sedrickkeh commited on
Commit
f147489
·
verified ·
1 Parent(s): d6af01d

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e3923de6f483afaffac780be9b2b1cca0ab330d32953c358d841b33f82ea9bd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1856ac7ca47613b55a850f977dcdc4cfc49b732013801fc21c438a1f09ab2af5
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:887c9d57b356b2c65e4a658b8f936e08ea2dee5761e4805790b03eb6eec30459
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37b66213d32da61eaedc3911c95eabbc1c73c2c73a5c46944432010342d2687
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:d25dfd0215d1e7827445f25c34638554fdb753a7034fa7af7e0b237ac9c744e0
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b0a1e5be178a7a974e8165ff7461c0ad67673150dac40a6898077a60af445d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d8b3a4444c8ba0d6fee5cc1b179958a44270708435f8ad8f6bbd8bd9cf5d6eb
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:849777b28c61e16fa99f774190933588c19991b2dd9bbda52eaccef4c1cd814f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -85,3 +85,45 @@
85
  {"current_steps": 840, "total_steps": 1275, "loss": 0.5398, "lr": 5e-06, "epoch": 1.9727032579982389, "percentage": 65.88, "elapsed_time": "7:31:45", "remaining_time": "3:53:56"}
86
  {"current_steps": 850, "total_steps": 1275, "loss": 0.547, "lr": 5e-06, "epoch": 1.9961843263868506, "percentage": 66.67, "elapsed_time": "7:37:03", "remaining_time": "3:48:31"}
87
  {"current_steps": 851, "total_steps": 1275, "eval_loss": 0.5846751928329468, "epoch": 1.9985324332257117, "percentage": 66.75, "elapsed_time": "7:42:41", "remaining_time": "3:50:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  {"current_steps": 840, "total_steps": 1275, "loss": 0.5398, "lr": 5e-06, "epoch": 1.9727032579982389, "percentage": 65.88, "elapsed_time": "7:31:45", "remaining_time": "3:53:56"}
86
  {"current_steps": 850, "total_steps": 1275, "loss": 0.547, "lr": 5e-06, "epoch": 1.9961843263868506, "percentage": 66.67, "elapsed_time": "7:37:03", "remaining_time": "3:48:31"}
87
  {"current_steps": 851, "total_steps": 1275, "eval_loss": 0.5846751928329468, "epoch": 1.9985324332257117, "percentage": 66.75, "elapsed_time": "7:42:41", "remaining_time": "3:50:31"}
88
+ {"current_steps": 860, "total_steps": 1275, "loss": 0.523, "lr": 5e-06, "epoch": 2.0199589081303198, "percentage": 67.45, "elapsed_time": "7:48:31", "remaining_time": "3:46:05"}
89
+ {"current_steps": 870, "total_steps": 1275, "loss": 0.4924, "lr": 5e-06, "epoch": 2.0434399765189317, "percentage": 68.24, "elapsed_time": "7:53:48", "remaining_time": "3:40:34"}
90
+ {"current_steps": 880, "total_steps": 1275, "loss": 0.4902, "lr": 5e-06, "epoch": 2.0669210449075432, "percentage": 69.02, "elapsed_time": "7:59:06", "remaining_time": "3:35:03"}
91
+ {"current_steps": 890, "total_steps": 1275, "loss": 0.4955, "lr": 5e-06, "epoch": 2.0904021132961548, "percentage": 69.8, "elapsed_time": "8:04:23", "remaining_time": "3:29:32"}
92
+ {"current_steps": 900, "total_steps": 1275, "loss": 0.4969, "lr": 5e-06, "epoch": 2.1138831816847667, "percentage": 70.59, "elapsed_time": "8:09:40", "remaining_time": "3:24:01"}
93
+ {"current_steps": 910, "total_steps": 1275, "loss": 0.4865, "lr": 5e-06, "epoch": 2.1373642500733783, "percentage": 71.37, "elapsed_time": "8:14:58", "remaining_time": "3:18:31"}
94
+ {"current_steps": 920, "total_steps": 1275, "loss": 0.4966, "lr": 5e-06, "epoch": 2.1608453184619902, "percentage": 72.16, "elapsed_time": "8:20:15", "remaining_time": "3:13:02"}
95
+ {"current_steps": 930, "total_steps": 1275, "loss": 0.497, "lr": 5e-06, "epoch": 2.1843263868506018, "percentage": 72.94, "elapsed_time": "8:25:33", "remaining_time": "3:07:32"}
96
+ {"current_steps": 940, "total_steps": 1275, "loss": 0.498, "lr": 5e-06, "epoch": 2.2078074552392133, "percentage": 73.73, "elapsed_time": "8:30:52", "remaining_time": "3:02:03"}
97
+ {"current_steps": 950, "total_steps": 1275, "loss": 0.4978, "lr": 5e-06, "epoch": 2.2312885236278253, "percentage": 74.51, "elapsed_time": "8:36:10", "remaining_time": "2:56:35"}
98
+ {"current_steps": 960, "total_steps": 1275, "loss": 0.4954, "lr": 5e-06, "epoch": 2.254769592016437, "percentage": 75.29, "elapsed_time": "8:41:25", "remaining_time": "2:51:05"}
99
+ {"current_steps": 970, "total_steps": 1275, "loss": 0.5024, "lr": 5e-06, "epoch": 2.2782506604050483, "percentage": 76.08, "elapsed_time": "8:46:44", "remaining_time": "2:45:37"}
100
+ {"current_steps": 980, "total_steps": 1275, "loss": 0.4982, "lr": 5e-06, "epoch": 2.3017317287936603, "percentage": 76.86, "elapsed_time": "8:52:00", "remaining_time": "2:40:08"}
101
+ {"current_steps": 990, "total_steps": 1275, "loss": 0.4994, "lr": 5e-06, "epoch": 2.325212797182272, "percentage": 77.65, "elapsed_time": "8:57:18", "remaining_time": "2:34:40"}
102
+ {"current_steps": 1000, "total_steps": 1275, "loss": 0.5002, "lr": 5e-06, "epoch": 2.3486938655708833, "percentage": 78.43, "elapsed_time": "9:02:35", "remaining_time": "2:29:12"}
103
+ {"current_steps": 1010, "total_steps": 1275, "loss": 0.4994, "lr": 5e-06, "epoch": 2.3721749339594953, "percentage": 79.22, "elapsed_time": "9:07:52", "remaining_time": "2:23:44"}
104
+ {"current_steps": 1020, "total_steps": 1275, "loss": 0.4906, "lr": 5e-06, "epoch": 2.395656002348107, "percentage": 80.0, "elapsed_time": "9:13:09", "remaining_time": "2:18:17"}
105
+ {"current_steps": 1030, "total_steps": 1275, "loss": 0.4975, "lr": 5e-06, "epoch": 2.4191370707367184, "percentage": 80.78, "elapsed_time": "9:18:27", "remaining_time": "2:12:50"}
106
+ {"current_steps": 1040, "total_steps": 1275, "loss": 0.4976, "lr": 5e-06, "epoch": 2.4426181391253303, "percentage": 81.57, "elapsed_time": "9:23:44", "remaining_time": "2:07:23"}
107
+ {"current_steps": 1050, "total_steps": 1275, "loss": 0.5052, "lr": 5e-06, "epoch": 2.466099207513942, "percentage": 82.35, "elapsed_time": "9:28:59", "remaining_time": "2:01:55"}
108
+ {"current_steps": 1060, "total_steps": 1275, "loss": 0.4989, "lr": 5e-06, "epoch": 2.4895802759025534, "percentage": 83.14, "elapsed_time": "9:34:17", "remaining_time": "1:56:28"}
109
+ {"current_steps": 1070, "total_steps": 1275, "loss": 0.5059, "lr": 5e-06, "epoch": 2.5130613442911653, "percentage": 83.92, "elapsed_time": "9:39:35", "remaining_time": "1:51:02"}
110
+ {"current_steps": 1080, "total_steps": 1275, "loss": 0.4946, "lr": 5e-06, "epoch": 2.536542412679777, "percentage": 84.71, "elapsed_time": "9:44:53", "remaining_time": "1:45:36"}
111
+ {"current_steps": 1090, "total_steps": 1275, "loss": 0.5086, "lr": 5e-06, "epoch": 2.560023481068389, "percentage": 85.49, "elapsed_time": "9:50:12", "remaining_time": "1:40:10"}
112
+ {"current_steps": 1100, "total_steps": 1275, "loss": 0.498, "lr": 5e-06, "epoch": 2.5835045494570004, "percentage": 86.27, "elapsed_time": "9:55:30", "remaining_time": "1:34:44"}
113
+ {"current_steps": 1110, "total_steps": 1275, "loss": 0.4998, "lr": 5e-06, "epoch": 2.606985617845612, "percentage": 87.06, "elapsed_time": "10:00:49", "remaining_time": "1:29:18"}
114
+ {"current_steps": 1120, "total_steps": 1275, "loss": 0.4944, "lr": 5e-06, "epoch": 2.6304666862342234, "percentage": 87.84, "elapsed_time": "10:06:07", "remaining_time": "1:23:53"}
115
+ {"current_steps": 1130, "total_steps": 1275, "loss": 0.5028, "lr": 5e-06, "epoch": 2.6539477546228354, "percentage": 88.63, "elapsed_time": "10:11:26", "remaining_time": "1:18:27"}
116
+ {"current_steps": 1140, "total_steps": 1275, "loss": 0.4982, "lr": 5e-06, "epoch": 2.677428823011447, "percentage": 89.41, "elapsed_time": "10:16:45", "remaining_time": "1:13:02"}
117
+ {"current_steps": 1150, "total_steps": 1275, "loss": 0.5009, "lr": 5e-06, "epoch": 2.700909891400059, "percentage": 90.2, "elapsed_time": "10:22:04", "remaining_time": "1:07:36"}
118
+ {"current_steps": 1160, "total_steps": 1275, "loss": 0.5012, "lr": 5e-06, "epoch": 2.7243909597886704, "percentage": 90.98, "elapsed_time": "10:27:23", "remaining_time": "1:02:11"}
119
+ {"current_steps": 1170, "total_steps": 1275, "loss": 0.5032, "lr": 5e-06, "epoch": 2.747872028177282, "percentage": 91.76, "elapsed_time": "10:32:41", "remaining_time": "0:56:46"}
120
+ {"current_steps": 1180, "total_steps": 1275, "loss": 0.5033, "lr": 5e-06, "epoch": 2.771353096565894, "percentage": 92.55, "elapsed_time": "10:37:58", "remaining_time": "0:51:21"}
121
+ {"current_steps": 1190, "total_steps": 1275, "loss": 0.5037, "lr": 5e-06, "epoch": 2.7948341649545054, "percentage": 93.33, "elapsed_time": "10:43:18", "remaining_time": "0:45:57"}
122
+ {"current_steps": 1200, "total_steps": 1275, "loss": 0.508, "lr": 5e-06, "epoch": 2.818315233343117, "percentage": 94.12, "elapsed_time": "10:48:36", "remaining_time": "0:40:32"}
123
+ {"current_steps": 1210, "total_steps": 1275, "loss": 0.4957, "lr": 5e-06, "epoch": 2.841796301731729, "percentage": 94.9, "elapsed_time": "10:53:53", "remaining_time": "0:35:07"}
124
+ {"current_steps": 1220, "total_steps": 1275, "loss": 0.499, "lr": 5e-06, "epoch": 2.8652773701203404, "percentage": 95.69, "elapsed_time": "10:59:11", "remaining_time": "0:29:43"}
125
+ {"current_steps": 1230, "total_steps": 1275, "loss": 0.4982, "lr": 5e-06, "epoch": 2.888758438508952, "percentage": 96.47, "elapsed_time": "11:04:30", "remaining_time": "0:24:18"}
126
+ {"current_steps": 1240, "total_steps": 1275, "loss": 0.5006, "lr": 5e-06, "epoch": 2.912239506897564, "percentage": 97.25, "elapsed_time": "11:09:48", "remaining_time": "0:18:54"}
127
+ {"current_steps": 1250, "total_steps": 1275, "loss": 0.494, "lr": 5e-06, "epoch": 2.9357205752861755, "percentage": 98.04, "elapsed_time": "11:15:07", "remaining_time": "0:13:30"}
128
+ {"current_steps": 1260, "total_steps": 1275, "loss": 0.5001, "lr": 5e-06, "epoch": 2.9592016436747874, "percentage": 98.82, "elapsed_time": "11:20:25", "remaining_time": "0:08:06"}
129
+ {"current_steps": 1270, "total_steps": 1275, "loss": 0.5003, "lr": 5e-06, "epoch": 2.982682712063399, "percentage": 99.61, "elapsed_time": "11:25:43", "remaining_time": "0:02:41"}