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 sha256:7173625f358f7e271d8d1be9fb81d592804c76425421eeb1ef6c945650a15f07
|
| 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 sha256:88b5f16ec93bce795f88e37cc49c6872d49d8a1cb133825d016173c787dc6920
|
| 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 sha256:53cd526278ed1332f803b01933dfc0af30b1fc9439a0bf3ec4ea33c1b8d75ab2
|
| 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 sha256:6f0f41ff1945f814d96f4b3707cebe3fad102aceffcbaea4325b753621209efa
|
| 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 sha256:8e42f31f58048c0902be8eeaec44c45f777d560a64f789e1f1a930ca10ab191c
|
| 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:bf71c09db21dfc36731631041539a745c32155825c078eb72984f53f5b98201e
|
| 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:df6024328860a32d536031602342926b2fc8cdf04043494089b1415aaeac953b
|
| 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:df6ab5cbb97c21300b47843eeffea413bfd70b6f12d8c774936c69144f7991be
|
| 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 sha256:194d3aa572f9f43695a882de9824ed9b0bbac59ca2d3904e65eb73c0b7c3c687
|
| 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 sha256:55cd62445526ce888b5b0464a3cdead214c29c5dd6eb98cb66dd731c257d523a
|
| 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:c5bf60d49280fbb54dd5a05d1e78e33f7daf69953008fc12782e2adefb6070f2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 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": 305.116,
|
| 1090 |
"eval_steps_per_second": 9.538,
|
| 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": 0.21058495342731476,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.2583144979011947,
|
| 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": 305.116,
|
| 1090 |
"eval_steps_per_second": 9.538,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.195027445915402,
|
| 1095 |
+
"grad_norm": 0.2851709723472595,
|
| 1096 |
+
"learning_rate": 1.8017502271123185e-05,
|
| 1097 |
+
"loss": 0.2149,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.19631901840490798,
|
| 1102 |
+
"grad_norm": 0.3053763806819916,
|
| 1103 |
+
"learning_rate": 1.732826651219566e-05,
|
| 1104 |
+
"loss": 0.2083,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.19761059089441396,
|
| 1109 |
+
"grad_norm": 0.32732897996902466,
|
| 1110 |
+
"learning_rate": 1.6650149999098972e-05,
|
| 1111 |
+
"loss": 0.2356,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.19890216338391992,
|
| 1116 |
+
"grad_norm": 0.33027902245521545,
|
| 1117 |
+
"learning_rate": 1.598333812211684e-05,
|
| 1118 |
+
"loss": 0.1953,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.2001937358734259,
|
| 1123 |
+
"grad_norm": 0.3354640603065491,
|
| 1124 |
+
"learning_rate": 1.532801318095837e-05,
|
| 1125 |
+
"loss": 0.2195,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.20148530836293188,
|
| 1130 |
+
"grad_norm": 0.3625624179840088,
|
| 1131 |
+
"learning_rate": 1.4684354334919093e-05,
|
| 1132 |
+
"loss": 0.2151,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.20277688085243784,
|
| 1137 |
+
"grad_norm": 0.3043861389160156,
|
| 1138 |
+
"learning_rate": 1.4052537553900597e-05,
|
| 1139 |
+
"loss": 0.2245,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.20406845334194382,
|
| 1144 |
+
"grad_norm": 0.3239808678627014,
|
| 1145 |
+
"learning_rate": 1.343273557030219e-05,
|
| 1146 |
+
"loss": 0.2339,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.2053600258314498,
|
| 1151 |
+
"grad_norm": 0.3253532648086548,
|
| 1152 |
+
"learning_rate": 1.2825117831797486e-05,
|
| 1153 |
+
"loss": 0.2038,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.20665159832095575,
|
| 1158 |
+
"grad_norm": 0.37263450026512146,
|
| 1159 |
+
"learning_rate": 1.2229850455009178e-05,
|
| 1160 |
+
"loss": 0.2135,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.20794317081046174,
|
| 1165 |
+
"grad_norm": 0.359662801027298,
|
| 1166 |
+
"learning_rate": 1.1647096180094368e-05,
|
| 1167 |
+
"loss": 0.2256,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.20923474329996772,
|
| 1172 |
+
"grad_norm": 0.35589319467544556,
|
| 1173 |
+
"learning_rate": 1.1077014326253055e-05,
|
| 1174 |
+
"loss": 0.2155,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.21052631578947367,
|
| 1179 |
+
"grad_norm": 0.3147713541984558,
|
| 1180 |
+
"learning_rate": 1.0519760748171843e-05,
|
| 1181 |
+
"loss": 0.2231,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.21181788827897965,
|
| 1186 |
+
"grad_norm": 0.28186672925949097,
|
| 1187 |
+
"learning_rate": 9.975487793414837e-06,
|
| 1188 |
+
"loss": 0.2021,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.21310946076848564,
|
| 1193 |
+
"grad_norm": 0.3106829524040222,
|
| 1194 |
+
"learning_rate": 9.444344260773344e-06,
|
| 1195 |
+
"loss": 0.2179,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.2144010332579916,
|
| 1200 |
+
"grad_norm": 0.3491388261318207,
|
| 1201 |
+
"learning_rate": 8.926475359585739e-06,
|
| 1202 |
+
"loss": 0.2223,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.21569260574749757,
|
| 1207 |
+
"grad_norm": 0.3049313724040985,
|
| 1208 |
+
"learning_rate": 8.42202267003873e-06,
|
| 1209 |
+
"loss": 0.2179,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.21698417823700356,
|
| 1214 |
+
"grad_norm": 0.4379768371582031,
|
| 1215 |
+
"learning_rate": 7.931124104460714e-06,
|
| 1216 |
+
"loss": 0.2364,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.21827575072650954,
|
| 1221 |
+
"grad_norm": 0.3478700518608093,
|
| 1222 |
+
"learning_rate": 7.4539138696179115e-06,
|
| 1223 |
+
"loss": 0.2086,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.2195673232160155,
|
| 1228 |
+
"grad_norm": 0.2904229164123535,
|
| 1229 |
+
"learning_rate": 6.99052243002364e-06,
|
| 1230 |
+
"loss": 0.209,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.22085889570552147,
|
| 1235 |
+
"grad_norm": 0.2990818917751312,
|
| 1236 |
+
"learning_rate": 6.541076472270515e-06,
|
| 1237 |
+
"loss": 0.2056,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.22215046819502746,
|
| 1242 |
+
"grad_norm": 0.31892794370651245,
|
| 1243 |
+
"learning_rate": 6.105698870395719e-06,
|
| 1244 |
+
"loss": 0.2015,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.2234420406845334,
|
| 1249 |
+
"grad_norm": 0.34722334146499634,
|
| 1250 |
+
"learning_rate": 5.684508652288384e-06,
|
| 1251 |
+
"loss": 0.2015,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.2247336131740394,
|
| 1256 |
+
"grad_norm": 0.3504562973976135,
|
| 1257 |
+
"learning_rate": 5.277620967148574e-06,
|
| 1258 |
+
"loss": 0.2313,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.22602518566354537,
|
| 1263 |
+
"grad_norm": 0.44840207695961,
|
| 1264 |
+
"learning_rate": 4.885147054006664e-06,
|
| 1265 |
+
"loss": 0.2236,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.22731675815305133,
|
| 1270 |
+
"grad_norm": 0.2762066423892975,
|
| 1271 |
+
"learning_rate": 4.5071942113116845e-06,
|
| 1272 |
+
"loss": 0.2039,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.2286083306425573,
|
| 1277 |
+
"grad_norm": 0.26788678765296936,
|
| 1278 |
+
"learning_rate": 4.143865767596996e-06,
|
| 1279 |
+
"loss": 0.1892,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.2298999031320633,
|
| 1284 |
+
"grad_norm": 0.3198692500591278,
|
| 1285 |
+
"learning_rate": 3.795261053231277e-06,
|
| 1286 |
+
"loss": 0.2203,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.23119147562156925,
|
| 1291 |
+
"grad_norm": 0.31342411041259766,
|
| 1292 |
+
"learning_rate": 3.4614753732626524e-06,
|
| 1293 |
+
"loss": 0.2294,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.23248304811107523,
|
| 1298 |
+
"grad_norm": 0.35023924708366394,
|
| 1299 |
+
"learning_rate": 3.1425999813631912e-06,
|
| 1300 |
+
"loss": 0.2169,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.2337746206005812,
|
| 1305 |
+
"grad_norm": 0.33099067211151123,
|
| 1306 |
+
"learning_rate": 2.8387220548810953e-06,
|
| 1307 |
+
"loss": 0.2243,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.2350661930900872,
|
| 1312 |
+
"grad_norm": 0.3305521011352539,
|
| 1313 |
+
"learning_rate": 2.5499246710072567e-06,
|
| 1314 |
+
"loss": 0.2361,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.23635776557959315,
|
| 1319 |
+
"grad_norm": 0.30110248923301697,
|
| 1320 |
+
"learning_rate": 2.2762867840628075e-06,
|
| 1321 |
+
"loss": 0.2053,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.23764933806909913,
|
| 1326 |
+
"grad_norm": 0.2850276827812195,
|
| 1327 |
+
"learning_rate": 2.0178832039137833e-06,
|
| 1328 |
+
"loss": 0.2046,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.2389409105586051,
|
| 1333 |
+
"grad_norm": 0.3346441090106964,
|
| 1334 |
+
"learning_rate": 1.7747845755188384e-06,
|
| 1335 |
+
"loss": 0.2302,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.24023248304811107,
|
| 1340 |
+
"grad_norm": 0.35186243057250977,
|
| 1341 |
+
"learning_rate": 1.547057359615667e-06,
|
| 1342 |
+
"loss": 0.2172,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.24152405553761705,
|
| 1347 |
+
"grad_norm": 0.3660377860069275,
|
| 1348 |
+
"learning_rate": 1.3347638145512424e-06,
|
| 1349 |
+
"loss": 0.2346,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.24281562802712303,
|
| 1354 |
+
"grad_norm": 0.3175855278968811,
|
| 1355 |
+
"learning_rate": 1.1379619792610574e-06,
|
| 1356 |
+
"loss": 0.2261,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.24410720051662899,
|
| 1361 |
+
"grad_norm": 0.29722821712493896,
|
| 1362 |
+
"learning_rate": 9.567056574018227e-07,
|
| 1363 |
+
"loss": 0.1927,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.24539877300613497,
|
| 1368 |
+
"grad_norm": 0.3248823881149292,
|
| 1369 |
+
"learning_rate": 7.910444026421053e-07,
|
| 1370 |
+
"loss": 0.2337,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.24669034549564095,
|
| 1375 |
+
"grad_norm": 0.32746952772140503,
|
| 1376 |
+
"learning_rate": 6.410235051148274e-07,
|
| 1377 |
+
"loss": 0.2389,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.2479819179851469,
|
| 1382 |
+
"grad_norm": 0.31796029210090637,
|
| 1383 |
+
"learning_rate": 5.066839790354388e-07,
|
| 1384 |
+
"loss": 0.2002,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.2492734904746529,
|
| 1389 |
+
"grad_norm": 0.3934653103351593,
|
| 1390 |
+
"learning_rate": 3.880625514889877e-07,
|
| 1391 |
+
"loss": 0.2106,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.25056506296415887,
|
| 1396 |
+
"grad_norm": 0.38169851899147034,
|
| 1397 |
+
"learning_rate": 2.851916523893379e-07,
|
| 1398 |
+
"loss": 0.2489,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.2518566354536648,
|
| 1403 |
+
"grad_norm": 0.3027445077896118,
|
| 1404 |
+
"learning_rate": 1.9809940561314888e-07,
|
| 1405 |
+
"loss": 0.2018,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.25314820794317083,
|
| 1410 |
+
"grad_norm": 0.3391249179840088,
|
| 1411 |
+
"learning_rate": 1.26809621311077e-07,
|
| 1412 |
+
"loss": 0.2064,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.2544397804326768,
|
| 1417 |
+
"grad_norm": 0.32039472460746765,
|
| 1418 |
+
"learning_rate": 7.134178939832526e-08,
|
| 1419 |
+
"loss": 0.1981,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.25573135292218274,
|
| 1424 |
+
"grad_norm": 0.3003426492214203,
|
| 1425 |
+
"learning_rate": 3.171107422628916e-08,
|
| 1426 |
+
"loss": 0.2144,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.25702292541168875,
|
| 1431 |
+
"grad_norm": 0.3412923216819763,
|
| 1432 |
+
"learning_rate": 7.92831043679776e-09,
|
| 1433 |
+
"loss": 0.2148,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.2583144979011947,
|
| 1438 |
+
"grad_norm": 0.4516880214214325,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.2211,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.2583144979011947,
|
| 1445 |
+
"eval_loss": 0.21058495342731476,
|
| 1446 |
+
"eval_runtime": 34.7158,
|
| 1447 |
+
"eval_samples_per_second": 300.411,
|
| 1448 |
+
"eval_steps_per_second": 9.391,
|
| 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": 3.20308997259264e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|