sedrickkeh commited on
Commit
f80b5cb
·
verified ·
1 Parent(s): d65d1ea

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 sha256:643689c4f9588deb56f6e7c238659870b6a606b6a1058a736a05ab4d234b1d6b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b515ac24751ba02c6121e346d9da80dd316cf1f7933e1fcc8ff11b8e6a40aa
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63a86f837b1e13be48958cd791cbc8381eb2e2e52da92c69b0931977a5cf9199
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b67916fccc37908075e0eab6356924fd6c792fb0399bced52b68ef6dd18ff42
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d8ff8d600f1abc3b25579272eb4a500252e7043e2c5f9e960fdd3d44e10f5df
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02c99cc6b1a05ea89fafc05ea54061cbda1e78d3ea0a803a8309c7801506e48
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:541847167d5798b53241c48398508ad69b52941566a534197d7986ed7345f398
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d8de5a9801bc9e0fb5ef697c050a481374c81f994dbd9cc06cccc7ae00dc96
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -62,3 +62,66 @@
62
  {"current_steps": 62, "total_steps": 186, "loss": 0.9178, "lr": 8.451426344174433e-06, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:57:34", "remaining_time": "1:55:08"}
63
  {"current_steps": 63, "total_steps": 186, "loss": 1.1564, "lr": 8.382763991447344e-06, "epoch": 1.008, "percentage": 33.87, "elapsed_time": "0:59:24", "remaining_time": "1:55:59"}
64
  {"current_steps": 64, "total_steps": 186, "loss": 1.0139, "lr": 8.312904551775731e-06, "epoch": 1.024, "percentage": 34.41, "elapsed_time": "1:00:27", "remaining_time": "1:55:15"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  {"current_steps": 62, "total_steps": 186, "loss": 0.9178, "lr": 8.451426344174433e-06, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:57:34", "remaining_time": "1:55:08"}
63
  {"current_steps": 63, "total_steps": 186, "loss": 1.1564, "lr": 8.382763991447344e-06, "epoch": 1.008, "percentage": 33.87, "elapsed_time": "0:59:24", "remaining_time": "1:55:59"}
64
  {"current_steps": 64, "total_steps": 186, "loss": 1.0139, "lr": 8.312904551775731e-06, "epoch": 1.024, "percentage": 34.41, "elapsed_time": "1:00:27", "remaining_time": "1:55:15"}
65
+ {"current_steps": 65, "total_steps": 186, "loss": 0.8157, "lr": 8.241872746902934e-06, "epoch": 1.04, "percentage": 34.95, "elapsed_time": "1:01:17", "remaining_time": "1:54:06"}
66
+ {"current_steps": 66, "total_steps": 186, "loss": 0.7933, "lr": 8.16969371344696e-06, "epoch": 1.056, "percentage": 35.48, "elapsed_time": "1:02:13", "remaining_time": "1:53:08"}
67
+ {"current_steps": 67, "total_steps": 186, "loss": 0.9664, "lr": 8.096392994005177e-06, "epoch": 1.072, "percentage": 36.02, "elapsed_time": "1:03:17", "remaining_time": "1:52:23"}
68
+ {"current_steps": 68, "total_steps": 186, "loss": 0.8397, "lr": 8.021996528115335e-06, "epoch": 1.088, "percentage": 36.56, "elapsed_time": "1:04:03", "remaining_time": "1:51:09"}
69
+ {"current_steps": 69, "total_steps": 186, "loss": 0.8189, "lr": 7.946530643076138e-06, "epoch": 1.104, "percentage": 37.1, "elapsed_time": "1:04:54", "remaining_time": "1:50:03"}
70
+ {"current_steps": 70, "total_steps": 186, "loss": 0.8748, "lr": 7.870022044630569e-06, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "1:05:42", "remaining_time": "1:48:53"}
71
+ {"current_steps": 71, "total_steps": 186, "loss": 0.911, "lr": 7.792497807515317e-06, "epoch": 1.1360000000000001, "percentage": 38.17, "elapsed_time": "1:06:43", "remaining_time": "1:48:03"}
72
+ {"current_steps": 72, "total_steps": 186, "loss": 0.9038, "lr": 7.713985365879607e-06, "epoch": 1.152, "percentage": 38.71, "elapsed_time": "1:07:38", "remaining_time": "1:47:05"}
73
+ {"current_steps": 73, "total_steps": 186, "loss": 0.7338, "lr": 7.63451250357685e-06, "epoch": 1.168, "percentage": 39.25, "elapsed_time": "1:08:31", "remaining_time": "1:46:04"}
74
+ {"current_steps": 74, "total_steps": 186, "loss": 0.9501, "lr": 7.55410734433254e-06, "epoch": 1.184, "percentage": 39.78, "elapsed_time": "1:09:28", "remaining_time": "1:45:08"}
75
+ {"current_steps": 75, "total_steps": 186, "loss": 0.8639, "lr": 7.472798341791877e-06, "epoch": 1.2, "percentage": 40.32, "elapsed_time": "1:10:24", "remaining_time": "1:44:11"}
76
+ {"current_steps": 76, "total_steps": 186, "loss": 0.9042, "lr": 7.390614269450633e-06, "epoch": 1.216, "percentage": 40.86, "elapsed_time": "1:11:19", "remaining_time": "1:43:13"}
77
+ {"current_steps": 77, "total_steps": 186, "loss": 0.7982, "lr": 7.3075842104728445e-06, "epoch": 1.232, "percentage": 41.4, "elapsed_time": "1:12:12", "remaining_time": "1:42:13"}
78
+ {"current_steps": 78, "total_steps": 186, "loss": 0.8959, "lr": 7.223737547398898e-06, "epoch": 1.248, "percentage": 41.94, "elapsed_time": "1:13:08", "remaining_time": "1:41:16"}
79
+ {"current_steps": 79, "total_steps": 186, "loss": 0.771, "lr": 7.139103951747694e-06, "epoch": 1.264, "percentage": 42.47, "elapsed_time": "1:14:04", "remaining_time": "1:40:19"}
80
+ {"current_steps": 80, "total_steps": 186, "loss": 0.8581, "lr": 7.053713373516538e-06, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "1:14:56", "remaining_time": "1:39:18"}
81
+ {"current_steps": 81, "total_steps": 186, "loss": 0.8207, "lr": 6.9675960305824785e-06, "epoch": 1.296, "percentage": 43.55, "elapsed_time": "1:15:53", "remaining_time": "1:38:22"}
82
+ {"current_steps": 82, "total_steps": 186, "loss": 0.8967, "lr": 6.880782398008862e-06, "epoch": 1.312, "percentage": 44.09, "elapsed_time": "1:16:50", "remaining_time": "1:37:26"}
83
+ {"current_steps": 83, "total_steps": 186, "loss": 0.8124, "lr": 6.7933031972608644e-06, "epoch": 1.328, "percentage": 44.62, "elapsed_time": "1:17:39", "remaining_time": "1:36:22"}
84
+ {"current_steps": 84, "total_steps": 186, "loss": 0.8149, "lr": 6.70518938533383e-06, "epoch": 1.3439999999999999, "percentage": 45.16, "elapsed_time": "1:18:26", "remaining_time": "1:35:15"}
85
+ {"current_steps": 85, "total_steps": 186, "loss": 0.933, "lr": 6.61647214379826e-06, "epoch": 1.3599999999999999, "percentage": 45.7, "elapsed_time": "1:19:19", "remaining_time": "1:34:15"}
86
+ {"current_steps": 86, "total_steps": 186, "loss": 0.825, "lr": 6.527182867765333e-06, "epoch": 1.376, "percentage": 46.24, "elapsed_time": "1:20:11", "remaining_time": "1:33:14"}
87
+ {"current_steps": 87, "total_steps": 186, "loss": 0.8886, "lr": 6.437353154776848e-06, "epoch": 1.392, "percentage": 46.77, "elapsed_time": "1:21:08", "remaining_time": "1:32:20"}
88
+ {"current_steps": 88, "total_steps": 186, "loss": 0.7722, "lr": 6.3470147936235485e-06, "epoch": 1.408, "percentage": 47.31, "elapsed_time": "1:21:57", "remaining_time": "1:31:16"}
89
+ {"current_steps": 89, "total_steps": 186, "loss": 0.7361, "lr": 6.256199753095745e-06, "epoch": 1.424, "percentage": 47.85, "elapsed_time": "1:22:48", "remaining_time": "1:30:15"}
90
+ {"current_steps": 90, "total_steps": 186, "loss": 0.8923, "lr": 6.164940170670266e-06, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "1:23:49", "remaining_time": "1:29:24"}
91
+ {"current_steps": 91, "total_steps": 186, "loss": 0.8711, "lr": 6.073268341137694e-06, "epoch": 1.456, "percentage": 48.92, "elapsed_time": "1:24:44", "remaining_time": "1:28:28"}
92
+ {"current_steps": 92, "total_steps": 186, "loss": 0.884, "lr": 5.98121670517393e-06, "epoch": 1.472, "percentage": 49.46, "elapsed_time": "1:25:40", "remaining_time": "1:27:32"}
93
+ {"current_steps": 93, "total_steps": 186, "loss": 0.8121, "lr": 5.8888178378601565e-06, "epoch": 1.488, "percentage": 50.0, "elapsed_time": "1:26:28", "remaining_time": "1:26:28"}
94
+ {"current_steps": 94, "total_steps": 186, "loss": 0.7203, "lr": 5.796104437155213e-06, "epoch": 1.504, "percentage": 50.54, "elapsed_time": "1:27:28", "remaining_time": "1:25:36"}
95
+ {"current_steps": 95, "total_steps": 186, "loss": 0.9225, "lr": 5.703109312324493e-06, "epoch": 1.52, "percentage": 51.08, "elapsed_time": "1:28:23", "remaining_time": "1:24:40"}
96
+ {"current_steps": 96, "total_steps": 186, "loss": 0.8223, "lr": 5.609865372329461e-06, "epoch": 1.536, "percentage": 51.61, "elapsed_time": "1:29:23", "remaining_time": "1:23:47"}
97
+ {"current_steps": 97, "total_steps": 186, "loss": 0.8242, "lr": 5.516405614181883e-06, "epoch": 1.552, "percentage": 52.15, "elapsed_time": "1:30:21", "remaining_time": "1:22:54"}
98
+ {"current_steps": 98, "total_steps": 186, "loss": 0.8194, "lr": 5.4227631112668955e-06, "epoch": 1.568, "percentage": 52.69, "elapsed_time": "1:31:06", "remaining_time": "1:21:48"}
99
+ {"current_steps": 99, "total_steps": 186, "loss": 0.8811, "lr": 5.328971001639054e-06, "epoch": 1.584, "percentage": 53.23, "elapsed_time": "1:32:06", "remaining_time": "1:20:56"}
100
+ {"current_steps": 100, "total_steps": 186, "loss": 0.813, "lr": 5.235062476295488e-06, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "1:33:13", "remaining_time": "1:20:10"}
101
+ {"current_steps": 101, "total_steps": 186, "loss": 0.8624, "lr": 5.141070767430331e-06, "epoch": 1.616, "percentage": 54.3, "elapsed_time": "1:34:14", "remaining_time": "1:19:18"}
102
+ {"current_steps": 102, "total_steps": 186, "loss": 0.8966, "lr": 5.047029136674563e-06, "epoch": 1.6320000000000001, "percentage": 54.84, "elapsed_time": "1:35:13", "remaining_time": "1:18:24"}
103
+ {"current_steps": 103, "total_steps": 186, "loss": 0.7797, "lr": 4.95297086332544e-06, "epoch": 1.6480000000000001, "percentage": 55.38, "elapsed_time": "1:36:03", "remaining_time": "1:17:24"}
104
+ {"current_steps": 104, "total_steps": 186, "loss": 0.8263, "lr": 4.858929232569671e-06, "epoch": 1.6640000000000001, "percentage": 55.91, "elapsed_time": "1:37:01", "remaining_time": "1:16:29"}
105
+ {"current_steps": 105, "total_steps": 186, "loss": 0.8809, "lr": 4.7649375237045135e-06, "epoch": 1.6800000000000002, "percentage": 56.45, "elapsed_time": "1:38:07", "remaining_time": "1:15:41"}
106
+ {"current_steps": 106, "total_steps": 186, "loss": 0.8502, "lr": 4.671028998360947e-06, "epoch": 1.696, "percentage": 56.99, "elapsed_time": "1:39:05", "remaining_time": "1:14:47"}
107
+ {"current_steps": 107, "total_steps": 186, "loss": 0.827, "lr": 4.5772368887331044e-06, "epoch": 1.712, "percentage": 57.53, "elapsed_time": "1:39:55", "remaining_time": "1:13:46"}
108
+ {"current_steps": 108, "total_steps": 186, "loss": 0.8734, "lr": 4.483594385818119e-06, "epoch": 1.728, "percentage": 58.06, "elapsed_time": "1:40:57", "remaining_time": "1:12:54"}
109
+ {"current_steps": 109, "total_steps": 186, "loss": 0.8396, "lr": 4.39013462767054e-06, "epoch": 1.744, "percentage": 58.6, "elapsed_time": "1:41:56", "remaining_time": "1:12:00"}
110
+ {"current_steps": 110, "total_steps": 186, "loss": 0.8963, "lr": 4.29689068767551e-06, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "1:42:57", "remaining_time": "1:11:07"}
111
+ {"current_steps": 111, "total_steps": 186, "loss": 0.8408, "lr": 4.203895562844789e-06, "epoch": 1.776, "percentage": 59.68, "elapsed_time": "1:43:42", "remaining_time": "1:10:04"}
112
+ {"current_steps": 112, "total_steps": 186, "loss": 0.7991, "lr": 4.111182162139844e-06, "epoch": 1.792, "percentage": 60.22, "elapsed_time": "1:44:36", "remaining_time": "1:09:07"}
113
+ {"current_steps": 113, "total_steps": 186, "loss": 0.8497, "lr": 4.018783294826071e-06, "epoch": 1.808, "percentage": 60.75, "elapsed_time": "1:45:34", "remaining_time": "1:08:12"}
114
+ {"current_steps": 114, "total_steps": 186, "loss": 0.807, "lr": 3.926731658862307e-06, "epoch": 1.8239999999999998, "percentage": 61.29, "elapsed_time": "1:46:21", "remaining_time": "1:07:10"}
115
+ {"current_steps": 115, "total_steps": 186, "loss": 0.7939, "lr": 3.8350598293297345e-06, "epoch": 1.8399999999999999, "percentage": 61.83, "elapsed_time": "1:47:16", "remaining_time": "1:06:14"}
116
+ {"current_steps": 116, "total_steps": 186, "loss": 0.8904, "lr": 3.7438002469042567e-06, "epoch": 1.8559999999999999, "percentage": 62.37, "elapsed_time": "1:48:15", "remaining_time": "1:05:19"}
117
+ {"current_steps": 117, "total_steps": 186, "loss": 0.6929, "lr": 3.652985206376455e-06, "epoch": 1.8719999999999999, "percentage": 62.9, "elapsed_time": "1:49:08", "remaining_time": "1:04:22"}
118
+ {"current_steps": 118, "total_steps": 186, "loss": 0.8963, "lr": 3.5626468452231534e-06, "epoch": 1.888, "percentage": 63.44, "elapsed_time": "1:50:01", "remaining_time": "1:03:24"}
119
+ {"current_steps": 119, "total_steps": 186, "loss": 0.8742, "lr": 3.472817132234669e-06, "epoch": 1.904, "percentage": 63.98, "elapsed_time": "1:51:01", "remaining_time": "1:02:30"}
120
+ {"current_steps": 120, "total_steps": 186, "loss": 0.7919, "lr": 3.3835278562017405e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "1:52:00", "remaining_time": "1:01:36"}
121
+ {"current_steps": 121, "total_steps": 186, "loss": 0.8288, "lr": 3.29481061466617e-06, "epoch": 1.936, "percentage": 65.05, "elapsed_time": "1:52:52", "remaining_time": "1:00:38"}
122
+ {"current_steps": 122, "total_steps": 186, "loss": 0.857, "lr": 3.2066968027391377e-06, "epoch": 1.952, "percentage": 65.59, "elapsed_time": "1:53:53", "remaining_time": "0:59:44"}
123
+ {"current_steps": 123, "total_steps": 186, "loss": 0.8831, "lr": 3.119217601991139e-06, "epoch": 1.968, "percentage": 66.13, "elapsed_time": "1:54:43", "remaining_time": "0:58:45"}
124
+ {"current_steps": 124, "total_steps": 186, "loss": 0.8452, "lr": 3.032403969417523e-06, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "1:55:38", "remaining_time": "0:57:49"}
125
+ {"current_steps": 125, "total_steps": 186, "loss": 1.2448, "lr": 2.946286626483463e-06, "epoch": 2.0, "percentage": 67.2, "elapsed_time": "1:56:36", "remaining_time": "0:56:54"}
126
+ {"current_steps": 126, "total_steps": 186, "loss": 0.7986, "lr": 2.8608960482523058e-06, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "1:58:31", "remaining_time": "0:56:26"}
127
+ {"current_steps": 127, "total_steps": 186, "loss": 0.7906, "lr": 2.776262452601104e-06, "epoch": 2.032, "percentage": 68.28, "elapsed_time": "1:59:23", "remaining_time": "0:55:27"}