ryanmarten commited on
Commit
1d8d543
·
verified ·
1 Parent(s): 5fe7890

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ad5b78aa99f0ab2541fb7c7343ce62045d3c32da3d56b66934cfa6432c09b82
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cfe20a3cd6075d13a0f0b4481e8b822a0e72037407f526125156879c738d3ae
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40d0c4debf39486bc453231de50f90a1584a8555e705c3386fe4612ae2f2b966
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae489119b6056159035f7d0329bacfb2a4c55ca4371680911d0c456663856004
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fb351c5e56dc22dc31c89e2e5297160c57cf709e09105e405626a6a203dd859
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f53b978211e30de6354ab737572f228526697c276944107cea4dfa6f133fe8
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:967e84a6a9c07b525614c0e0ffa83a31ef4cb47a2d38335fbd3c5651528e68d9
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eac4f640f6c90693ddf2585a6d779910f25b4f345980caa9640e493cb2262ef
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -239,3 +239,80 @@
239
  {"current_steps": 239, "total_steps": 380, "loss": 0.455, "lr": 2.9115861406186593e-05, "epoch": 3.1112916328188467, "percentage": 62.89, "elapsed_time": "6:52:14", "remaining_time": "4:03:12"}
240
  {"current_steps": 240, "total_steps": 380, "loss": 0.4548, "lr": 2.8762752009057232e-05, "epoch": 3.124289195775792, "percentage": 63.16, "elapsed_time": "6:53:54", "remaining_time": "4:01:26"}
241
  {"current_steps": 241, "total_steps": 380, "loss": 0.4518, "lr": 2.841059082173902e-05, "epoch": 3.1372867587327375, "percentage": 63.42, "elapsed_time": "6:55:38", "remaining_time": "3:59:43"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
239
  {"current_steps": 239, "total_steps": 380, "loss": 0.455, "lr": 2.9115861406186593e-05, "epoch": 3.1112916328188467, "percentage": 62.89, "elapsed_time": "6:52:14", "remaining_time": "4:03:12"}
240
  {"current_steps": 240, "total_steps": 380, "loss": 0.4548, "lr": 2.8762752009057232e-05, "epoch": 3.124289195775792, "percentage": 63.16, "elapsed_time": "6:53:54", "remaining_time": "4:01:26"}
241
  {"current_steps": 241, "total_steps": 380, "loss": 0.4518, "lr": 2.841059082173902e-05, "epoch": 3.1372867587327375, "percentage": 63.42, "elapsed_time": "6:55:38", "remaining_time": "3:59:43"}
242
+ {"current_steps": 242, "total_steps": 380, "loss": 0.4551, "lr": 2.805940755993223e-05, "epoch": 3.150284321689683, "percentage": 63.68, "elapsed_time": "6:57:19", "remaining_time": "3:57:58"}
243
+ {"current_steps": 243, "total_steps": 380, "loss": 0.4552, "lr": 2.770923185681878e-05, "epoch": 3.163281884646629, "percentage": 63.95, "elapsed_time": "6:58:59", "remaining_time": "3:56:13"}
244
+ {"current_steps": 244, "total_steps": 380, "loss": 0.4554, "lr": 2.7360093260561904e-05, "epoch": 3.1762794476035743, "percentage": 64.21, "elapsed_time": "7:00:40", "remaining_time": "3:54:28"}
245
+ {"current_steps": 245, "total_steps": 380, "loss": 0.4548, "lr": 2.7012021231812666e-05, "epoch": 3.1892770105605197, "percentage": 64.47, "elapsed_time": "7:02:20", "remaining_time": "3:52:43"}
246
+ {"current_steps": 246, "total_steps": 380, "loss": 0.4524, "lr": 2.6665045141224193e-05, "epoch": 3.2022745735174656, "percentage": 64.74, "elapsed_time": "7:04:01", "remaining_time": "3:50:58"}
247
+ {"current_steps": 247, "total_steps": 380, "loss": 0.4571, "lr": 2.6319194266973256e-05, "epoch": 3.215272136474411, "percentage": 65.0, "elapsed_time": "7:05:44", "remaining_time": "3:49:14"}
248
+ {"current_steps": 248, "total_steps": 380, "loss": 0.4486, "lr": 2.597449779228983e-05, "epoch": 3.2282696994313564, "percentage": 65.26, "elapsed_time": "7:07:28", "remaining_time": "3:47:31"}
249
+ {"current_steps": 249, "total_steps": 380, "loss": 0.4564, "lr": 2.563098480299451e-05, "epoch": 3.2412672623883023, "percentage": 65.53, "elapsed_time": "7:09:09", "remaining_time": "3:45:46"}
250
+ {"current_steps": 250, "total_steps": 380, "loss": 0.4564, "lr": 2.5288684285044283e-05, "epoch": 3.2542648253452477, "percentage": 65.79, "elapsed_time": "7:10:50", "remaining_time": "3:44:02"}
251
+ {"current_steps": 251, "total_steps": 380, "loss": 0.4558, "lr": 2.4947625122086585e-05, "epoch": 3.267262388302193, "percentage": 66.05, "elapsed_time": "7:12:31", "remaining_time": "3:42:17"}
252
+ {"current_steps": 252, "total_steps": 380, "loss": 0.4591, "lr": 2.460783609302218e-05, "epoch": 3.280259951259139, "percentage": 66.32, "elapsed_time": "7:14:11", "remaining_time": "3:40:32"}
253
+ {"current_steps": 253, "total_steps": 380, "loss": 0.4532, "lr": 2.4269345869576676e-05, "epoch": 3.2932575142160845, "percentage": 66.58, "elapsed_time": "7:15:54", "remaining_time": "3:38:48"}
254
+ {"current_steps": 254, "total_steps": 380, "loss": 0.4524, "lr": 2.393218301388123e-05, "epoch": 3.30625507717303, "percentage": 66.84, "elapsed_time": "7:17:35", "remaining_time": "3:37:04"}
255
+ {"current_steps": 255, "total_steps": 380, "loss": 0.4499, "lr": 2.35963759760624e-05, "epoch": 3.319252640129976, "percentage": 67.11, "elapsed_time": "7:19:19", "remaining_time": "3:35:21"}
256
+ {"current_steps": 256, "total_steps": 380, "loss": 0.4476, "lr": 2.3261953091841553e-05, "epoch": 3.332250203086921, "percentage": 67.37, "elapsed_time": "7:21:00", "remaining_time": "3:33:36"}
257
+ {"current_steps": 257, "total_steps": 380, "loss": 0.4586, "lr": 2.2928942580143855e-05, "epoch": 3.3452477660438666, "percentage": 67.63, "elapsed_time": "7:22:41", "remaining_time": "3:31:52"}
258
+ {"current_steps": 258, "total_steps": 380, "loss": 0.4506, "lr": 2.2597372540717083e-05, "epoch": 3.3582453290008125, "percentage": 67.89, "elapsed_time": "7:24:22", "remaining_time": "3:30:07"}
259
+ {"current_steps": 259, "total_steps": 380, "loss": 0.459, "lr": 2.226727095176057e-05, "epoch": 3.371242891957758, "percentage": 68.16, "elapsed_time": "7:26:03", "remaining_time": "3:28:23"}
260
+ {"current_steps": 260, "total_steps": 380, "loss": 0.4516, "lr": 2.1938665667564435e-05, "epoch": 3.3842404549147034, "percentage": 68.42, "elapsed_time": "7:27:44", "remaining_time": "3:26:38"}
261
+ {"current_steps": 261, "total_steps": 380, "loss": 0.4612, "lr": 2.1611584416159106e-05, "epoch": 3.3972380178716493, "percentage": 68.68, "elapsed_time": "7:29:25", "remaining_time": "3:24:54"}
262
+ {"current_steps": 262, "total_steps": 380, "loss": 0.4553, "lr": 2.1286054796975696e-05, "epoch": 3.4102355808285947, "percentage": 68.95, "elapsed_time": "7:31:05", "remaining_time": "3:23:10"}
263
+ {"current_steps": 263, "total_steps": 380, "loss": 0.4514, "lr": 2.096210427851706e-05, "epoch": 3.42323314378554, "percentage": 69.21, "elapsed_time": "7:32:46", "remaining_time": "3:21:25"}
264
+ {"current_steps": 264, "total_steps": 380, "loss": 0.4505, "lr": 2.063976019604006e-05, "epoch": 3.436230706742486, "percentage": 69.47, "elapsed_time": "7:34:26", "remaining_time": "3:19:40"}
265
+ {"current_steps": 265, "total_steps": 380, "loss": 0.4593, "lr": 2.0319049749248876e-05, "epoch": 3.4492282696994314, "percentage": 69.74, "elapsed_time": "7:36:09", "remaining_time": "3:17:57"}
266
+ {"current_steps": 266, "total_steps": 380, "loss": 0.4489, "lr": 2.0000000000000012e-05, "epoch": 3.462225832656377, "percentage": 70.0, "elapsed_time": "7:37:50", "remaining_time": "3:16:13"}
267
+ {"current_steps": 267, "total_steps": 380, "loss": 0.4521, "lr": 1.9682637870018638e-05, "epoch": 3.4752233956133223, "percentage": 70.26, "elapsed_time": "7:39:31", "remaining_time": "3:14:28"}
268
+ {"current_steps": 268, "total_steps": 380, "loss": 0.4518, "lr": 1.9366990138627054e-05, "epoch": 3.488220958570268, "percentage": 70.53, "elapsed_time": "7:41:13", "remaining_time": "3:12:45"}
269
+ {"current_steps": 269, "total_steps": 380, "loss": 0.4483, "lr": 1.9053083440484887e-05, "epoch": 3.5012185215272136, "percentage": 70.79, "elapsed_time": "7:42:55", "remaining_time": "3:11:01"}
270
+ {"current_steps": 270, "total_steps": 380, "loss": 0.455, "lr": 1.8740944263341773e-05, "epoch": 3.5142160844841595, "percentage": 71.05, "elapsed_time": "7:44:37", "remaining_time": "3:09:17"}
271
+ {"current_steps": 271, "total_steps": 380, "loss": 0.4592, "lr": 1.8430598945802156e-05, "epoch": 3.527213647441105, "percentage": 71.32, "elapsed_time": "7:46:19", "remaining_time": "3:07:33"}
272
+ {"current_steps": 272, "total_steps": 380, "loss": 0.4514, "lr": 1.8122073675102935e-05, "epoch": 3.5402112103980503, "percentage": 71.58, "elapsed_time": "7:48:00", "remaining_time": "3:05:49"}
273
+ {"current_steps": 273, "total_steps": 380, "loss": 0.4522, "lr": 1.781539448490365e-05, "epoch": 3.5532087733549957, "percentage": 71.84, "elapsed_time": "7:49:41", "remaining_time": "3:04:05"}
274
+ {"current_steps": 274, "total_steps": 380, "loss": 0.4576, "lr": 1.7510587253089842e-05, "epoch": 3.5662063363119416, "percentage": 72.11, "elapsed_time": "7:51:21", "remaining_time": "3:02:21"}
275
+ {"current_steps": 275, "total_steps": 380, "loss": 0.4575, "lr": 1.7207677699589355e-05, "epoch": 3.579203899268887, "percentage": 72.37, "elapsed_time": "7:53:01", "remaining_time": "3:00:36"}
276
+ {"current_steps": 276, "total_steps": 380, "loss": 0.4552, "lr": 1.690669138420215e-05, "epoch": 3.592201462225833, "percentage": 72.63, "elapsed_time": "7:54:42", "remaining_time": "2:58:52"}
277
+ {"current_steps": 277, "total_steps": 380, "loss": 0.4564, "lr": 1.6607653704443457e-05, "epoch": 3.6051990251827783, "percentage": 72.89, "elapsed_time": "7:56:24", "remaining_time": "2:57:08"}
278
+ {"current_steps": 278, "total_steps": 380, "loss": 0.4513, "lr": 1.6310589893400804e-05, "epoch": 3.618196588139724, "percentage": 73.16, "elapsed_time": "7:58:06", "remaining_time": "2:55:25"}
279
+ {"current_steps": 279, "total_steps": 380, "loss": 0.4628, "lr": 1.601552501760473e-05, "epoch": 3.631194151096669, "percentage": 73.42, "elapsed_time": "7:59:48", "remaining_time": "2:53:41"}
280
+ {"current_steps": 280, "total_steps": 380, "loss": 0.4535, "lr": 1.5722483974913737e-05, "epoch": 3.644191714053615, "percentage": 73.68, "elapsed_time": "8:01:30", "remaining_time": "2:51:57"}
281
+ {"current_steps": 281, "total_steps": 380, "loss": 0.4525, "lr": 1.5431491492413288e-05, "epoch": 3.6571892770105605, "percentage": 73.95, "elapsed_time": "8:03:12", "remaining_time": "2:50:14"}
282
+ {"current_steps": 282, "total_steps": 380, "loss": 0.4545, "lr": 1.5142572124329418e-05, "epoch": 3.670186839967506, "percentage": 74.21, "elapsed_time": "8:04:53", "remaining_time": "2:48:30"}
283
+ {"current_steps": 283, "total_steps": 380, "loss": 0.455, "lr": 1.4855750249956718e-05, "epoch": 3.683184402924452, "percentage": 74.47, "elapsed_time": "8:06:34", "remaining_time": "2:46:46"}
284
+ {"current_steps": 284, "total_steps": 380, "loss": 0.4603, "lr": 1.457105007160129e-05, "epoch": 3.6961819658813972, "percentage": 74.74, "elapsed_time": "8:08:17", "remaining_time": "2:45:03"}
285
+ {"current_steps": 285, "total_steps": 380, "loss": 0.4561, "lr": 1.4288495612538427e-05, "epoch": 3.7091795288383427, "percentage": 75.0, "elapsed_time": "8:09:58", "remaining_time": "2:43:19"}
286
+ {"current_steps": 286, "total_steps": 380, "loss": 0.458, "lr": 1.4008110714985623e-05, "epoch": 3.722177091795288, "percentage": 75.26, "elapsed_time": "8:11:38", "remaining_time": "2:41:35"}
287
+ {"current_steps": 287, "total_steps": 380, "loss": 0.4544, "lr": 1.3729919038090627e-05, "epoch": 3.735174654752234, "percentage": 75.53, "elapsed_time": "8:13:19", "remaining_time": "2:39:51"}
288
+ {"current_steps": 288, "total_steps": 380, "loss": 0.4567, "lr": 1.3453944055935151e-05, "epoch": 3.7481722177091794, "percentage": 75.79, "elapsed_time": "8:14:59", "remaining_time": "2:38:07"}
289
+ {"current_steps": 289, "total_steps": 380, "loss": 0.4575, "lr": 1.3180209055554043e-05, "epoch": 3.7611697806661253, "percentage": 76.05, "elapsed_time": "8:16:40", "remaining_time": "2:36:23"}
290
+ {"current_steps": 290, "total_steps": 380, "loss": 0.4582, "lr": 1.2908737134970367e-05, "epoch": 3.7741673436230707, "percentage": 76.32, "elapsed_time": "8:18:22", "remaining_time": "2:34:40"}
291
+ {"current_steps": 291, "total_steps": 380, "loss": 0.4532, "lr": 1.2639551201246278e-05, "epoch": 3.787164906580016, "percentage": 76.58, "elapsed_time": "8:20:03", "remaining_time": "2:32:56"}
292
+ {"current_steps": 292, "total_steps": 380, "loss": 0.4492, "lr": 1.2372673968550229e-05, "epoch": 3.8001624695369616, "percentage": 76.84, "elapsed_time": "8:21:44", "remaining_time": "2:31:12"}
293
+ {"current_steps": 293, "total_steps": 380, "loss": 0.4484, "lr": 1.2108127956240186e-05, "epoch": 3.8131600324939074, "percentage": 77.11, "elapsed_time": "8:23:26", "remaining_time": "2:29:29"}
294
+ {"current_steps": 294, "total_steps": 380, "loss": 0.4533, "lr": 1.1845935486963546e-05, "epoch": 3.826157595450853, "percentage": 77.37, "elapsed_time": "8:25:07", "remaining_time": "2:27:45"}
295
+ {"current_steps": 295, "total_steps": 380, "loss": 0.4499, "lr": 1.158611868477344e-05, "epoch": 3.8391551584077988, "percentage": 77.63, "elapsed_time": "8:26:47", "remaining_time": "2:26:01"}
296
+ {"current_steps": 296, "total_steps": 380, "loss": 0.4475, "lr": 1.1328699473261957e-05, "epoch": 3.852152721364744, "percentage": 77.89, "elapsed_time": "8:28:30", "remaining_time": "2:24:18"}
297
+ {"current_steps": 297, "total_steps": 380, "loss": 0.46, "lr": 1.107369957371013e-05, "epoch": 3.8651502843216896, "percentage": 78.16, "elapsed_time": "8:30:12", "remaining_time": "2:22:34"}
298
+ {"current_steps": 298, "total_steps": 380, "loss": 0.4493, "lr": 1.0821140503255174e-05, "epoch": 3.878147847278635, "percentage": 78.42, "elapsed_time": "8:31:52", "remaining_time": "2:20:51"}
299
+ {"current_steps": 299, "total_steps": 380, "loss": 0.4486, "lr": 1.0571043573074737e-05, "epoch": 3.891145410235581, "percentage": 78.68, "elapsed_time": "8:33:33", "remaining_time": "2:19:07"}
300
+ {"current_steps": 300, "total_steps": 380, "loss": 0.4571, "lr": 1.0323429886588743e-05, "epoch": 3.9041429731925263, "percentage": 78.95, "elapsed_time": "8:35:16", "remaining_time": "2:17:24"}
301
+ {"current_steps": 301, "total_steps": 380, "loss": 0.4487, "lr": 1.0078320337678584e-05, "epoch": 3.917140536149472, "percentage": 79.21, "elapsed_time": "8:36:58", "remaining_time": "2:15:41"}
302
+ {"current_steps": 302, "total_steps": 380, "loss": 0.4548, "lr": 9.835735608924155e-06, "epoch": 3.9301380991064176, "percentage": 79.47, "elapsed_time": "8:38:39", "remaining_time": "2:13:57"}
303
+ {"current_steps": 303, "total_steps": 380, "loss": 0.4535, "lr": 9.595696169858542e-06, "epoch": 3.943135662063363, "percentage": 79.74, "elapsed_time": "8:40:22", "remaining_time": "2:12:14"}
304
+ {"current_steps": 304, "total_steps": 380, "loss": 0.4556, "lr": 9.358222275240884e-06, "epoch": 3.9561332250203085, "percentage": 80.0, "elapsed_time": "8:42:04", "remaining_time": "2:10:31"}
305
+ {"current_steps": 305, "total_steps": 380, "loss": 0.4579, "lr": 9.123333963347166e-06, "epoch": 3.9691307879772544, "percentage": 80.26, "elapsed_time": "8:43:45", "remaining_time": "2:08:47"}
306
+ {"current_steps": 306, "total_steps": 380, "loss": 0.4516, "lr": 8.89105105427945e-06, "epoch": 3.9821283509342, "percentage": 80.53, "elapsed_time": "8:45:26", "remaining_time": "2:07:04"}
307
+ {"current_steps": 307, "total_steps": 380, "loss": 0.453, "lr": 8.661393148293355e-06, "epoch": 3.9951259138911457, "percentage": 80.79, "elapsed_time": "8:47:07", "remaining_time": "2:05:20"}
308
+ {"current_steps": 308, "total_steps": 380, "loss": 0.4399, "lr": 8.434379624144261e-06, "epoch": 4.0097481722177095, "percentage": 81.05, "elapsed_time": "8:50:33", "remaining_time": "2:04:01"}
309
+ {"current_steps": 309, "total_steps": 380, "loss": 0.4236, "lr": 8.210029637452016e-06, "epoch": 4.022745735174655, "percentage": 81.32, "elapsed_time": "8:52:14", "remaining_time": "2:02:17"}
310
+ {"current_steps": 310, "total_steps": 380, "loss": 0.4246, "lr": 7.988362119084642e-06, "epoch": 4.0357432981316, "percentage": 81.58, "elapsed_time": "8:53:54", "remaining_time": "2:00:33"}
311
+ {"current_steps": 311, "total_steps": 380, "loss": 0.4281, "lr": 7.769395773560874e-06, "epoch": 4.048740861088546, "percentage": 81.84, "elapsed_time": "8:55:34", "remaining_time": "1:58:49"}
312
+ {"current_steps": 312, "total_steps": 380, "loss": 0.4314, "lr": 7.553149077471915e-06, "epoch": 4.061738424045491, "percentage": 82.11, "elapsed_time": "8:57:15", "remaining_time": "1:57:05"}
313
+ {"current_steps": 313, "total_steps": 380, "loss": 0.4285, "lr": 7.3396402779222845e-06, "epoch": 4.074735987002437, "percentage": 82.37, "elapsed_time": "8:58:58", "remaining_time": "1:55:22"}
314
+ {"current_steps": 314, "total_steps": 380, "loss": 0.4218, "lr": 7.128887390990198e-06, "epoch": 4.087733549959383, "percentage": 82.63, "elapsed_time": "9:00:38", "remaining_time": "1:53:38"}
315
+ {"current_steps": 315, "total_steps": 380, "loss": 0.4251, "lr": 6.9209082002072725e-06, "epoch": 4.100731112916328, "percentage": 82.89, "elapsed_time": "9:02:20", "remaining_time": "1:51:54"}
316
+ {"current_steps": 316, "total_steps": 380, "loss": 0.434, "lr": 6.715720255058e-06, "epoch": 4.113728675873274, "percentage": 83.16, "elapsed_time": "9:04:00", "remaining_time": "1:50:10"}
317
+ {"current_steps": 317, "total_steps": 380, "loss": 0.4246, "lr": 6.513340869498859e-06, "epoch": 4.126726238830219, "percentage": 83.42, "elapsed_time": "9:05:40", "remaining_time": "1:48:26"}
318
+ {"current_steps": 318, "total_steps": 380, "loss": 0.4288, "lr": 6.313787120497376e-06, "epoch": 4.139723801787165, "percentage": 83.68, "elapsed_time": "9:07:23", "remaining_time": "1:46:43"}