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 sha256:7b6b864b75dbb13213102e1615ceb4164e49fc42ce5fa1511e93d7a2f6187817
|
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 sha256:86edbf3ac0716264bce9acdb2644ec43742ec981a04907a3a980bbe238ed6374
|
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 sha256:224f749851b404a9dea0a46907e47cf4924f1737c89a22f05b04fab1df2ac97f
|
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 sha256:998e27076e96f4aeefa03d061addb9ac6e96ec724e91b072a6258f50faf049e8
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -170,3 +170,37 @@
|
|
170 |
{"current_steps": 170, "total_steps": 231, "loss": 0.2309, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:16:38", "remaining_time": "0:27:29"}
|
171 |
{"current_steps": 171, "total_steps": 231, "loss": 0.2142, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:17:01", "remaining_time": "0:27:01"}
|
172 |
{"current_steps": 172, "total_steps": 231, "loss": 0.1937, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:17:22", "remaining_time": "0:26:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
170 |
{"current_steps": 170, "total_steps": 231, "loss": 0.2309, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:16:38", "remaining_time": "0:27:29"}
|
171 |
{"current_steps": 171, "total_steps": 231, "loss": 0.2142, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:17:01", "remaining_time": "0:27:01"}
|
172 |
{"current_steps": 172, "total_steps": 231, "loss": 0.1937, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:17:22", "remaining_time": "0:26:32"}
|
173 |
+
{"current_steps": 173, "total_steps": 231, "loss": 0.2191, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:17:42", "remaining_time": "0:26:03"}
|
174 |
+
{"current_steps": 174, "total_steps": 231, "loss": 0.2168, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:18:10", "remaining_time": "0:25:36"}
|
175 |
+
{"current_steps": 175, "total_steps": 231, "loss": 0.2378, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:18:32", "remaining_time": "0:25:08"}
|
176 |
+
{"current_steps": 176, "total_steps": 231, "loss": 0.2183, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:18:53", "remaining_time": "0:24:39"}
|
177 |
+
{"current_steps": 177, "total_steps": 231, "loss": 0.249, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:19:19", "remaining_time": "0:24:11"}
|
178 |
+
{"current_steps": 178, "total_steps": 231, "loss": 0.2281, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:19:43", "remaining_time": "0:23:44"}
|
179 |
+
{"current_steps": 179, "total_steps": 231, "loss": 0.2075, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:20:01", "remaining_time": "0:23:14"}
|
180 |
+
{"current_steps": 180, "total_steps": 231, "loss": 0.2307, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:20:24", "remaining_time": "0:22:46"}
|
181 |
+
{"current_steps": 181, "total_steps": 231, "loss": 0.2338, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:20:50", "remaining_time": "0:22:19"}
|
182 |
+
{"current_steps": 182, "total_steps": 231, "loss": 0.205, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:21:09", "remaining_time": "0:21:50"}
|
183 |
+
{"current_steps": 183, "total_steps": 231, "loss": 0.2318, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:21:34", "remaining_time": "0:21:23"}
|
184 |
+
{"current_steps": 184, "total_steps": 231, "loss": 0.2008, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:21:58", "remaining_time": "0:20:56"}
|
185 |
+
{"current_steps": 185, "total_steps": 231, "loss": 0.2436, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:22:22", "remaining_time": "0:20:28"}
|
186 |
+
{"current_steps": 186, "total_steps": 231, "loss": 0.2644, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:22:47", "remaining_time": "0:20:01"}
|
187 |
+
{"current_steps": 187, "total_steps": 231, "loss": 0.2149, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:23:11", "remaining_time": "0:19:34"}
|
188 |
+
{"current_steps": 188, "total_steps": 231, "loss": 0.2137, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:23:36", "remaining_time": "0:19:07"}
|
189 |
+
{"current_steps": 189, "total_steps": 231, "loss": 0.1969, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:23:54", "remaining_time": "0:18:38"}
|
190 |
+
{"current_steps": 190, "total_steps": 231, "loss": 0.2273, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:24:22", "remaining_time": "0:18:12"}
|
191 |
+
{"current_steps": 191, "total_steps": 231, "loss": 0.2018, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "1:24:43", "remaining_time": "0:17:44"}
|
192 |
+
{"current_steps": 192, "total_steps": 231, "loss": 0.2428, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "1:25:09", "remaining_time": "0:17:17"}
|
193 |
+
{"current_steps": 193, "total_steps": 231, "loss": 0.2207, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "1:25:31", "remaining_time": "0:16:50"}
|
194 |
+
{"current_steps": 194, "total_steps": 231, "loss": 0.2033, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "1:25:53", "remaining_time": "0:16:22"}
|
195 |
+
{"current_steps": 195, "total_steps": 231, "loss": 0.2268, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "1:26:21", "remaining_time": "0:15:56"}
|
196 |
+
{"current_steps": 196, "total_steps": 231, "loss": 0.222, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "1:26:42", "remaining_time": "0:15:28"}
|
197 |
+
{"current_steps": 197, "total_steps": 231, "loss": 0.2645, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "1:27:06", "remaining_time": "0:15:02"}
|
198 |
+
{"current_steps": 198, "total_steps": 231, "loss": 0.2091, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "1:27:28", "remaining_time": "0:14:34"}
|
199 |
+
{"current_steps": 199, "total_steps": 231, "loss": 0.1993, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "1:29:48", "remaining_time": "0:14:26"}
|
200 |
+
{"current_steps": 200, "total_steps": 231, "loss": 0.2206, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "1:30:08", "remaining_time": "0:13:58"}
|
201 |
+
{"current_steps": 201, "total_steps": 231, "loss": 0.2131, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "1:30:34", "remaining_time": "0:13:31"}
|
202 |
+
{"current_steps": 202, "total_steps": 231, "loss": 0.1723, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "1:30:52", "remaining_time": "0:13:02"}
|
203 |
+
{"current_steps": 203, "total_steps": 231, "loss": 0.2044, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "1:31:16", "remaining_time": "0:12:35"}
|
204 |
+
{"current_steps": 204, "total_steps": 231, "loss": 0.1862, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "1:31:35", "remaining_time": "0:12:07"}
|
205 |
+
{"current_steps": 205, "total_steps": 231, "loss": 0.1575, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "1:31:50", "remaining_time": "0:11:38"}
|
206 |
+
{"current_steps": 206, "total_steps": 231, "loss": 0.2109, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "1:32:13", "remaining_time": "0:11:11"}
|