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:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:903131e87a8483acf71b18d7cc1f7bcfe585f2daf0eaf8116a24f499d724b51f
|
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:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bdcfad7b5e398e0d03dd0de92c31113ccd8addf88d7723fba8cf5a5eed509f0
|
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:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ed0005da36cceef0ddbc2885c3d8f8ab2eba6dd2486c08ee3c3889384fb6877
|
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:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50194bf964167c433a899a6d09b7c242edcbd78b29ab629c639698186f079e47
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -233,3 +233,82 @@
|
|
233 |
{"current_steps": 233, "total_steps": 390, "loss": 0.4566, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "9:38:05", "remaining_time": "6:29:31"}
|
234 |
{"current_steps": 234, "total_steps": 390, "loss": 0.4301, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "9:40:16", "remaining_time": "6:26:51"}
|
235 |
{"current_steps": 235, "total_steps": 390, "loss": 0.3689, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "9:43:17", "remaining_time": "6:24:43"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
233 |
{"current_steps": 233, "total_steps": 390, "loss": 0.4566, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "9:38:05", "remaining_time": "6:29:31"}
|
234 |
{"current_steps": 234, "total_steps": 390, "loss": 0.4301, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "9:40:16", "remaining_time": "6:26:51"}
|
235 |
{"current_steps": 235, "total_steps": 390, "loss": 0.3689, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "9:43:17", "remaining_time": "6:24:43"}
|
236 |
+
{"current_steps": 236, "total_steps": 390, "loss": 0.3781, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "9:45:47", "remaining_time": "6:22:15"}
|
237 |
+
{"current_steps": 237, "total_steps": 390, "loss": 0.3607, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "9:48:09", "remaining_time": "6:19:41"}
|
238 |
+
{"current_steps": 238, "total_steps": 390, "loss": 0.3798, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "9:50:43", "remaining_time": "6:17:16"}
|
239 |
+
{"current_steps": 239, "total_steps": 390, "loss": 0.3588, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "9:53:07", "remaining_time": "6:14:43"}
|
240 |
+
{"current_steps": 240, "total_steps": 390, "loss": 0.374, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "9:55:32", "remaining_time": "6:12:13"}
|
241 |
+
{"current_steps": 241, "total_steps": 390, "loss": 0.3706, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "9:57:48", "remaining_time": "6:09:35"}
|
242 |
+
{"current_steps": 242, "total_steps": 390, "loss": 0.3671, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:00:19", "remaining_time": "6:07:08"}
|
243 |
+
{"current_steps": 243, "total_steps": 390, "loss": 0.3621, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:02:34", "remaining_time": "6:04:31"}
|
244 |
+
{"current_steps": 244, "total_steps": 390, "loss": 0.3757, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "10:05:12", "remaining_time": "6:02:07"}
|
245 |
+
{"current_steps": 245, "total_steps": 390, "loss": 0.3695, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "10:07:38", "remaining_time": "5:59:37"}
|
246 |
+
{"current_steps": 246, "total_steps": 390, "loss": 0.3601, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "10:10:15", "remaining_time": "5:57:13"}
|
247 |
+
{"current_steps": 247, "total_steps": 390, "loss": 0.3577, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "10:12:42", "remaining_time": "5:54:43"}
|
248 |
+
{"current_steps": 248, "total_steps": 390, "loss": 0.3479, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "10:14:56", "remaining_time": "5:52:06"}
|
249 |
+
{"current_steps": 249, "total_steps": 390, "loss": 0.3643, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "10:17:24", "remaining_time": "5:49:36"}
|
250 |
+
{"current_steps": 250, "total_steps": 390, "loss": 0.3787, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "10:20:03", "remaining_time": "5:47:13"}
|
251 |
+
{"current_steps": 251, "total_steps": 390, "loss": 0.3707, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "10:22:34", "remaining_time": "5:44:46"}
|
252 |
+
{"current_steps": 252, "total_steps": 390, "loss": 0.3905, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "10:25:13", "remaining_time": "5:42:23"}
|
253 |
+
{"current_steps": 253, "total_steps": 390, "loss": 0.369, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "10:27:33", "remaining_time": "5:39:49"}
|
254 |
+
{"current_steps": 254, "total_steps": 390, "loss": 0.3549, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "10:29:52", "remaining_time": "5:37:15"}
|
255 |
+
{"current_steps": 255, "total_steps": 390, "loss": 0.3326, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "10:31:53", "remaining_time": "5:34:32"}
|
256 |
+
{"current_steps": 256, "total_steps": 390, "loss": 0.396, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "10:34:28", "remaining_time": "5:32:06"}
|
257 |
+
{"current_steps": 257, "total_steps": 390, "loss": 0.3702, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "10:36:49", "remaining_time": "5:29:33"}
|
258 |
+
{"current_steps": 258, "total_steps": 390, "loss": 0.3733, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "10:39:21", "remaining_time": "5:27:06"}
|
259 |
+
{"current_steps": 259, "total_steps": 390, "loss": 0.3652, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "10:41:56", "remaining_time": "5:24:41"}
|
260 |
+
{"current_steps": 260, "total_steps": 390, "loss": 0.3505, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "10:44:30", "remaining_time": "5:22:15"}
|
261 |
+
{"current_steps": 261, "total_steps": 390, "loss": 0.3574, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "10:46:47", "remaining_time": "5:19:40"}
|
262 |
+
{"current_steps": 262, "total_steps": 390, "loss": 0.3845, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "10:49:32", "remaining_time": "5:17:19"}
|
263 |
+
{"current_steps": 263, "total_steps": 390, "loss": 0.3913, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "10:51:56", "remaining_time": "5:14:48"}
|
264 |
+
{"current_steps": 264, "total_steps": 390, "loss": 0.3488, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "10:54:12", "remaining_time": "5:12:14"}
|
265 |
+
{"current_steps": 265, "total_steps": 390, "loss": 0.3543, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "10:56:20", "remaining_time": "5:09:35"}
|
266 |
+
{"current_steps": 266, "total_steps": 390, "loss": 0.3525, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "10:58:49", "remaining_time": "5:07:07"}
|
267 |
+
{"current_steps": 267, "total_steps": 390, "loss": 0.3747, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "11:01:10", "remaining_time": "5:04:35"}
|
268 |
+
{"current_steps": 268, "total_steps": 390, "loss": 0.397, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "11:03:37", "remaining_time": "5:02:05"}
|
269 |
+
{"current_steps": 269, "total_steps": 390, "loss": 0.353, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "11:06:01", "remaining_time": "4:59:35"}
|
270 |
+
{"current_steps": 270, "total_steps": 390, "loss": 0.3698, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "11:08:35", "remaining_time": "4:57:08"}
|
271 |
+
{"current_steps": 271, "total_steps": 390, "loss": 0.3429, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "11:10:56", "remaining_time": "4:54:37"}
|
272 |
+
{"current_steps": 272, "total_steps": 390, "loss": 0.3464, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "11:13:06", "remaining_time": "4:52:00"}
|
273 |
+
{"current_steps": 273, "total_steps": 390, "loss": 0.3851, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "11:15:50", "remaining_time": "4:49:38"}
|
274 |
+
{"current_steps": 274, "total_steps": 390, "loss": 0.356, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "11:18:04", "remaining_time": "4:47:03"}
|
275 |
+
{"current_steps": 275, "total_steps": 390, "loss": 0.3605, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "11:20:33", "remaining_time": "4:44:36"}
|
276 |
+
{"current_steps": 276, "total_steps": 390, "loss": 0.3916, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "11:23:07", "remaining_time": "4:42:09"}
|
277 |
+
{"current_steps": 277, "total_steps": 390, "loss": 0.3623, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "11:25:30", "remaining_time": "4:39:38"}
|
278 |
+
{"current_steps": 278, "total_steps": 390, "loss": 0.3722, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "11:28:00", "remaining_time": "4:37:10"}
|
279 |
+
{"current_steps": 279, "total_steps": 390, "loss": 0.3616, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "11:30:21", "remaining_time": "4:34:39"}
|
280 |
+
{"current_steps": 280, "total_steps": 390, "loss": 0.3708, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "11:32:33", "remaining_time": "4:32:04"}
|
281 |
+
{"current_steps": 281, "total_steps": 390, "loss": 0.3932, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "11:35:06", "remaining_time": "4:29:37"}
|
282 |
+
{"current_steps": 282, "total_steps": 390, "loss": 0.3931, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "11:37:49", "remaining_time": "4:27:15"}
|
283 |
+
{"current_steps": 283, "total_steps": 390, "loss": 0.3719, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "11:40:09", "remaining_time": "4:24:43"}
|
284 |
+
{"current_steps": 284, "total_steps": 390, "loss": 0.3565, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "11:42:22", "remaining_time": "4:22:09"}
|
285 |
+
{"current_steps": 285, "total_steps": 390, "loss": 0.3621, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "11:44:52", "remaining_time": "4:19:41"}
|
286 |
+
{"current_steps": 286, "total_steps": 390, "loss": 0.3632, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "11:47:21", "remaining_time": "4:17:13"}
|
287 |
+
{"current_steps": 287, "total_steps": 390, "loss": 0.3849, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "11:49:47", "remaining_time": "4:14:44"}
|
288 |
+
{"current_steps": 288, "total_steps": 390, "loss": 0.3758, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "11:52:25", "remaining_time": "4:12:19"}
|
289 |
+
{"current_steps": 289, "total_steps": 390, "loss": 0.3414, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "11:54:44", "remaining_time": "4:09:47"}
|
290 |
+
{"current_steps": 290, "total_steps": 390, "loss": 0.3723, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "11:57:02", "remaining_time": "4:07:15"}
|
291 |
+
{"current_steps": 291, "total_steps": 390, "loss": 0.378, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "11:59:18", "remaining_time": "4:04:42"}
|
292 |
+
{"current_steps": 292, "total_steps": 390, "loss": 0.3785, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "12:01:54", "remaining_time": "4:02:17"}
|
293 |
+
{"current_steps": 293, "total_steps": 390, "loss": 0.354, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "12:04:30", "remaining_time": "3:59:51"}
|
294 |
+
{"current_steps": 294, "total_steps": 390, "loss": 0.371, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "12:06:50", "remaining_time": "3:57:20"}
|
295 |
+
{"current_steps": 295, "total_steps": 390, "loss": 0.3501, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "12:09:04", "remaining_time": "3:54:47"}
|
296 |
+
{"current_steps": 296, "total_steps": 390, "loss": 0.3709, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "12:11:30", "remaining_time": "3:52:18"}
|
297 |
+
{"current_steps": 297, "total_steps": 390, "loss": 0.3913, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "12:13:56", "remaining_time": "3:49:49"}
|
298 |
+
{"current_steps": 298, "total_steps": 390, "loss": 0.362, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "12:16:04", "remaining_time": "3:47:14"}
|
299 |
+
{"current_steps": 299, "total_steps": 390, "loss": 0.3658, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "12:18:40", "remaining_time": "3:44:48"}
|
300 |
+
{"current_steps": 300, "total_steps": 390, "loss": 0.3909, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "12:20:54", "remaining_time": "3:42:16"}
|
301 |
+
{"current_steps": 301, "total_steps": 390, "loss": 0.3556, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "12:23:18", "remaining_time": "3:39:47"}
|
302 |
+
{"current_steps": 302, "total_steps": 390, "loss": 0.3557, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "12:25:33", "remaining_time": "3:37:14"}
|
303 |
+
{"current_steps": 303, "total_steps": 390, "loss": 0.3356, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "12:27:46", "remaining_time": "3:34:42"}
|
304 |
+
{"current_steps": 304, "total_steps": 390, "loss": 0.3617, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "12:30:24", "remaining_time": "3:32:17"}
|
305 |
+
{"current_steps": 305, "total_steps": 390, "loss": 0.3621, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "12:32:48", "remaining_time": "3:29:47"}
|
306 |
+
{"current_steps": 306, "total_steps": 390, "loss": 0.3673, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "12:35:06", "remaining_time": "3:27:17"}
|
307 |
+
{"current_steps": 307, "total_steps": 390, "loss": 0.3575, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "12:37:27", "remaining_time": "3:24:47"}
|
308 |
+
{"current_steps": 308, "total_steps": 390, "loss": 0.3903, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "12:40:03", "remaining_time": "3:22:21"}
|
309 |
+
{"current_steps": 309, "total_steps": 390, "loss": 0.3574, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "12:42:29", "remaining_time": "3:19:52"}
|
310 |
+
{"current_steps": 310, "total_steps": 390, "loss": 0.3849, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "12:45:07", "remaining_time": "3:17:27"}
|
311 |
+
{"current_steps": 311, "total_steps": 390, "loss": 0.3744, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "12:47:42", "remaining_time": "3:15:00"}
|
312 |
+
{"current_steps": 312, "total_steps": 390, "loss": 0.3415, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "12:49:55", "remaining_time": "3:12:28"}
|
313 |
+
{"current_steps": 313, "total_steps": 390, "loss": 0.3231, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "12:53:02", "remaining_time": "3:10:10"}
|
314 |
+
{"current_steps": 314, "total_steps": 390, "loss": 0.3025, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "12:55:13", "remaining_time": "3:07:38"}
|