mikhail-panzo
commited on
Commit
•
ad70d28
1
Parent(s):
231145c
Training in progress, step 7000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ffb8e39772cc3eedbcc25f5ce9b458d14a3f0a3a473dd8cff1f5898823ec1a8
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc6c03e31aa0f853402ce0829599343697da56c499480c398f89162a1e215b62
|
3 |
size 1155772233
|
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 sha256:2aea31e4a563fe214da83b26d48a3300cae390596cf180e66c6eb45c76a1d83f
|
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 sha256:99fe53e70f7d3663f3190692e038a033b96587726a76c7cd28c10e5edcb17fd7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.40983906388282776,
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-5500",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1021,6 +1021,84 @@
|
|
1021 |
"eval_samples_per_second": 24.136,
|
1022 |
"eval_steps_per_second": 3.036,
|
1023 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1024 |
}
|
1025 |
],
|
1026 |
"logging_steps": 50,
|
@@ -1040,7 +1118,7 @@
|
|
1040 |
"attributes": {}
|
1041 |
}
|
1042 |
},
|
1043 |
-
"total_flos":
|
1044 |
"train_batch_size": 64,
|
1045 |
"trial_name": null,
|
1046 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.40983906388282776,
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-5500",
|
4 |
+
"epoch": 304.3478260869565,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1021 |
"eval_samples_per_second": 24.136,
|
1022 |
"eval_steps_per_second": 3.036,
|
1023 |
"step": 6500
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 284.7826086956522,
|
1027 |
+
"grad_norm": 1.1955006122589111,
|
1028 |
+
"learning_rate": 2.421666666666667e-06,
|
1029 |
+
"loss": 0.4065,
|
1030 |
+
"step": 6550
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 286.95652173913044,
|
1034 |
+
"grad_norm": 1.8908520936965942,
|
1035 |
+
"learning_rate": 2.3383333333333335e-06,
|
1036 |
+
"loss": 0.4162,
|
1037 |
+
"step": 6600
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 289.1304347826087,
|
1041 |
+
"grad_norm": 1.1614066362380981,
|
1042 |
+
"learning_rate": 2.2550000000000004e-06,
|
1043 |
+
"loss": 0.4099,
|
1044 |
+
"step": 6650
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 291.30434782608694,
|
1048 |
+
"grad_norm": 0.8983772993087769,
|
1049 |
+
"learning_rate": 2.171666666666667e-06,
|
1050 |
+
"loss": 0.4121,
|
1051 |
+
"step": 6700
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 293.4782608695652,
|
1055 |
+
"grad_norm": 1.2100547552108765,
|
1056 |
+
"learning_rate": 2.088333333333334e-06,
|
1057 |
+
"loss": 0.4041,
|
1058 |
+
"step": 6750
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 295.6521739130435,
|
1062 |
+
"grad_norm": 1.1354186534881592,
|
1063 |
+
"learning_rate": 2.006666666666667e-06,
|
1064 |
+
"loss": 0.4127,
|
1065 |
+
"step": 6800
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 297.82608695652175,
|
1069 |
+
"grad_norm": 1.1679037809371948,
|
1070 |
+
"learning_rate": 1.9233333333333333e-06,
|
1071 |
+
"loss": 0.4068,
|
1072 |
+
"step": 6850
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 300.0,
|
1076 |
+
"grad_norm": 1.502341389656067,
|
1077 |
+
"learning_rate": 1.8400000000000002e-06,
|
1078 |
+
"loss": 0.4147,
|
1079 |
+
"step": 6900
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 302.17391304347825,
|
1083 |
+
"grad_norm": 0.9498834013938904,
|
1084 |
+
"learning_rate": 1.7566666666666669e-06,
|
1085 |
+
"loss": 0.4056,
|
1086 |
+
"step": 6950
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 304.3478260869565,
|
1090 |
+
"grad_norm": 0.8643518686294556,
|
1091 |
+
"learning_rate": 1.6733333333333335e-06,
|
1092 |
+
"loss": 0.4146,
|
1093 |
+
"step": 7000
|
1094 |
+
},
|
1095 |
+
{
|
1096 |
+
"epoch": 304.3478260869565,
|
1097 |
+
"eval_loss": 0.41151124238967896,
|
1098 |
+
"eval_runtime": 6.5375,
|
1099 |
+
"eval_samples_per_second": 24.321,
|
1100 |
+
"eval_steps_per_second": 3.059,
|
1101 |
+
"step": 7000
|
1102 |
}
|
1103 |
],
|
1104 |
"logging_steps": 50,
|
|
|
1118 |
"attributes": {}
|
1119 |
}
|
1120 |
},
|
1121 |
+
"total_flos": 1.039188053667456e+17,
|
1122 |
"train_batch_size": 64,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|