Training in progress, step 2600, 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:d8e7cadebbae1d54eaf66ccc7b9f5c9ff4dd4bf44b4d8a1f8b8a0084844d5797
|
| 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:ad5f8e1609877fa0eb8aa18abf22e51f9d92e64d503e8b3d45179c00ded279ac
|
| 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 sha256:5d5e082edfc1c825c97152696481c3dec5a3c519176259229a60653e2b9ec26f
|
| 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 sha256:4376ea4c2891899450d26351d7f334694fcd1845e06b10d3542406ce1aa6a830
|
| 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,
|
|
@@ -2608,6 +2608,16 @@
|
|
| 2608 |
"mean_token_accuracy": 0.7832803040742874,
|
| 2609 |
"num_tokens": 12032447.0,
|
| 2610 |
"step": 2590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2611 |
}
|
| 2612 |
],
|
| 2613 |
"logging_steps": 10,
|
|
@@ -2627,7 +2637,7 @@
|
|
| 2627 |
"attributes": {}
|
| 2628 |
}
|
| 2629 |
},
|
| 2630 |
-
"total_flos": 5.
|
| 2631 |
"train_batch_size": 4,
|
| 2632 |
"trial_name": null,
|
| 2633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5546666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2608 |
"mean_token_accuracy": 0.7832803040742874,
|
| 2609 |
"num_tokens": 12032447.0,
|
| 2610 |
"step": 2590
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"entropy": 0.981315091997385,
|
| 2614 |
+
"epoch": 0.5546666666666666,
|
| 2615 |
+
"grad_norm": 0.25849565863609314,
|
| 2616 |
+
"learning_rate": 8.498629947969807e-05,
|
| 2617 |
+
"loss": 1.135009765625,
|
| 2618 |
+
"mean_token_accuracy": 0.7560776218771934,
|
| 2619 |
+
"num_tokens": 12082379.0,
|
| 2620 |
+
"step": 2600
|
| 2621 |
}
|
| 2622 |
],
|
| 2623 |
"logging_steps": 10,
|
|
|
|
| 2637 |
"attributes": {}
|
| 2638 |
}
|
| 2639 |
},
|
| 2640 |
+
"total_flos": 5.727758984615424e+16,
|
| 2641 |
"train_batch_size": 4,
|
| 2642 |
"trial_name": null,
|
| 2643 |
"trial_params": null
|