ryanmarten commited on
Commit
a142827
·
verified ·
1 Parent(s): 9cb37ee

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 sha256:353908f767f8bc376c556d9be3e0eb6f0bfed147d1aec7355d27030bf571d1e7
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c40a898fa67832c7881a628420f3ddec2feade22f1d6be16a275322d57863e
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:abaa66e0a6ecb6a69cffbd9efafd11b65298548c049ed5885375cf3f27b3b276
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e66edd28f35a628d95604eeb877e17fed2ef699a0111cff892ab2f95583dba7
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:647a9efba8e3d89687d9633185c6c37ae5ee1725f1073ca749e6a1bdc6d25c19
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582dadb21ca4452947df5297999170e8ab52214714b873bb9d3b24ed65b0e160
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e990bb35ef009dcf87cdef6d3970619de8aacb5b40c21b6819041cd0ab109f8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499774f847941a5fda2ff0d5189e6684e9cba29ce873ee50b8f05325ca18d2c8
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -229,3 +229,139 @@
229
  {"current_steps": 229, "total_steps": 380, "loss": 0.4954, "lr": 3.269251550189573e-05, "epoch": 2.9796913078797727, "percentage": 60.26, "elapsed_time": "6:33:45", "remaining_time": "4:19:38"}
230
  {"current_steps": 230, "total_steps": 380, "loss": 0.5042, "lr": 3.2331574723050474e-05, "epoch": 2.992688870836718, "percentage": 60.53, "elapsed_time": "6:35:25", "remaining_time": "4:17:53"}
231
  {"current_steps": 231, "total_steps": 380, "loss": 0.4791, "lr": 3.197128101331764e-05, "epoch": 3.007311129163282, "percentage": 60.79, "elapsed_time": "6:38:56", "remaining_time": "4:17:19"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
229
  {"current_steps": 229, "total_steps": 380, "loss": 0.4954, "lr": 3.269251550189573e-05, "epoch": 2.9796913078797727, "percentage": 60.26, "elapsed_time": "6:33:45", "remaining_time": "4:19:38"}
230
  {"current_steps": 230, "total_steps": 380, "loss": 0.5042, "lr": 3.2331574723050474e-05, "epoch": 2.992688870836718, "percentage": 60.53, "elapsed_time": "6:35:25", "remaining_time": "4:17:53"}
231
  {"current_steps": 231, "total_steps": 380, "loss": 0.4791, "lr": 3.197128101331764e-05, "epoch": 3.007311129163282, "percentage": 60.79, "elapsed_time": "6:38:56", "remaining_time": "4:17:19"}
232
+ {"current_steps": 232, "total_steps": 380, "loss": 0.4531, "lr": 3.161166477462759e-05, "epoch": 3.0203086921202273, "percentage": 61.05, "elapsed_time": "6:40:37", "remaining_time": "4:15:34"}
233
+ {"current_steps": 233, "total_steps": 380, "loss": 0.457, "lr": 3.125275635174497e-05, "epoch": 3.033306255077173, "percentage": 61.32, "elapsed_time": "6:42:17", "remaining_time": "4:13:48"}
234
+ {"current_steps": 234, "total_steps": 380, "loss": 0.4496, "lr": 3.089458602970828e-05, "epoch": 3.0463038180341186, "percentage": 61.58, "elapsed_time": "6:43:58", "remaining_time": "4:12:03"}
235
+ {"current_steps": 235, "total_steps": 380, "loss": 0.4526, "lr": 3.0537184031274306e-05, "epoch": 3.059301380991064, "percentage": 61.84, "elapsed_time": "6:45:40", "remaining_time": "4:10:18"}
236
+ {"current_steps": 236, "total_steps": 380, "loss": 0.4598, "lr": 3.0180580514368037e-05, "epoch": 3.07229894394801, "percentage": 62.11, "elapsed_time": "6:47:22", "remaining_time": "4:08:33"}
237
+ {"current_steps": 237, "total_steps": 380, "loss": 0.449, "lr": 2.9824805569537747e-05, "epoch": 3.0852965069049554, "percentage": 62.37, "elapsed_time": "6:49:02", "remaining_time": "4:06:48"}
238
+ {"current_steps": 238, "total_steps": 380, "loss": 0.4561, "lr": 2.9469889217416045e-05, "epoch": 3.098294069861901, "percentage": 62.63, "elapsed_time": "6:50:43", "remaining_time": "4:05:03"}
239
+ {"current_steps": 239, "total_steps": 380, "loss": 0.4538, "lr": 2.9115861406186593e-05, "epoch": 3.1112916328188467, "percentage": 62.89, "elapsed_time": "6:52:24", "remaining_time": "4:03:18"}
240
+ {"current_steps": 240, "total_steps": 380, "loss": 0.4539, "lr": 2.8762752009057232e-05, "epoch": 3.124289195775792, "percentage": 63.16, "elapsed_time": "6:54:07", "remaining_time": "4:01:34"}
241
+ {"current_steps": 241, "total_steps": 380, "loss": 0.4507, "lr": 2.841059082173902e-05, "epoch": 3.1372867587327375, "percentage": 63.42, "elapsed_time": "6:55:47", "remaining_time": "3:59:48"}
242
+ {"current_steps": 242, "total_steps": 380, "loss": 0.4541, "lr": 2.805940755993223e-05, "epoch": 3.150284321689683, "percentage": 63.68, "elapsed_time": "6:57:28", "remaining_time": "3:58:03"}
243
+ {"current_steps": 243, "total_steps": 380, "loss": 0.4537, "lr": 2.770923185681878e-05, "epoch": 3.163281884646629, "percentage": 63.95, "elapsed_time": "6:59:10", "remaining_time": "3:56:19"}
244
+ {"current_steps": 244, "total_steps": 380, "loss": 0.4541, "lr": 2.7360093260561904e-05, "epoch": 3.1762794476035743, "percentage": 64.21, "elapsed_time": "7:00:53", "remaining_time": "3:54:35"}
245
+ {"current_steps": 245, "total_steps": 380, "loss": 0.4537, "lr": 2.7012021231812666e-05, "epoch": 3.1892770105605197, "percentage": 64.47, "elapsed_time": "7:02:33", "remaining_time": "3:52:50"}
246
+ {"current_steps": 246, "total_steps": 380, "loss": 0.4514, "lr": 2.6665045141224193e-05, "epoch": 3.2022745735174656, "percentage": 64.74, "elapsed_time": "7:04:14", "remaining_time": "3:51:05"}
247
+ {"current_steps": 247, "total_steps": 380, "loss": 0.4562, "lr": 2.6319194266973256e-05, "epoch": 3.215272136474411, "percentage": 65.0, "elapsed_time": "7:05:56", "remaining_time": "3:49:21"}
248
+ {"current_steps": 248, "total_steps": 380, "loss": 0.4473, "lr": 2.597449779228983e-05, "epoch": 3.2282696994313564, "percentage": 65.26, "elapsed_time": "7:07:38", "remaining_time": "3:47:37"}
249
+ {"current_steps": 249, "total_steps": 380, "loss": 0.4559, "lr": 2.563098480299451e-05, "epoch": 3.2412672623883023, "percentage": 65.53, "elapsed_time": "7:09:19", "remaining_time": "3:45:52"}
250
+ {"current_steps": 250, "total_steps": 380, "loss": 0.4554, "lr": 2.5288684285044283e-05, "epoch": 3.2542648253452477, "percentage": 65.79, "elapsed_time": "7:11:00", "remaining_time": "3:44:07"}
251
+ {"current_steps": 251, "total_steps": 380, "loss": 0.4547, "lr": 2.4947625122086585e-05, "epoch": 3.267262388302193, "percentage": 66.05, "elapsed_time": "7:12:42", "remaining_time": "3:42:23"}
252
+ {"current_steps": 252, "total_steps": 380, "loss": 0.4581, "lr": 2.460783609302218e-05, "epoch": 3.280259951259139, "percentage": 66.32, "elapsed_time": "7:14:25", "remaining_time": "3:40:39"}
253
+ {"current_steps": 253, "total_steps": 380, "loss": 0.4523, "lr": 2.4269345869576676e-05, "epoch": 3.2932575142160845, "percentage": 66.58, "elapsed_time": "7:16:06", "remaining_time": "3:38:54"}
254
+ {"current_steps": 254, "total_steps": 380, "loss": 0.451, "lr": 2.393218301388123e-05, "epoch": 3.30625507717303, "percentage": 66.84, "elapsed_time": "7:17:46", "remaining_time": "3:37:09"}
255
+ {"current_steps": 255, "total_steps": 380, "loss": 0.4487, "lr": 2.35963759760624e-05, "epoch": 3.319252640129976, "percentage": 67.11, "elapsed_time": "7:19:29", "remaining_time": "3:35:26"}
256
+ {"current_steps": 256, "total_steps": 380, "loss": 0.447, "lr": 2.3261953091841553e-05, "epoch": 3.332250203086921, "percentage": 67.37, "elapsed_time": "7:21:13", "remaining_time": "3:33:43"}
257
+ {"current_steps": 257, "total_steps": 380, "loss": 0.4575, "lr": 2.2928942580143855e-05, "epoch": 3.3452477660438666, "percentage": 67.63, "elapsed_time": "7:22:55", "remaining_time": "3:31:59"}
258
+ {"current_steps": 258, "total_steps": 380, "loss": 0.4498, "lr": 2.2597372540717083e-05, "epoch": 3.3582453290008125, "percentage": 67.89, "elapsed_time": "7:24:36", "remaining_time": "3:30:14"}
259
+ {"current_steps": 259, "total_steps": 380, "loss": 0.4581, "lr": 2.226727095176057e-05, "epoch": 3.371242891957758, "percentage": 68.16, "elapsed_time": "7:26:20", "remaining_time": "3:28:31"}
260
+ {"current_steps": 260, "total_steps": 380, "loss": 0.4503, "lr": 2.1938665667564435e-05, "epoch": 3.3842404549147034, "percentage": 68.42, "elapsed_time": "7:28:06", "remaining_time": "3:26:49"}
261
+ {"current_steps": 261, "total_steps": 380, "loss": 0.4604, "lr": 2.1611584416159106e-05, "epoch": 3.3972380178716493, "percentage": 68.68, "elapsed_time": "7:29:50", "remaining_time": "3:25:05"}
262
+ {"current_steps": 262, "total_steps": 380, "loss": 0.4548, "lr": 2.1286054796975696e-05, "epoch": 3.4102355808285947, "percentage": 68.95, "elapsed_time": "7:31:32", "remaining_time": "3:23:21"}
263
+ {"current_steps": 263, "total_steps": 380, "loss": 0.4504, "lr": 2.096210427851706e-05, "epoch": 3.42323314378554, "percentage": 69.21, "elapsed_time": "7:33:16", "remaining_time": "3:21:38"}
264
+ {"current_steps": 264, "total_steps": 380, "loss": 0.4496, "lr": 2.063976019604006e-05, "epoch": 3.436230706742486, "percentage": 69.47, "elapsed_time": "7:35:01", "remaining_time": "3:19:56"}
265
+ {"current_steps": 265, "total_steps": 380, "loss": 0.4583, "lr": 2.0319049749248876e-05, "epoch": 3.4492282696994314, "percentage": 69.74, "elapsed_time": "7:36:46", "remaining_time": "3:18:13"}
266
+ {"current_steps": 266, "total_steps": 380, "loss": 0.4481, "lr": 2.0000000000000012e-05, "epoch": 3.462225832656377, "percentage": 70.0, "elapsed_time": "7:38:28", "remaining_time": "3:16:29"}
267
+ {"current_steps": 267, "total_steps": 380, "loss": 0.4506, "lr": 1.9682637870018638e-05, "epoch": 3.4752233956133223, "percentage": 70.26, "elapsed_time": "7:40:13", "remaining_time": "3:14:46"}
268
+ {"current_steps": 268, "total_steps": 380, "loss": 0.4512, "lr": 1.9366990138627054e-05, "epoch": 3.488220958570268, "percentage": 70.53, "elapsed_time": "7:41:57", "remaining_time": "3:13:03"}
269
+ {"current_steps": 269, "total_steps": 380, "loss": 0.4474, "lr": 1.9053083440484887e-05, "epoch": 3.5012185215272136, "percentage": 70.79, "elapsed_time": "7:43:41", "remaining_time": "3:11:20"}
270
+ {"current_steps": 270, "total_steps": 380, "loss": 0.4542, "lr": 1.8740944263341773e-05, "epoch": 3.5142160844841595, "percentage": 71.05, "elapsed_time": "7:45:22", "remaining_time": "3:09:35"}
271
+ {"current_steps": 271, "total_steps": 380, "loss": 0.4581, "lr": 1.8430598945802156e-05, "epoch": 3.527213647441105, "percentage": 71.32, "elapsed_time": "7:47:05", "remaining_time": "3:07:52"}
272
+ {"current_steps": 272, "total_steps": 380, "loss": 0.4507, "lr": 1.8122073675102935e-05, "epoch": 3.5402112103980503, "percentage": 71.58, "elapsed_time": "7:48:50", "remaining_time": "3:06:09"}
273
+ {"current_steps": 273, "total_steps": 380, "loss": 0.4511, "lr": 1.781539448490365e-05, "epoch": 3.5532087733549957, "percentage": 71.84, "elapsed_time": "7:50:34", "remaining_time": "3:04:26"}
274
+ {"current_steps": 274, "total_steps": 380, "loss": 0.4569, "lr": 1.7510587253089842e-05, "epoch": 3.5662063363119416, "percentage": 72.11, "elapsed_time": "7:52:16", "remaining_time": "3:02:42"}
275
+ {"current_steps": 275, "total_steps": 380, "loss": 0.4569, "lr": 1.7207677699589355e-05, "epoch": 3.579203899268887, "percentage": 72.37, "elapsed_time": "7:53:59", "remaining_time": "3:00:58"}
276
+ {"current_steps": 276, "total_steps": 380, "loss": 0.4545, "lr": 1.690669138420215e-05, "epoch": 3.592201462225833, "percentage": 72.63, "elapsed_time": "7:55:45", "remaining_time": "2:59:16"}
277
+ {"current_steps": 277, "total_steps": 380, "loss": 0.4553, "lr": 1.6607653704443457e-05, "epoch": 3.6051990251827783, "percentage": 72.89, "elapsed_time": "7:57:30", "remaining_time": "2:57:33"}
278
+ {"current_steps": 278, "total_steps": 380, "loss": 0.4501, "lr": 1.6310589893400804e-05, "epoch": 3.618196588139724, "percentage": 73.16, "elapsed_time": "7:59:12", "remaining_time": "2:55:49"}
279
+ {"current_steps": 279, "total_steps": 380, "loss": 0.4617, "lr": 1.601552501760473e-05, "epoch": 3.631194151096669, "percentage": 73.42, "elapsed_time": "8:00:55", "remaining_time": "2:54:05"}
280
+ {"current_steps": 280, "total_steps": 380, "loss": 0.4524, "lr": 1.5722483974913737e-05, "epoch": 3.644191714053615, "percentage": 73.68, "elapsed_time": "8:02:40", "remaining_time": "2:52:23"}
281
+ {"current_steps": 281, "total_steps": 380, "loss": 0.4515, "lr": 1.5431491492413288e-05, "epoch": 3.6571892770105605, "percentage": 73.95, "elapsed_time": "8:04:27", "remaining_time": "2:50:40"}
282
+ {"current_steps": 282, "total_steps": 380, "loss": 0.4538, "lr": 1.5142572124329418e-05, "epoch": 3.670186839967506, "percentage": 74.21, "elapsed_time": "8:06:09", "remaining_time": "2:48:56"}
283
+ {"current_steps": 283, "total_steps": 380, "loss": 0.4538, "lr": 1.4855750249956718e-05, "epoch": 3.683184402924452, "percentage": 74.47, "elapsed_time": "8:07:50", "remaining_time": "2:47:12"}
284
+ {"current_steps": 284, "total_steps": 380, "loss": 0.4591, "lr": 1.457105007160129e-05, "epoch": 3.6961819658813972, "percentage": 74.74, "elapsed_time": "8:09:32", "remaining_time": "2:45:28"}
285
+ {"current_steps": 285, "total_steps": 380, "loss": 0.455, "lr": 1.4288495612538427e-05, "epoch": 3.7091795288383427, "percentage": 75.0, "elapsed_time": "8:11:15", "remaining_time": "2:43:45"}
286
+ {"current_steps": 286, "total_steps": 380, "loss": 0.4567, "lr": 1.4008110714985623e-05, "epoch": 3.722177091795288, "percentage": 75.26, "elapsed_time": "8:12:56", "remaining_time": "2:42:00"}
287
+ {"current_steps": 287, "total_steps": 380, "loss": 0.4536, "lr": 1.3729919038090627e-05, "epoch": 3.735174654752234, "percentage": 75.53, "elapsed_time": "8:14:38", "remaining_time": "2:40:17"}
288
+ {"current_steps": 288, "total_steps": 380, "loss": 0.456, "lr": 1.3453944055935151e-05, "epoch": 3.7481722177091794, "percentage": 75.79, "elapsed_time": "8:16:20", "remaining_time": "2:38:33"}
289
+ {"current_steps": 289, "total_steps": 380, "loss": 0.4562, "lr": 1.3180209055554043e-05, "epoch": 3.7611697806661253, "percentage": 76.05, "elapsed_time": "8:18:05", "remaining_time": "2:36:50"}
290
+ {"current_steps": 290, "total_steps": 380, "loss": 0.4575, "lr": 1.2908737134970367e-05, "epoch": 3.7741673436230707, "percentage": 76.32, "elapsed_time": "8:19:45", "remaining_time": "2:35:05"}
291
+ {"current_steps": 291, "total_steps": 380, "loss": 0.4519, "lr": 1.2639551201246278e-05, "epoch": 3.787164906580016, "percentage": 76.58, "elapsed_time": "8:21:28", "remaining_time": "2:33:22"}
292
+ {"current_steps": 231, "total_steps": 380, "loss": 0.4549, "lr": 3.197128101331764e-05, "epoch": 3.0389926888708367, "percentage": 60.79, "elapsed_time": "0:01:56", "remaining_time": "0:01:14"}
293
+ {"current_steps": 232, "total_steps": 380, "loss": 0.4548, "lr": 3.161166477462759e-05, "epoch": 3.051990251827782, "percentage": 61.05, "elapsed_time": "0:03:40", "remaining_time": "0:02:20"}
294
+ {"current_steps": 233, "total_steps": 380, "loss": 0.4582, "lr": 3.125275635174497e-05, "epoch": 3.064987814784728, "percentage": 61.32, "elapsed_time": "0:05:25", "remaining_time": "0:03:25"}
295
+ {"current_steps": 234, "total_steps": 380, "loss": 0.453, "lr": 3.089458602970828e-05, "epoch": 3.0779853777416735, "percentage": 61.58, "elapsed_time": "0:07:10", "remaining_time": "0:04:28"}
296
+ {"current_steps": 235, "total_steps": 380, "loss": 0.4547, "lr": 3.0537184031274306e-05, "epoch": 3.090982940698619, "percentage": 61.84, "elapsed_time": "0:08:55", "remaining_time": "0:05:30"}
297
+ {"current_steps": 236, "total_steps": 380, "loss": 0.4586, "lr": 3.0180580514368037e-05, "epoch": 3.1039805036555648, "percentage": 62.11, "elapsed_time": "0:10:40", "remaining_time": "0:06:30"}
298
+ {"current_steps": 237, "total_steps": 380, "loss": 0.4551, "lr": 2.9824805569537747e-05, "epoch": 3.11697806661251, "percentage": 62.37, "elapsed_time": "0:12:25", "remaining_time": "0:07:29"}
299
+ {"current_steps": 238, "total_steps": 380, "loss": 0.4526, "lr": 2.9469889217416045e-05, "epoch": 3.1299756295694556, "percentage": 62.63, "elapsed_time": "0:14:11", "remaining_time": "0:08:28"}
300
+ {"current_steps": 239, "total_steps": 380, "loss": 0.4543, "lr": 2.9115861406186593e-05, "epoch": 3.1429731925264015, "percentage": 62.89, "elapsed_time": "0:15:58", "remaining_time": "0:09:25"}
301
+ {"current_steps": 240, "total_steps": 380, "loss": 0.4523, "lr": 2.8762752009057232e-05, "epoch": 3.155970755483347, "percentage": 63.16, "elapsed_time": "0:17:46", "remaining_time": "0:10:22"}
302
+ {"current_steps": 241, "total_steps": 380, "loss": 0.4551, "lr": 2.841059082173902e-05, "epoch": 3.1689683184402924, "percentage": 63.42, "elapsed_time": "0:19:30", "remaining_time": "0:11:15"}
303
+ {"current_steps": 242, "total_steps": 380, "loss": 0.4522, "lr": 2.805940755993223e-05, "epoch": 3.181965881397238, "percentage": 63.68, "elapsed_time": "0:21:15", "remaining_time": "0:12:07"}
304
+ {"current_steps": 243, "total_steps": 380, "loss": 0.4543, "lr": 2.770923185681878e-05, "epoch": 3.1949634443541837, "percentage": 63.95, "elapsed_time": "0:23:00", "remaining_time": "0:12:58"}
305
+ {"current_steps": 244, "total_steps": 380, "loss": 0.4547, "lr": 2.7360093260561904e-05, "epoch": 3.207961007311129, "percentage": 64.21, "elapsed_time": "0:24:45", "remaining_time": "0:13:48"}
306
+ {"current_steps": 245, "total_steps": 380, "loss": 0.4485, "lr": 2.7012021231812666e-05, "epoch": 3.2209585702680745, "percentage": 64.47, "elapsed_time": "0:26:30", "remaining_time": "0:14:36"}
307
+ {"current_steps": 246, "total_steps": 380, "loss": 0.4514, "lr": 2.6665045141224193e-05, "epoch": 3.2339561332250204, "percentage": 64.74, "elapsed_time": "0:28:15", "remaining_time": "0:15:23"}
308
+ {"current_steps": 247, "total_steps": 380, "loss": 0.4587, "lr": 2.6319194266973256e-05, "epoch": 3.246953696181966, "percentage": 65.0, "elapsed_time": "0:30:02", "remaining_time": "0:16:10"}
309
+ {"current_steps": 248, "total_steps": 380, "loss": 0.4534, "lr": 2.597449779228983e-05, "epoch": 3.2599512591389113, "percentage": 65.26, "elapsed_time": "0:31:51", "remaining_time": "0:16:57"}
310
+ {"current_steps": 249, "total_steps": 380, "loss": 0.457, "lr": 2.563098480299451e-05, "epoch": 3.272948822095857, "percentage": 65.53, "elapsed_time": "0:33:36", "remaining_time": "0:17:40"}
311
+ {"current_steps": 250, "total_steps": 380, "loss": 0.4549, "lr": 2.5288684285044283e-05, "epoch": 3.2859463850528026, "percentage": 65.79, "elapsed_time": "0:35:21", "remaining_time": "0:18:23"}
312
+ {"current_steps": 251, "total_steps": 380, "loss": 0.4548, "lr": 2.4947625122086585e-05, "epoch": 3.298943948009748, "percentage": 66.05, "elapsed_time": "0:37:05", "remaining_time": "0:19:03"}
313
+ {"current_steps": 252, "total_steps": 380, "loss": 0.4521, "lr": 2.460783609302218e-05, "epoch": 3.311941510966694, "percentage": 66.32, "elapsed_time": "0:38:51", "remaining_time": "0:19:44"}
314
+ {"current_steps": 253, "total_steps": 380, "loss": 0.4469, "lr": 2.4269345869576676e-05, "epoch": 3.3249390739236393, "percentage": 66.58, "elapsed_time": "0:40:35", "remaining_time": "0:20:22"}
315
+ {"current_steps": 254, "total_steps": 380, "loss": 0.4532, "lr": 2.393218301388123e-05, "epoch": 3.3379366368805847, "percentage": 66.84, "elapsed_time": "0:42:20", "remaining_time": "0:21:00"}
316
+ {"current_steps": 255, "total_steps": 380, "loss": 0.4524, "lr": 2.35963759760624e-05, "epoch": 3.3509341998375306, "percentage": 67.11, "elapsed_time": "0:44:04", "remaining_time": "0:21:36"}
317
+ {"current_steps": 256, "total_steps": 380, "loss": 0.4546, "lr": 2.3261953091841553e-05, "epoch": 3.363931762794476, "percentage": 67.37, "elapsed_time": "0:45:48", "remaining_time": "0:22:11"}
318
+ {"current_steps": 257, "total_steps": 380, "loss": 0.4526, "lr": 2.2928942580143855e-05, "epoch": 3.3769293257514215, "percentage": 67.63, "elapsed_time": "0:47:33", "remaining_time": "0:22:45"}
319
+ {"current_steps": 258, "total_steps": 380, "loss": 0.4568, "lr": 2.2597372540717083e-05, "epoch": 3.3899268887083673, "percentage": 67.89, "elapsed_time": "0:49:18", "remaining_time": "0:23:19"}
320
+ {"current_steps": 259, "total_steps": 380, "loss": 0.4588, "lr": 2.226727095176057e-05, "epoch": 3.4029244516653128, "percentage": 68.16, "elapsed_time": "0:51:03", "remaining_time": "0:23:51"}
321
+ {"current_steps": 260, "total_steps": 380, "loss": 0.4507, "lr": 2.1938665667564435e-05, "epoch": 3.415922014622258, "percentage": 68.42, "elapsed_time": "0:52:47", "remaining_time": "0:24:22"}
322
+ {"current_steps": 261, "total_steps": 380, "loss": 0.4496, "lr": 2.1611584416159106e-05, "epoch": 3.428919577579204, "percentage": 68.68, "elapsed_time": "0:54:33", "remaining_time": "0:24:52"}
323
+ {"current_steps": 262, "total_steps": 380, "loss": 0.4541, "lr": 2.1286054796975696e-05, "epoch": 3.4419171405361495, "percentage": 68.95, "elapsed_time": "0:56:17", "remaining_time": "0:25:21"}
324
+ {"current_steps": 263, "total_steps": 380, "loss": 0.4544, "lr": 2.096210427851706e-05, "epoch": 3.454914703493095, "percentage": 69.21, "elapsed_time": "0:58:02", "remaining_time": "0:25:49"}
325
+ {"current_steps": 264, "total_steps": 380, "loss": 0.451, "lr": 2.063976019604006e-05, "epoch": 3.467912266450041, "percentage": 69.47, "elapsed_time": "0:59:46", "remaining_time": "0:26:16"}
326
+ {"current_steps": 265, "total_steps": 380, "loss": 0.4487, "lr": 2.0319049749248876e-05, "epoch": 3.4809098294069862, "percentage": 69.74, "elapsed_time": "1:01:31", "remaining_time": "0:26:41"}
327
+ {"current_steps": 266, "total_steps": 380, "loss": 0.4522, "lr": 2.0000000000000012e-05, "epoch": 3.4939073923639317, "percentage": 70.0, "elapsed_time": "1:03:15", "remaining_time": "0:27:06"}
328
+ {"current_steps": 267, "total_steps": 380, "loss": 0.4486, "lr": 1.9682637870018638e-05, "epoch": 3.506904955320877, "percentage": 70.26, "elapsed_time": "1:05:02", "remaining_time": "0:27:31"}
329
+ {"current_steps": 268, "total_steps": 380, "loss": 0.4556, "lr": 1.9366990138627054e-05, "epoch": 3.519902518277823, "percentage": 70.53, "elapsed_time": "1:06:50", "remaining_time": "0:27:55"}
330
+ {"current_steps": 269, "total_steps": 380, "loss": 0.4573, "lr": 1.9053083440484887e-05, "epoch": 3.5329000812347684, "percentage": 70.79, "elapsed_time": "1:08:37", "remaining_time": "0:28:19"}
331
+ {"current_steps": 270, "total_steps": 380, "loss": 0.4496, "lr": 1.8740944263341773e-05, "epoch": 3.5458976441917143, "percentage": 71.05, "elapsed_time": "1:10:25", "remaining_time": "0:28:41"}
332
+ {"current_steps": 271, "total_steps": 380, "loss": 0.4529, "lr": 1.8430598945802156e-05, "epoch": 3.5588952071486597, "percentage": 71.32, "elapsed_time": "1:12:10", "remaining_time": "0:29:01"}
333
+ {"current_steps": 272, "total_steps": 380, "loss": 0.4606, "lr": 1.8122073675102935e-05, "epoch": 3.571892770105605, "percentage": 71.58, "elapsed_time": "1:13:55", "remaining_time": "0:29:21"}
334
+ {"current_steps": 273, "total_steps": 380, "loss": 0.4559, "lr": 1.781539448490365e-05, "epoch": 3.5848903330625506, "percentage": 71.84, "elapsed_time": "1:15:39", "remaining_time": "0:29:39"}
335
+ {"current_steps": 274, "total_steps": 380, "loss": 0.4525, "lr": 1.7510587253089842e-05, "epoch": 3.5978878960194964, "percentage": 72.11, "elapsed_time": "1:17:24", "remaining_time": "0:29:56"}
336
+ {"current_steps": 275, "total_steps": 380, "loss": 0.4529, "lr": 1.7207677699589355e-05, "epoch": 3.610885458976442, "percentage": 72.37, "elapsed_time": "1:19:08", "remaining_time": "0:30:13"}
337
+ {"current_steps": 276, "total_steps": 380, "loss": 0.4582, "lr": 1.690669138420215e-05, "epoch": 3.6238830219333877, "percentage": 72.63, "elapsed_time": "1:20:53", "remaining_time": "0:30:29"}
338
+ {"current_steps": 277, "total_steps": 380, "loss": 0.4559, "lr": 1.6607653704443457e-05, "epoch": 3.636880584890333, "percentage": 72.89, "elapsed_time": "1:22:37", "remaining_time": "0:30:43"}
339
+ {"current_steps": 278, "total_steps": 380, "loss": 0.4518, "lr": 1.6310589893400804e-05, "epoch": 3.6498781478472786, "percentage": 73.16, "elapsed_time": "1:24:22", "remaining_time": "0:30:57"}
340
+ {"current_steps": 279, "total_steps": 380, "loss": 0.4513, "lr": 1.601552501760473e-05, "epoch": 3.662875710804224, "percentage": 73.42, "elapsed_time": "1:26:07", "remaining_time": "0:31:10"}
341
+ {"current_steps": 280, "total_steps": 380, "loss": 0.4585, "lr": 1.5722483974913737e-05, "epoch": 3.67587327376117, "percentage": 73.68, "elapsed_time": "1:27:53", "remaining_time": "0:31:23"}
342
+ {"current_steps": 281, "total_steps": 380, "loss": 0.4548, "lr": 1.5431491492413288e-05, "epoch": 3.6888708367181153, "percentage": 73.95, "elapsed_time": "1:29:37", "remaining_time": "0:31:34"}
343
+ {"current_steps": 282, "total_steps": 380, "loss": 0.456, "lr": 1.5142572124329418e-05, "epoch": 3.7018683996750608, "percentage": 74.21, "elapsed_time": "1:31:22", "remaining_time": "0:31:45"}
344
+ {"current_steps": 283, "total_steps": 380, "loss": 0.4567, "lr": 1.4855750249956718e-05, "epoch": 3.7148659626320066, "percentage": 74.47, "elapsed_time": "1:33:06", "remaining_time": "0:31:54"}
345
+ {"current_steps": 284, "total_steps": 380, "loss": 0.4567, "lr": 1.457105007160129e-05, "epoch": 3.727863525588952, "percentage": 74.74, "elapsed_time": "1:34:51", "remaining_time": "0:32:04"}
346
+ {"current_steps": 285, "total_steps": 380, "loss": 0.4543, "lr": 1.4288495612538427e-05, "epoch": 3.7408610885458975, "percentage": 75.0, "elapsed_time": "1:36:37", "remaining_time": "0:32:12"}
347
+ {"current_steps": 286, "total_steps": 380, "loss": 0.457, "lr": 1.4008110714985623e-05, "epoch": 3.7538586515028434, "percentage": 75.26, "elapsed_time": "1:38:21", "remaining_time": "0:32:19"}
348
+ {"current_steps": 287, "total_steps": 380, "loss": 0.4574, "lr": 1.3729919038090627e-05, "epoch": 3.766856214459789, "percentage": 75.53, "elapsed_time": "1:40:06", "remaining_time": "0:32:26"}
349
+ {"current_steps": 288, "total_steps": 380, "loss": 0.4547, "lr": 1.3453944055935151e-05, "epoch": 3.7798537774167342, "percentage": 75.79, "elapsed_time": "1:41:50", "remaining_time": "0:32:31"}
350
+ {"current_steps": 289, "total_steps": 380, "loss": 0.4513, "lr": 1.3180209055554043e-05, "epoch": 3.79285134037368, "percentage": 76.05, "elapsed_time": "1:43:35", "remaining_time": "0:32:37"}
351
+ {"current_steps": 290, "total_steps": 380, "loss": 0.443, "lr": 1.2908737134970367e-05, "epoch": 3.8058489033306255, "percentage": 76.32, "elapsed_time": "1:45:19", "remaining_time": "0:32:41"}
352
+ {"current_steps": 291, "total_steps": 380, "loss": 0.4516, "lr": 1.2639551201246278e-05, "epoch": 3.818846466287571, "percentage": 76.58, "elapsed_time": "1:47:04", "remaining_time": "0:32:44"}
353
+ {"current_steps": 292, "total_steps": 380, "loss": 0.4547, "lr": 1.2372673968550229e-05, "epoch": 3.8318440292445164, "percentage": 76.84, "elapsed_time": "1:48:48", "remaining_time": "0:32:47"}
354
+ {"current_steps": 293, "total_steps": 380, "loss": 0.4455, "lr": 1.2108127956240186e-05, "epoch": 3.8448415922014623, "percentage": 77.11, "elapsed_time": "1:50:33", "remaining_time": "0:32:49"}
355
+ {"current_steps": 294, "total_steps": 380, "loss": 0.4525, "lr": 1.1845935486963546e-05, "epoch": 3.8578391551584077, "percentage": 77.37, "elapsed_time": "1:52:17", "remaining_time": "0:32:50"}
356
+ {"current_steps": 295, "total_steps": 380, "loss": 0.4566, "lr": 1.158611868477344e-05, "epoch": 3.8708367181153536, "percentage": 77.63, "elapsed_time": "1:54:02", "remaining_time": "0:32:51"}
357
+ {"current_steps": 296, "total_steps": 380, "loss": 0.4472, "lr": 1.1328699473261957e-05, "epoch": 3.883834281072299, "percentage": 77.89, "elapsed_time": "1:55:47", "remaining_time": "0:32:51"}
358
+ {"current_steps": 297, "total_steps": 380, "loss": 0.4473, "lr": 1.107369957371013e-05, "epoch": 3.8968318440292444, "percentage": 78.16, "elapsed_time": "1:57:31", "remaining_time": "0:32:50"}
359
+ {"current_steps": 298, "total_steps": 380, "loss": 0.4539, "lr": 1.0821140503255174e-05, "epoch": 3.90982940698619, "percentage": 78.42, "elapsed_time": "1:59:15", "remaining_time": "0:32:48"}
360
+ {"current_steps": 299, "total_steps": 380, "loss": 0.4524, "lr": 1.0571043573074737e-05, "epoch": 3.9228269699431357, "percentage": 78.68, "elapsed_time": "2:00:59", "remaining_time": "0:32:46"}
361
+ {"current_steps": 300, "total_steps": 380, "loss": 0.4551, "lr": 1.0323429886588743e-05, "epoch": 3.935824532900081, "percentage": 78.95, "elapsed_time": "2:02:44", "remaining_time": "0:32:43"}
362
+ {"current_steps": 301, "total_steps": 380, "loss": 0.4542, "lr": 1.0078320337678584e-05, "epoch": 3.948822095857027, "percentage": 79.21, "elapsed_time": "2:04:28", "remaining_time": "0:32:40"}
363
+ {"current_steps": 302, "total_steps": 380, "loss": 0.4559, "lr": 9.835735608924155e-06, "epoch": 3.9618196588139725, "percentage": 79.47, "elapsed_time": "2:06:13", "remaining_time": "0:32:35"}
364
+ {"current_steps": 303, "total_steps": 380, "loss": 0.4556, "lr": 9.595696169858542e-06, "epoch": 3.974817221770918, "percentage": 79.74, "elapsed_time": "2:07:57", "remaining_time": "0:32:30"}
365
+ {"current_steps": 304, "total_steps": 380, "loss": 0.452, "lr": 9.358222275240884e-06, "epoch": 3.9878147847278633, "percentage": 80.0, "elapsed_time": "2:09:41", "remaining_time": "0:32:25"}
366
+ {"current_steps": 305, "total_steps": 380, "loss": 0.4523, "lr": 9.123333963347166e-06, "epoch": 4.000812347684809, "percentage": 80.26, "elapsed_time": "2:13:16", "remaining_time": "0:32:46"}
367
+ {"current_steps": 306, "total_steps": 380, "loss": 0.4304, "lr": 8.89105105427945e-06, "epoch": 4.013809910641755, "percentage": 80.53, "elapsed_time": "2:14:59", "remaining_time": "0:32:38"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0d60b7a4708d52b545324b06c9ef5e68853f444b39db0cbb858968e8e801ec3
3
- size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a2f9f7c3ea784a944e190bb3b4c37c7b2ce3f1701579a146100a3934c6fb49
3
+ size 7480