MohamedAhmedAE
commited on
Commit
•
9fb38bb
1
Parent(s):
879581f
Training in progress, step 20000, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"q_proj",
|
24 |
-
"o_proj",
|
25 |
-
"k_proj",
|
26 |
"gate_proj",
|
27 |
"down_proj",
|
28 |
"up_proj",
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
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 |
+
"k_proj",
|
29 |
+
"o_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:fb5d4a8e80692092cbb6ea69a8cd6902d7306436bd2ef4db3d268beb6d254345
|
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 sha256:5ed3c0ef76d1963f5e466fac078e7bdfa634f48c1b91aaad0c42e6ae39ac1315
|
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:adc80d060b3614ce93cf171cfa62b9a17755ba93a67b6a802cd87b68b0a907bb
|
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 sha256:55ba296f12eae4fc0511f08bee2c4fc9bf546a7ddf44e3e343ade2d2cae2ed71
|
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,
|
@@ -672,6 +672,41 @@
|
|
672 |
"learning_rate": 1.9998426349986698e-05,
|
673 |
"loss": 1.5367,
|
674 |
"step": 19000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
675 |
}
|
676 |
],
|
677 |
"logging_steps": 200,
|
@@ -679,7 +714,7 @@
|
|
679 |
"num_input_tokens_seen": 0,
|
680 |
"num_train_epochs": 5,
|
681 |
"save_steps": 200,
|
682 |
-
"total_flos": 3.
|
683 |
"train_batch_size": 1,
|
684 |
"trial_name": null,
|
685 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02974652244561034,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 20000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
672 |
"learning_rate": 1.9998426349986698e-05,
|
673 |
"loss": 1.5367,
|
674 |
"step": 19000
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.03,
|
678 |
+
"grad_norm": 3.7834692001342773,
|
679 |
+
"learning_rate": 1.9998393186348416e-05,
|
680 |
+
"loss": 1.5619,
|
681 |
+
"step": 19200
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.03,
|
685 |
+
"grad_norm": 2.51110577583313,
|
686 |
+
"learning_rate": 1.9998359507659452e-05,
|
687 |
+
"loss": 1.5688,
|
688 |
+
"step": 19400
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.03,
|
692 |
+
"grad_norm": 2.6746368408203125,
|
693 |
+
"learning_rate": 1.999832547969925e-05,
|
694 |
+
"loss": 1.5216,
|
695 |
+
"step": 19600
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.03,
|
699 |
+
"grad_norm": 2.6558778285980225,
|
700 |
+
"learning_rate": 1.9998291102469e-05,
|
701 |
+
"loss": 1.5335,
|
702 |
+
"step": 19800
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.03,
|
706 |
+
"grad_norm": 2.4056808948516846,
|
707 |
+
"learning_rate": 1.99982565504712e-05,
|
708 |
+
"loss": 1.5135,
|
709 |
+
"step": 20000
|
710 |
}
|
711 |
],
|
712 |
"logging_steps": 200,
|
|
|
714 |
"num_input_tokens_seen": 0,
|
715 |
"num_train_epochs": 5,
|
716 |
"save_steps": 200,
|
717 |
+
"total_flos": 3.6983529369430426e+17,
|
718 |
"train_batch_size": 1,
|
719 |
"trial_name": null,
|
720 |
"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 sha256:7da6c64555cac2ee9fc43605b134636b4610ed6cd244e07ab7cb4ce3c058548c
|
3 |
size 4920
|