reinhardh commited on
Commit
4a9f196
·
verified ·
1 Parent(s): d3108fe

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7512dfef29be0a2935622e50d7ea4d2e1c85aa2566e386a9d6b8f45027fb27a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76c4c8759bd4cccf916c822e56947b3465676458f7abff5c29d68824de2c556
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bdabd3f7af059c0d8864124cf074062acb355d359aa80a5970bac5f532f6b4b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98ee46bbade61772b2fae9baf4be1d029a3e607fe3d17cd3ea439a8a828ea24
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:b96f8731798becce52650a7bbf47b9dfe3c4829957fa2fac25a5fdedd161c732
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1e3a272c5128d8b7cc3be310bd35e0c3adbbce72c93c45732b75312c8f8730
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71747b11da6d331a4d58aa731fd3752161fd7b3dd7768600278b552bf276bc92
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934ce1d50d9cc06492cf74f7e10c7072e645905401819481289221ee35e80c12
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -208,3 +208,85 @@
208
  {"current_steps": 162, "total_steps": 390, "loss": 0.299, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "1:44:11", "remaining_time": "2:26:38"}
209
  {"current_steps": 163, "total_steps": 390, "loss": 0.2867, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "1:44:54", "remaining_time": "2:26:05"}
210
  {"current_steps": 164, "total_steps": 390, "loss": 0.2884, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "1:45:34", "remaining_time": "2:25:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
208
  {"current_steps": 162, "total_steps": 390, "loss": 0.299, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "1:44:11", "remaining_time": "2:26:38"}
209
  {"current_steps": 163, "total_steps": 390, "loss": 0.2867, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "1:44:54", "remaining_time": "2:26:05"}
210
  {"current_steps": 164, "total_steps": 390, "loss": 0.2884, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "1:45:34", "remaining_time": "2:25:29"}
211
+ {"current_steps": 165, "total_steps": 390, "loss": 0.3118, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "1:46:16", "remaining_time": "2:24:55"}
212
+ {"current_steps": 166, "total_steps": 390, "loss": 0.2907, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "1:46:59", "remaining_time": "2:24:22"}
213
+ {"current_steps": 167, "total_steps": 390, "loss": 0.3138, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "1:47:37", "remaining_time": "2:23:42"}
214
+ {"current_steps": 168, "total_steps": 390, "loss": 0.3052, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "1:48:20", "remaining_time": "2:23:09"}
215
+ {"current_steps": 169, "total_steps": 390, "loss": 0.3047, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "1:49:03", "remaining_time": "2:22:36"}
216
+ {"current_steps": 170, "total_steps": 390, "loss": 0.2951, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "1:49:43", "remaining_time": "2:21:59"}
217
+ {"current_steps": 171, "total_steps": 390, "loss": 0.3039, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "1:50:18", "remaining_time": "2:21:15"}
218
+ {"current_steps": 172, "total_steps": 390, "loss": 0.2757, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "1:50:52", "remaining_time": "2:20:32"}
219
+ {"current_steps": 173, "total_steps": 390, "loss": 0.294, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "1:51:30", "remaining_time": "2:19:51"}
220
+ {"current_steps": 174, "total_steps": 390, "loss": 0.3041, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "1:52:03", "remaining_time": "2:19:06"}
221
+ {"current_steps": 175, "total_steps": 390, "loss": 0.2892, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "1:52:42", "remaining_time": "2:18:28"}
222
+ {"current_steps": 176, "total_steps": 390, "loss": 0.2947, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "1:53:20", "remaining_time": "2:17:49"}
223
+ {"current_steps": 177, "total_steps": 390, "loss": 0.3027, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "1:53:56", "remaining_time": "2:17:07"}
224
+ {"current_steps": 178, "total_steps": 390, "loss": 0.3098, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "1:54:32", "remaining_time": "2:16:25"}
225
+ {"current_steps": 179, "total_steps": 390, "loss": 0.2947, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "1:55:08", "remaining_time": "2:15:43"}
226
+ {"current_steps": 180, "total_steps": 390, "loss": 0.2771, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "1:55:46", "remaining_time": "2:15:03"}
227
+ {"current_steps": 181, "total_steps": 390, "loss": 0.2901, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "1:56:23", "remaining_time": "2:14:23"}
228
+ {"current_steps": 182, "total_steps": 390, "loss": 0.2788, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "1:56:57", "remaining_time": "2:13:39"}
229
+ {"current_steps": 183, "total_steps": 390, "loss": 0.3049, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "1:57:32", "remaining_time": "2:12:57"}
230
+ {"current_steps": 184, "total_steps": 390, "loss": 0.2899, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "1:58:11", "remaining_time": "2:12:19"}
231
+ {"current_steps": 185, "total_steps": 390, "loss": 0.2946, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "1:58:52", "remaining_time": "2:11:44"}
232
+ {"current_steps": 186, "total_steps": 390, "loss": 0.3145, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "1:59:28", "remaining_time": "2:11:02"}
233
+ {"current_steps": 187, "total_steps": 390, "loss": 0.3066, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "2:00:10", "remaining_time": "2:10:27"}
234
+ {"current_steps": 188, "total_steps": 390, "loss": 0.2786, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "2:00:40", "remaining_time": "2:09:39"}
235
+ {"current_steps": 189, "total_steps": 390, "loss": 0.3007, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "2:01:19", "remaining_time": "2:09:02"}
236
+ {"current_steps": 190, "total_steps": 390, "loss": 0.2856, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "2:01:57", "remaining_time": "2:08:22"}
237
+ {"current_steps": 191, "total_steps": 390, "loss": 0.2954, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "2:02:33", "remaining_time": "2:07:41"}
238
+ {"current_steps": 192, "total_steps": 390, "loss": 0.3081, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "2:03:09", "remaining_time": "2:07:00"}
239
+ {"current_steps": 193, "total_steps": 390, "loss": 0.3019, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "2:03:44", "remaining_time": "2:06:18"}
240
+ {"current_steps": 194, "total_steps": 390, "loss": 0.2836, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "2:04:20", "remaining_time": "2:05:37"}
241
+ {"current_steps": 195, "total_steps": 390, "loss": 0.2941, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "2:05:00", "remaining_time": "2:05:00"}
242
+ {"current_steps": 196, "total_steps": 390, "loss": 0.3131, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "2:05:39", "remaining_time": "2:04:22"}
243
+ {"current_steps": 197, "total_steps": 390, "loss": 0.3076, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "2:06:19", "remaining_time": "2:03:45"}
244
+ {"current_steps": 198, "total_steps": 390, "loss": 0.301, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "2:06:58", "remaining_time": "2:03:07"}
245
+ {"current_steps": 199, "total_steps": 390, "loss": 0.2936, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "2:07:35", "remaining_time": "2:02:27"}
246
+ {"current_steps": 200, "total_steps": 390, "loss": 0.2922, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "2:08:12", "remaining_time": "2:01:48"}
247
+ {"current_steps": 201, "total_steps": 390, "loss": 0.2871, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "2:08:52", "remaining_time": "2:01:10"}
248
+ {"current_steps": 202, "total_steps": 390, "loss": 0.3046, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "2:09:31", "remaining_time": "2:00:33"}
249
+ {"current_steps": 203, "total_steps": 390, "loss": 0.2865, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "2:10:06", "remaining_time": "1:59:51"}
250
+ {"current_steps": 204, "total_steps": 390, "loss": 0.2793, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "2:10:55", "remaining_time": "1:59:22"}
251
+ {"current_steps": 205, "total_steps": 390, "loss": 0.2944, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "2:11:26", "remaining_time": "1:58:36"}
252
+ {"current_steps": 206, "total_steps": 390, "loss": 0.3128, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "2:12:02", "remaining_time": "1:57:56"}
253
+ {"current_steps": 207, "total_steps": 390, "loss": 0.2741, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "2:12:35", "remaining_time": "1:57:13"}
254
+ {"current_steps": 208, "total_steps": 390, "loss": 0.3025, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "2:13:11", "remaining_time": "1:56:32"}
255
+ {"current_steps": 209, "total_steps": 390, "loss": 0.2857, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "2:13:47", "remaining_time": "1:55:52"}
256
+ {"current_steps": 210, "total_steps": 390, "loss": 0.3139, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "2:14:28", "remaining_time": "1:55:15"}
257
+ {"current_steps": 211, "total_steps": 390, "loss": 0.2833, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "2:15:08", "remaining_time": "1:54:38"}
258
+ {"current_steps": 212, "total_steps": 390, "loss": 0.2958, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "2:15:39", "remaining_time": "1:53:54"}
259
+ {"current_steps": 213, "total_steps": 390, "loss": 0.2982, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "2:16:20", "remaining_time": "1:53:17"}
260
+ {"current_steps": 214, "total_steps": 390, "loss": 0.3014, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "2:16:55", "remaining_time": "1:52:36"}
261
+ {"current_steps": 215, "total_steps": 390, "loss": 0.301, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "2:17:32", "remaining_time": "1:51:57"}
262
+ {"current_steps": 216, "total_steps": 390, "loss": 0.3098, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "2:18:14", "remaining_time": "1:51:21"}
263
+ {"current_steps": 217, "total_steps": 390, "loss": 0.2957, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "2:18:54", "remaining_time": "1:50:44"}
264
+ {"current_steps": 218, "total_steps": 390, "loss": 0.2964, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "2:19:31", "remaining_time": "1:50:05"}
265
+ {"current_steps": 219, "total_steps": 390, "loss": 0.3053, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "2:20:17", "remaining_time": "1:49:32"}
266
+ {"current_steps": 220, "total_steps": 390, "loss": 0.2961, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "2:20:54", "remaining_time": "1:48:53"}
267
+ {"current_steps": 221, "total_steps": 390, "loss": 0.3033, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "2:21:36", "remaining_time": "1:48:17"}
268
+ {"current_steps": 222, "total_steps": 390, "loss": 0.3154, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "2:22:18", "remaining_time": "1:47:41"}
269
+ {"current_steps": 223, "total_steps": 390, "loss": 0.3195, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "2:23:01", "remaining_time": "1:47:06"}
270
+ {"current_steps": 224, "total_steps": 390, "loss": 0.284, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "2:23:36", "remaining_time": "1:46:25"}
271
+ {"current_steps": 225, "total_steps": 390, "loss": 0.2765, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "2:24:13", "remaining_time": "1:45:45"}
272
+ {"current_steps": 226, "total_steps": 390, "loss": 0.3275, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "2:24:48", "remaining_time": "1:45:05"}
273
+ {"current_steps": 227, "total_steps": 390, "loss": 0.2743, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "2:25:26", "remaining_time": "1:44:26"}
274
+ {"current_steps": 228, "total_steps": 390, "loss": 0.3119, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "2:26:04", "remaining_time": "1:43:47"}
275
+ {"current_steps": 229, "total_steps": 390, "loss": 0.2873, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "2:26:39", "remaining_time": "1:43:06"}
276
+ {"current_steps": 230, "total_steps": 390, "loss": 0.2798, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "2:27:17", "remaining_time": "1:42:27"}
277
+ {"current_steps": 231, "total_steps": 390, "loss": 0.2785, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "2:27:50", "remaining_time": "1:41:45"}
278
+ {"current_steps": 232, "total_steps": 390, "loss": 0.3147, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "2:28:28", "remaining_time": "1:41:06"}
279
+ {"current_steps": 233, "total_steps": 390, "loss": 0.3061, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "2:29:02", "remaining_time": "1:40:25"}
280
+ {"current_steps": 234, "total_steps": 390, "loss": 0.3089, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "2:29:41", "remaining_time": "1:39:47"}
281
+ {"current_steps": 235, "total_steps": 390, "loss": 0.2583, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "2:31:13", "remaining_time": "1:39:44"}
282
+ {"current_steps": 236, "total_steps": 390, "loss": 0.2231, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "2:31:58", "remaining_time": "1:39:10"}
283
+ {"current_steps": 237, "total_steps": 390, "loss": 0.2268, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "2:32:37", "remaining_time": "1:38:31"}
284
+ {"current_steps": 238, "total_steps": 390, "loss": 0.2265, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "2:33:18", "remaining_time": "1:37:54"}
285
+ {"current_steps": 239, "total_steps": 390, "loss": 0.2275, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "2:34:03", "remaining_time": "1:37:19"}
286
+ {"current_steps": 240, "total_steps": 390, "loss": 0.2229, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "2:34:41", "remaining_time": "1:36:40"}
287
+ {"current_steps": 241, "total_steps": 390, "loss": 0.2141, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "2:35:19", "remaining_time": "1:36:02"}
288
+ {"current_steps": 242, "total_steps": 390, "loss": 0.2048, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "2:35:53", "remaining_time": "1:35:20"}
289
+ {"current_steps": 243, "total_steps": 390, "loss": 0.2191, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "2:36:36", "remaining_time": "1:34:44"}
290
+ {"current_steps": 244, "total_steps": 390, "loss": 0.2035, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "2:37:12", "remaining_time": "1:34:03"}
291
+ {"current_steps": 245, "total_steps": 390, "loss": 0.2217, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "2:37:55", "remaining_time": "1:33:27"}
292
+ {"current_steps": 246, "total_steps": 390, "loss": 0.2268, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "2:38:34", "remaining_time": "1:32:49"}