MohamedAhmedAE
commited on
Commit
•
7aa503b
1
Parent(s):
f08beac
Training in progress, step 23400, 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 |
-
"k_proj",
|
28 |
"q_proj",
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"k_proj",
|
25 |
"up_proj",
|
26 |
"v_proj",
|
|
|
|
|
27 |
"q_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"down_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 sha256:8c7f93eabe6ac3c54d66eaa201fd02227487a26f7778737a9f254ff462e973e4
|
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 sha256:73914a91d2c85155b01b949bf4bca1b47684ea4ff1764db4a597aed9516fd5ab
|
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 sha256:0f8c4f9076fe893e7a53debd026211a9b9066658d86f31864434230c495759f3
|
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 sha256:8114cada636c19d5007acc44352f3b0449c4b5ebb7cb27bcb702507137d58166
|
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,
|
@@ -819,14 +819,21 @@
|
|
819 |
"learning_rate": 1.9994721882148102e-05,
|
820 |
"loss": 1.5488,
|
821 |
"step": 23200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
822 |
}
|
823 |
],
|
824 |
"logging_steps": 200,
|
825 |
-
"max_steps":
|
826 |
"num_input_tokens_seen": 0,
|
827 |
"num_train_epochs": 5,
|
828 |
"save_steps": 200,
|
829 |
-
"total_flos": 4.
|
830 |
"train_batch_size": 1,
|
831 |
"trial_name": null,
|
832 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0696068625227282,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 23400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
819 |
"learning_rate": 1.9994721882148102e-05,
|
820 |
"loss": 1.5488,
|
821 |
"step": 23200
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.07,
|
825 |
+
"grad_norm": 1.663493275642395,
|
826 |
+
"learning_rate": 1.999045551990737e-05,
|
827 |
+
"loss": 1.536,
|
828 |
+
"step": 23400
|
829 |
}
|
830 |
],
|
831 |
"logging_steps": 200,
|
832 |
+
"max_steps": 1680865,
|
833 |
"num_input_tokens_seen": 0,
|
834 |
"num_train_epochs": 5,
|
835 |
"save_steps": 200,
|
836 |
+
"total_flos": 4.745472228553851e+17,
|
837 |
"train_batch_size": 1,
|
838 |
"trial_name": null,
|
839 |
"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:e88463ac0cd6182d9b1cd0ac83ec16eba34109ec5568773d1ab337bb23a66942
|
3 |
size 4920
|