ryanmarten commited on
Commit
fe5d5d0
·
verified ·
1 Parent(s): 1ea09a4

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 sha256:0357b18050a9ffd64a9364f0351c5bb872b9b247b06e45547a7b18f768a32800
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b273a0de18b9bb0cb048920cc2a72787bafd7a3ccdf058aab5a70a06ffc343ba
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:431b4d5058b808113169a059d3cf446eb11b6fb9ef3dea83d6c9312c40b310f6
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0964e9b7e94f40c49caf3f905de595d217dc7f3ba43f72095980ae6e3b9ba0
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:a831fcf87de1024780dddb23685839cfeb1ab49e7783c139cf8a07ed9046eb82
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e6a78499e1f29772b52f73f72ba170238306010e53f97c483bb5e7a026cac9
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85d7c6a62cfb801f9ad8a57c228085137a1aadf96b6dc30838984ac7a780ea25
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ffe9e5199eecafc43b8d27d2f4ce6d452850b480912bcceb83df30f772279b6
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -233,3 +233,81 @@
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.4764, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:00:46", "remaining_time": "6:44:48"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.5048, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:03:21", "remaining_time": "6:42:14"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4821, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:06:53", "remaining_time": "6:40:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.4764, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:00:46", "remaining_time": "6:44:48"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.5048, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:03:21", "remaining_time": "6:42:14"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4821, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:06:53", "remaining_time": "6:40:17"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.4258, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:09:27", "remaining_time": "6:37:41"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.4354, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:12:14", "remaining_time": "6:35:14"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.437, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:14:48", "remaining_time": "6:32:38"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.4553, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:17:36", "remaining_time": "6:30:12"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4408, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:20:21", "remaining_time": "6:27:43"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4347, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:22:57", "remaining_time": "6:25:08"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4445, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:25:27", "remaining_time": "6:22:30"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.433, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:27:58", "remaining_time": "6:19:53"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.419, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "10:30:29", "remaining_time": "6:17:15"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4288, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "10:33:07", "remaining_time": "6:14:42"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4275, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "10:35:26", "remaining_time": "6:11:57"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4483, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "10:38:04", "remaining_time": "6:09:24"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4454, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "10:40:42", "remaining_time": "6:06:51"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4506, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "10:43:13", "remaining_time": "6:04:14"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.4451, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "10:46:01", "remaining_time": "6:01:46"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.4242, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "10:48:49", "remaining_time": "5:59:18"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4385, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "10:51:30", "remaining_time": "5:56:46"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4476, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "10:54:00", "remaining_time": "5:54:08"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4324, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "10:56:34", "remaining_time": "5:51:32"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4434, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "10:59:03", "remaining_time": "5:48:54"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.4241, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:01:31", "remaining_time": "5:46:15"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4226, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:04:11", "remaining_time": "5:43:43"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4237, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:06:39", "remaining_time": "5:41:04"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4316, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:09:12", "remaining_time": "5:38:28"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4367, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:11:39", "remaining_time": "5:35:49"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4301, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:14:19", "remaining_time": "5:33:17"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4295, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:16:54", "remaining_time": "5:30:42"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.4507, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:19:25", "remaining_time": "5:28:05"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.449, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:22:07", "remaining_time": "5:25:33"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4589, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "11:24:44", "remaining_time": "5:22:59"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4459, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "11:27:23", "remaining_time": "5:20:26"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4478, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "11:29:52", "remaining_time": "5:17:48"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4296, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "11:32:20", "remaining_time": "5:15:10"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4337, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "11:34:50", "remaining_time": "5:12:33"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4596, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "11:37:18", "remaining_time": "5:09:54"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.4297, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "11:40:00", "remaining_time": "5:07:22"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.4464, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "11:42:45", "remaining_time": "5:04:52"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.4417, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "11:45:09", "remaining_time": "5:02:12"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4402, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "11:47:39", "remaining_time": "4:59:35"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4515, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "11:50:19", "remaining_time": "4:57:02"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4413, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "11:53:04", "remaining_time": "4:54:31"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4353, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "11:55:33", "remaining_time": "4:51:54"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4369, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "11:58:04", "remaining_time": "4:49:17"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4271, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:00:36", "remaining_time": "4:46:41"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4278, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:03:14", "remaining_time": "4:44:07"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.4219, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:05:47", "remaining_time": "4:41:32"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.4425, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:08:39", "remaining_time": "4:39:03"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4402, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:11:14", "remaining_time": "4:36:28"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4463, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:13:29", "remaining_time": "4:33:46"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4309, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:16:05", "remaining_time": "4:31:11"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4419, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:18:37", "remaining_time": "4:28:35"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4248, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "12:20:56", "remaining_time": "4:25:54"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4351, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "12:23:29", "remaining_time": "4:23:19"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.4269, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "12:25:47", "remaining_time": "4:20:38"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.4342, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "12:28:16", "remaining_time": "4:18:01"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4439, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "12:30:47", "remaining_time": "4:15:25"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.4412, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "12:33:31", "remaining_time": "4:12:53"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4304, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "12:35:48", "remaining_time": "4:10:12"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4364, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "12:38:27", "remaining_time": "4:07:39"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4242, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "12:40:57", "remaining_time": "4:05:03"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.43, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "12:43:33", "remaining_time": "4:02:28"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4353, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "12:46:19", "remaining_time": "3:59:57"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4474, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "12:49:09", "remaining_time": "3:57:27"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.4285, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "12:51:37", "remaining_time": "3:54:50"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.4279, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "12:54:13", "remaining_time": "3:52:16"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4358, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "12:56:48", "remaining_time": "3:49:41"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4396, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "12:59:19", "remaining_time": "3:47:05"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4381, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:02:00", "remaining_time": "3:44:32"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.4291, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:04:33", "remaining_time": "3:41:56"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4222, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:06:58", "remaining_time": "3:39:19"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.4364, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:09:28", "remaining_time": "3:36:43"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4298, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:11:59", "remaining_time": "3:34:07"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4221, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:14:35", "remaining_time": "3:31:32"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.42, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "13:16:59", "remaining_time": "3:28:55"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4398, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "13:19:33", "remaining_time": "3:26:20"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.4358, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:21:57", "remaining_time": "3:23:42"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4334, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:24:52", "remaining_time": "3:21:13"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4189, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:28:24", "remaining_time": "3:18:52"}