EtashGuha commited on
Commit
b793e75
·
verified ·
1 Parent(s): 18c4d47

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a29d3262695bba3e3439a626b95536341574005eaadb126f842028c4ea6aee
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b079b97133531b1ba00bae37df370b204ea37948f2859505119ec72e3b4582f9
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8370e8f729999c7e755e7a37e7a5ae848baa7a16b881255b6dfaa2a019b93510
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75130cfb4403c5bef9ee704e44d5f5eea81fea875dd5fe3a6e32c34bb933f284
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8774445db58cc6ed7cf4b3cb465af654725e9e158540fc91339197ff147ae251
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5700a655542266ddcaff5823e922faba697380c1376e47f333146f135a718fa6
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17a725d72bdac3560bc38b8dafd56c4fd6e664bbab764c2c03d3282a37097546
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0dd3cdcc8e6a0db85cdd505fe2c49b68828efa650a428c7e6893d608bf5b16
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -313,3 +313,79 @@
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2735, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "3:58:26", "remaining_time": "0:58:39"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2568, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "3:59:09", "remaining_time": "0:57:53"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.2571, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "3:59:53", "remaining_time": "0:57:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2735, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "3:58:26", "remaining_time": "0:58:39"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2568, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "3:59:09", "remaining_time": "0:57:53"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.2571, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "3:59:53", "remaining_time": "0:57:07"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.2577, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "4:00:37", "remaining_time": "0:56:21"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.2504, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "4:01:21", "remaining_time": "0:55:34"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.261, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "4:02:06", "remaining_time": "0:54:49"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.2461, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "4:02:52", "remaining_time": "0:54:03"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.2558, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "4:03:37", "remaining_time": "0:53:17"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.2505, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "4:04:22", "remaining_time": "0:52:31"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.2483, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "4:05:04", "remaining_time": "0:51:45"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.2577, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "4:05:48", "remaining_time": "0:50:59"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.2597, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "4:06:33", "remaining_time": "0:50:13"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.2543, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "4:07:19", "remaining_time": "0:49:27"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.2564, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "4:08:03", "remaining_time": "0:48:41"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.2546, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "4:08:48", "remaining_time": "0:47:56"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.2524, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "4:09:32", "remaining_time": "0:47:10"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.2491, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "4:10:17", "remaining_time": "0:46:24"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.2454, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "4:11:03", "remaining_time": "0:45:38"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.2648, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "4:11:46", "remaining_time": "0:44:52"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.2503, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "4:12:32", "remaining_time": "0:44:07"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.2415, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "4:13:14", "remaining_time": "0:43:20"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.261, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "4:14:00", "remaining_time": "0:42:35"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.2564, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "4:14:44", "remaining_time": "0:41:49"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.2446, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "4:15:28", "remaining_time": "0:41:03"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.2484, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "4:16:12", "remaining_time": "0:40:17"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.2601, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "4:16:59", "remaining_time": "0:39:32"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.2528, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "4:17:44", "remaining_time": "0:38:46"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.2614, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "4:18:28", "remaining_time": "0:38:00"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.2536, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "4:19:13", "remaining_time": "0:37:14"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.2506, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "4:20:00", "remaining_time": "0:36:29"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.2387, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "4:20:43", "remaining_time": "0:35:43"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.2472, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "4:21:27", "remaining_time": "0:34:57"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.25, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "4:22:12", "remaining_time": "0:34:12"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.252, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "4:22:54", "remaining_time": "0:33:25"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.2552, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "4:23:37", "remaining_time": "0:32:40"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.2491, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "4:24:20", "remaining_time": "0:31:54"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.2466, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "4:25:04", "remaining_time": "0:31:08"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.2437, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "4:25:49", "remaining_time": "0:30:22"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.2567, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "4:26:32", "remaining_time": "0:29:36"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.2442, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "4:27:15", "remaining_time": "0:28:51"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.2488, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "4:28:01", "remaining_time": "0:28:05"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.261, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "4:28:46", "remaining_time": "0:27:19"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.2446, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "4:29:29", "remaining_time": "0:26:34"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.2554, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "4:30:14", "remaining_time": "0:25:48"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.2343, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "4:30:58", "remaining_time": "0:25:02"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.2503, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "4:31:44", "remaining_time": "0:24:17"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.2524, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "4:32:29", "remaining_time": "0:23:31"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.2583, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "4:33:16", "remaining_time": "0:22:46"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.2509, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "4:34:01", "remaining_time": "0:22:00"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.2557, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "4:34:45", "remaining_time": "0:21:15"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.2487, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "4:35:28", "remaining_time": "0:20:29"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.2615, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "4:36:11", "remaining_time": "0:19:43"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.2529, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "4:36:54", "remaining_time": "0:18:57"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.2537, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "4:37:37", "remaining_time": "0:18:12"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.2513, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "4:38:23", "remaining_time": "0:17:26"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.2568, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "4:39:07", "remaining_time": "0:16:41"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.2504, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "4:39:48", "remaining_time": "0:15:55"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.2413, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "4:40:32", "remaining_time": "0:15:09"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.2489, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "4:41:17", "remaining_time": "0:14:24"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.2365, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "4:42:00", "remaining_time": "0:13:38"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.2478, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "4:42:44", "remaining_time": "0:12:53"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.2477, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "4:43:29", "remaining_time": "0:12:07"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.2531, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "4:44:15", "remaining_time": "0:11:22"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.2514, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "4:44:58", "remaining_time": "0:10:36"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.2515, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "4:45:39", "remaining_time": "0:09:51"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.2522, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "4:46:25", "remaining_time": "0:09:05"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.2578, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "4:47:09", "remaining_time": "0:08:20"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.2588, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "4:47:52", "remaining_time": "0:07:34"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.2476, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "4:48:35", "remaining_time": "0:06:49"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.2466, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "4:49:20", "remaining_time": "0:06:03"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.2595, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "4:50:04", "remaining_time": "0:05:18"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.2615, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "4:50:48", "remaining_time": "0:04:32"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.2494, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "4:51:29", "remaining_time": "0:03:47"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.2494, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "4:52:13", "remaining_time": "0:03:01"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.2383, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "4:52:56", "remaining_time": "0:02:16"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.2466, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "4:53:39", "remaining_time": "0:01:30"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.2458, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "4:54:24", "remaining_time": "0:00:45"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.256, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "4:55:10", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "4:58:45", "remaining_time": "0:00:00"}