Training in progress, step 3500
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +50 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 645976488
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2718e9d217610e6111d8550e15ee2ef2b49e663758cb1f0851ccaf9563417934
|
3 |
size 645976488
|
trainer_log.jsonl
CHANGED
@@ -303,3 +303,53 @@
|
|
303 |
{"current_steps": 2990, "total_steps": 3537, "loss": 1.5618, "lr": 3.5557937691520382e-06, "epoch": 2.536047497879559, "percentage": 84.53, "elapsed_time": "1:43:39", "remaining_time": "0:18:57"}
|
304 |
{"current_steps": 3000, "total_steps": 3537, "loss": 1.5356, "lr": 3.4300029274990734e-06, "epoch": 2.544529262086514, "percentage": 84.82, "elapsed_time": "1:43:59", "remaining_time": "0:18:36"}
|
305 |
{"current_steps": 3000, "total_steps": 3537, "eval_loss": 1.6116546392440796, "epoch": 2.544529262086514, "percentage": 84.82, "elapsed_time": "1:44:08", "remaining_time": "0:18:38"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
303 |
{"current_steps": 2990, "total_steps": 3537, "loss": 1.5618, "lr": 3.5557937691520382e-06, "epoch": 2.536047497879559, "percentage": 84.53, "elapsed_time": "1:43:39", "remaining_time": "0:18:57"}
|
304 |
{"current_steps": 3000, "total_steps": 3537, "loss": 1.5356, "lr": 3.4300029274990734e-06, "epoch": 2.544529262086514, "percentage": 84.82, "elapsed_time": "1:43:59", "remaining_time": "0:18:36"}
|
305 |
{"current_steps": 3000, "total_steps": 3537, "eval_loss": 1.6116546392440796, "epoch": 2.544529262086514, "percentage": 84.82, "elapsed_time": "1:44:08", "remaining_time": "0:18:38"}
|
306 |
+
{"current_steps": 3010, "total_steps": 3537, "loss": 1.5331, "lr": 3.3063133131172403e-06, "epoch": 2.553011026293469, "percentage": 85.1, "elapsed_time": "1:44:51", "remaining_time": "0:18:21"}
|
307 |
+
{"current_steps": 3020, "total_steps": 3537, "loss": 1.5251, "lr": 3.1847369751500766e-06, "epoch": 2.561492790500424, "percentage": 85.38, "elapsed_time": "1:45:11", "remaining_time": "0:18:00"}
|
308 |
+
{"current_steps": 3030, "total_steps": 3537, "loss": 1.5296, "lr": 3.065285756877684e-06, "epoch": 2.569974554707379, "percentage": 85.67, "elapsed_time": "1:45:32", "remaining_time": "0:17:39"}
|
309 |
+
{"current_steps": 3040, "total_steps": 3537, "loss": 1.5432, "lr": 2.947971294562976e-06, "epoch": 2.578456318914334, "percentage": 85.95, "elapsed_time": "1:45:52", "remaining_time": "0:17:18"}
|
310 |
+
{"current_steps": 3050, "total_steps": 3537, "loss": 1.5209, "lr": 2.8328050163182017e-06, "epoch": 2.5869380831212894, "percentage": 86.23, "elapsed_time": "1:46:12", "remaining_time": "0:16:57"}
|
311 |
+
{"current_steps": 3060, "total_steps": 3537, "loss": 1.5096, "lr": 2.7197981409916416e-06, "epoch": 2.595419847328244, "percentage": 86.51, "elapsed_time": "1:46:33", "remaining_time": "0:16:36"}
|
312 |
+
{"current_steps": 3070, "total_steps": 3537, "loss": 1.5133, "lr": 2.6089616770747394e-06, "epoch": 2.6039016115351994, "percentage": 86.8, "elapsed_time": "1:46:53", "remaining_time": "0:16:15"}
|
313 |
+
{"current_steps": 3080, "total_steps": 3537, "loss": 1.5477, "lr": 2.500306421629728e-06, "epoch": 2.612383375742154, "percentage": 87.08, "elapsed_time": "1:47:13", "remaining_time": "0:15:54"}
|
314 |
+
{"current_steps": 3090, "total_steps": 3537, "loss": 1.5082, "lr": 2.393842959237813e-06, "epoch": 2.6208651399491094, "percentage": 87.36, "elapsed_time": "1:47:34", "remaining_time": "0:15:33"}
|
315 |
+
{"current_steps": 3100, "total_steps": 3537, "loss": 1.5568, "lr": 2.289581660968121e-06, "epoch": 2.6293469041560646, "percentage": 87.64, "elapsed_time": "1:47:54", "remaining_time": "0:15:12"}
|
316 |
+
{"current_steps": 3110, "total_steps": 3537, "loss": 1.5065, "lr": 2.187532683367385e-06, "epoch": 2.6378286683630194, "percentage": 87.93, "elapsed_time": "1:48:14", "remaining_time": "0:14:51"}
|
317 |
+
{"current_steps": 3120, "total_steps": 3537, "loss": 1.5217, "lr": 2.0877059674705464e-06, "epoch": 2.6463104325699747, "percentage": 88.21, "elapsed_time": "1:48:35", "remaining_time": "0:14:30"}
|
318 |
+
{"current_steps": 3130, "total_steps": 3537, "loss": 1.5044, "lr": 1.9901112378323846e-06, "epoch": 2.6547921967769295, "percentage": 88.49, "elapsed_time": "1:48:55", "remaining_time": "0:14:09"}
|
319 |
+
{"current_steps": 3140, "total_steps": 3537, "loss": 1.536, "lr": 1.8947580015801575e-06, "epoch": 2.6632739609838847, "percentage": 88.78, "elapsed_time": "1:49:15", "remaining_time": "0:13:48"}
|
320 |
+
{"current_steps": 3150, "total_steps": 3537, "loss": 1.5325, "lr": 1.8016555474875213e-06, "epoch": 2.67175572519084, "percentage": 89.06, "elapsed_time": "1:49:35", "remaining_time": "0:13:27"}
|
321 |
+
{"current_steps": 3160, "total_steps": 3537, "loss": 1.5302, "lr": 1.710812945069637e-06, "epoch": 2.6802374893977947, "percentage": 89.34, "elapsed_time": "1:49:56", "remaining_time": "0:13:06"}
|
322 |
+
{"current_steps": 3170, "total_steps": 3537, "loss": 1.5353, "lr": 1.622239043699686e-06, "epoch": 2.68871925360475, "percentage": 89.62, "elapsed_time": "1:50:16", "remaining_time": "0:12:46"}
|
323 |
+
{"current_steps": 3180, "total_steps": 3537, "loss": 1.5171, "lr": 1.535942471746807e-06, "epoch": 2.6972010178117047, "percentage": 89.91, "elapsed_time": "1:50:36", "remaining_time": "0:12:25"}
|
324 |
+
{"current_steps": 3190, "total_steps": 3537, "loss": 1.5308, "lr": 1.4519316357355733e-06, "epoch": 2.70568278201866, "percentage": 90.19, "elapsed_time": "1:50:57", "remaining_time": "0:12:04"}
|
325 |
+
{"current_steps": 3200, "total_steps": 3537, "loss": 1.5366, "lr": 1.3702147195270687e-06, "epoch": 2.714164546225615, "percentage": 90.47, "elapsed_time": "1:51:17", "remaining_time": "0:11:43"}
|
326 |
+
{"current_steps": 3210, "total_steps": 3537, "loss": 1.5148, "lr": 1.2907996835216734e-06, "epoch": 2.72264631043257, "percentage": 90.75, "elapsed_time": "1:51:37", "remaining_time": "0:11:22"}
|
327 |
+
{"current_steps": 3220, "total_steps": 3537, "loss": 1.5228, "lr": 1.2136942638835995e-06, "epoch": 2.731128074639525, "percentage": 91.04, "elapsed_time": "1:51:57", "remaining_time": "0:11:01"}
|
328 |
+
{"current_steps": 3230, "total_steps": 3537, "loss": 1.5197, "lr": 1.1389059717872741e-06, "epoch": 2.73960983884648, "percentage": 91.32, "elapsed_time": "1:52:18", "remaining_time": "0:10:40"}
|
329 |
+
{"current_steps": 3240, "total_steps": 3537, "loss": 1.5125, "lr": 1.06644209268566e-06, "epoch": 2.7480916030534353, "percentage": 91.6, "elapsed_time": "1:52:38", "remaining_time": "0:10:19"}
|
330 |
+
{"current_steps": 3250, "total_steps": 3537, "loss": 1.5549, "lr": 9.963096856005216e-07, "epoch": 2.75657336726039, "percentage": 91.89, "elapsed_time": "1:52:58", "remaining_time": "0:09:58"}
|
331 |
+
{"current_steps": 3260, "total_steps": 3537, "loss": 1.5183, "lr": 9.285155824347969e-07, "epoch": 2.7650551314673453, "percentage": 92.17, "elapsed_time": "1:53:19", "remaining_time": "0:09:37"}
|
332 |
+
{"current_steps": 3270, "total_steps": 3537, "loss": 1.5323, "lr": 8.630663873070627e-07, "epoch": 2.7735368956743, "percentage": 92.45, "elapsed_time": "1:53:39", "remaining_time": "0:09:16"}
|
333 |
+
{"current_steps": 3280, "total_steps": 3537, "loss": 1.5202, "lr": 7.999684759082083e-07, "epoch": 2.7820186598812553, "percentage": 92.73, "elapsed_time": "1:53:59", "remaining_time": "0:08:55"}
|
334 |
+
{"current_steps": 3290, "total_steps": 3537, "loss": 1.541, "lr": 7.392279948803371e-07, "epoch": 2.7905004240882105, "percentage": 93.02, "elapsed_time": "1:54:20", "remaining_time": "0:08:35"}
|
335 |
+
{"current_steps": 3300, "total_steps": 3537, "loss": 1.5437, "lr": 6.808508612179937e-07, "epoch": 2.7989821882951653, "percentage": 93.3, "elapsed_time": "1:54:40", "remaining_time": "0:08:14"}
|
336 |
+
{"current_steps": 3310, "total_steps": 3537, "loss": 1.5489, "lr": 6.248427616917907e-07, "epoch": 2.8074639525021206, "percentage": 93.58, "elapsed_time": "1:55:00", "remaining_time": "0:07:53"}
|
337 |
+
{"current_steps": 3320, "total_steps": 3537, "loss": 1.5159, "lr": 5.712091522943996e-07, "epoch": 2.8159457167090753, "percentage": 93.86, "elapsed_time": "1:55:20", "remaining_time": "0:07:32"}
|
338 |
+
{"current_steps": 3330, "total_steps": 3537, "loss": 1.5359, "lr": 5.199552577090927e-07, "epoch": 2.8244274809160306, "percentage": 94.15, "elapsed_time": "1:55:41", "remaining_time": "0:07:11"}
|
339 |
+
{"current_steps": 3340, "total_steps": 3537, "loss": 1.5281, "lr": 4.710860708007553e-07, "epoch": 2.832909245122986, "percentage": 94.43, "elapsed_time": "1:56:01", "remaining_time": "0:06:50"}
|
340 |
+
{"current_steps": 3350, "total_steps": 3537, "loss": 1.511, "lr": 4.2460635212952515e-07, "epoch": 2.8413910093299406, "percentage": 94.71, "elapsed_time": "1:56:21", "remaining_time": "0:06:29"}
|
341 |
+
{"current_steps": 3360, "total_steps": 3537, "loss": 1.5074, "lr": 3.805206294870439e-07, "epoch": 2.849872773536896, "percentage": 95.0, "elapsed_time": "1:56:42", "remaining_time": "0:06:08"}
|
342 |
+
{"current_steps": 3370, "total_steps": 3537, "loss": 1.5001, "lr": 3.388331974553821e-07, "epoch": 2.8583545377438506, "percentage": 95.28, "elapsed_time": "1:57:02", "remaining_time": "0:05:47"}
|
343 |
+
{"current_steps": 3380, "total_steps": 3537, "loss": 1.5362, "lr": 2.995481169886849e-07, "epoch": 2.866836301950806, "percentage": 95.56, "elapsed_time": "1:57:22", "remaining_time": "0:05:27"}
|
344 |
+
{"current_steps": 3390, "total_steps": 3537, "loss": 1.5205, "lr": 2.6266921501758024e-07, "epoch": 2.875318066157761, "percentage": 95.84, "elapsed_time": "1:57:42", "remaining_time": "0:05:06"}
|
345 |
+
{"current_steps": 3400, "total_steps": 3537, "loss": 1.5117, "lr": 2.2820008407637983e-07, "epoch": 2.883799830364716, "percentage": 96.13, "elapsed_time": "1:58:03", "remaining_time": "0:04:45"}
|
346 |
+
{"current_steps": 3410, "total_steps": 3537, "loss": 1.5184, "lr": 1.9614408195310907e-07, "epoch": 2.8922815945716707, "percentage": 96.41, "elapsed_time": "1:58:23", "remaining_time": "0:04:24"}
|
347 |
+
{"current_steps": 3420, "total_steps": 3537, "loss": 1.5141, "lr": 1.6650433136241872e-07, "epoch": 2.900763358778626, "percentage": 96.69, "elapsed_time": "1:58:43", "remaining_time": "0:04:03"}
|
348 |
+
{"current_steps": 3430, "total_steps": 3537, "loss": 1.5328, "lr": 1.3928371964138653e-07, "epoch": 2.909245122985581, "percentage": 96.97, "elapsed_time": "1:59:04", "remaining_time": "0:03:42"}
|
349 |
+
{"current_steps": 3440, "total_steps": 3537, "loss": 1.5251, "lr": 1.1448489846824228e-07, "epoch": 2.917726887192536, "percentage": 97.26, "elapsed_time": "1:59:24", "remaining_time": "0:03:22"}
|
350 |
+
{"current_steps": 3450, "total_steps": 3537, "loss": 1.5303, "lr": 9.211028360406326e-08, "epoch": 2.926208651399491, "percentage": 97.54, "elapsed_time": "1:59:44", "remaining_time": "0:03:01"}
|
351 |
+
{"current_steps": 3460, "total_steps": 3537, "loss": 1.5128, "lr": 7.216205465743753e-08, "epoch": 2.934690415606446, "percentage": 97.82, "elapsed_time": "2:00:05", "remaining_time": "0:02:40"}
|
352 |
+
{"current_steps": 3470, "total_steps": 3537, "loss": 1.5382, "lr": 5.464215487214763e-08, "epoch": 2.943172179813401, "percentage": 98.11, "elapsed_time": "2:00:25", "remaining_time": "0:02:19"}
|
353 |
+
{"current_steps": 3480, "total_steps": 3537, "loss": 1.5374, "lr": 3.95522909378665e-08, "epoch": 2.9516539440203564, "percentage": 98.39, "elapsed_time": "2:00:45", "remaining_time": "0:01:58"}
|
354 |
+
{"current_steps": 3490, "total_steps": 3537, "loss": 1.5138, "lr": 2.6893932823898738e-08, "epoch": 2.960135708227311, "percentage": 98.67, "elapsed_time": "2:01:06", "remaining_time": "0:01:37"}
|
355 |
+
{"current_steps": 3500, "total_steps": 3537, "loss": 1.5293, "lr": 1.666831363598964e-08, "epoch": 2.9686174724342664, "percentage": 98.95, "elapsed_time": "2:01:26", "remaining_time": "0:01:17"}
|