Training in progress, step 2750, 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:ce94a5b1e3b400b149d2ecf3ee1b3dd4aa14f31896bc979121978907fffc6905
|
| 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 sha256:8664e7824d8b3bba40659baf27145335ca033b25b9896ed5512f2a1eabe9df23
|
| 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 sha256:0b4620901f2758e01da843da2db128a11d9df79e7a18131b8f46a15775daebc4
|
| 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 sha256:0a7f63523305b465edcf4a901415b1488702abd4e2aa16500e27bb14080a8b45
|
| 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,
|
|
@@ -2758,6 +2758,16 @@
|
|
| 2758 |
"mean_token_accuracy": 0.7658515647053719,
|
| 2759 |
"num_tokens": 12728360.0,
|
| 2760 |
"step": 2740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2761 |
}
|
| 2762 |
],
|
| 2763 |
"logging_steps": 10,
|
|
@@ -2777,7 +2787,7 @@
|
|
| 2777 |
"attributes": {}
|
| 2778 |
}
|
| 2779 |
},
|
| 2780 |
-
"total_flos": 6.
|
| 2781 |
"train_batch_size": 4,
|
| 2782 |
"trial_name": null,
|
| 2783 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5866666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2758 |
"mean_token_accuracy": 0.7658515647053719,
|
| 2759 |
"num_tokens": 12728360.0,
|
| 2760 |
"step": 2740
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"entropy": 1.02061934620142,
|
| 2764 |
+
"epoch": 0.5866666666666667,
|
| 2765 |
+
"grad_norm": 0.2634807229042053,
|
| 2766 |
+
"learning_rate": 8.308532175392456e-05,
|
| 2767 |
+
"loss": 1.098531150817871,
|
| 2768 |
+
"mean_token_accuracy": 0.7488874278962612,
|
| 2769 |
+
"num_tokens": 12776988.0,
|
| 2770 |
+
"step": 2750
|
| 2771 |
}
|
| 2772 |
],
|
| 2773 |
"logging_steps": 10,
|
|
|
|
| 2787 |
"attributes": {}
|
| 2788 |
}
|
| 2789 |
},
|
| 2790 |
+
"total_flos": 6.057115748971008e+16,
|
| 2791 |
"train_batch_size": 4,
|
| 2792 |
"trial_name": null,
|
| 2793 |
"trial_params": null
|