Training in progress, step 200, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +364 -6
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 180385008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a453a16a4c117cff1b388e994b08e5489236446b8ccf435303e2332a51b29c9
|
| 3 |
size 180385008
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 91850362
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b1664526ab6181569600c2eb53c73bade3e656a15926b1644638881cf1a94e7
|
| 3 |
size 91850362
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6787ff0be37de3fe00e5d811b448a56f363a1038aba2964b56cfe7a0475559d4
|
| 3 |
size 15984
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27429cdddfa4255271447900523c947d30528626dae3d322d6a179286d342964
|
| 3 |
size 15984
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2b8f31fa5a5112f4642a4c5061d747e63182fd38fcf27dda6fc47015689d0ff
|
| 3 |
size 15984
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:954a26211011b6884d09cd959b24c533870e8642230c31e17939d89408afbde9
|
| 3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ac4ff248caf17aaa5b125d73d8af8b6f64d20eaf2135e3e19fc4e7a804ccf32
|
| 3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74963718ce3ad006b8bcd7a4b55f6447d803a9876b34339d2f4f6ccd2fcd8afb
|
| 3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41a422dfeaec88fb61711b468f73c7cff50d251ead26107a1dc87b4af999dd37
|
| 3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b4dbcebcad58992fe6187cd885a221e44df4678e3183d25f9e0cce00de43405
|
| 3 |
size 15984
|
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:ba4af3b1b4fa156d60adeec70df709d1741ac2f3147c676ab2805007313fc707
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 423.285,
|
| 1090 |
"eval_steps_per_second": 13.235,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0081819295883179,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.47058823529411764,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 423.285,
|
| 1090 |
"eval_steps_per_second": 13.235,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.3552941176470588,
|
| 1095 |
+
"grad_norm": 0.6219114661216736,
|
| 1096 |
+
"learning_rate": 2.6047368421052634e-05,
|
| 1097 |
+
"loss": 1.2679,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.35764705882352943,
|
| 1102 |
+
"grad_norm": 0.6947327852249146,
|
| 1103 |
+
"learning_rate": 2.5515789473684213e-05,
|
| 1104 |
+
"loss": 1.1812,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.36,
|
| 1109 |
+
"grad_norm": 0.6886230707168579,
|
| 1110 |
+
"learning_rate": 2.4984210526315788e-05,
|
| 1111 |
+
"loss": 1.0995,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.3623529411764706,
|
| 1116 |
+
"grad_norm": 0.7634572982788086,
|
| 1117 |
+
"learning_rate": 2.445263157894737e-05,
|
| 1118 |
+
"loss": 1.026,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.36470588235294116,
|
| 1123 |
+
"grad_norm": 0.7814245223999023,
|
| 1124 |
+
"learning_rate": 2.3921052631578946e-05,
|
| 1125 |
+
"loss": 0.9492,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.36705882352941177,
|
| 1130 |
+
"grad_norm": 0.8378550410270691,
|
| 1131 |
+
"learning_rate": 2.3389473684210528e-05,
|
| 1132 |
+
"loss": 0.7962,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.36941176470588233,
|
| 1137 |
+
"grad_norm": 0.7198935151100159,
|
| 1138 |
+
"learning_rate": 2.2857894736842106e-05,
|
| 1139 |
+
"loss": 1.2946,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.37176470588235294,
|
| 1144 |
+
"grad_norm": 0.6716011166572571,
|
| 1145 |
+
"learning_rate": 2.2326315789473685e-05,
|
| 1146 |
+
"loss": 1.2314,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.37411764705882355,
|
| 1151 |
+
"grad_norm": 0.7164915800094604,
|
| 1152 |
+
"learning_rate": 2.1794736842105264e-05,
|
| 1153 |
+
"loss": 1.0985,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.3764705882352941,
|
| 1158 |
+
"grad_norm": 0.7440788745880127,
|
| 1159 |
+
"learning_rate": 2.1263157894736842e-05,
|
| 1160 |
+
"loss": 1.0568,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.3788235294117647,
|
| 1165 |
+
"grad_norm": 0.7702521085739136,
|
| 1166 |
+
"learning_rate": 2.073157894736842e-05,
|
| 1167 |
+
"loss": 0.9384,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.3811764705882353,
|
| 1172 |
+
"grad_norm": 0.8371986746788025,
|
| 1173 |
+
"learning_rate": 2.0200000000000003e-05,
|
| 1174 |
+
"loss": 0.7604,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.3835294117647059,
|
| 1179 |
+
"grad_norm": 0.7777345776557922,
|
| 1180 |
+
"learning_rate": 1.966842105263158e-05,
|
| 1181 |
+
"loss": 1.202,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.38588235294117645,
|
| 1186 |
+
"grad_norm": 0.6666561365127563,
|
| 1187 |
+
"learning_rate": 1.913684210526316e-05,
|
| 1188 |
+
"loss": 1.2439,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.38823529411764707,
|
| 1193 |
+
"grad_norm": 0.6794990301132202,
|
| 1194 |
+
"learning_rate": 1.8605263157894736e-05,
|
| 1195 |
+
"loss": 1.1159,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.3905882352941176,
|
| 1200 |
+
"grad_norm": 0.7484257221221924,
|
| 1201 |
+
"learning_rate": 1.8073684210526318e-05,
|
| 1202 |
+
"loss": 1.0882,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.39294117647058824,
|
| 1207 |
+
"grad_norm": 0.7433997988700867,
|
| 1208 |
+
"learning_rate": 1.7542105263157897e-05,
|
| 1209 |
+
"loss": 0.9214,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.3952941176470588,
|
| 1214 |
+
"grad_norm": 0.8234543800354004,
|
| 1215 |
+
"learning_rate": 1.7010526315789475e-05,
|
| 1216 |
+
"loss": 0.8793,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.3976470588235294,
|
| 1221 |
+
"grad_norm": 0.8275732398033142,
|
| 1222 |
+
"learning_rate": 1.6478947368421054e-05,
|
| 1223 |
+
"loss": 1.0662,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.4,
|
| 1228 |
+
"grad_norm": 0.6753153800964355,
|
| 1229 |
+
"learning_rate": 1.5947368421052633e-05,
|
| 1230 |
+
"loss": 1.2686,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.4023529411764706,
|
| 1235 |
+
"grad_norm": 0.7300885319709778,
|
| 1236 |
+
"learning_rate": 1.541578947368421e-05,
|
| 1237 |
+
"loss": 1.1619,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.4047058823529412,
|
| 1242 |
+
"grad_norm": 0.720065176486969,
|
| 1243 |
+
"learning_rate": 1.4884210526315788e-05,
|
| 1244 |
+
"loss": 1.0637,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.40705882352941175,
|
| 1249 |
+
"grad_norm": 0.7786014080047607,
|
| 1250 |
+
"learning_rate": 1.4352631578947369e-05,
|
| 1251 |
+
"loss": 0.9741,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.40941176470588236,
|
| 1256 |
+
"grad_norm": 0.8148536086082458,
|
| 1257 |
+
"learning_rate": 1.3821052631578949e-05,
|
| 1258 |
+
"loss": 0.8535,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.4117647058823529,
|
| 1263 |
+
"grad_norm": 0.8557289242744446,
|
| 1264 |
+
"learning_rate": 1.3289473684210526e-05,
|
| 1265 |
+
"loss": 0.7194,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.41411764705882353,
|
| 1270 |
+
"grad_norm": 0.6708107590675354,
|
| 1271 |
+
"learning_rate": 1.2757894736842106e-05,
|
| 1272 |
+
"loss": 1.2988,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.4164705882352941,
|
| 1277 |
+
"grad_norm": 0.695059597492218,
|
| 1278 |
+
"learning_rate": 1.2226315789473685e-05,
|
| 1279 |
+
"loss": 1.1462,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.4188235294117647,
|
| 1284 |
+
"grad_norm": 0.7289761304855347,
|
| 1285 |
+
"learning_rate": 1.1694736842105264e-05,
|
| 1286 |
+
"loss": 1.0924,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.4211764705882353,
|
| 1291 |
+
"grad_norm": 0.7350468635559082,
|
| 1292 |
+
"learning_rate": 1.1163157894736842e-05,
|
| 1293 |
+
"loss": 0.9741,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.4235294117647059,
|
| 1298 |
+
"grad_norm": 0.7673172950744629,
|
| 1299 |
+
"learning_rate": 1.0631578947368421e-05,
|
| 1300 |
+
"loss": 0.8985,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.4258823529411765,
|
| 1305 |
+
"grad_norm": 0.907876193523407,
|
| 1306 |
+
"learning_rate": 1.0100000000000002e-05,
|
| 1307 |
+
"loss": 0.7691,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.42823529411764705,
|
| 1312 |
+
"grad_norm": 0.6842520236968994,
|
| 1313 |
+
"learning_rate": 9.56842105263158e-06,
|
| 1314 |
+
"loss": 1.2146,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.43058823529411766,
|
| 1319 |
+
"grad_norm": 0.6845569014549255,
|
| 1320 |
+
"learning_rate": 9.036842105263159e-06,
|
| 1321 |
+
"loss": 1.1655,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.4329411764705882,
|
| 1326 |
+
"grad_norm": 0.7404122352600098,
|
| 1327 |
+
"learning_rate": 8.505263157894738e-06,
|
| 1328 |
+
"loss": 1.1055,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.43529411764705883,
|
| 1333 |
+
"grad_norm": 0.7731722593307495,
|
| 1334 |
+
"learning_rate": 7.973684210526316e-06,
|
| 1335 |
+
"loss": 1.067,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.4376470588235294,
|
| 1340 |
+
"grad_norm": 0.8028244972229004,
|
| 1341 |
+
"learning_rate": 7.442105263157894e-06,
|
| 1342 |
+
"loss": 0.9007,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.44,
|
| 1347 |
+
"grad_norm": 0.9162750244140625,
|
| 1348 |
+
"learning_rate": 6.9105263157894745e-06,
|
| 1349 |
+
"loss": 0.8109,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.4423529411764706,
|
| 1354 |
+
"grad_norm": 0.729189932346344,
|
| 1355 |
+
"learning_rate": 6.378947368421053e-06,
|
| 1356 |
+
"loss": 1.1673,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.4447058823529412,
|
| 1361 |
+
"grad_norm": 0.691579282283783,
|
| 1362 |
+
"learning_rate": 5.847368421052632e-06,
|
| 1363 |
+
"loss": 1.2002,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.4470588235294118,
|
| 1368 |
+
"grad_norm": 0.6862315535545349,
|
| 1369 |
+
"learning_rate": 5.315789473684211e-06,
|
| 1370 |
+
"loss": 1.075,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.44941176470588234,
|
| 1375 |
+
"grad_norm": 0.795240044593811,
|
| 1376 |
+
"learning_rate": 4.78421052631579e-06,
|
| 1377 |
+
"loss": 1.0699,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.45176470588235296,
|
| 1382 |
+
"grad_norm": 0.7700913548469543,
|
| 1383 |
+
"learning_rate": 4.252631578947369e-06,
|
| 1384 |
+
"loss": 0.8609,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.4541176470588235,
|
| 1389 |
+
"grad_norm": 0.8226372003555298,
|
| 1390 |
+
"learning_rate": 3.721052631578947e-06,
|
| 1391 |
+
"loss": 0.8284,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.45647058823529413,
|
| 1396 |
+
"grad_norm": 0.7959129810333252,
|
| 1397 |
+
"learning_rate": 3.1894736842105266e-06,
|
| 1398 |
+
"loss": 0.9911,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.4588235294117647,
|
| 1403 |
+
"grad_norm": 0.6747735142707825,
|
| 1404 |
+
"learning_rate": 2.6578947368421053e-06,
|
| 1405 |
+
"loss": 1.2293,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.4611764705882353,
|
| 1410 |
+
"grad_norm": 0.729983925819397,
|
| 1411 |
+
"learning_rate": 2.1263157894736844e-06,
|
| 1412 |
+
"loss": 1.1679,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.46352941176470586,
|
| 1417 |
+
"grad_norm": 0.7446680665016174,
|
| 1418 |
+
"learning_rate": 1.5947368421052633e-06,
|
| 1419 |
+
"loss": 0.9839,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.46588235294117647,
|
| 1424 |
+
"grad_norm": 0.7689118385314941,
|
| 1425 |
+
"learning_rate": 1.0631578947368422e-06,
|
| 1426 |
+
"loss": 0.9591,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.4682352941176471,
|
| 1431 |
+
"grad_norm": 0.8310439586639404,
|
| 1432 |
+
"learning_rate": 5.315789473684211e-07,
|
| 1433 |
+
"loss": 0.8448,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.47058823529411764,
|
| 1438 |
+
"grad_norm": 0.9187881350517273,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.7259,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.47058823529411764,
|
| 1445 |
+
"eval_loss": 1.0081819295883179,
|
| 1446 |
+
"eval_runtime": 13.5434,
|
| 1447 |
+
"eval_samples_per_second": 422.714,
|
| 1448 |
+
"eval_steps_per_second": 13.217,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 3.205091905167688e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|