Commit
•
8ae9b84
1
Parent(s):
0a31dd4
Training in progress, step 26600, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"k_proj",
|
24 |
-
"down_proj",
|
25 |
"up_proj",
|
26 |
"q_proj",
|
27 |
-
"
|
28 |
-
"o_proj",
|
29 |
-
"v_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"o_proj",
|
25 |
+
"gate_proj",
|
26 |
"k_proj",
|
|
|
27 |
"up_proj",
|
28 |
"q_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:a66649ed360eedf7f38576a034cb81a9f0d0d85b4e760a08a7af7c644b300130
|
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 sha256:0a84728d3e6388a2e313a0b930591e1caa03457e9373fa5a9018a74d4f76a4dd
|
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:e52e46a86dee0df6899d8616f9314a071547c40c5f77f9c7869ec679d05b2712
|
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 sha256:034fc0fef9516d254e4e7d37234cc827f307f60cceb9a55e70e7d8869181a03e
|
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,
|
@@ -910,14 +910,42 @@
|
|
910 |
"learning_rate": 1.998839744298062e-05,
|
911 |
"loss": 1.5509,
|
912 |
"step": 25800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
913 |
}
|
914 |
],
|
915 |
"logging_steps": 200,
|
916 |
-
"max_steps":
|
917 |
"num_input_tokens_seen": 0,
|
918 |
"num_train_epochs": 5,
|
919 |
"save_steps": 200,
|
920 |
-
"total_flos":
|
921 |
"train_batch_size": 1,
|
922 |
"trial_name": null,
|
923 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.31650299882129407,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 26600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
910 |
"learning_rate": 1.998839744298062e-05,
|
911 |
"loss": 1.5509,
|
912 |
"step": 25800
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.31,
|
916 |
+
"grad_norm": 0.8327608704566956,
|
917 |
+
"learning_rate": 1.9812018045085563e-05,
|
918 |
+
"loss": 1.5483,
|
919 |
+
"step": 26000
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.31,
|
923 |
+
"grad_norm": 0.7521975636482239,
|
924 |
+
"learning_rate": 1.980912147882786e-05,
|
925 |
+
"loss": 1.5296,
|
926 |
+
"step": 26200
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.31,
|
930 |
+
"grad_norm": 0.7781311869621277,
|
931 |
+
"learning_rate": 1.9806202981642514e-05,
|
932 |
+
"loss": 1.5346,
|
933 |
+
"step": 26400
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.32,
|
937 |
+
"grad_norm": 0.7848681211471558,
|
938 |
+
"learning_rate": 1.9803262560054603e-05,
|
939 |
+
"loss": 1.5271,
|
940 |
+
"step": 26600
|
941 |
}
|
942 |
],
|
943 |
"logging_steps": 200,
|
944 |
+
"max_steps": 420215,
|
945 |
"num_input_tokens_seen": 0,
|
946 |
"num_train_epochs": 5,
|
947 |
"save_steps": 200,
|
948 |
+
"total_flos": 7.664136678128517e+17,
|
949 |
"train_batch_size": 1,
|
950 |
"trial_name": null,
|
951 |
"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:c09e4d0caa94d3d4acabbf865ee69cc816a077a03533c04bf2c5e62bf08ec171
|
3 |
size 4920
|