Training in progress, step 1500, 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:d82d7e9644813fab2dbfdf5b081b4b7be0573af2a648f8e0fbddc9c1d0675ffb
|
| 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 sha256:3fb8aa24d8e3d3eb500901b3fd10076d282796e7f6d53611769937ea1230d04f
|
| 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 sha256:7303fc176b8c045d14c714d2d98924d581b3b304691f118afeb16499892f5326
|
| 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": 11.
|
| 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,
|
|
@@ -2690,6 +2690,24 @@
|
|
| 2690 |
"mean_token_accuracy": 0.6546613723039627,
|
| 2691 |
"num_tokens": 5433912.0,
|
| 2692 |
"step": 1490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2693 |
}
|
| 2694 |
],
|
| 2695 |
"logging_steps": 5,
|
|
@@ -2709,7 +2727,7 @@
|
|
| 2709 |
"attributes": {}
|
| 2710 |
}
|
| 2711 |
},
|
| 2712 |
-
"total_flos": 2.
|
| 2713 |
"train_batch_size": 4,
|
| 2714 |
"trial_name": null,
|
| 2715 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2690 |
"mean_token_accuracy": 0.6546613723039627,
|
| 2691 |
"num_tokens": 5433912.0,
|
| 2692 |
"step": 1490
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 11.5,
|
| 2696 |
+
"grad_norm": 0.0,
|
| 2697 |
+
"learning_rate": 4.253e-05,
|
| 2698 |
+
"loss": 1.6738,
|
| 2699 |
+
"mean_token_accuracy": 0.6659036576747894,
|
| 2700 |
+
"num_tokens": 5453181.0,
|
| 2701 |
+
"step": 1495
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 11.538461538461538,
|
| 2705 |
+
"grad_norm": 0.0,
|
| 2706 |
+
"learning_rate": 4.2505e-05,
|
| 2707 |
+
"loss": 1.7129,
|
| 2708 |
+
"mean_token_accuracy": 0.6556811064481736,
|
| 2709 |
+
"num_tokens": 5472123.0,
|
| 2710 |
+
"step": 1500
|
| 2711 |
}
|
| 2712 |
],
|
| 2713 |
"logging_steps": 5,
|
|
|
|
| 2727 |
"attributes": {}
|
| 2728 |
}
|
| 2729 |
},
|
| 2730 |
+
"total_flos": 2.7734207520374784e+17,
|
| 2731 |
"train_batch_size": 4,
|
| 2732 |
"trial_name": null,
|
| 2733 |
"trial_params": null
|