sedrickkeh commited on
Commit
0688a31
·
verified ·
1 Parent(s): 11e4a19

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a65fea4ba78a397f11e1f5ca6ae65e9be18b51ef09408a4f728829ddd6dbeb5e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560b63175837f5897493176da7d8843328baa2888c8e3db434e3672e05ac8a35
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20866b7feb726e158cf9bfb535e4be5a9004dbab430823cc26a64fa1e7085bf1
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb29252f3527c504896a973ddff87090474d9eaed0972caab501f72e27aed60e
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:e99b8f6bd127561d0c4b9ef370a55b278093265f3fddaf1f6b73f4c703cf721b
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ff5fcd33cd47238da9d85ade20c13a3549b61771a099e56ea98495d49f12c9
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30a215bd91443bba7e4890c9f9227c508712977b0f7d6f985bdb84c6361e2d64
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb021a34da2589dc5441ae5331fca668cbe041c6ca97fdb59b79e52020d34b4
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -53,3 +53,58 @@
53
  {"current_steps": 530, "total_steps": 1617, "loss": 0.5897, "lr": 5e-06, "epoch": 0.9830744261534895, "percentage": 32.78, "elapsed_time": "8:26:17", "remaining_time": "17:18:23"}
54
  {"current_steps": 539, "total_steps": 1617, "eval_loss": 0.5783212780952454, "epoch": 0.9997681428240204, "percentage": 33.33, "elapsed_time": "8:44:26", "remaining_time": "17:28:53"}
55
  {"current_steps": 540, "total_steps": 1617, "loss": 0.6241, "lr": 5e-06, "epoch": 1.0016230002318571, "percentage": 33.4, "elapsed_time": "8:46:26", "remaining_time": "17:29:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  {"current_steps": 530, "total_steps": 1617, "loss": 0.5897, "lr": 5e-06, "epoch": 0.9830744261534895, "percentage": 32.78, "elapsed_time": "8:26:17", "remaining_time": "17:18:23"}
54
  {"current_steps": 539, "total_steps": 1617, "eval_loss": 0.5783212780952454, "epoch": 0.9997681428240204, "percentage": 33.33, "elapsed_time": "8:44:26", "remaining_time": "17:28:53"}
55
  {"current_steps": 540, "total_steps": 1617, "loss": 0.6241, "lr": 5e-06, "epoch": 1.0016230002318571, "percentage": 33.4, "elapsed_time": "8:46:26", "remaining_time": "17:29:56"}
56
+ {"current_steps": 550, "total_steps": 1617, "loss": 0.5375, "lr": 5e-06, "epoch": 1.0201715743102249, "percentage": 34.01, "elapsed_time": "8:55:59", "remaining_time": "17:19:49"}
57
+ {"current_steps": 560, "total_steps": 1617, "loss": 0.5428, "lr": 5e-06, "epoch": 1.0387201483885926, "percentage": 34.63, "elapsed_time": "9:05:33", "remaining_time": "17:09:44"}
58
+ {"current_steps": 570, "total_steps": 1617, "loss": 0.5265, "lr": 5e-06, "epoch": 1.0572687224669604, "percentage": 35.25, "elapsed_time": "9:15:06", "remaining_time": "16:59:39"}
59
+ {"current_steps": 580, "total_steps": 1617, "loss": 0.5341, "lr": 5e-06, "epoch": 1.075817296545328, "percentage": 35.87, "elapsed_time": "9:24:39", "remaining_time": "16:49:34"}
60
+ {"current_steps": 590, "total_steps": 1617, "loss": 0.525, "lr": 5e-06, "epoch": 1.0943658706236958, "percentage": 36.49, "elapsed_time": "9:34:12", "remaining_time": "16:39:31"}
61
+ {"current_steps": 600, "total_steps": 1617, "loss": 0.538, "lr": 5e-06, "epoch": 1.1129144447020636, "percentage": 37.11, "elapsed_time": "9:43:46", "remaining_time": "16:29:30"}
62
+ {"current_steps": 610, "total_steps": 1617, "loss": 0.5298, "lr": 5e-06, "epoch": 1.1314630187804313, "percentage": 37.72, "elapsed_time": "9:53:20", "remaining_time": "16:19:29"}
63
+ {"current_steps": 620, "total_steps": 1617, "loss": 0.5234, "lr": 5e-06, "epoch": 1.150011592858799, "percentage": 38.34, "elapsed_time": "10:02:54", "remaining_time": "16:09:30"}
64
+ {"current_steps": 630, "total_steps": 1617, "loss": 0.5314, "lr": 5e-06, "epoch": 1.1685601669371668, "percentage": 38.96, "elapsed_time": "10:12:28", "remaining_time": "15:59:31"}
65
+ {"current_steps": 640, "total_steps": 1617, "loss": 0.5314, "lr": 5e-06, "epoch": 1.1871087410155345, "percentage": 39.58, "elapsed_time": "10:22:01", "remaining_time": "15:49:34"}
66
+ {"current_steps": 650, "total_steps": 1617, "loss": 0.5359, "lr": 5e-06, "epoch": 1.205657315093902, "percentage": 40.2, "elapsed_time": "10:31:35", "remaining_time": "15:39:37"}
67
+ {"current_steps": 660, "total_steps": 1617, "loss": 0.5314, "lr": 5e-06, "epoch": 1.2242058891722698, "percentage": 40.82, "elapsed_time": "10:41:09", "remaining_time": "15:29:40"}
68
+ {"current_steps": 670, "total_steps": 1617, "loss": 0.5305, "lr": 5e-06, "epoch": 1.2427544632506375, "percentage": 41.43, "elapsed_time": "10:50:42", "remaining_time": "15:19:43"}
69
+ {"current_steps": 680, "total_steps": 1617, "loss": 0.5427, "lr": 5e-06, "epoch": 1.2613030373290053, "percentage": 42.05, "elapsed_time": "11:00:15", "remaining_time": "15:09:48"}
70
+ {"current_steps": 690, "total_steps": 1617, "loss": 0.5304, "lr": 5e-06, "epoch": 1.279851611407373, "percentage": 42.67, "elapsed_time": "11:09:48", "remaining_time": "14:59:52"}
71
+ {"current_steps": 700, "total_steps": 1617, "loss": 0.5301, "lr": 5e-06, "epoch": 1.2984001854857408, "percentage": 43.29, "elapsed_time": "11:19:22", "remaining_time": "14:49:58"}
72
+ {"current_steps": 710, "total_steps": 1617, "loss": 0.5216, "lr": 5e-06, "epoch": 1.3169487595641085, "percentage": 43.91, "elapsed_time": "11:28:55", "remaining_time": "14:40:04"}
73
+ {"current_steps": 720, "total_steps": 1617, "loss": 0.5465, "lr": 5e-06, "epoch": 1.3354973336424762, "percentage": 44.53, "elapsed_time": "11:38:28", "remaining_time": "14:30:11"}
74
+ {"current_steps": 730, "total_steps": 1617, "loss": 0.5432, "lr": 5e-06, "epoch": 1.354045907720844, "percentage": 45.15, "elapsed_time": "11:48:01", "remaining_time": "14:20:18"}
75
+ {"current_steps": 740, "total_steps": 1617, "loss": 0.5318, "lr": 5e-06, "epoch": 1.3725944817992117, "percentage": 45.76, "elapsed_time": "11:57:35", "remaining_time": "14:10:25"}
76
+ {"current_steps": 750, "total_steps": 1617, "loss": 0.5282, "lr": 5e-06, "epoch": 1.3911430558775795, "percentage": 46.38, "elapsed_time": "12:07:08", "remaining_time": "14:00:34"}
77
+ {"current_steps": 760, "total_steps": 1617, "loss": 0.5204, "lr": 5e-06, "epoch": 1.4096916299559472, "percentage": 47.0, "elapsed_time": "12:16:41", "remaining_time": "13:50:43"}
78
+ {"current_steps": 770, "total_steps": 1617, "loss": 0.5262, "lr": 5e-06, "epoch": 1.428240204034315, "percentage": 47.62, "elapsed_time": "12:26:15", "remaining_time": "13:40:53"}
79
+ {"current_steps": 780, "total_steps": 1617, "loss": 0.5264, "lr": 5e-06, "epoch": 1.4467887781126825, "percentage": 48.24, "elapsed_time": "12:35:49", "remaining_time": "13:31:03"}
80
+ {"current_steps": 790, "total_steps": 1617, "loss": 0.5264, "lr": 5e-06, "epoch": 1.4653373521910504, "percentage": 48.86, "elapsed_time": "12:45:22", "remaining_time": "13:21:13"}
81
+ {"current_steps": 800, "total_steps": 1617, "loss": 0.5268, "lr": 5e-06, "epoch": 1.483885926269418, "percentage": 49.47, "elapsed_time": "12:54:56", "remaining_time": "13:11:24"}
82
+ {"current_steps": 810, "total_steps": 1617, "loss": 0.5301, "lr": 5e-06, "epoch": 1.502434500347786, "percentage": 50.09, "elapsed_time": "13:04:29", "remaining_time": "13:01:35"}
83
+ {"current_steps": 820, "total_steps": 1617, "loss": 0.5193, "lr": 5e-06, "epoch": 1.5209830744261534, "percentage": 50.71, "elapsed_time": "13:14:03", "remaining_time": "12:51:47"}
84
+ {"current_steps": 830, "total_steps": 1617, "loss": 0.5216, "lr": 5e-06, "epoch": 1.5395316485045212, "percentage": 51.33, "elapsed_time": "13:23:37", "remaining_time": "12:41:59"}
85
+ {"current_steps": 840, "total_steps": 1617, "loss": 0.5259, "lr": 5e-06, "epoch": 1.558080222582889, "percentage": 51.95, "elapsed_time": "13:33:10", "remaining_time": "12:32:11"}
86
+ {"current_steps": 850, "total_steps": 1617, "loss": 0.5241, "lr": 5e-06, "epoch": 1.5766287966612567, "percentage": 52.57, "elapsed_time": "13:42:44", "remaining_time": "12:22:24"}
87
+ {"current_steps": 860, "total_steps": 1617, "loss": 0.5267, "lr": 5e-06, "epoch": 1.5951773707396244, "percentage": 53.18, "elapsed_time": "13:52:18", "remaining_time": "12:12:37"}
88
+ {"current_steps": 870, "total_steps": 1617, "loss": 0.5317, "lr": 5e-06, "epoch": 1.6137259448179921, "percentage": 53.8, "elapsed_time": "14:01:52", "remaining_time": "12:02:50"}
89
+ {"current_steps": 880, "total_steps": 1617, "loss": 0.527, "lr": 5e-06, "epoch": 1.6322745188963599, "percentage": 54.42, "elapsed_time": "14:11:26", "remaining_time": "11:53:04"}
90
+ {"current_steps": 890, "total_steps": 1617, "loss": 0.5194, "lr": 5e-06, "epoch": 1.6508230929747274, "percentage": 55.04, "elapsed_time": "14:21:00", "remaining_time": "11:43:18"}
91
+ {"current_steps": 900, "total_steps": 1617, "loss": 0.5206, "lr": 5e-06, "epoch": 1.6693716670530954, "percentage": 55.66, "elapsed_time": "14:30:34", "remaining_time": "11:33:33"}
92
+ {"current_steps": 910, "total_steps": 1617, "loss": 0.515, "lr": 5e-06, "epoch": 1.6879202411314629, "percentage": 56.28, "elapsed_time": "14:40:08", "remaining_time": "11:23:48"}
93
+ {"current_steps": 920, "total_steps": 1617, "loss": 0.5304, "lr": 5e-06, "epoch": 1.7064688152098308, "percentage": 56.9, "elapsed_time": "14:49:42", "remaining_time": "11:14:03"}
94
+ {"current_steps": 930, "total_steps": 1617, "loss": 0.5228, "lr": 5e-06, "epoch": 1.7250173892881984, "percentage": 57.51, "elapsed_time": "14:59:16", "remaining_time": "11:04:18"}
95
+ {"current_steps": 940, "total_steps": 1617, "loss": 0.5066, "lr": 5e-06, "epoch": 1.7435659633665663, "percentage": 58.13, "elapsed_time": "15:08:51", "remaining_time": "10:54:34"}
96
+ {"current_steps": 950, "total_steps": 1617, "loss": 0.5219, "lr": 5e-06, "epoch": 1.7621145374449338, "percentage": 58.75, "elapsed_time": "15:18:25", "remaining_time": "10:44:50"}
97
+ {"current_steps": 960, "total_steps": 1617, "loss": 0.519, "lr": 5e-06, "epoch": 1.7806631115233018, "percentage": 59.37, "elapsed_time": "15:27:59", "remaining_time": "10:35:05"}
98
+ {"current_steps": 970, "total_steps": 1617, "loss": 0.5155, "lr": 5e-06, "epoch": 1.7992116856016693, "percentage": 59.99, "elapsed_time": "15:37:33", "remaining_time": "10:25:21"}
99
+ {"current_steps": 980, "total_steps": 1617, "loss": 0.5056, "lr": 5e-06, "epoch": 1.817760259680037, "percentage": 60.61, "elapsed_time": "15:47:07", "remaining_time": "10:15:38"}
100
+ {"current_steps": 990, "total_steps": 1617, "loss": 0.5178, "lr": 5e-06, "epoch": 1.8363088337584048, "percentage": 61.22, "elapsed_time": "15:56:42", "remaining_time": "10:05:54"}
101
+ {"current_steps": 1000, "total_steps": 1617, "loss": 0.5235, "lr": 5e-06, "epoch": 1.8548574078367726, "percentage": 61.84, "elapsed_time": "16:06:16", "remaining_time": "9:56:11"}
102
+ {"current_steps": 1010, "total_steps": 1617, "loss": 0.5291, "lr": 5e-06, "epoch": 1.8734059819151403, "percentage": 62.46, "elapsed_time": "16:15:50", "remaining_time": "9:46:28"}
103
+ {"current_steps": 1020, "total_steps": 1617, "loss": 0.5136, "lr": 5e-06, "epoch": 1.891954555993508, "percentage": 63.08, "elapsed_time": "16:25:24", "remaining_time": "9:36:45"}
104
+ {"current_steps": 1030, "total_steps": 1617, "loss": 0.5174, "lr": 5e-06, "epoch": 1.9105031300718758, "percentage": 63.7, "elapsed_time": "16:34:58", "remaining_time": "9:27:02"}
105
+ {"current_steps": 1040, "total_steps": 1617, "loss": 0.524, "lr": 5e-06, "epoch": 1.9290517041502433, "percentage": 64.32, "elapsed_time": "16:44:32", "remaining_time": "9:17:19"}
106
+ {"current_steps": 1050, "total_steps": 1617, "loss": 0.5117, "lr": 5e-06, "epoch": 1.9476002782286113, "percentage": 64.94, "elapsed_time": "16:54:07", "remaining_time": "9:07:37"}
107
+ {"current_steps": 1060, "total_steps": 1617, "loss": 0.5101, "lr": 5e-06, "epoch": 1.9661488523069788, "percentage": 65.55, "elapsed_time": "17:03:41", "remaining_time": "8:57:55"}
108
+ {"current_steps": 1070, "total_steps": 1617, "loss": 0.519, "lr": 5e-06, "epoch": 1.9846974263853467, "percentage": 66.17, "elapsed_time": "17:13:16", "remaining_time": "8:48:13"}
109
+ {"current_steps": 1078, "total_steps": 1617, "eval_loss": 0.5572099685668945, "epoch": 1.9995362856480408, "percentage": 66.67, "elapsed_time": "17:30:39", "remaining_time": "8:45:19"}
110
+ {"current_steps": 1080, "total_steps": 1617, "loss": 0.5612, "lr": 5e-06, "epoch": 2.0032460004637143, "percentage": 66.79, "elapsed_time": "17:33:34", "remaining_time": "8:43:51"}