sedrickkeh commited on
Commit
3381a09
·
verified ·
1 Parent(s): 569dac6

Training in progress, epoch 5

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b32584ff74829ef6d25dd444b927b40d9c2f3c65c13f83eeca11759d9c0fa4bc
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9f78ca2f324c5e60bba34a1fb15eeedad4f2abd3f76465aee39a7853109f4c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7152740923a6f105daa1d052b5c7b1f00579a8db40370c936401475b3397614c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7b87132e20464a498f66663612f62a092f3f38d15662f12ae53b67dbf40336
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c7e927606cafa755a84206b47fe7dd6afe747090d14eaf9b2ed64fdce5fb96f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ecc3d7ead39c09f6232732e54de8918808b4b45a35624348250be1bb1cc58c3
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00c66d7324409d6d79a23be44b2a75fdd823641824fc6f1aac931d4651048cbf
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378ef395d97ffafe11775d5a4e77a3f46fd72121930f5267cb1987f2d0286cb1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -278,3 +278,58 @@
278
  {"current_steps": 2740, "total_steps": 4392, "loss": 0.5947, "lr": 5e-06, "epoch": 4.988620846609012, "percentage": 62.39, "elapsed_time": "1 day, 0:57:47", "remaining_time": "15:03:03"}
279
  {"current_steps": 2746, "total_steps": 4392, "eval_loss": 0.7756755352020264, "epoch": 4.999544833864361, "percentage": 62.52, "elapsed_time": "1 day, 1:07:27", "remaining_time": "15:03:35"}
280
  {"current_steps": 2750, "total_steps": 4392, "loss": 0.6175, "lr": 5e-06, "epoch": 5.006827492034593, "percentage": 62.61, "elapsed_time": "1 day, 1:10:47", "remaining_time": "15:02:04"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
278
  {"current_steps": 2740, "total_steps": 4392, "loss": 0.5947, "lr": 5e-06, "epoch": 4.988620846609012, "percentage": 62.39, "elapsed_time": "1 day, 0:57:47", "remaining_time": "15:03:03"}
279
  {"current_steps": 2746, "total_steps": 4392, "eval_loss": 0.7756755352020264, "epoch": 4.999544833864361, "percentage": 62.52, "elapsed_time": "1 day, 1:07:27", "remaining_time": "15:03:35"}
280
  {"current_steps": 2750, "total_steps": 4392, "loss": 0.6175, "lr": 5e-06, "epoch": 5.006827492034593, "percentage": 62.61, "elapsed_time": "1 day, 1:10:47", "remaining_time": "15:02:04"}
281
+ {"current_steps": 2760, "total_steps": 4392, "loss": 0.5284, "lr": 5e-06, "epoch": 5.025034137460173, "percentage": 62.84, "elapsed_time": "1 day, 1:16:08", "remaining_time": "14:56:30"}
282
+ {"current_steps": 2770, "total_steps": 4392, "loss": 0.5308, "lr": 5e-06, "epoch": 5.0432407828857535, "percentage": 63.07, "elapsed_time": "1 day, 1:21:30", "remaining_time": "14:50:56"}
283
+ {"current_steps": 2780, "total_steps": 4392, "loss": 0.5312, "lr": 5e-06, "epoch": 5.061447428311333, "percentage": 63.3, "elapsed_time": "1 day, 1:26:53", "remaining_time": "14:45:22"}
284
+ {"current_steps": 2790, "total_steps": 4392, "loss": 0.5304, "lr": 5e-06, "epoch": 5.079654073736914, "percentage": 63.52, "elapsed_time": "1 day, 1:32:14", "remaining_time": "14:39:47"}
285
+ {"current_steps": 2800, "total_steps": 4392, "loss": 0.5279, "lr": 5e-06, "epoch": 5.097860719162495, "percentage": 63.75, "elapsed_time": "1 day, 1:37:36", "remaining_time": "14:34:14"}
286
+ {"current_steps": 2810, "total_steps": 4392, "loss": 0.5363, "lr": 5e-06, "epoch": 5.1160673645880745, "percentage": 63.98, "elapsed_time": "1 day, 1:42:58", "remaining_time": "14:28:40"}
287
+ {"current_steps": 2820, "total_steps": 4392, "loss": 0.5338, "lr": 5e-06, "epoch": 5.134274010013655, "percentage": 64.21, "elapsed_time": "1 day, 1:48:20", "remaining_time": "14:23:06"}
288
+ {"current_steps": 2830, "total_steps": 4392, "loss": 0.5321, "lr": 5e-06, "epoch": 5.152480655439235, "percentage": 64.44, "elapsed_time": "1 day, 1:53:42", "remaining_time": "14:17:33"}
289
+ {"current_steps": 2840, "total_steps": 4392, "loss": 0.534, "lr": 5e-06, "epoch": 5.170687300864816, "percentage": 64.66, "elapsed_time": "1 day, 1:59:05", "remaining_time": "14:12:00"}
290
+ {"current_steps": 2850, "total_steps": 4392, "loss": 0.5363, "lr": 5e-06, "epoch": 5.188893946290396, "percentage": 64.89, "elapsed_time": "1 day, 2:04:27", "remaining_time": "14:06:27"}
291
+ {"current_steps": 2860, "total_steps": 4392, "loss": 0.534, "lr": 5e-06, "epoch": 5.207100591715976, "percentage": 65.12, "elapsed_time": "1 day, 2:09:49", "remaining_time": "14:00:54"}
292
+ {"current_steps": 2870, "total_steps": 4392, "loss": 0.5349, "lr": 5e-06, "epoch": 5.225307237141557, "percentage": 65.35, "elapsed_time": "1 day, 2:15:12", "remaining_time": "13:55:21"}
293
+ {"current_steps": 2880, "total_steps": 4392, "loss": 0.534, "lr": 5e-06, "epoch": 5.243513882567137, "percentage": 65.57, "elapsed_time": "1 day, 2:20:32", "remaining_time": "13:49:46"}
294
+ {"current_steps": 2890, "total_steps": 4392, "loss": 0.5368, "lr": 5e-06, "epoch": 5.2617205279927175, "percentage": 65.8, "elapsed_time": "1 day, 2:25:53", "remaining_time": "13:44:13"}
295
+ {"current_steps": 2900, "total_steps": 4392, "loss": 0.5348, "lr": 5e-06, "epoch": 5.279927173418297, "percentage": 66.03, "elapsed_time": "1 day, 2:31:16", "remaining_time": "13:38:41"}
296
+ {"current_steps": 2910, "total_steps": 4392, "loss": 0.539, "lr": 5e-06, "epoch": 5.298133818843878, "percentage": 66.26, "elapsed_time": "1 day, 2:36:36", "remaining_time": "13:33:07"}
297
+ {"current_steps": 2920, "total_steps": 4392, "loss": 0.5354, "lr": 5e-06, "epoch": 5.316340464269459, "percentage": 66.48, "elapsed_time": "1 day, 2:41:57", "remaining_time": "13:27:33"}
298
+ {"current_steps": 2930, "total_steps": 4392, "loss": 0.538, "lr": 5e-06, "epoch": 5.3345471096950385, "percentage": 66.71, "elapsed_time": "1 day, 2:47:18", "remaining_time": "13:22:00"}
299
+ {"current_steps": 2940, "total_steps": 4392, "loss": 0.5388, "lr": 5e-06, "epoch": 5.352753755120619, "percentage": 66.94, "elapsed_time": "1 day, 2:52:38", "remaining_time": "13:16:26"}
300
+ {"current_steps": 2950, "total_steps": 4392, "loss": 0.5387, "lr": 5e-06, "epoch": 5.370960400546199, "percentage": 67.17, "elapsed_time": "1 day, 2:57:59", "remaining_time": "13:10:53"}
301
+ {"current_steps": 2960, "total_steps": 4392, "loss": 0.5392, "lr": 5e-06, "epoch": 5.38916704597178, "percentage": 67.4, "elapsed_time": "1 day, 3:03:21", "remaining_time": "13:05:21"}
302
+ {"current_steps": 2970, "total_steps": 4392, "loss": 0.5393, "lr": 5e-06, "epoch": 5.4073736913973605, "percentage": 67.62, "elapsed_time": "1 day, 3:08:42", "remaining_time": "12:59:48"}
303
+ {"current_steps": 2980, "total_steps": 4392, "loss": 0.5406, "lr": 5e-06, "epoch": 5.42558033682294, "percentage": 67.85, "elapsed_time": "1 day, 3:14:04", "remaining_time": "12:54:15"}
304
+ {"current_steps": 2990, "total_steps": 4392, "loss": 0.5368, "lr": 5e-06, "epoch": 5.443786982248521, "percentage": 68.08, "elapsed_time": "1 day, 3:19:26", "remaining_time": "12:48:43"}
305
+ {"current_steps": 3000, "total_steps": 4392, "loss": 0.5403, "lr": 5e-06, "epoch": 5.461993627674101, "percentage": 68.31, "elapsed_time": "1 day, 3:24:48", "remaining_time": "12:43:11"}
306
+ {"current_steps": 3010, "total_steps": 4392, "loss": 0.5411, "lr": 5e-06, "epoch": 5.4802002730996815, "percentage": 68.53, "elapsed_time": "1 day, 3:30:09", "remaining_time": "12:37:39"}
307
+ {"current_steps": 3020, "total_steps": 4392, "loss": 0.5411, "lr": 5e-06, "epoch": 5.498406918525261, "percentage": 68.76, "elapsed_time": "1 day, 3:35:32", "remaining_time": "12:32:07"}
308
+ {"current_steps": 3030, "total_steps": 4392, "loss": 0.5433, "lr": 5e-06, "epoch": 5.516613563950842, "percentage": 68.99, "elapsed_time": "1 day, 3:40:54", "remaining_time": "12:26:35"}
309
+ {"current_steps": 3040, "total_steps": 4392, "loss": 0.5459, "lr": 5e-06, "epoch": 5.534820209376423, "percentage": 69.22, "elapsed_time": "1 day, 3:46:16", "remaining_time": "12:21:03"}
310
+ {"current_steps": 3050, "total_steps": 4392, "loss": 0.5456, "lr": 5e-06, "epoch": 5.5530268548020025, "percentage": 69.44, "elapsed_time": "1 day, 3:51:38", "remaining_time": "12:15:31"}
311
+ {"current_steps": 3060, "total_steps": 4392, "loss": 0.5434, "lr": 5e-06, "epoch": 5.571233500227583, "percentage": 69.67, "elapsed_time": "1 day, 3:57:01", "remaining_time": "12:09:59"}
312
+ {"current_steps": 3070, "total_steps": 4392, "loss": 0.5381, "lr": 5e-06, "epoch": 5.589440145653163, "percentage": 69.9, "elapsed_time": "1 day, 4:02:23", "remaining_time": "12:04:28"}
313
+ {"current_steps": 3080, "total_steps": 4392, "loss": 0.5424, "lr": 5e-06, "epoch": 5.607646791078744, "percentage": 70.13, "elapsed_time": "1 day, 4:07:44", "remaining_time": "11:58:55"}
314
+ {"current_steps": 3090, "total_steps": 4392, "loss": 0.5434, "lr": 5e-06, "epoch": 5.6258534365043245, "percentage": 70.36, "elapsed_time": "1 day, 4:13:06", "remaining_time": "11:53:24"}
315
+ {"current_steps": 3100, "total_steps": 4392, "loss": 0.5456, "lr": 5e-06, "epoch": 5.644060081929904, "percentage": 70.58, "elapsed_time": "1 day, 4:18:29", "remaining_time": "11:47:53"}
316
+ {"current_steps": 3110, "total_steps": 4392, "loss": 0.5437, "lr": 5e-06, "epoch": 5.662266727355485, "percentage": 70.81, "elapsed_time": "1 day, 4:23:50", "remaining_time": "11:42:21"}
317
+ {"current_steps": 3120, "total_steps": 4392, "loss": 0.543, "lr": 5e-06, "epoch": 5.680473372781065, "percentage": 71.04, "elapsed_time": "1 day, 4:29:13", "remaining_time": "11:36:50"}
318
+ {"current_steps": 3130, "total_steps": 4392, "loss": 0.5456, "lr": 5e-06, "epoch": 5.6986800182066455, "percentage": 71.27, "elapsed_time": "1 day, 4:34:35", "remaining_time": "11:31:18"}
319
+ {"current_steps": 3140, "total_steps": 4392, "loss": 0.5488, "lr": 5e-06, "epoch": 5.716886663632225, "percentage": 71.49, "elapsed_time": "1 day, 4:39:57", "remaining_time": "11:25:47"}
320
+ {"current_steps": 3150, "total_steps": 4392, "loss": 0.5461, "lr": 5e-06, "epoch": 5.735093309057806, "percentage": 71.72, "elapsed_time": "1 day, 4:45:19", "remaining_time": "11:20:16"}
321
+ {"current_steps": 3160, "total_steps": 4392, "loss": 0.548, "lr": 5e-06, "epoch": 5.753299954483387, "percentage": 71.95, "elapsed_time": "1 day, 4:50:41", "remaining_time": "11:14:45"}
322
+ {"current_steps": 3170, "total_steps": 4392, "loss": 0.5471, "lr": 5e-06, "epoch": 5.7715065999089665, "percentage": 72.18, "elapsed_time": "1 day, 4:56:04", "remaining_time": "11:09:14"}
323
+ {"current_steps": 3180, "total_steps": 4392, "loss": 0.5435, "lr": 5e-06, "epoch": 5.789713245334547, "percentage": 72.4, "elapsed_time": "1 day, 5:01:25", "remaining_time": "11:03:42"}
324
+ {"current_steps": 3190, "total_steps": 4392, "loss": 0.5485, "lr": 5e-06, "epoch": 5.807919890760127, "percentage": 72.63, "elapsed_time": "1 day, 5:06:46", "remaining_time": "10:58:11"}
325
+ {"current_steps": 3200, "total_steps": 4392, "loss": 0.5442, "lr": 5e-06, "epoch": 5.826126536185708, "percentage": 72.86, "elapsed_time": "1 day, 5:12:09", "remaining_time": "10:52:40"}
326
+ {"current_steps": 3210, "total_steps": 4392, "loss": 0.545, "lr": 5e-06, "epoch": 5.8443331816112885, "percentage": 73.09, "elapsed_time": "1 day, 5:17:31", "remaining_time": "10:47:09"}
327
+ {"current_steps": 3220, "total_steps": 4392, "loss": 0.5476, "lr": 5e-06, "epoch": 5.862539827036868, "percentage": 73.32, "elapsed_time": "1 day, 5:22:50", "remaining_time": "10:41:37"}
328
+ {"current_steps": 3230, "total_steps": 4392, "loss": 0.5496, "lr": 5e-06, "epoch": 5.880746472462449, "percentage": 73.54, "elapsed_time": "1 day, 5:28:10", "remaining_time": "10:36:06"}
329
+ {"current_steps": 3240, "total_steps": 4392, "loss": 0.5467, "lr": 5e-06, "epoch": 5.898953117888029, "percentage": 73.77, "elapsed_time": "1 day, 5:33:29", "remaining_time": "10:30:34"}
330
+ {"current_steps": 3250, "total_steps": 4392, "loss": 0.5498, "lr": 5e-06, "epoch": 5.9171597633136095, "percentage": 74.0, "elapsed_time": "1 day, 5:38:50", "remaining_time": "10:25:03"}
331
+ {"current_steps": 3260, "total_steps": 4392, "loss": 0.5457, "lr": 5e-06, "epoch": 5.93536640873919, "percentage": 74.23, "elapsed_time": "1 day, 5:44:09", "remaining_time": "10:19:31"}
332
+ {"current_steps": 3270, "total_steps": 4392, "loss": 0.5484, "lr": 5e-06, "epoch": 5.95357305416477, "percentage": 74.45, "elapsed_time": "1 day, 5:49:31", "remaining_time": "10:14:01"}
333
+ {"current_steps": 3280, "total_steps": 4392, "loss": 0.5522, "lr": 5e-06, "epoch": 5.971779699590351, "percentage": 74.68, "elapsed_time": "1 day, 5:54:53", "remaining_time": "10:08:30"}
334
+ {"current_steps": 3290, "total_steps": 4392, "loss": 0.5504, "lr": 5e-06, "epoch": 5.9899863450159305, "percentage": 74.91, "elapsed_time": "1 day, 6:00:16", "remaining_time": "10:03:00"}
335
+ {"current_steps": 3295, "total_steps": 4392, "eval_loss": 0.8121561408042908, "epoch": 5.999089667728721, "percentage": 75.02, "elapsed_time": "1 day, 6:09:36", "remaining_time": "10:02:28"}