Training in progress, step 6300, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:665dde0e6fc7879a3d8e727d0af19a6de37f41e7534931323b7c9a32ab251b0f
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a61835c0a67b04b968d6d9f06bbe32b89bc83df175554840187efb830ae2fd5
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18e8192e5bf44c5b1022a96307c0207d3667ab7ab9f900e7a2f317769b1db21b
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3cedce883a74f810c460975dabc630b4202f69ba8bff18b8215fe35b663ca8e
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 12.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -537,6 +537,13 @@
|
|
| 537 |
"learning_rate": 5.866666666666667e-05,
|
| 538 |
"loss": 1.2458,
|
| 539 |
"step": 6200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 540 |
}
|
| 541 |
],
|
| 542 |
"logging_steps": 100,
|
|
@@ -556,7 +563,7 @@
|
|
| 556 |
"attributes": {}
|
| 557 |
}
|
| 558 |
},
|
| 559 |
-
"total_flos": 9.
|
| 560 |
"train_batch_size": 8,
|
| 561 |
"trial_name": null,
|
| 562 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.59803155756913,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 537 |
"learning_rate": 5.866666666666667e-05,
|
| 538 |
"loss": 1.2458,
|
| 539 |
"step": 6200
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 12.59803155756913,
|
| 543 |
+
"grad_norm": 0.1970139741897583,
|
| 544 |
+
"learning_rate": 5.8e-05,
|
| 545 |
+
"loss": 1.2423,
|
| 546 |
+
"step": 6300
|
| 547 |
}
|
| 548 |
],
|
| 549 |
"logging_steps": 100,
|
|
|
|
| 563 |
"attributes": {}
|
| 564 |
}
|
| 565 |
},
|
| 566 |
+
"total_flos": 9.832613302411198e+18,
|
| 567 |
"train_batch_size": 8,
|
| 568 |
"trial_name": null,
|
| 569 |
"trial_params": null
|