chancharikm commited on
Commit
96123b3
·
verified ·
1 Parent(s): 457d6c0

Training in progress, step 350

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f169a5cf7a218426bd887afae294bc4839c3a9229b597c792398fbc6018e83a
3
  size 4998056552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea1c1bcb724cfa28b3c5bee1020fcfab6683a4f456f95ab057ad3b7340c9a86
3
  size 4998056552
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e546047a602208cf99253121ca7936c155134bd167636b7c1a63409bf20121f8
3
  size 4915962464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e739edc6cbdc0898de2ea6bc868e0a05f4cb5858714800c29e6265feb1e9d813
3
  size 4915962464
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e676b882a8fbc19a333f5bd267b2cbb710f1609e2626e7a20a6b06262a4f4f3
3
  size 4915962496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6e17ccbbe2715ef6ae77d85f92591557c13e5b42c7efd7731bd24e3885db7c8
3
  size 4915962496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1c6e8d6ba96b7f403634157a75d29507bd38630b12976f5840d1d555880ac9c
3
  size 2704357976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0323dac437dd16044bd39db21c19b5fa6c55ec201e51b688f053ba00b2515702
3
  size 2704357976
trainer_log.jsonl CHANGED
@@ -298,3 +298,53 @@
298
  {"current_steps": 298, "total_steps": 2820, "loss": 0.1262, "lr": 2.974970437055914e-05, "epoch": 0.21142249024476764, "percentage": 10.57, "elapsed_time": "19:47:05", "remaining_time": "6 days, 23:26:26"}
299
  {"current_steps": 299, "total_steps": 2820, "loss": 0.1342, "lr": 2.974649426546832e-05, "epoch": 0.21213196168854204, "percentage": 10.6, "elapsed_time": "19:50:49", "remaining_time": "6 days, 23:20:25"}
300
  {"current_steps": 300, "total_steps": 2820, "loss": 0.1305, "lr": 2.974326388154002e-05, "epoch": 0.21284143313231643, "percentage": 10.64, "elapsed_time": "19:55:07", "remaining_time": "6 days, 23:18:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298
  {"current_steps": 298, "total_steps": 2820, "loss": 0.1262, "lr": 2.974970437055914e-05, "epoch": 0.21142249024476764, "percentage": 10.57, "elapsed_time": "19:47:05", "remaining_time": "6 days, 23:26:26"}
299
  {"current_steps": 299, "total_steps": 2820, "loss": 0.1342, "lr": 2.974649426546832e-05, "epoch": 0.21213196168854204, "percentage": 10.6, "elapsed_time": "19:50:49", "remaining_time": "6 days, 23:20:25"}
300
  {"current_steps": 300, "total_steps": 2820, "loss": 0.1305, "lr": 2.974326388154002e-05, "epoch": 0.21284143313231643, "percentage": 10.64, "elapsed_time": "19:55:07", "remaining_time": "6 days, 23:18:59"}
301
+ {"current_steps": 301, "total_steps": 2820, "loss": 0.139, "lr": 2.9740013223216548e-05, "epoch": 0.2135509045760908, "percentage": 10.67, "elapsed_time": "19:59:59", "remaining_time": "6 days, 23:22:23"}
302
+ {"current_steps": 302, "total_steps": 2820, "loss": 0.13, "lr": 2.9736742294968088e-05, "epoch": 0.2142603760198652, "percentage": 10.71, "elapsed_time": "20:04:27", "remaining_time": "6 days, 23:22:29"}
303
+ {"current_steps": 303, "total_steps": 2820, "loss": 0.1265, "lr": 2.9733451101292698e-05, "epoch": 0.2149698474636396, "percentage": 10.74, "elapsed_time": "20:08:17", "remaining_time": "6 days, 23:17:12"}
304
+ {"current_steps": 304, "total_steps": 2820, "loss": 0.1382, "lr": 2.9730139646716308e-05, "epoch": 0.21567931890741399, "percentage": 10.78, "elapsed_time": "20:11:46", "remaining_time": "6 days, 23:09:05"}
305
+ {"current_steps": 305, "total_steps": 2820, "loss": 0.1686, "lr": 2.9726807935792714e-05, "epoch": 0.21638879035118835, "percentage": 10.82, "elapsed_time": "20:15:03", "remaining_time": "6 days, 22:59:12"}
306
+ {"current_steps": 306, "total_steps": 2820, "loss": 0.1313, "lr": 2.9723455973103554e-05, "epoch": 0.21709826179496275, "percentage": 10.85, "elapsed_time": "20:18:47", "remaining_time": "6 days, 22:53:13"}
307
+ {"current_steps": 307, "total_steps": 2820, "loss": 0.1112, "lr": 2.9720083763258326e-05, "epoch": 0.21780773323873714, "percentage": 10.89, "elapsed_time": "20:22:39", "remaining_time": "6 days, 22:48:14"}
308
+ {"current_steps": 308, "total_steps": 2820, "loss": 0.113, "lr": 2.971669131089438e-05, "epoch": 0.21851720468251154, "percentage": 10.92, "elapsed_time": "20:26:38", "remaining_time": "6 days, 22:44:17"}
309
+ {"current_steps": 309, "total_steps": 2820, "loss": 0.1408, "lr": 2.9713278620676876e-05, "epoch": 0.2192266761262859, "percentage": 10.96, "elapsed_time": "20:30:49", "remaining_time": "6 days, 22:42:00"}
310
+ {"current_steps": 310, "total_steps": 2820, "loss": 0.1144, "lr": 2.970984569729883e-05, "epoch": 0.2199361475700603, "percentage": 10.99, "elapsed_time": "20:34:14", "remaining_time": "6 days, 22:33:23"}
311
+ {"current_steps": 311, "total_steps": 2820, "loss": 0.1267, "lr": 2.970639254548107e-05, "epoch": 0.2206456190138347, "percentage": 11.03, "elapsed_time": "20:38:09", "remaining_time": "6 days, 22:28:50"}
312
+ {"current_steps": 312, "total_steps": 2820, "loss": 0.1339, "lr": 2.970291916997224e-05, "epoch": 0.2213550904576091, "percentage": 11.06, "elapsed_time": "20:42:16", "remaining_time": "6 days, 22:26:00"}
313
+ {"current_steps": 313, "total_steps": 2820, "loss": 0.1377, "lr": 2.9699425575548802e-05, "epoch": 0.22206456190138346, "percentage": 11.1, "elapsed_time": "20:46:07", "remaining_time": "6 days, 22:21:00"}
314
+ {"current_steps": 314, "total_steps": 2820, "loss": 0.1005, "lr": 2.9695911767015024e-05, "epoch": 0.22277403334515786, "percentage": 11.13, "elapsed_time": "20:49:44", "remaining_time": "6 days, 22:14:02"}
315
+ {"current_steps": 315, "total_steps": 2820, "loss": 0.1321, "lr": 2.9692377749202953e-05, "epoch": 0.22348350478893225, "percentage": 11.17, "elapsed_time": "20:53:08", "remaining_time": "6 days, 22:05:30"}
316
+ {"current_steps": 316, "total_steps": 2820, "loss": 0.1141, "lr": 2.9688823526972453e-05, "epoch": 0.22419297623270662, "percentage": 11.21, "elapsed_time": "20:57:04", "remaining_time": "6 days, 22:01:05"}
317
+ {"current_steps": 317, "total_steps": 2820, "loss": 0.1494, "lr": 2.9685249105211154e-05, "epoch": 0.22490244767648102, "percentage": 11.24, "elapsed_time": "21:00:30", "remaining_time": "6 days, 21:52:51"}
318
+ {"current_steps": 318, "total_steps": 2820, "loss": 0.1351, "lr": 2.9681654488834472e-05, "epoch": 0.2256119191202554, "percentage": 11.28, "elapsed_time": "21:04:33", "remaining_time": "6 days, 21:49:24"}
319
+ {"current_steps": 319, "total_steps": 2820, "loss": 0.0999, "lr": 2.9678039682785594e-05, "epoch": 0.2263213905640298, "percentage": 11.31, "elapsed_time": "21:09:01", "remaining_time": "6 days, 21:49:22"}
320
+ {"current_steps": 320, "total_steps": 2820, "loss": 0.1286, "lr": 2.9674404692035458e-05, "epoch": 0.22703086200780417, "percentage": 11.35, "elapsed_time": "21:12:43", "remaining_time": "6 days, 21:43:07"}
321
+ {"current_steps": 321, "total_steps": 2820, "loss": 0.1197, "lr": 2.9670749521582778e-05, "epoch": 0.22774033345157857, "percentage": 11.38, "elapsed_time": "21:16:11", "remaining_time": "6 days, 21:35:14"}
322
+ {"current_steps": 322, "total_steps": 2820, "loss": 0.1108, "lr": 2.9667074176454013e-05, "epoch": 0.22844980489535296, "percentage": 11.42, "elapsed_time": "21:20:26", "remaining_time": "6 days, 21:33:23"}
323
+ {"current_steps": 323, "total_steps": 2820, "loss": 0.1386, "lr": 2.9663378661703356e-05, "epoch": 0.22915927633912736, "percentage": 11.45, "elapsed_time": "21:24:05", "remaining_time": "6 days, 21:26:55"}
324
+ {"current_steps": 324, "total_steps": 2820, "loss": 0.1091, "lr": 2.965966298241275e-05, "epoch": 0.22986874778290173, "percentage": 11.49, "elapsed_time": "21:28:42", "remaining_time": "6 days, 21:27:49"}
325
+ {"current_steps": 325, "total_steps": 2820, "loss": 0.1382, "lr": 2.965592714369185e-05, "epoch": 0.23057821922667612, "percentage": 11.52, "elapsed_time": "21:32:23", "remaining_time": "6 days, 21:21:36"}
326
+ {"current_steps": 326, "total_steps": 2820, "loss": 0.1027, "lr": 2.9652171150678055e-05, "epoch": 0.23128769067045052, "percentage": 11.56, "elapsed_time": "21:36:52", "remaining_time": "6 days, 21:21:30"}
327
+ {"current_steps": 327, "total_steps": 2820, "loss": 0.1167, "lr": 2.9648395008536464e-05, "epoch": 0.23199716211422491, "percentage": 11.6, "elapsed_time": "21:41:01", "remaining_time": "6 days, 21:18:52"}
328
+ {"current_steps": 328, "total_steps": 2820, "loss": 0.106, "lr": 2.964459872245989e-05, "epoch": 0.23270663355799928, "percentage": 11.63, "elapsed_time": "21:44:45", "remaining_time": "6 days, 21:12:56"}
329
+ {"current_steps": 329, "total_steps": 2820, "loss": 0.1174, "lr": 2.9640782297668845e-05, "epoch": 0.23341610500177368, "percentage": 11.67, "elapsed_time": "21:49:15", "remaining_time": "6 days, 21:12:57"}
330
+ {"current_steps": 330, "total_steps": 2820, "loss": 0.1267, "lr": 2.9636945739411533e-05, "epoch": 0.23412557644554807, "percentage": 11.7, "elapsed_time": "21:52:59", "remaining_time": "6 days, 21:07:10"}
331
+ {"current_steps": 331, "total_steps": 2820, "loss": 0.1238, "lr": 2.9633089052963858e-05, "epoch": 0.23483504788932247, "percentage": 11.74, "elapsed_time": "21:57:45", "remaining_time": "6 days, 21:09:00"}
332
+ {"current_steps": 332, "total_steps": 2820, "loss": 0.1141, "lr": 2.9629212243629387e-05, "epoch": 0.23554451933309684, "percentage": 11.77, "elapsed_time": "22:01:52", "remaining_time": "6 days, 21:06:02"}
333
+ {"current_steps": 333, "total_steps": 2820, "loss": 0.1137, "lr": 2.9625315316739365e-05, "epoch": 0.23625399077687123, "percentage": 11.81, "elapsed_time": "22:05:40", "remaining_time": "6 days, 21:00:45"}
334
+ {"current_steps": 334, "total_steps": 2820, "loss": 0.1523, "lr": 2.9621398277652703e-05, "epoch": 0.23696346222064563, "percentage": 11.84, "elapsed_time": "22:10:18", "remaining_time": "6 days, 21:01:35"}
335
+ {"current_steps": 335, "total_steps": 2820, "loss": 0.1004, "lr": 2.9617461131755974e-05, "epoch": 0.23767293366442, "percentage": 11.88, "elapsed_time": "22:13:53", "remaining_time": "6 days, 20:54:38"}
336
+ {"current_steps": 336, "total_steps": 2820, "loss": 0.1508, "lr": 2.961350388446339e-05, "epoch": 0.2383824051081944, "percentage": 11.91, "elapsed_time": "22:18:09", "remaining_time": "6 days, 20:52:52"}
337
+ {"current_steps": 337, "total_steps": 2820, "loss": 0.1069, "lr": 2.9609526541216817e-05, "epoch": 0.23909187655196878, "percentage": 11.95, "elapsed_time": "22:22:11", "remaining_time": "6 days, 20:49:09"}
338
+ {"current_steps": 338, "total_steps": 2820, "loss": 0.11, "lr": 2.960552910748575e-05, "epoch": 0.23980134799574318, "percentage": 11.99, "elapsed_time": "22:25:52", "remaining_time": "6 days, 20:43:00"}
339
+ {"current_steps": 339, "total_steps": 2820, "loss": 0.1151, "lr": 2.9601511588767314e-05, "epoch": 0.24051081943951755, "percentage": 12.02, "elapsed_time": "22:30:05", "remaining_time": "6 days, 20:40:47"}
340
+ {"current_steps": 340, "total_steps": 2820, "loss": 0.127, "lr": 2.959747399058625e-05, "epoch": 0.24122029088329194, "percentage": 12.06, "elapsed_time": "22:33:43", "remaining_time": "6 days, 20:34:11"}
341
+ {"current_steps": 341, "total_steps": 2820, "loss": 0.1247, "lr": 2.9593416318494916e-05, "epoch": 0.24192976232706634, "percentage": 12.09, "elapsed_time": "22:37:01", "remaining_time": "6 days, 20:25:15"}
342
+ {"current_steps": 342, "total_steps": 2820, "loss": 0.1257, "lr": 2.9589338578073277e-05, "epoch": 0.24263923377084073, "percentage": 12.13, "elapsed_time": "22:41:18", "remaining_time": "6 days, 20:23:31"}
343
+ {"current_steps": 343, "total_steps": 2820, "loss": 0.1399, "lr": 2.9585240774928887e-05, "epoch": 0.2433487052146151, "percentage": 12.16, "elapsed_time": "22:45:34", "remaining_time": "6 days, 20:21:32"}
344
+ {"current_steps": 344, "total_steps": 2820, "loss": 0.1194, "lr": 2.9581122914696898e-05, "epoch": 0.2440581766583895, "percentage": 12.2, "elapsed_time": "22:49:40", "remaining_time": "6 days, 20:18:30"}
345
+ {"current_steps": 345, "total_steps": 2820, "loss": 0.1245, "lr": 2.957698500304004e-05, "epoch": 0.2447676481021639, "percentage": 12.23, "elapsed_time": "22:53:24", "remaining_time": "6 days, 20:12:42"}
346
+ {"current_steps": 346, "total_steps": 2820, "loss": 0.1109, "lr": 2.9572827045648614e-05, "epoch": 0.2454771195459383, "percentage": 12.27, "elapsed_time": "22:57:24", "remaining_time": "6 days, 20:08:51"}
347
+ {"current_steps": 347, "total_steps": 2820, "loss": 0.1679, "lr": 2.9568649048240496e-05, "epoch": 0.24618659098971266, "percentage": 12.3, "elapsed_time": "23:02:05", "remaining_time": "6 days, 20:09:52"}
348
+ {"current_steps": 348, "total_steps": 2820, "loss": 0.1596, "lr": 2.9564451016561107e-05, "epoch": 0.24689606243348705, "percentage": 12.34, "elapsed_time": "23:05:34", "remaining_time": "6 days, 20:02:20"}
349
+ {"current_steps": 349, "total_steps": 2820, "loss": 0.1171, "lr": 2.9560232956383433e-05, "epoch": 0.24760553387726145, "percentage": 12.38, "elapsed_time": "23:09:37", "remaining_time": "6 days, 19:58:50"}
350
+ {"current_steps": 350, "total_steps": 2820, "loss": 0.1423, "lr": 2.9555994873507992e-05, "epoch": 0.24831500532103584, "percentage": 12.41, "elapsed_time": "23:13:16", "remaining_time": "6 days, 19:52:34"}