Training in progress, step 100, 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 100966336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3ce26b2833b28803c8aab9ef27885305339358f453f9374089eff208aa943c9
|
3 |
size 100966336
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 202110330
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e9d12b28ba1e071c6cda15ed53d26da5d977cf291c9026ab54c9d4599d25a4e
|
3 |
size 202110330
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deb0faa09832f00a697bad032c8f4da1c80c1ae05de14fb01ee2fd76432202ec
|
3 |
size 14244
|
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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
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": 0.
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -732,6 +732,21 @@
|
|
732 |
"learning_rate": 7.709637592770991e-08,
|
733 |
"loss": 1.3893,
|
734 |
"step": 99
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
735 |
}
|
736 |
],
|
737 |
"logging_steps": 1,
|
@@ -746,12 +761,12 @@
|
|
746 |
"should_evaluate": false,
|
747 |
"should_log": false,
|
748 |
"should_save": true,
|
749 |
-
"should_training_stop":
|
750 |
},
|
751 |
"attributes": {}
|
752 |
}
|
753 |
},
|
754 |
-
"total_flos": 8.
|
755 |
"train_batch_size": 2,
|
756 |
"trial_name": null,
|
757 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.13220955214014213,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
732 |
"learning_rate": 7.709637592770991e-08,
|
733 |
"loss": 1.3893,
|
734 |
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.13220955214014213,
|
738 |
+
"grad_norm": 0.27371945977211,
|
739 |
+
"learning_rate": 0.0,
|
740 |
+
"loss": 1.459,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.13220955214014213,
|
745 |
+
"eval_loss": 1.4851912260055542,
|
746 |
+
"eval_runtime": 186.5599,
|
747 |
+
"eval_samples_per_second": 13.658,
|
748 |
+
"eval_steps_per_second": 6.829,
|
749 |
+
"step": 100
|
750 |
}
|
751 |
],
|
752 |
"logging_steps": 1,
|
|
|
761 |
"should_evaluate": false,
|
762 |
"should_log": false,
|
763 |
"should_save": true,
|
764 |
+
"should_training_stop": true
|
765 |
},
|
766 |
"attributes": {}
|
767 |
}
|
768 |
},
|
769 |
+
"total_flos": 8.33416392081408e+16,
|
770 |
"train_batch_size": 2,
|
771 |
"trial_name": null,
|
772 |
"trial_params": null
|