MohamedAhmedAE
commited on
Commit
•
e9a8d7c
1
Parent(s):
62ee238
Training in progress, step 22200, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"v_proj",
|
24 |
"q_proj",
|
25 |
-
"gate_proj",
|
26 |
-
"down_proj",
|
27 |
"up_proj",
|
28 |
-
"
|
29 |
-
"
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"q_proj",
|
|
|
|
|
24 |
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"o_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ad5df223fcbfdd3ad46ed054bfdef283483890238b3a6ac51915a4695682e23
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 85736914
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6982f8b3fe44594c163fc5ab0e300f13004e4862a415b5b03ac8da4472123835
|
3 |
size 85736914
|
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:dd8f2420f5ce27e32ef99ce3a23532d1502953314af1258b35a9d3e59a9189b5
|
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 sha256:3636d6407e959c81f7c73cc51cbd4d3f955a426c0e115359ea4e27b55c546296
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -707,6 +707,83 @@
|
|
707 |
"learning_rate": 1.99982565504712e-05,
|
708 |
"loss": 1.5135,
|
709 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
710 |
}
|
711 |
],
|
712 |
"logging_steps": 200,
|
@@ -714,7 +791,7 @@
|
|
714 |
"num_input_tokens_seen": 0,
|
715 |
"num_train_epochs": 5,
|
716 |
"save_steps": 200,
|
717 |
-
"total_flos":
|
718 |
"train_batch_size": 1,
|
719 |
"trial_name": null,
|
720 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.03301863991462748,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 22200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
707 |
"learning_rate": 1.99982565504712e-05,
|
708 |
"loss": 1.5135,
|
709 |
"step": 20000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.03,
|
713 |
+
"grad_norm": 2.2242326736450195,
|
714 |
+
"learning_rate": 1.9998221652689703e-05,
|
715 |
+
"loss": 1.5325,
|
716 |
+
"step": 20200
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.03,
|
720 |
+
"grad_norm": 1.6685123443603516,
|
721 |
+
"learning_rate": 1.9998186409125715e-05,
|
722 |
+
"loss": 1.5765,
|
723 |
+
"step": 20400
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.03,
|
727 |
+
"grad_norm": 1.8478649854660034,
|
728 |
+
"learning_rate": 1.999815064006636e-05,
|
729 |
+
"loss": 1.5597,
|
730 |
+
"step": 20600
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.03,
|
734 |
+
"grad_norm": 2.6228203773498535,
|
735 |
+
"learning_rate": 1.999811452174307e-05,
|
736 |
+
"loss": 1.5312,
|
737 |
+
"step": 20800
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.03,
|
741 |
+
"grad_norm": 1.2979694604873657,
|
742 |
+
"learning_rate": 1.9998078054157092e-05,
|
743 |
+
"loss": 1.5863,
|
744 |
+
"step": 21000
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.03,
|
748 |
+
"grad_norm": 1.4286555051803589,
|
749 |
+
"learning_rate": 1.999804123730971e-05,
|
750 |
+
"loss": 1.5265,
|
751 |
+
"step": 21200
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.03,
|
755 |
+
"grad_norm": 2.2393202781677246,
|
756 |
+
"learning_rate": 1.999800407120221e-05,
|
757 |
+
"loss": 1.5599,
|
758 |
+
"step": 21400
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.03,
|
762 |
+
"grad_norm": 8.066116333007812,
|
763 |
+
"learning_rate": 1.9997966555835886e-05,
|
764 |
+
"loss": 1.5345,
|
765 |
+
"step": 21600
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.03,
|
769 |
+
"grad_norm": 2.866185426712036,
|
770 |
+
"learning_rate": 1.9997928691212052e-05,
|
771 |
+
"loss": 1.5141,
|
772 |
+
"step": 21800
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.03,
|
776 |
+
"grad_norm": 2.5764899253845215,
|
777 |
+
"learning_rate": 1.9997890477332027e-05,
|
778 |
+
"loss": 1.5189,
|
779 |
+
"step": 22000
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.03,
|
783 |
+
"grad_norm": 3.597501039505005,
|
784 |
+
"learning_rate": 1.9997851914197147e-05,
|
785 |
+
"loss": 1.5368,
|
786 |
+
"step": 22200
|
787 |
}
|
788 |
],
|
789 |
"logging_steps": 200,
|
|
|
791 |
"num_input_tokens_seen": 0,
|
792 |
"num_train_epochs": 5,
|
793 |
"save_steps": 200,
|
794 |
+
"total_flos": 4.275111434343137e+17,
|
795 |
"train_batch_size": 1,
|
796 |
"trial_name": null,
|
797 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a7800ffb29813f89bbd542587a923598ba056a5186a554421f6b09a6d22b374
|
3 |
size 4920
|