b025683fbdff156b647b41e6fb83bfdf07b01c6
|
| 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": 0.
|
| 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,
|
|
@@ -2778,6 +2778,16 @@
|
|
| 2778 |
"mean_token_accuracy": 0.7844551488757133,
|
| 2779 |
"num_tokens": 12821354.0,
|
| 2780 |
"step": 2760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2781 |
}
|
| 2782 |
],
|
| 2783 |
"logging_steps": 10,
|
|
@@ -2797,7 +2807,7 @@
|
|
| 2797 |
"attributes": {}
|
| 2798 |
}
|
| 2799 |
},
|
| 2800 |
-
"total_flos": 6.
|
| 2801 |
"train_batch_size": 4,
|
| 2802 |
"trial_name": null,
|
| 2803 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5909333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2778 |
"mean_token_accuracy": 0.7844551488757133,
|
| 2779 |
"num_tokens": 12821354.0,
|
| 2780 |
"step": 2760
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"entropy": 1.0409190684556962,
|
| 2784 |
+
"epoch": 0.5909333333333333,
|
| 2785 |
+
"grad_norm": 0.211833655834198,
|
| 2786 |
+
"learning_rate": 8.28250058848195e-05,
|
| 2787 |
+
"loss": 1.101518440246582,
|
| 2788 |
+
"mean_token_accuracy": 0.7454183496534824,
|
| 2789 |
+
"num_tokens": 12874281.0,
|
| 2790 |
+
"step": 2770
|
| 2791 |
}
|
| 2792 |
],
|
| 2793 |
"logging_steps": 10,
|
|
|
|
| 2807 |
"attributes": {}
|
| 2808 |
}
|
| 2809 |
},
|
| 2810 |
+
"total_flos": 6.101931771876864e+16,
|
| 2811 |
"train_batch_size": 4,
|
| 2812 |
"trial_name": null,
|
| 2813 |
"trial_params": null
|