Training in progress, step 120, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 90207248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7890d150186359623165f222ca4830c2a039fc03af0d56fe99e682d415fc31f6
|
3 |
size 90207248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46057082
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d30705974fe66df92448604887f4ff2019bdf74272d27933dc0a7e38b3354a13
|
3 |
size 46057082
|
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 sha256:98bbd4b4faf598bcf20005208e29928176693d773d6281a511c45efeae497be2
|
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 sha256:7e549a35cd7e532c378c88126565a201f68fd1d73868bbbba082980ce1de2c27
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.6011497974395752,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -873,6 +873,84 @@
|
|
873 |
"eval_samples_per_second": 5.581,
|
874 |
"eval_steps_per_second": 5.581,
|
875 |
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
876 |
}
|
877 |
],
|
878 |
"logging_steps": 1,
|
@@ -887,7 +965,7 @@
|
|
887 |
"early_stopping_threshold": 0.0
|
888 |
},
|
889 |
"attributes": {
|
890 |
-
"early_stopping_patience_counter":
|
891 |
}
|
892 |
},
|
893 |
"TrainerControl": {
|
@@ -901,7 +979,7 @@
|
|
901 |
"attributes": {}
|
902 |
}
|
903 |
},
|
904 |
-
"total_flos": 1.
|
905 |
"train_batch_size": 1,
|
906 |
"trial_name": null,
|
907 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.6011497974395752,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.0338863395693611,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 120,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
873 |
"eval_samples_per_second": 5.581,
|
874 |
"eval_steps_per_second": 5.581,
|
875 |
"step": 110
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 0.03134486410165902,
|
879 |
+
"grad_norm": 0.7646064758300781,
|
880 |
+
"learning_rate": 0.00017975624426754848,
|
881 |
+
"loss": 1.6671,
|
882 |
+
"step": 111
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 0.03162725026473703,
|
886 |
+
"grad_norm": 2.133544445037842,
|
887 |
+
"learning_rate": 0.00017936784788148328,
|
888 |
+
"loss": 1.5909,
|
889 |
+
"step": 112
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.03190963642781504,
|
893 |
+
"grad_norm": 2.059943199157715,
|
894 |
+
"learning_rate": 0.00017897618899405423,
|
895 |
+
"loss": 1.7489,
|
896 |
+
"step": 113
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.032192022590893044,
|
900 |
+
"grad_norm": 0.8779903650283813,
|
901 |
+
"learning_rate": 0.00017858128370482426,
|
902 |
+
"loss": 1.4871,
|
903 |
+
"step": 114
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.032474408753971055,
|
907 |
+
"grad_norm": 1.5168753862380981,
|
908 |
+
"learning_rate": 0.000178183148246803,
|
909 |
+
"loss": 1.8045,
|
910 |
+
"step": 115
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 0.03275679491704907,
|
914 |
+
"grad_norm": 1.1241475343704224,
|
915 |
+
"learning_rate": 0.00017778179898577973,
|
916 |
+
"loss": 1.64,
|
917 |
+
"step": 116
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 0.03303918108012707,
|
921 |
+
"grad_norm": 9.078608512878418,
|
922 |
+
"learning_rate": 0.00017737725241965069,
|
923 |
+
"loss": 2.7736,
|
924 |
+
"step": 117
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.033321567243205084,
|
928 |
+
"grad_norm": 3.2590787410736084,
|
929 |
+
"learning_rate": 0.00017696952517774062,
|
930 |
+
"loss": 2.5064,
|
931 |
+
"step": 118
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 0.03360395340628309,
|
935 |
+
"grad_norm": 2.293269395828247,
|
936 |
+
"learning_rate": 0.00017655863402011947,
|
937 |
+
"loss": 2.146,
|
938 |
+
"step": 119
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.0338863395693611,
|
942 |
+
"grad_norm": 1.5803933143615723,
|
943 |
+
"learning_rate": 0.00017614459583691346,
|
944 |
+
"loss": 1.4979,
|
945 |
+
"step": 120
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.0338863395693611,
|
949 |
+
"eval_loss": 1.603722095489502,
|
950 |
+
"eval_runtime": 133.2987,
|
951 |
+
"eval_samples_per_second": 5.596,
|
952 |
+
"eval_steps_per_second": 5.596,
|
953 |
+
"step": 120
|
954 |
}
|
955 |
],
|
956 |
"logging_steps": 1,
|
|
|
965 |
"early_stopping_threshold": 0.0
|
966 |
},
|
967 |
"attributes": {
|
968 |
+
"early_stopping_patience_counter": 2
|
969 |
}
|
970 |
},
|
971 |
"TrainerControl": {
|
|
|
979 |
"attributes": {}
|
980 |
}
|
981 |
},
|
982 |
+
"total_flos": 1.174564302225408e+16,
|
983 |
"train_batch_size": 1,
|
984 |
"trial_name": null,
|
985 |
"trial_params": null
|