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 sha256:56d791ece4d96ce6fe9f04b857fce49eafb6217c9bb050e16655cd1de34d7b7f
|
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:e71485d125a919a0823e403113afc7cf95bbc48bff0a1aee20499b842a9dd08b
|
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:cc2442288da7ed3d5f12bb07e35f3cc563520f504d7943d2b57e141f89314cab
|
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:f7caecac307f0eac713ed6bff086e6af69614dda94657dd9e93bc639015194cc
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -233,3 +233,82 @@
|
|
233 |
{"current_steps": 233, "total_steps": 390, "loss": 0.3314, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "8:10:42", "remaining_time": "5:30:38"}
|
234 |
{"current_steps": 234, "total_steps": 390, "loss": 0.3307, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "8:12:42", "remaining_time": "5:28:28"}
|
235 |
{"current_steps": 235, "total_steps": 390, "loss": 0.2769, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "8:15:26", "remaining_time": "5:26:46"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
233 |
{"current_steps": 233, "total_steps": 390, "loss": 0.3314, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "8:10:42", "remaining_time": "5:30:38"}
|
234 |
{"current_steps": 234, "total_steps": 390, "loss": 0.3307, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "8:12:42", "remaining_time": "5:28:28"}
|
235 |
{"current_steps": 235, "total_steps": 390, "loss": 0.2769, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "8:15:26", "remaining_time": "5:26:46"}
|
236 |
+
{"current_steps": 236, "total_steps": 390, "loss": 0.2608, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "8:17:28", "remaining_time": "5:24:37"}
|
237 |
+
{"current_steps": 237, "total_steps": 390, "loss": 0.2701, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "8:19:16", "remaining_time": "5:22:19"}
|
238 |
+
{"current_steps": 238, "total_steps": 390, "loss": 0.258, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "8:21:29", "remaining_time": "5:20:16"}
|
239 |
+
{"current_steps": 239, "total_steps": 390, "loss": 0.2439, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "8:23:16", "remaining_time": "5:17:57"}
|
240 |
+
{"current_steps": 240, "total_steps": 390, "loss": 0.2411, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "8:25:09", "remaining_time": "5:15:43"}
|
241 |
+
{"current_steps": 241, "total_steps": 390, "loss": 0.239, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "8:27:02", "remaining_time": "5:13:29"}
|
242 |
+
{"current_steps": 242, "total_steps": 390, "loss": 0.2818, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "8:29:15", "remaining_time": "5:11:26"}
|
243 |
+
{"current_steps": 243, "total_steps": 390, "loss": 0.2418, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "8:31:13", "remaining_time": "5:09:15"}
|
244 |
+
{"current_steps": 244, "total_steps": 390, "loss": 0.2466, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "8:33:04", "remaining_time": "5:07:00"}
|
245 |
+
{"current_steps": 245, "total_steps": 390, "loss": 0.2653, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "8:35:08", "remaining_time": "5:04:52"}
|
246 |
+
{"current_steps": 246, "total_steps": 390, "loss": 0.2661, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "8:37:15", "remaining_time": "5:02:47"}
|
247 |
+
{"current_steps": 247, "total_steps": 390, "loss": 0.2607, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "8:39:13", "remaining_time": "5:00:36"}
|
248 |
+
{"current_steps": 248, "total_steps": 390, "loss": 0.2449, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "8:41:09", "remaining_time": "4:58:24"}
|
249 |
+
{"current_steps": 249, "total_steps": 390, "loss": 0.2632, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "8:43:24", "remaining_time": "4:56:23"}
|
250 |
+
{"current_steps": 250, "total_steps": 390, "loss": 0.2331, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "8:45:13", "remaining_time": "4:54:07"}
|
251 |
+
{"current_steps": 251, "total_steps": 390, "loss": 0.2534, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "8:47:25", "remaining_time": "4:52:04"}
|
252 |
+
{"current_steps": 252, "total_steps": 390, "loss": 0.2781, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "8:49:44", "remaining_time": "4:50:05"}
|
253 |
+
{"current_steps": 253, "total_steps": 390, "loss": 0.262, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "8:52:02", "remaining_time": "4:48:05"}
|
254 |
+
{"current_steps": 254, "total_steps": 390, "loss": 0.2458, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "8:53:59", "remaining_time": "4:45:54"}
|
255 |
+
{"current_steps": 255, "total_steps": 390, "loss": 0.2649, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "8:56:07", "remaining_time": "4:43:50"}
|
256 |
+
{"current_steps": 256, "total_steps": 390, "loss": 0.262, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "8:58:10", "remaining_time": "4:41:42"}
|
257 |
+
{"current_steps": 257, "total_steps": 390, "loss": 0.2626, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "9:00:15", "remaining_time": "4:39:35"}
|
258 |
+
{"current_steps": 258, "total_steps": 390, "loss": 0.2286, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "9:02:04", "remaining_time": "4:37:20"}
|
259 |
+
{"current_steps": 259, "total_steps": 390, "loss": 0.2398, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "9:03:54", "remaining_time": "4:35:06"}
|
260 |
+
{"current_steps": 260, "total_steps": 390, "loss": 0.2537, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "9:05:52", "remaining_time": "4:32:56"}
|
261 |
+
{"current_steps": 261, "total_steps": 390, "loss": 0.2589, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "9:07:56", "remaining_time": "4:30:49"}
|
262 |
+
{"current_steps": 262, "total_steps": 390, "loss": 0.2616, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "9:09:59", "remaining_time": "4:28:41"}
|
263 |
+
{"current_steps": 263, "total_steps": 390, "loss": 0.263, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "9:12:10", "remaining_time": "4:26:38"}
|
264 |
+
{"current_steps": 264, "total_steps": 390, "loss": 0.2659, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "9:14:30", "remaining_time": "4:24:38"}
|
265 |
+
{"current_steps": 265, "total_steps": 390, "loss": 0.2623, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "9:16:23", "remaining_time": "4:22:27"}
|
266 |
+
{"current_steps": 266, "total_steps": 390, "loss": 0.2516, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "9:18:32", "remaining_time": "4:20:22"}
|
267 |
+
{"current_steps": 267, "total_steps": 390, "loss": 0.2716, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "9:20:43", "remaining_time": "4:18:18"}
|
268 |
+
{"current_steps": 268, "total_steps": 390, "loss": 0.2493, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "9:22:28", "remaining_time": "4:16:02"}
|
269 |
+
{"current_steps": 269, "total_steps": 390, "loss": 0.2564, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "9:24:42", "remaining_time": "4:14:00"}
|
270 |
+
{"current_steps": 270, "total_steps": 390, "loss": 0.2568, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "9:26:48", "remaining_time": "4:11:55"}
|
271 |
+
{"current_steps": 271, "total_steps": 390, "loss": 0.2583, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "9:28:47", "remaining_time": "4:09:45"}
|
272 |
+
{"current_steps": 272, "total_steps": 390, "loss": 0.2298, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "9:30:36", "remaining_time": "4:07:32"}
|
273 |
+
{"current_steps": 273, "total_steps": 390, "loss": 0.2636, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "9:32:40", "remaining_time": "4:05:25"}
|
274 |
+
{"current_steps": 274, "total_steps": 390, "loss": 0.2541, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "9:34:53", "remaining_time": "4:03:23"}
|
275 |
+
{"current_steps": 275, "total_steps": 390, "loss": 0.2442, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "9:36:31", "remaining_time": "4:01:05"}
|
276 |
+
{"current_steps": 276, "total_steps": 390, "loss": 0.2462, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "9:38:37", "remaining_time": "3:58:59"}
|
277 |
+
{"current_steps": 277, "total_steps": 390, "loss": 0.2447, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "9:40:40", "remaining_time": "3:56:53"}
|
278 |
+
{"current_steps": 278, "total_steps": 390, "loss": 0.2463, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "9:42:52", "remaining_time": "3:54:49"}
|
279 |
+
{"current_steps": 279, "total_steps": 390, "loss": 0.259, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "9:44:48", "remaining_time": "3:52:40"}
|
280 |
+
{"current_steps": 280, "total_steps": 390, "loss": 0.2562, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "9:46:46", "remaining_time": "3:50:31"}
|
281 |
+
{"current_steps": 281, "total_steps": 390, "loss": 0.2611, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "9:48:53", "remaining_time": "3:48:25"}
|
282 |
+
{"current_steps": 282, "total_steps": 390, "loss": 0.2671, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "9:50:47", "remaining_time": "3:46:15"}
|
283 |
+
{"current_steps": 283, "total_steps": 390, "loss": 0.2405, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "9:52:54", "remaining_time": "3:44:10"}
|
284 |
+
{"current_steps": 284, "total_steps": 390, "loss": 0.2633, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "9:55:06", "remaining_time": "3:42:07"}
|
285 |
+
{"current_steps": 285, "total_steps": 390, "loss": 0.2563, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "9:56:58", "remaining_time": "3:39:56"}
|
286 |
+
{"current_steps": 286, "total_steps": 390, "loss": 0.249, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "9:58:57", "remaining_time": "3:37:48"}
|
287 |
+
{"current_steps": 287, "total_steps": 390, "loss": 0.2519, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "10:00:59", "remaining_time": "3:35:41"}
|
288 |
+
{"current_steps": 288, "total_steps": 390, "loss": 0.2521, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "10:02:54", "remaining_time": "3:33:31"}
|
289 |
+
{"current_steps": 289, "total_steps": 390, "loss": 0.2452, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "10:04:48", "remaining_time": "3:31:22"}
|
290 |
+
{"current_steps": 290, "total_steps": 390, "loss": 0.2413, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "10:06:44", "remaining_time": "3:29:13"}
|
291 |
+
{"current_steps": 291, "total_steps": 390, "loss": 0.2378, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "10:08:50", "remaining_time": "3:27:07"}
|
292 |
+
{"current_steps": 292, "total_steps": 390, "loss": 0.2565, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "10:10:54", "remaining_time": "3:25:01"}
|
293 |
+
{"current_steps": 293, "total_steps": 390, "loss": 0.2608, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "10:13:06", "remaining_time": "3:22:58"}
|
294 |
+
{"current_steps": 294, "total_steps": 390, "loss": 0.248, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "10:15:08", "remaining_time": "3:20:51"}
|
295 |
+
{"current_steps": 295, "total_steps": 390, "loss": 0.2607, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "10:17:05", "remaining_time": "3:18:43"}
|
296 |
+
{"current_steps": 296, "total_steps": 390, "loss": 0.24, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "10:18:59", "remaining_time": "3:16:34"}
|
297 |
+
{"current_steps": 297, "total_steps": 390, "loss": 0.2517, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "10:20:52", "remaining_time": "3:14:24"}
|
298 |
+
{"current_steps": 298, "total_steps": 390, "loss": 0.2293, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "10:22:52", "remaining_time": "3:12:17"}
|
299 |
+
{"current_steps": 299, "total_steps": 390, "loss": 0.2471, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "10:25:05", "remaining_time": "3:10:14"}
|
300 |
+
{"current_steps": 300, "total_steps": 390, "loss": 0.251, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "10:27:04", "remaining_time": "3:08:07"}
|
301 |
+
{"current_steps": 301, "total_steps": 390, "loss": 0.252, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "10:29:11", "remaining_time": "3:06:02"}
|
302 |
+
{"current_steps": 302, "total_steps": 390, "loss": 0.2425, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "10:31:09", "remaining_time": "3:03:54"}
|
303 |
+
{"current_steps": 303, "total_steps": 390, "loss": 0.269, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "10:33:22", "remaining_time": "3:01:51"}
|
304 |
+
{"current_steps": 304, "total_steps": 390, "loss": 0.2626, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "10:35:29", "remaining_time": "2:59:46"}
|
305 |
+
{"current_steps": 305, "total_steps": 390, "loss": 0.2454, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "10:37:26", "remaining_time": "2:57:38"}
|
306 |
+
{"current_steps": 306, "total_steps": 390, "loss": 0.2441, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "10:39:31", "remaining_time": "2:55:33"}
|
307 |
+
{"current_steps": 307, "total_steps": 390, "loss": 0.2596, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "10:41:39", "remaining_time": "2:53:28"}
|
308 |
+
{"current_steps": 308, "total_steps": 390, "loss": 0.2626, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "10:43:36", "remaining_time": "2:51:20"}
|
309 |
+
{"current_steps": 309, "total_steps": 390, "loss": 0.2266, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "10:45:21", "remaining_time": "2:49:10"}
|
310 |
+
{"current_steps": 310, "total_steps": 390, "loss": 0.2551, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "10:47:21", "remaining_time": "2:47:03"}
|
311 |
+
{"current_steps": 311, "total_steps": 390, "loss": 0.2562, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "10:49:20", "remaining_time": "2:44:56"}
|
312 |
+
{"current_steps": 312, "total_steps": 390, "loss": 0.279, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "10:51:18", "remaining_time": "2:42:49"}
|
313 |
+
{"current_steps": 313, "total_steps": 390, "loss": 0.2314, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "10:54:04", "remaining_time": "2:40:54"}
|
314 |
+
{"current_steps": 314, "total_steps": 390, "loss": 0.2259, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "10:56:11", "remaining_time": "2:38:49"}
|