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 sha256:29e5fc1de9d81ce2b45a73ed8394a27abcf1139c15b9c86d8ef4ecc85942e8a5
|
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:d29e6c5f2fabfe3b6764bbaf6949ce9cae752ce01397444e97322b43d5c8822b
|
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:fb130427b151a5599083c99e7d1ed08955a7262e83c3c40eb088038563e1adf0
|
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:bf7a7215cfba49d0db824e8adf243cec63e31ca6bf57b625f172317731af74df
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -235,3 +235,81 @@
|
|
235 |
{"current_steps": 235, "total_steps": 390, "loss": 0.352, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "5:51:08", "remaining_time": "3:51:36"}
|
236 |
{"current_steps": 236, "total_steps": 390, "loss": 0.2892, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "5:52:31", "remaining_time": "3:50:02"}
|
237 |
{"current_steps": 237, "total_steps": 390, "loss": 0.304, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "5:54:06", "remaining_time": "3:48:36"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
235 |
{"current_steps": 235, "total_steps": 390, "loss": 0.352, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "5:51:08", "remaining_time": "3:51:36"}
|
236 |
{"current_steps": 236, "total_steps": 390, "loss": 0.2892, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "5:52:31", "remaining_time": "3:50:02"}
|
237 |
{"current_steps": 237, "total_steps": 390, "loss": 0.304, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "5:54:06", "remaining_time": "3:48:36"}
|
238 |
+
{"current_steps": 238, "total_steps": 390, "loss": 0.304, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "5:55:28", "remaining_time": "3:47:01"}
|
239 |
+
{"current_steps": 239, "total_steps": 390, "loss": 0.301, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "5:56:48", "remaining_time": "3:45:26"}
|
240 |
+
{"current_steps": 240, "total_steps": 390, "loss": 0.3283, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "5:58:40", "remaining_time": "3:44:10"}
|
241 |
+
{"current_steps": 241, "total_steps": 390, "loss": 0.3123, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "6:00:21", "remaining_time": "3:42:47"}
|
242 |
+
{"current_steps": 242, "total_steps": 390, "loss": 0.3099, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "6:01:51", "remaining_time": "3:41:17"}
|
243 |
+
{"current_steps": 243, "total_steps": 390, "loss": 0.2901, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "6:03:27", "remaining_time": "3:39:52"}
|
244 |
+
{"current_steps": 244, "total_steps": 390, "loss": 0.3431, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "6:05:04", "remaining_time": "3:38:26"}
|
245 |
+
{"current_steps": 245, "total_steps": 390, "loss": 0.3072, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "6:06:25", "remaining_time": "3:36:52"}
|
246 |
+
{"current_steps": 246, "total_steps": 390, "loss": 0.2894, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "6:07:54", "remaining_time": "3:35:21"}
|
247 |
+
{"current_steps": 247, "total_steps": 390, "loss": 0.2742, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "6:09:10", "remaining_time": "3:33:43"}
|
248 |
+
{"current_steps": 248, "total_steps": 390, "loss": 0.3073, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "6:10:38", "remaining_time": "3:32:13"}
|
249 |
+
{"current_steps": 249, "total_steps": 390, "loss": 0.2831, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "6:11:55", "remaining_time": "3:30:36"}
|
250 |
+
{"current_steps": 250, "total_steps": 390, "loss": 0.2852, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "6:13:23", "remaining_time": "3:29:06"}
|
251 |
+
{"current_steps": 251, "total_steps": 390, "loss": 0.2782, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "6:14:45", "remaining_time": "3:27:32"}
|
252 |
+
{"current_steps": 252, "total_steps": 390, "loss": 0.2822, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "6:16:10", "remaining_time": "3:26:00"}
|
253 |
+
{"current_steps": 253, "total_steps": 390, "loss": 0.2772, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "6:17:34", "remaining_time": "3:24:27"}
|
254 |
+
{"current_steps": 254, "total_steps": 390, "loss": 0.2696, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "6:19:06", "remaining_time": "3:22:59"}
|
255 |
+
{"current_steps": 255, "total_steps": 390, "loss": 0.2842, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "6:20:39", "remaining_time": "3:21:31"}
|
256 |
+
{"current_steps": 256, "total_steps": 390, "loss": 0.2807, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "6:22:19", "remaining_time": "3:20:07"}
|
257 |
+
{"current_steps": 257, "total_steps": 390, "loss": 0.3328, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "6:23:51", "remaining_time": "3:18:39"}
|
258 |
+
{"current_steps": 258, "total_steps": 390, "loss": 0.2927, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "6:25:14", "remaining_time": "3:17:06"}
|
259 |
+
{"current_steps": 259, "total_steps": 390, "loss": 0.3151, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "6:26:45", "remaining_time": "3:15:37"}
|
260 |
+
{"current_steps": 260, "total_steps": 390, "loss": 0.2961, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "6:28:12", "remaining_time": "3:14:06"}
|
261 |
+
{"current_steps": 261, "total_steps": 390, "loss": 0.2817, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "6:29:47", "remaining_time": "3:12:39"}
|
262 |
+
{"current_steps": 262, "total_steps": 390, "loss": 0.2963, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "6:31:19", "remaining_time": "3:11:11"}
|
263 |
+
{"current_steps": 263, "total_steps": 390, "loss": 0.3033, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "6:32:54", "remaining_time": "3:09:43"}
|
264 |
+
{"current_steps": 264, "total_steps": 390, "loss": 0.287, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "6:34:26", "remaining_time": "3:08:15"}
|
265 |
+
{"current_steps": 265, "total_steps": 390, "loss": 0.2809, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "6:35:44", "remaining_time": "3:06:40"}
|
266 |
+
{"current_steps": 266, "total_steps": 390, "loss": 0.3117, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "6:37:11", "remaining_time": "3:05:09"}
|
267 |
+
{"current_steps": 267, "total_steps": 390, "loss": 0.29, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "6:38:27", "remaining_time": "3:03:33"}
|
268 |
+
{"current_steps": 268, "total_steps": 390, "loss": 0.2819, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "6:39:55", "remaining_time": "3:02:03"}
|
269 |
+
{"current_steps": 269, "total_steps": 390, "loss": 0.2732, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "6:41:14", "remaining_time": "3:00:29"}
|
270 |
+
{"current_steps": 270, "total_steps": 390, "loss": 0.262, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "6:42:38", "remaining_time": "2:58:57"}
|
271 |
+
{"current_steps": 271, "total_steps": 390, "loss": 0.284, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "6:44:09", "remaining_time": "2:57:28"}
|
272 |
+
{"current_steps": 272, "total_steps": 390, "loss": 0.2846, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "6:45:37", "remaining_time": "2:55:58"}
|
273 |
+
{"current_steps": 273, "total_steps": 390, "loss": 0.2675, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "6:47:00", "remaining_time": "2:54:25"}
|
274 |
+
{"current_steps": 274, "total_steps": 390, "loss": 0.2646, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "6:48:22", "remaining_time": "2:52:53"}
|
275 |
+
{"current_steps": 275, "total_steps": 390, "loss": 0.2762, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "6:49:51", "remaining_time": "2:51:23"}
|
276 |
+
{"current_steps": 276, "total_steps": 390, "loss": 0.2953, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "6:51:28", "remaining_time": "2:49:57"}
|
277 |
+
{"current_steps": 277, "total_steps": 390, "loss": 0.3223, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "6:53:01", "remaining_time": "2:48:29"}
|
278 |
+
{"current_steps": 278, "total_steps": 390, "loss": 0.2684, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "6:54:28", "remaining_time": "2:46:59"}
|
279 |
+
{"current_steps": 279, "total_steps": 390, "loss": 0.2823, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "6:55:51", "remaining_time": "2:45:27"}
|
280 |
+
{"current_steps": 280, "total_steps": 390, "loss": 0.3021, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "6:57:14", "remaining_time": "2:43:55"}
|
281 |
+
{"current_steps": 281, "total_steps": 390, "loss": 0.3036, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "6:58:33", "remaining_time": "2:42:21"}
|
282 |
+
{"current_steps": 282, "total_steps": 390, "loss": 0.2785, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "6:59:54", "remaining_time": "2:40:48"}
|
283 |
+
{"current_steps": 283, "total_steps": 390, "loss": 0.2912, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "7:01:09", "remaining_time": "2:39:14"}
|
284 |
+
{"current_steps": 284, "total_steps": 390, "loss": 0.2945, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "7:02:36", "remaining_time": "2:37:44"}
|
285 |
+
{"current_steps": 285, "total_steps": 390, "loss": 0.2633, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "7:03:57", "remaining_time": "2:36:11"}
|
286 |
+
{"current_steps": 286, "total_steps": 390, "loss": 0.2852, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "7:05:27", "remaining_time": "2:34:42"}
|
287 |
+
{"current_steps": 287, "total_steps": 390, "loss": 0.2757, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "7:06:51", "remaining_time": "2:33:11"}
|
288 |
+
{"current_steps": 288, "total_steps": 390, "loss": 0.2795, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "7:08:14", "remaining_time": "2:31:39"}
|
289 |
+
{"current_steps": 289, "total_steps": 390, "loss": 0.2785, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "7:09:41", "remaining_time": "2:30:10"}
|
290 |
+
{"current_steps": 290, "total_steps": 390, "loss": 0.2974, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "7:11:14", "remaining_time": "2:28:42"}
|
291 |
+
{"current_steps": 291, "total_steps": 390, "loss": 0.2573, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "7:12:30", "remaining_time": "2:27:08"}
|
292 |
+
{"current_steps": 292, "total_steps": 390, "loss": 0.2612, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "7:13:48", "remaining_time": "2:25:35"}
|
293 |
+
{"current_steps": 293, "total_steps": 390, "loss": 0.2853, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "7:15:26", "remaining_time": "2:24:09"}
|
294 |
+
{"current_steps": 294, "total_steps": 390, "loss": 0.3063, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "7:17:01", "remaining_time": "2:22:41"}
|
295 |
+
{"current_steps": 295, "total_steps": 390, "loss": 0.3334, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "7:18:50", "remaining_time": "2:21:19"}
|
296 |
+
{"current_steps": 296, "total_steps": 390, "loss": 0.3178, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "7:20:18", "remaining_time": "2:19:49"}
|
297 |
+
{"current_steps": 297, "total_steps": 390, "loss": 0.3078, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "7:22:03", "remaining_time": "2:18:25"}
|
298 |
+
{"current_steps": 298, "total_steps": 390, "loss": 0.2826, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "7:23:19", "remaining_time": "2:16:52"}
|
299 |
+
{"current_steps": 299, "total_steps": 390, "loss": 0.2857, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "7:24:40", "remaining_time": "2:15:20"}
|
300 |
+
{"current_steps": 300, "total_steps": 390, "loss": 0.286, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "7:26:00", "remaining_time": "2:13:48"}
|
301 |
+
{"current_steps": 301, "total_steps": 390, "loss": 0.2884, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "7:27:26", "remaining_time": "2:12:17"}
|
302 |
+
{"current_steps": 302, "total_steps": 390, "loss": 0.2967, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "7:28:59", "remaining_time": "2:10:49"}
|
303 |
+
{"current_steps": 303, "total_steps": 390, "loss": 0.2649, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "7:30:28", "remaining_time": "2:09:20"}
|
304 |
+
{"current_steps": 304, "total_steps": 390, "loss": 0.2538, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "7:31:39", "remaining_time": "2:07:46"}
|
305 |
+
{"current_steps": 305, "total_steps": 390, "loss": 0.2887, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "7:33:12", "remaining_time": "2:06:18"}
|
306 |
+
{"current_steps": 306, "total_steps": 390, "loss": 0.2905, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "7:34:24", "remaining_time": "2:04:44"}
|
307 |
+
{"current_steps": 307, "total_steps": 390, "loss": 0.3102, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "7:35:48", "remaining_time": "2:03:13"}
|
308 |
+
{"current_steps": 308, "total_steps": 390, "loss": 0.2895, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "7:37:13", "remaining_time": "2:01:43"}
|
309 |
+
{"current_steps": 309, "total_steps": 390, "loss": 0.3035, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "7:38:59", "remaining_time": "2:00:19"}
|
310 |
+
{"current_steps": 310, "total_steps": 390, "loss": 0.3029, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "7:40:43", "remaining_time": "1:58:53"}
|
311 |
+
{"current_steps": 311, "total_steps": 390, "loss": 0.2916, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "7:42:00", "remaining_time": "1:57:21"}
|
312 |
+
{"current_steps": 312, "total_steps": 390, "loss": 0.2972, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "7:43:36", "remaining_time": "1:55:54"}
|
313 |
+
{"current_steps": 313, "total_steps": 390, "loss": 0.2832, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "7:46:24", "remaining_time": "1:54:44"}
|
314 |
+
{"current_steps": 314, "total_steps": 390, "loss": 0.2363, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "7:47:52", "remaining_time": "1:53:14"}
|
315 |
+
{"current_steps": 315, "total_steps": 390, "loss": 0.2323, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "7:49:21", "remaining_time": "1:51:45"}
|