Training in progress, step 3800
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +3 -102
- last-checkpoint/training_args.bin +1 -1
- model.safetensors +1 -1
- runs/Dec07_22-41-15_600fd1113bad/events.out.tfevents.1701988894.600fd1113bad.712.0 +2 -2
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c20757676a83e9b79b55197874149746ed730a010a68d7587e7a7a8797e4af1
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8502d4c8fda153d19bf8f43fc8963d5f83d32afabe6587e68b89400a1db97099
|
3 |
size 1925064044
|
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:e965350b0250570f0290355734c648f6a779f3eafb0bec172682cdf9092f567d
|
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 sha256:069be83226f429c691ea9e58c35ae52310d302cf0b73d3f098f087a042d5fe52
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1129,105 +1129,6 @@
|
|
1129 |
"eval_steps_per_second": 0.112,
|
1130 |
"eval_wer": 189.57986688851912,
|
1131 |
"step": 3400
|
1132 |
-
},
|
1133 |
-
{
|
1134 |
-
"epoch": 6.54,
|
1135 |
-
"learning_rate": 1.6600000000000002e-06,
|
1136 |
-
"loss": 0.006,
|
1137 |
-
"step": 3425
|
1138 |
-
},
|
1139 |
-
{
|
1140 |
-
"epoch": 6.58,
|
1141 |
-
"learning_rate": 1.5885714285714288e-06,
|
1142 |
-
"loss": 0.0069,
|
1143 |
-
"step": 3450
|
1144 |
-
},
|
1145 |
-
{
|
1146 |
-
"epoch": 6.63,
|
1147 |
-
"learning_rate": 1.5171428571428574e-06,
|
1148 |
-
"loss": 0.0049,
|
1149 |
-
"step": 3475
|
1150 |
-
},
|
1151 |
-
{
|
1152 |
-
"epoch": 6.68,
|
1153 |
-
"learning_rate": 1.4457142857142858e-06,
|
1154 |
-
"loss": 0.0051,
|
1155 |
-
"step": 3500
|
1156 |
-
},
|
1157 |
-
{
|
1158 |
-
"epoch": 6.68,
|
1159 |
-
"eval_loss": 0.45023292303085327,
|
1160 |
-
"eval_runtime": 1638.7418,
|
1161 |
-
"eval_samples_per_second": 0.915,
|
1162 |
-
"eval_steps_per_second": 0.115,
|
1163 |
-
"eval_wer": 194.2179700499168,
|
1164 |
-
"step": 3500
|
1165 |
-
},
|
1166 |
-
{
|
1167 |
-
"epoch": 6.73,
|
1168 |
-
"learning_rate": 1.3742857142857143e-06,
|
1169 |
-
"loss": 0.0059,
|
1170 |
-
"step": 3525
|
1171 |
-
},
|
1172 |
-
{
|
1173 |
-
"epoch": 6.77,
|
1174 |
-
"learning_rate": 1.302857142857143e-06,
|
1175 |
-
"loss": 0.0061,
|
1176 |
-
"step": 3550
|
1177 |
-
},
|
1178 |
-
{
|
1179 |
-
"epoch": 6.82,
|
1180 |
-
"learning_rate": 1.2314285714285715e-06,
|
1181 |
-
"loss": 0.0053,
|
1182 |
-
"step": 3575
|
1183 |
-
},
|
1184 |
-
{
|
1185 |
-
"epoch": 6.87,
|
1186 |
-
"learning_rate": 1.1600000000000001e-06,
|
1187 |
-
"loss": 0.0064,
|
1188 |
-
"step": 3600
|
1189 |
-
},
|
1190 |
-
{
|
1191 |
-
"epoch": 6.87,
|
1192 |
-
"eval_loss": 0.4511769413948059,
|
1193 |
-
"eval_runtime": 1630.1101,
|
1194 |
-
"eval_samples_per_second": 0.92,
|
1195 |
-
"eval_steps_per_second": 0.115,
|
1196 |
-
"eval_wer": 187.41680532445923,
|
1197 |
-
"step": 3600
|
1198 |
-
},
|
1199 |
-
{
|
1200 |
-
"epoch": 6.92,
|
1201 |
-
"learning_rate": 1.0885714285714287e-06,
|
1202 |
-
"loss": 0.0063,
|
1203 |
-
"step": 3625
|
1204 |
-
},
|
1205 |
-
{
|
1206 |
-
"epoch": 6.97,
|
1207 |
-
"learning_rate": 1.0171428571428573e-06,
|
1208 |
-
"loss": 0.0057,
|
1209 |
-
"step": 3650
|
1210 |
-
},
|
1211 |
-
{
|
1212 |
-
"epoch": 7.01,
|
1213 |
-
"learning_rate": 9.457142857142858e-07,
|
1214 |
-
"loss": 0.0045,
|
1215 |
-
"step": 3675
|
1216 |
-
},
|
1217 |
-
{
|
1218 |
-
"epoch": 7.06,
|
1219 |
-
"learning_rate": 8.742857142857144e-07,
|
1220 |
-
"loss": 0.0053,
|
1221 |
-
"step": 3700
|
1222 |
-
},
|
1223 |
-
{
|
1224 |
-
"epoch": 7.06,
|
1225 |
-
"eval_loss": 0.45203542709350586,
|
1226 |
-
"eval_runtime": 1642.6362,
|
1227 |
-
"eval_samples_per_second": 0.913,
|
1228 |
-
"eval_steps_per_second": 0.114,
|
1229 |
-
"eval_wer": 190.1968940654465,
|
1230 |
-
"step": 3700
|
1231 |
}
|
1232 |
],
|
1233 |
"logging_steps": 25,
|
@@ -1235,7 +1136,7 @@
|
|
1235 |
"num_input_tokens_seen": 0,
|
1236 |
"num_train_epochs": 8,
|
1237 |
"save_steps": 100,
|
1238 |
-
"total_flos": 3.
|
1239 |
"trial_name": null,
|
1240 |
"trial_params": null
|
1241 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 6.488549618320611,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1129 |
"eval_steps_per_second": 0.112,
|
1130 |
"eval_wer": 189.57986688851912,
|
1131 |
"step": 3400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1132 |
}
|
1133 |
],
|
1134 |
"logging_steps": 25,
|
|
|
1136 |
"num_input_tokens_seen": 0,
|
1137 |
"num_train_epochs": 8,
|
1138 |
"save_steps": 100,
|
1139 |
+
"total_flos": 3.138597096800256e+19,
|
1140 |
"trial_name": null,
|
1141 |
"trial_params": null
|
1142 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6dbc4dfe40c6e33f03f512f01526c1128aacac99b0beb33850a3ef004ff4c98
|
3 |
size 4856
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95d21fe86e17b73959794ce11ad74e73bd1518a97c41faa4f8be18d8b2bf9ffd
|
3 |
size 966995080
|
runs/Dec07_22-41-15_600fd1113bad/events.out.tfevents.1701988894.600fd1113bad.712.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dd23e81c5b7c364e45965e39a8ca7514685a727ec7ac96723d2f3c4d8cba1fe
|
3 |
+
size 8957
|