MohamedAhmedAE
commited on
Commit
•
869b071
1
Parent(s):
4437f26
Training in progress, step 23200, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
"up_proj",
|
25 |
"v_proj",
|
26 |
"down_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
"up_proj",
|
25 |
"v_proj",
|
26 |
"down_proj",
|
27 |
+
"k_proj",
|
28 |
+
"q_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 sha256:2e7f627d305f378c78e9f5383b187508dd29135634d00313e9ea84b8956b2c84
|
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:b46e266c798c9afd8e6ff2fa3e7ace3e707953edb004e4467129ee189289adcc
|
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 sha256:5e76919056ec8898be3700e1aa15e2687b14a94dd025c0e9da95ad09620b0a32
|
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:f4951502290c05c8b85ac5c7ba7e4d82d3ec30601aec1ebc772e1f7b17f05750
|
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,
|
@@ -791,14 +791,42 @@
|
|
791 |
"learning_rate": 1.9997813001808763e-05,
|
792 |
"loss": 1.5603,
|
793 |
"step": 22400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
794 |
}
|
795 |
],
|
796 |
"logging_steps": 200,
|
797 |
-
"max_steps":
|
798 |
"num_input_tokens_seen": 0,
|
799 |
"num_train_epochs": 5,
|
800 |
"save_steps": 200,
|
801 |
-
"total_flos": 4.
|
802 |
"train_batch_size": 1,
|
803 |
"trial_name": null,
|
804 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.051758949055362,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 23200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
791 |
"learning_rate": 1.9997813001808763e-05,
|
792 |
"loss": 1.5603,
|
793 |
"step": 22400
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.05,
|
797 |
+
"grad_norm": 3.027528762817383,
|
798 |
+
"learning_rate": 1.9994991132809548e-05,
|
799 |
+
"loss": 1.5228,
|
800 |
+
"step": 22600
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.05,
|
804 |
+
"grad_norm": 1.9839845895767212,
|
805 |
+
"learning_rate": 1.9994902463916502e-05,
|
806 |
+
"loss": 1.5413,
|
807 |
+
"step": 22800
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.05,
|
811 |
+
"grad_norm": 1.558858871459961,
|
812 |
+
"learning_rate": 1.999481256582422e-05,
|
813 |
+
"loss": 1.5713,
|
814 |
+
"step": 23000
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.05,
|
818 |
+
"grad_norm": 2.022099256515503,
|
819 |
+
"learning_rate": 1.9994721882148102e-05,
|
820 |
+
"loss": 1.5488,
|
821 |
+
"step": 23200
|
822 |
}
|
823 |
],
|
824 |
"logging_steps": 200,
|
825 |
+
"max_steps": 2241155,
|
826 |
"num_input_tokens_seen": 0,
|
827 |
"num_train_epochs": 5,
|
828 |
"save_steps": 200,
|
829 |
+
"total_flos": 4.6409799585243955e+17,
|
830 |
"train_batch_size": 1,
|
831 |
"trial_name": null,
|
832 |
"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:c8b8d5d55034cf9499e0ba365ba364383f0583a4c0942d2f91245e7ceb5c8746
|
3 |
size 4920
|