Commit
•
faf38e1
1
Parent(s):
6cd612b
Training in progress, step 25800, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
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 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"k_proj",
|
24 |
+
"down_proj",
|
25 |
"up_proj",
|
|
|
26 |
"q_proj",
|
27 |
"gate_proj",
|
28 |
+
"o_proj",
|
29 |
+
"v_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 sha256:09e7569231f9d48775234e444dc3002609a2aaf23f9fbb03afc31dd08b174acd
|
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 sha256:1795d0f5907365f50ee8bf592e588c51cf0c1336607a8958053b6df1866c85ef
|
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:e1e0be0fbdc67baa64bde42b3f62fb0cbfa6b616dea815616465446e745a61cd
|
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:afd4eb6473181bbf6da6b1613c063360450d1f8ec75384d51547bd12664e8b3a
|
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,
|
@@ -826,6 +826,90 @@
|
|
826 |
"learning_rate": 1.999045551990737e-05,
|
827 |
"loss": 1.536,
|
828 |
"step": 23400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
829 |
}
|
830 |
],
|
831 |
"logging_steps": 200,
|
@@ -833,7 +917,7 @@
|
|
833 |
"num_input_tokens_seen": 0,
|
834 |
"num_train_epochs": 5,
|
835 |
"save_steps": 200,
|
836 |
-
"total_flos":
|
837 |
"train_batch_size": 1,
|
838 |
"trial_name": null,
|
839 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07674602790967469,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 25800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
826 |
"learning_rate": 1.999045551990737e-05,
|
827 |
"loss": 1.536,
|
828 |
"step": 23400
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.07,
|
832 |
+
"grad_norm": 1.7328152656555176,
|
833 |
+
"learning_rate": 1.9990292364225084e-05,
|
834 |
+
"loss": 1.5166,
|
835 |
+
"step": 23600
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.07,
|
839 |
+
"grad_norm": 1.3295519351959229,
|
840 |
+
"learning_rate": 1.9990126996188935e-05,
|
841 |
+
"loss": 1.5488,
|
842 |
+
"step": 23800
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.07,
|
846 |
+
"grad_norm": 2.1913652420043945,
|
847 |
+
"learning_rate": 1.998996023220988e-05,
|
848 |
+
"loss": 1.5219,
|
849 |
+
"step": 24000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.07,
|
853 |
+
"grad_norm": 1.8065701723098755,
|
854 |
+
"learning_rate": 1.998979207231122e-05,
|
855 |
+
"loss": 1.5181,
|
856 |
+
"step": 24200
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.07,
|
860 |
+
"grad_norm": 1.8158023357391357,
|
861 |
+
"learning_rate": 1.998962336776768e-05,
|
862 |
+
"loss": 1.5176,
|
863 |
+
"step": 24400
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.07,
|
867 |
+
"grad_norm": 1.4990816116333008,
|
868 |
+
"learning_rate": 1.9989452423079802e-05,
|
869 |
+
"loss": 1.4998,
|
870 |
+
"step": 24600
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.07,
|
874 |
+
"grad_norm": 1.655572533607483,
|
875 |
+
"learning_rate": 1.9989280082543273e-05,
|
876 |
+
"loss": 1.5426,
|
877 |
+
"step": 24800
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.07,
|
881 |
+
"grad_norm": 1.9679639339447021,
|
882 |
+
"learning_rate": 1.9989106346182187e-05,
|
883 |
+
"loss": 1.5603,
|
884 |
+
"step": 25000
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.07,
|
888 |
+
"grad_norm": 1.2155619859695435,
|
889 |
+
"learning_rate": 1.9988931214020803e-05,
|
890 |
+
"loss": 1.5368,
|
891 |
+
"step": 25200
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.08,
|
895 |
+
"grad_norm": 1.3557419776916504,
|
896 |
+
"learning_rate": 1.9988754686083607e-05,
|
897 |
+
"loss": 1.531,
|
898 |
+
"step": 25400
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.08,
|
902 |
+
"grad_norm": 1.433875322341919,
|
903 |
+
"learning_rate": 1.998857676239526e-05,
|
904 |
+
"loss": 1.5502,
|
905 |
+
"step": 25600
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.08,
|
909 |
+
"grad_norm": 1.2107449769973755,
|
910 |
+
"learning_rate": 1.998839744298062e-05,
|
911 |
+
"loss": 1.5509,
|
912 |
+
"step": 25800
|
913 |
}
|
914 |
],
|
915 |
"logging_steps": 200,
|
|
|
917 |
"num_input_tokens_seen": 0,
|
918 |
"num_train_epochs": 5,
|
919 |
"save_steps": 200,
|
920 |
+
"total_flos": 5.996940170325443e+17,
|
921 |
"train_batch_size": 1,
|
922 |
"trial_name": null,
|
923 |
"trial_params": null
|