Training in progress, epoch 6
Browse files
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18ff8ffa2f5469cdf300e96d841480bee238d2cab412a17c21d2d19496a0065f
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc2430dab697377bcd6a7e3abb53148144cddea03a58700422a805d9ffafdffb
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5aa4872934f5dc719aa8f5eac1f82c0b2f785298efb2ade859990e7e61ca1cb
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be36aa77955b9a79322a4f73d1bf2e136303bf2630529fbf8b80bff9da74026a
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -171,3 +171,36 @@
|
|
171 |
{"current_steps": 171, "total_steps": 231, "loss": 0.1172, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:03:14", "remaining_time": "0:22:11"}
|
172 |
{"current_steps": 172, "total_steps": 231, "loss": 0.1003, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:03:29", "remaining_time": "0:21:46"}
|
173 |
{"current_steps": 173, "total_steps": 231, "loss": 0.0705, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:03:44", "remaining_time": "0:21:22"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
171 |
{"current_steps": 171, "total_steps": 231, "loss": 0.1172, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:03:14", "remaining_time": "0:22:11"}
|
172 |
{"current_steps": 172, "total_steps": 231, "loss": 0.1003, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:03:29", "remaining_time": "0:21:46"}
|
173 |
{"current_steps": 173, "total_steps": 231, "loss": 0.0705, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:03:44", "remaining_time": "0:21:22"}
|
174 |
+
{"current_steps": 174, "total_steps": 231, "loss": 0.0913, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:04:04", "remaining_time": "0:20:59"}
|
175 |
+
{"current_steps": 175, "total_steps": 231, "loss": 0.1206, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:04:22", "remaining_time": "0:20:35"}
|
176 |
+
{"current_steps": 176, "total_steps": 231, "loss": 0.0903, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:04:43", "remaining_time": "0:20:13"}
|
177 |
+
{"current_steps": 177, "total_steps": 231, "loss": 0.1286, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:05:02", "remaining_time": "0:19:50"}
|
178 |
+
{"current_steps": 178, "total_steps": 231, "loss": 0.1061, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:05:19", "remaining_time": "0:19:27"}
|
179 |
+
{"current_steps": 179, "total_steps": 231, "loss": 0.0877, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:05:37", "remaining_time": "0:19:03"}
|
180 |
+
{"current_steps": 180, "total_steps": 231, "loss": 0.0815, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:05:55", "remaining_time": "0:18:40"}
|
181 |
+
{"current_steps": 181, "total_steps": 231, "loss": 0.1071, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:06:16", "remaining_time": "0:18:18"}
|
182 |
+
{"current_steps": 182, "total_steps": 231, "loss": 0.1129, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:06:36", "remaining_time": "0:17:56"}
|
183 |
+
{"current_steps": 183, "total_steps": 231, "loss": 0.1145, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:06:57", "remaining_time": "0:17:33"}
|
184 |
+
{"current_steps": 184, "total_steps": 231, "loss": 0.1016, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:07:19", "remaining_time": "0:17:11"}
|
185 |
+
{"current_steps": 185, "total_steps": 231, "loss": 0.0848, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:07:34", "remaining_time": "0:16:48"}
|
186 |
+
{"current_steps": 186, "total_steps": 231, "loss": 0.0768, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:07:48", "remaining_time": "0:16:24"}
|
187 |
+
{"current_steps": 187, "total_steps": 231, "loss": 0.0985, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:08:05", "remaining_time": "0:16:01"}
|
188 |
+
{"current_steps": 188, "total_steps": 231, "loss": 0.0984, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:08:25", "remaining_time": "0:15:39"}
|
189 |
+
{"current_steps": 189, "total_steps": 231, "loss": 0.1196, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:08:49", "remaining_time": "0:15:17"}
|
190 |
+
{"current_steps": 190, "total_steps": 231, "loss": 0.1209, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:09:04", "remaining_time": "0:14:54"}
|
191 |
+
{"current_steps": 191, "total_steps": 231, "loss": 0.1126, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "1:09:24", "remaining_time": "0:14:32"}
|
192 |
+
{"current_steps": 192, "total_steps": 231, "loss": 0.0841, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "1:09:40", "remaining_time": "0:14:09"}
|
193 |
+
{"current_steps": 193, "total_steps": 231, "loss": 0.1037, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "1:10:00", "remaining_time": "0:13:47"}
|
194 |
+
{"current_steps": 194, "total_steps": 231, "loss": 0.0823, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "1:10:21", "remaining_time": "0:13:25"}
|
195 |
+
{"current_steps": 195, "total_steps": 231, "loss": 0.0963, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "1:10:34", "remaining_time": "0:13:01"}
|
196 |
+
{"current_steps": 196, "total_steps": 231, "loss": 0.0854, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "1:10:54", "remaining_time": "0:12:39"}
|
197 |
+
{"current_steps": 197, "total_steps": 231, "loss": 0.1002, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "1:11:15", "remaining_time": "0:12:17"}
|
198 |
+
{"current_steps": 198, "total_steps": 231, "loss": 0.1155, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "1:11:37", "remaining_time": "0:11:56"}
|
199 |
+
{"current_steps": 199, "total_steps": 231, "loss": 0.0922, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "1:13:52", "remaining_time": "0:11:52"}
|
200 |
+
{"current_steps": 200, "total_steps": 231, "loss": 0.1147, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "1:14:12", "remaining_time": "0:11:30"}
|
201 |
+
{"current_steps": 201, "total_steps": 231, "loss": 0.0955, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "1:14:32", "remaining_time": "0:11:07"}
|
202 |
+
{"current_steps": 202, "total_steps": 231, "loss": 0.0931, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "1:14:51", "remaining_time": "0:10:44"}
|
203 |
+
{"current_steps": 203, "total_steps": 231, "loss": 0.1104, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "1:15:15", "remaining_time": "0:10:22"}
|
204 |
+
{"current_steps": 204, "total_steps": 231, "loss": 0.1045, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "1:15:36", "remaining_time": "0:10:00"}
|
205 |
+
{"current_steps": 205, "total_steps": 231, "loss": 0.0925, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "1:15:54", "remaining_time": "0:09:37"}
|
206 |
+
{"current_steps": 206, "total_steps": 231, "loss": 0.074, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "1:16:12", "remaining_time": "0:09:14"}
|