EtashGuha commited on
Commit
de07b95
·
verified ·
1 Parent(s): cb3c8e7

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 sha256:72569b310b414810be622d9dd4dab8147fb3bc6250efddb769aa812a7ce93696
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6dcf6ca3d9100cc7370bb87a8391b496645341b682df4625f62d05b30b3c1f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fd065c45ed3952ead2f1bab51854c38243c2e3ed2d7bdbc5f2677ae554ec563
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2031334122b4ef3c65f25f1ce6dfe139eef47c530b5a025520af73b1157b80a
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:c5c4b65283e5e9499c1145fae7f7ae385501b394c4f35428a1ad0804cc03ecf1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fff735a6c88a3483fa14fa6ea278a77267b35bed4c6c1c570a98341a619cea
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1800867005d8387430e6cbfa4d574536c1ffdccf0c8baa0a3ff6e76ee132df20
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bc89c04f6daf55e642a7fb423fe99649e1fea822c348590be887239b304588
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -235,3 +235,81 @@
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4606, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "3:01:30", "remaining_time": "1:59:43"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.4162, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "3:02:14", "remaining_time": "1:58:55"}
237
  {"current_steps": 237, "total_steps": 390, "loss": 0.4145, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "3:02:59", "remaining_time": "1:58:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4606, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "3:01:30", "remaining_time": "1:59:43"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.4162, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "3:02:14", "remaining_time": "1:58:55"}
237
  {"current_steps": 237, "total_steps": 390, "loss": 0.4145, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "3:02:59", "remaining_time": "1:58:07"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.4226, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "3:03:42", "remaining_time": "1:57:19"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.4201, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "3:04:26", "remaining_time": "1:56:31"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4171, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "3:05:11", "remaining_time": "1:55:44"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4213, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "3:05:56", "remaining_time": "1:54:57"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4414, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "3:06:38", "remaining_time": "1:54:08"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.4323, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "3:07:21", "remaining_time": "1:53:20"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.4312, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "3:08:08", "remaining_time": "1:52:34"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4373, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "3:08:51", "remaining_time": "1:51:46"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.419, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "3:09:38", "remaining_time": "1:51:00"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4354, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "3:10:24", "remaining_time": "1:50:14"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4378, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "3:11:10", "remaining_time": "1:49:27"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4294, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "3:11:53", "remaining_time": "1:48:39"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.4154, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "3:12:38", "remaining_time": "1:47:52"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.4265, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "3:13:24", "remaining_time": "1:47:06"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4144, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "3:14:08", "remaining_time": "1:46:18"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4205, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "3:14:52", "remaining_time": "1:45:31"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4149, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "3:15:37", "remaining_time": "1:44:44"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4227, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "3:16:23", "remaining_time": "1:43:58"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.4202, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "3:17:08", "remaining_time": "1:43:11"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4216, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "3:17:52", "remaining_time": "1:42:24"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4157, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "3:18:37", "remaining_time": "1:41:37"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4298, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "3:19:21", "remaining_time": "1:40:49"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4254, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "3:20:06", "remaining_time": "1:40:03"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4262, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "3:20:49", "remaining_time": "1:39:15"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4355, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "3:21:35", "remaining_time": "1:38:29"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.4194, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "3:22:18", "remaining_time": "1:37:41"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4244, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "3:23:02", "remaining_time": "1:36:54"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4195, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "3:23:47", "remaining_time": "1:36:07"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4234, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "3:24:31", "remaining_time": "1:35:20"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.418, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "3:25:15", "remaining_time": "1:34:33"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4155, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "3:26:02", "remaining_time": "1:33:47"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4169, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "3:26:46", "remaining_time": "1:33:00"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4263, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "3:27:31", "remaining_time": "1:32:14"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.4314, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "3:28:15", "remaining_time": "1:31:26"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.4321, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "3:28:57", "remaining_time": "1:30:39"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.414, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "3:29:41", "remaining_time": "1:29:52"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4146, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "3:30:28", "remaining_time": "1:29:06"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4303, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "3:31:13", "remaining_time": "1:28:19"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4276, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "3:31:58", "remaining_time": "1:27:33"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4313, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "3:32:42", "remaining_time": "1:26:46"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4126, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "3:33:29", "remaining_time": "1:26:00"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.423, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "3:34:14", "remaining_time": "1:25:14"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4254, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "3:34:58", "remaining_time": "1:24:27"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.4065, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "3:35:41", "remaining_time": "1:23:40"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.4365, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "3:36:28", "remaining_time": "1:22:54"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4224, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "3:37:12", "remaining_time": "1:22:07"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4312, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "3:37:57", "remaining_time": "1:21:20"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4159, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "3:38:41", "remaining_time": "1:20:34"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4126, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "3:39:22", "remaining_time": "1:19:46"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4426, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "3:40:05", "remaining_time": "1:18:59"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4276, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "3:40:49", "remaining_time": "1:18:12"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.4127, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "3:41:35", "remaining_time": "1:17:26"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.4136, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "3:42:21", "remaining_time": "1:16:40"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4222, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "3:43:07", "remaining_time": "1:15:54"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.4157, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "3:43:51", "remaining_time": "1:15:07"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4125, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "3:44:35", "remaining_time": "1:14:21"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4255, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "3:45:19", "remaining_time": "1:13:34"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4213, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "3:46:04", "remaining_time": "1:12:48"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4147, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "3:46:48", "remaining_time": "1:12:01"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.419, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "3:47:32", "remaining_time": "1:11:15"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4271, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "3:48:15", "remaining_time": "1:10:28"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.4101, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "3:48:58", "remaining_time": "1:09:41"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.4281, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "3:49:42", "remaining_time": "1:08:54"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4277, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "3:50:26", "remaining_time": "1:08:08"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4331, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "3:51:12", "remaining_time": "1:07:22"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4151, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "3:51:58", "remaining_time": "1:06:36"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.433, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "3:52:42", "remaining_time": "1:05:49"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4176, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "3:53:24", "remaining_time": "1:05:02"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.4182, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "3:54:10", "remaining_time": "1:04:16"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4216, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "3:54:55", "remaining_time": "1:03:30"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4372, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "3:55:42", "remaining_time": "1:02:45"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.4191, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "3:56:27", "remaining_time": "1:01:58"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4279, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "3:57:10", "remaining_time": "1:01:12"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.422, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "3:57:55", "remaining_time": "1:00:26"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4234, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "3:58:40", "remaining_time": "0:59:40"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4033, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "4:01:19", "remaining_time": "0:59:22"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3765, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "4:02:03", "remaining_time": "0:58:35"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3773, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "4:02:49", "remaining_time": "0:57:48"}