Training in progress, step 7100, 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:f01a54f82d05acf791a5e7b569131867fd08c15c079c3f6d6bdaa2f81cdac33b
|
| 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:a3948432802a85983a29c5d971f2ce3ee3a9817c5eac33a45329659a3dc38c64
|
| 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 sha256:79ea812e9e3da797685a12b8dd2431ee245e659e16d2c4620bfceefa5e2cf3ed
|
| 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 sha256:128d562d022a9ff2e771b0c22f899302b1ef5ab5cbd109d50f3a9757e24c4614
|
| 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":
|
| 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,
|
|
@@ -609,6 +609,13 @@
|
|
| 609 |
"eval_samples_per_second": 19.872,
|
| 610 |
"eval_steps_per_second": 2.485,
|
| 611 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 612 |
}
|
| 613 |
],
|
| 614 |
"logging_steps": 100,
|
|
@@ -628,7 +635,7 @@
|
|
| 628 |
"attributes": {}
|
| 629 |
}
|
| 630 |
},
|
| 631 |
-
"total_flos": 1.
|
| 632 |
"train_batch_size": 8,
|
| 633 |
"trial_name": null,
|
| 634 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.197781596625527,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 609 |
"eval_samples_per_second": 19.872,
|
| 610 |
"eval_steps_per_second": 2.485,
|
| 611 |
"step": 7000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 14.197781596625527,
|
| 615 |
+
"grad_norm": 0.21237194538116455,
|
| 616 |
+
"learning_rate": 5.266666666666666e-05,
|
| 617 |
+
"loss": 1.2406,
|
| 618 |
+
"step": 7100
|
| 619 |
}
|
| 620 |
],
|
| 621 |
"logging_steps": 100,
|
|
|
|
| 635 |
"attributes": {}
|
| 636 |
}
|
| 637 |
},
|
| 638 |
+
"total_flos": 1.1081194758175982e+19,
|
| 639 |
"train_batch_size": 8,
|
| 640 |
"trial_name": null,
|
| 641 |
"trial_params": null
|