Commit
•
5fee177
1
Parent(s):
50a0243
Training in progress, step 7500, 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 sha256:92ef1101cc9fb02e54282334b0e6bd4e60d0595cb559d42d57d36013d19881dd
|
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 sha256:674c977647d24c2401ddc1a423df58aa831693103103edd9672feaafde0d28d5
|
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:e709aa0555fa5194531caefe8b2d088ae3dbd38583b58f3fca70a67516efdf96
|
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:c124d5873e6dde5040a6a31973ca68127e3dfe277695e3cb113af8a1a01ff662
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.40593138337135315,
|
3 |
"best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-7000",
|
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,
|
@@ -1099,6 +1099,84 @@
|
|
1099 |
"eval_samples_per_second": 12.175,
|
1100 |
"eval_steps_per_second": 1.588,
|
1101 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1102 |
}
|
1103 |
],
|
1104 |
"logging_steps": 50,
|
@@ -1118,7 +1196,7 @@
|
|
1118 |
"attributes": {}
|
1119 |
}
|
1120 |
},
|
1121 |
-
"total_flos":
|
1122 |
"train_batch_size": 32,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.40593138337135315,
|
3 |
"best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-7000",
|
4 |
+
"epoch": 326.0869565217391,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1099 |
"eval_samples_per_second": 12.175,
|
1100 |
"eval_steps_per_second": 1.588,
|
1101 |
"step": 7000
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 306.5217391304348,
|
1105 |
+
"grad_norm": 0.8590102791786194,
|
1106 |
+
"learning_rate": 1.5883333333333333e-06,
|
1107 |
+
"loss": 0.4127,
|
1108 |
+
"step": 7050
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 308.69565217391306,
|
1112 |
+
"grad_norm": 0.9405089616775513,
|
1113 |
+
"learning_rate": 1.505e-06,
|
1114 |
+
"loss": 0.413,
|
1115 |
+
"step": 7100
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 310.8695652173913,
|
1119 |
+
"grad_norm": 0.7493429780006409,
|
1120 |
+
"learning_rate": 1.4216666666666667e-06,
|
1121 |
+
"loss": 0.4137,
|
1122 |
+
"step": 7150
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 313.04347826086956,
|
1126 |
+
"grad_norm": 0.8461248278617859,
|
1127 |
+
"learning_rate": 1.3383333333333334e-06,
|
1128 |
+
"loss": 0.4104,
|
1129 |
+
"step": 7200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 315.2173913043478,
|
1133 |
+
"grad_norm": 0.6727828979492188,
|
1134 |
+
"learning_rate": 1.255e-06,
|
1135 |
+
"loss": 0.4071,
|
1136 |
+
"step": 7250
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 317.39130434782606,
|
1140 |
+
"grad_norm": 0.7143705487251282,
|
1141 |
+
"learning_rate": 1.1716666666666667e-06,
|
1142 |
+
"loss": 0.4086,
|
1143 |
+
"step": 7300
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 319.5652173913044,
|
1147 |
+
"grad_norm": 0.8034409284591675,
|
1148 |
+
"learning_rate": 1.0883333333333334e-06,
|
1149 |
+
"loss": 0.4051,
|
1150 |
+
"step": 7350
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 321.7391304347826,
|
1154 |
+
"grad_norm": 0.7853546738624573,
|
1155 |
+
"learning_rate": 1.0050000000000001e-06,
|
1156 |
+
"loss": 0.4067,
|
1157 |
+
"step": 7400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 323.9130434782609,
|
1161 |
+
"grad_norm": 0.8830783367156982,
|
1162 |
+
"learning_rate": 9.216666666666667e-07,
|
1163 |
+
"loss": 0.4089,
|
1164 |
+
"step": 7450
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 326.0869565217391,
|
1168 |
+
"grad_norm": 0.8115708231925964,
|
1169 |
+
"learning_rate": 8.383333333333334e-07,
|
1170 |
+
"loss": 0.4129,
|
1171 |
+
"step": 7500
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 326.0869565217391,
|
1175 |
+
"eval_loss": 0.4083060622215271,
|
1176 |
+
"eval_runtime": 12.9398,
|
1177 |
+
"eval_samples_per_second": 12.442,
|
1178 |
+
"eval_steps_per_second": 1.623,
|
1179 |
+
"step": 7500
|
1180 |
}
|
1181 |
],
|
1182 |
"logging_steps": 50,
|
|
|
1196 |
"attributes": {}
|
1197 |
}
|
1198 |
},
|
1199 |
+
"total_flos": 9.088988346445709e+16,
|
1200 |
"train_batch_size": 32,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|