Training in progress, epoch 4
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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a34be29a4e4f66902203293e32e1bb78196e6f915f3e2525b9c4cd0b0a9415f1
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95d61a351f34292d6a7c027c51957242f96b94671e954533fef673c516638539
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0878291c0cd48778cefcffd8633a7fef3d15ced9c19a7290aba9e5a2630c934
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2a05c3c588995c3f1001506d69c46628958682b428a4a1630b5be401fb2a15b
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -213,3 +213,67 @@
|
|
213 |
{"current_steps": 213, "total_steps": 315, "loss": 0.0645, "lr": 2.6068994669706184e-06, "epoch": 3.380952380952381, "percentage": 67.62, "elapsed_time": "0:19:58", "remaining_time": "0:09:33"}
|
214 |
{"current_steps": 214, "total_steps": 315, "loss": 0.0976, "lr": 2.560905524549364e-06, "epoch": 3.3968253968253967, "percentage": 67.94, "elapsed_time": "0:20:03", "remaining_time": "0:09:27"}
|
215 |
{"current_steps": 215, "total_steps": 315, "loss": 0.0732, "lr": 2.515180848423853e-06, "epoch": 3.4126984126984126, "percentage": 68.25, "elapsed_time": "0:20:08", "remaining_time": "0:09:22"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
213 |
{"current_steps": 213, "total_steps": 315, "loss": 0.0645, "lr": 2.6068994669706184e-06, "epoch": 3.380952380952381, "percentage": 67.62, "elapsed_time": "0:19:58", "remaining_time": "0:09:33"}
|
214 |
{"current_steps": 214, "total_steps": 315, "loss": 0.0976, "lr": 2.560905524549364e-06, "epoch": 3.3968253968253967, "percentage": 67.94, "elapsed_time": "0:20:03", "remaining_time": "0:09:27"}
|
215 |
{"current_steps": 215, "total_steps": 315, "loss": 0.0732, "lr": 2.515180848423853e-06, "epoch": 3.4126984126984126, "percentage": 68.25, "elapsed_time": "0:20:08", "remaining_time": "0:09:22"}
|
216 |
+
{"current_steps": 216, "total_steps": 315, "loss": 0.0651, "lr": 2.469730486415842e-06, "epoch": 3.4285714285714284, "percentage": 68.57, "elapsed_time": "0:20:13", "remaining_time": "0:09:16"}
|
217 |
+
{"current_steps": 217, "total_steps": 315, "loss": 0.0758, "lr": 2.4245594560639086e-06, "epoch": 3.4444444444444446, "percentage": 68.89, "elapsed_time": "0:20:19", "remaining_time": "0:09:10"}
|
218 |
+
{"current_steps": 218, "total_steps": 315, "loss": 0.0791, "lr": 2.379672744069527e-06, "epoch": 3.4603174603174605, "percentage": 69.21, "elapsed_time": "0:20:24", "remaining_time": "0:09:04"}
|
219 |
+
{"current_steps": 219, "total_steps": 315, "loss": 0.0766, "lr": 2.335075305746558e-06, "epoch": 3.4761904761904763, "percentage": 69.52, "elapsed_time": "0:20:29", "remaining_time": "0:08:59"}
|
220 |
+
{"current_steps": 220, "total_steps": 315, "loss": 0.0828, "lr": 2.2907720644742064e-06, "epoch": 3.492063492063492, "percentage": 69.84, "elapsed_time": "0:20:34", "remaining_time": "0:08:52"}
|
221 |
+
{"current_steps": 221, "total_steps": 315, "loss": 0.0738, "lr": 2.2467679111534963e-06, "epoch": 3.507936507936508, "percentage": 70.16, "elapsed_time": "0:20:38", "remaining_time": "0:08:46"}
|
222 |
+
{"current_steps": 222, "total_steps": 315, "loss": 0.0862, "lr": 2.2030677036673345e-06, "epoch": 3.5238095238095237, "percentage": 70.48, "elapsed_time": "0:20:43", "remaining_time": "0:08:40"}
|
223 |
+
{"current_steps": 223, "total_steps": 315, "loss": 0.0794, "lr": 2.159676266344222e-06, "epoch": 3.5396825396825395, "percentage": 70.79, "elapsed_time": "0:20:48", "remaining_time": "0:08:34"}
|
224 |
+
{"current_steps": 224, "total_steps": 315, "loss": 0.1081, "lr": 2.1165983894256647e-06, "epoch": 3.5555555555555554, "percentage": 71.11, "elapsed_time": "0:20:53", "remaining_time": "0:08:29"}
|
225 |
+
{"current_steps": 225, "total_steps": 315, "loss": 0.072, "lr": 2.0738388285373532e-06, "epoch": 3.571428571428571, "percentage": 71.43, "elapsed_time": "0:20:58", "remaining_time": "0:08:23"}
|
226 |
+
{"current_steps": 226, "total_steps": 315, "loss": 0.0848, "lr": 2.0314023041641567e-06, "epoch": 3.5873015873015874, "percentage": 71.75, "elapsed_time": "0:21:02", "remaining_time": "0:08:17"}
|
227 |
+
{"current_steps": 227, "total_steps": 315, "loss": 0.0827, "lr": 1.9892935011290037e-06, "epoch": 3.6031746031746033, "percentage": 72.06, "elapsed_time": "0:21:06", "remaining_time": "0:08:11"}
|
228 |
+
{"current_steps": 228, "total_steps": 315, "loss": 0.0544, "lr": 1.947517068075694e-06, "epoch": 3.619047619047619, "percentage": 72.38, "elapsed_time": "0:21:12", "remaining_time": "0:08:05"}
|
229 |
+
{"current_steps": 229, "total_steps": 315, "loss": 0.0954, "lr": 1.9060776169557083e-06, "epoch": 3.634920634920635, "percentage": 72.7, "elapsed_time": "0:21:16", "remaining_time": "0:07:59"}
|
230 |
+
{"current_steps": 230, "total_steps": 315, "loss": 0.0933, "lr": 1.864979722519068e-06, "epoch": 3.6507936507936507, "percentage": 73.02, "elapsed_time": "0:21:21", "remaining_time": "0:07:53"}
|
231 |
+
{"current_steps": 231, "total_steps": 315, "loss": 0.0759, "lr": 1.8242279218092968e-06, "epoch": 3.6666666666666665, "percentage": 73.33, "elapsed_time": "0:21:26", "remaining_time": "0:07:47"}
|
232 |
+
{"current_steps": 232, "total_steps": 315, "loss": 0.0821, "lr": 1.7838267136625536e-06, "epoch": 3.682539682539683, "percentage": 73.65, "elapsed_time": "0:21:31", "remaining_time": "0:07:41"}
|
233 |
+
{"current_steps": 233, "total_steps": 315, "loss": 0.0971, "lr": 1.743780558210979e-06, "epoch": 3.6984126984126986, "percentage": 73.97, "elapsed_time": "0:21:36", "remaining_time": "0:07:36"}
|
234 |
+
{"current_steps": 234, "total_steps": 315, "loss": 0.07, "lr": 1.704093876390312e-06, "epoch": 3.7142857142857144, "percentage": 74.29, "elapsed_time": "0:21:41", "remaining_time": "0:07:30"}
|
235 |
+
{"current_steps": 235, "total_steps": 315, "loss": 0.0811, "lr": 1.664771049451837e-06, "epoch": 3.7301587301587302, "percentage": 74.6, "elapsed_time": "0:21:47", "remaining_time": "0:07:24"}
|
236 |
+
{"current_steps": 236, "total_steps": 315, "loss": 0.0711, "lr": 1.6258164184787123e-06, "epoch": 3.746031746031746, "percentage": 74.92, "elapsed_time": "0:21:52", "remaining_time": "0:07:19"}
|
237 |
+
{"current_steps": 237, "total_steps": 315, "loss": 0.0671, "lr": 1.5872342839067305e-06, "epoch": 3.761904761904762, "percentage": 75.24, "elapsed_time": "0:21:57", "remaining_time": "0:07:13"}
|
238 |
+
{"current_steps": 238, "total_steps": 315, "loss": 0.0725, "lr": 1.5490289050495678e-06, "epoch": 3.7777777777777777, "percentage": 75.56, "elapsed_time": "0:22:02", "remaining_time": "0:07:07"}
|
239 |
+
{"current_steps": 239, "total_steps": 315, "loss": 0.0779, "lr": 1.511204499628574e-06, "epoch": 3.7936507936507935, "percentage": 75.87, "elapsed_time": "0:22:07", "remaining_time": "0:07:02"}
|
240 |
+
{"current_steps": 240, "total_steps": 315, "loss": 0.0591, "lr": 1.4737652433071515e-06, "epoch": 3.8095238095238093, "percentage": 76.19, "elapsed_time": "0:22:13", "remaining_time": "0:06:56"}
|
241 |
+
{"current_steps": 241, "total_steps": 315, "loss": 0.0861, "lr": 1.4367152692297799e-06, "epoch": 3.825396825396825, "percentage": 76.51, "elapsed_time": "0:22:18", "remaining_time": "0:06:50"}
|
242 |
+
{"current_steps": 242, "total_steps": 315, "loss": 0.0709, "lr": 1.4000586675657312e-06, "epoch": 3.8412698412698414, "percentage": 76.83, "elapsed_time": "0:22:23", "remaining_time": "0:06:45"}
|
243 |
+
{"current_steps": 243, "total_steps": 315, "loss": 0.0777, "lr": 1.3637994850575342e-06, "epoch": 3.857142857142857, "percentage": 77.14, "elapsed_time": "0:22:28", "remaining_time": "0:06:39"}
|
244 |
+
{"current_steps": 244, "total_steps": 315, "loss": 0.0708, "lr": 1.3279417245742288e-06, "epoch": 3.873015873015873, "percentage": 77.46, "elapsed_time": "0:22:33", "remaining_time": "0:06:33"}
|
245 |
+
{"current_steps": 245, "total_steps": 315, "loss": 0.0739, "lr": 1.2924893446694648e-06, "epoch": 3.888888888888889, "percentage": 77.78, "elapsed_time": "0:22:39", "remaining_time": "0:06:28"}
|
246 |
+
{"current_steps": 246, "total_steps": 315, "loss": 0.0818, "lr": 1.257446259144494e-06, "epoch": 3.9047619047619047, "percentage": 78.1, "elapsed_time": "0:22:44", "remaining_time": "0:06:22"}
|
247 |
+
{"current_steps": 247, "total_steps": 315, "loss": 0.0818, "lr": 1.222816336616104e-06, "epoch": 3.9206349206349205, "percentage": 78.41, "elapsed_time": "0:22:49", "remaining_time": "0:06:16"}
|
248 |
+
{"current_steps": 248, "total_steps": 315, "loss": 0.0786, "lr": 1.1886034000895341e-06, "epoch": 3.9365079365079367, "percentage": 78.73, "elapsed_time": "0:22:54", "remaining_time": "0:06:11"}
|
249 |
+
{"current_steps": 249, "total_steps": 315, "loss": 0.062, "lr": 1.1548112265364336e-06, "epoch": 3.9523809523809526, "percentage": 79.05, "elapsed_time": "0:22:59", "remaining_time": "0:06:05"}
|
250 |
+
{"current_steps": 250, "total_steps": 315, "loss": 0.0684, "lr": 1.1214435464779006e-06, "epoch": 3.9682539682539684, "percentage": 79.37, "elapsed_time": "0:23:04", "remaining_time": "0:05:59"}
|
251 |
+
{"current_steps": 251, "total_steps": 315, "loss": 0.074, "lr": 1.088504043572643e-06, "epoch": 3.984126984126984, "percentage": 79.68, "elapsed_time": "0:23:08", "remaining_time": "0:05:54"}
|
252 |
+
{"current_steps": 252, "total_steps": 315, "loss": 0.0591, "lr": 1.055996354210323e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:23:13", "remaining_time": "0:05:48"}
|
253 |
+
{"current_steps": 253, "total_steps": 315, "loss": 0.0465, "lr": 1.0239240671101065e-06, "epoch": 4.015873015873016, "percentage": 80.32, "elapsed_time": "0:24:18", "remaining_time": "0:05:57"}
|
254 |
+
{"current_steps": 254, "total_steps": 315, "loss": 0.0477, "lr": 9.922907229244905e-07, "epoch": 4.031746031746032, "percentage": 80.63, "elapsed_time": "0:24:23", "remaining_time": "0:05:51"}
|
255 |
+
{"current_steps": 255, "total_steps": 315, "loss": 0.042, "lr": 9.610998138484262e-07, "epoch": 4.0476190476190474, "percentage": 80.95, "elapsed_time": "0:24:28", "remaining_time": "0:05:45"}
|
256 |
+
{"current_steps": 256, "total_steps": 315, "loss": 0.0528, "lr": 9.303547832337934e-07, "epoch": 4.063492063492063, "percentage": 81.27, "elapsed_time": "0:24:33", "remaining_time": "0:05:39"}
|
257 |
+
{"current_steps": 257, "total_steps": 315, "loss": 0.0467, "lr": 9.000590252092701e-07, "epoch": 4.079365079365079, "percentage": 81.59, "elapsed_time": "0:24:38", "remaining_time": "0:05:33"}
|
258 |
+
{"current_steps": 258, "total_steps": 315, "loss": 0.0348, "lr": 8.702158843056319e-07, "epoch": 4.095238095238095, "percentage": 81.9, "elapsed_time": "0:24:43", "remaining_time": "0:05:27"}
|
259 |
+
{"current_steps": 259, "total_steps": 315, "loss": 0.0266, "lr": 8.408286550865319e-07, "epoch": 4.111111111111111, "percentage": 82.22, "elapsed_time": "0:24:47", "remaining_time": "0:05:21"}
|
260 |
+
{"current_steps": 260, "total_steps": 315, "loss": 0.0307, "lr": 8.119005817847924e-07, "epoch": 4.1269841269841265, "percentage": 82.54, "elapsed_time": "0:24:52", "remaining_time": "0:05:15"}
|
261 |
+
{"current_steps": 261, "total_steps": 315, "loss": 0.0361, "lr": 7.834348579442552e-07, "epoch": 4.142857142857143, "percentage": 82.86, "elapsed_time": "0:24:57", "remaining_time": "0:05:09"}
|
262 |
+
{"current_steps": 262, "total_steps": 315, "loss": 0.0403, "lr": 7.554346260672263e-07, "epoch": 4.158730158730159, "percentage": 83.17, "elapsed_time": "0:25:03", "remaining_time": "0:05:04"}
|
263 |
+
{"current_steps": 263, "total_steps": 315, "loss": 0.0485, "lr": 7.279029772675572e-07, "epoch": 4.174603174603175, "percentage": 83.49, "elapsed_time": "0:25:08", "remaining_time": "0:04:58"}
|
264 |
+
{"current_steps": 264, "total_steps": 315, "loss": 0.0241, "lr": 7.008429509293979e-07, "epoch": 4.190476190476191, "percentage": 83.81, "elapsed_time": "0:25:13", "remaining_time": "0:04:52"}
|
265 |
+
{"current_steps": 265, "total_steps": 315, "loss": 0.046, "lr": 6.742575343716584e-07, "epoch": 4.2063492063492065, "percentage": 84.13, "elapsed_time": "0:25:18", "remaining_time": "0:04:46"}
|
266 |
+
{"current_steps": 266, "total_steps": 315, "loss": 0.0458, "lr": 6.481496625182271e-07, "epoch": 4.222222222222222, "percentage": 84.44, "elapsed_time": "0:25:23", "remaining_time": "0:04:40"}
|
267 |
+
{"current_steps": 267, "total_steps": 315, "loss": 0.057, "lr": 6.225222175739598e-07, "epoch": 4.238095238095238, "percentage": 84.76, "elapsed_time": "0:25:28", "remaining_time": "0:04:34"}
|
268 |
+
{"current_steps": 268, "total_steps": 315, "loss": 0.0493, "lr": 5.973780287065007e-07, "epoch": 4.253968253968254, "percentage": 85.08, "elapsed_time": "0:25:33", "remaining_time": "0:04:28"}
|
269 |
+
{"current_steps": 269, "total_steps": 315, "loss": 0.0501, "lr": 5.727198717339511e-07, "epoch": 4.26984126984127, "percentage": 85.4, "elapsed_time": "0:25:38", "remaining_time": "0:04:23"}
|
270 |
+
{"current_steps": 270, "total_steps": 315, "loss": 0.0365, "lr": 5.485504688184307e-07, "epoch": 4.285714285714286, "percentage": 85.71, "elapsed_time": "0:25:43", "remaining_time": "0:04:17"}
|
271 |
+
{"current_steps": 271, "total_steps": 315, "loss": 0.0277, "lr": 5.24872488165562e-07, "epoch": 4.301587301587301, "percentage": 86.03, "elapsed_time": "0:25:49", "remaining_time": "0:04:11"}
|
272 |
+
{"current_steps": 272, "total_steps": 315, "loss": 0.0319, "lr": 5.016885437299113e-07, "epoch": 4.317460317460317, "percentage": 86.35, "elapsed_time": "0:25:54", "remaining_time": "0:04:05"}
|
273 |
+
{"current_steps": 273, "total_steps": 315, "loss": 0.0404, "lr": 4.790011949264173e-07, "epoch": 4.333333333333333, "percentage": 86.67, "elapsed_time": "0:25:59", "remaining_time": "0:03:59"}
|
274 |
+
{"current_steps": 274, "total_steps": 315, "loss": 0.0533, "lr": 4.5681294634784437e-07, "epoch": 4.349206349206349, "percentage": 86.98, "elapsed_time": "0:26:04", "remaining_time": "0:03:54"}
|
275 |
+
{"current_steps": 275, "total_steps": 315, "loss": 0.0395, "lr": 4.3512624748828225e-07, "epoch": 4.365079365079365, "percentage": 87.3, "elapsed_time": "0:26:09", "remaining_time": "0:03:48"}
|
276 |
+
{"current_steps": 276, "total_steps": 315, "loss": 0.0424, "lr": 4.139434924727359e-07, "epoch": 4.380952380952381, "percentage": 87.62, "elapsed_time": "0:26:14", "remaining_time": "0:03:42"}
|
277 |
+
{"current_steps": 277, "total_steps": 315, "loss": 0.0551, "lr": 3.9326701979281623e-07, "epoch": 4.396825396825397, "percentage": 87.94, "elapsed_time": "0:26:18", "remaining_time": "0:03:36"}
|
278 |
+
{"current_steps": 278, "total_steps": 315, "loss": 0.0281, "lr": 3.7309911204858997e-07, "epoch": 4.412698412698413, "percentage": 88.25, "elapsed_time": "0:26:22", "remaining_time": "0:03:30"}
|
279 |
+
{"current_steps": 279, "total_steps": 315, "loss": 0.0404, "lr": 3.534419956965823e-07, "epoch": 4.428571428571429, "percentage": 88.57, "elapsed_time": "0:26:27", "remaining_time": "0:03:24"}
|