sedrickkeh commited on
Commit
18f9f0e
·
verified ·
1 Parent(s): e334966

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 sha256:439550c86a644ef33c99174a091647664a5ef335a2b98e390f6ea6a601357306
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a190dd601dc73eeb38f88b19d4867b541d5c944a61859f2174da05aa6c645ec8
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:ed49a857241163a3ead15d3bd87a644ddafd7718e9eea3a53370d79e22d3af46
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e2dce0330da8ed9061a3b6bdddfffcc0ec67766518066e5c52b878bbe4dc238
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:f09af0aba76b8ac10049d7ec00601970c857124beca76e816d26f5d802267f66
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0b69f06f941a65f042c55325113a404eda7e9695255fbeee246be16461b8f0
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:daee6effc19c228eb79da39e7dfbe89b9d1aff6135ec8759f612cc1e521d357f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0468e20ffba214f2d01be60087bed235fb296e770e1ce092b527a1a435c236
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -97,3 +97,52 @@
97
  {"current_steps": 97, "total_steps": 147, "loss": 0.55, "lr": 2.5133501773586905e-05, "epoch": 1.9573934837092732, "percentage": 65.99, "elapsed_time": "4:08:02", "remaining_time": "2:07:51"}
98
  {"current_steps": 98, "total_steps": 147, "loss": 0.5615, "lr": 2.425399127352235e-05, "epoch": 1.9774436090225564, "percentage": 66.67, "elapsed_time": "4:10:34", "remaining_time": "2:05:17"}
99
  {"current_steps": 99, "total_steps": 147, "loss": 0.984, "lr": 2.338339947992455e-05, "epoch": 2.0100250626566414, "percentage": 67.35, "elapsed_time": "4:14:41", "remaining_time": "2:03:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  {"current_steps": 97, "total_steps": 147, "loss": 0.55, "lr": 2.5133501773586905e-05, "epoch": 1.9573934837092732, "percentage": 65.99, "elapsed_time": "4:08:02", "remaining_time": "2:07:51"}
98
  {"current_steps": 98, "total_steps": 147, "loss": 0.5615, "lr": 2.425399127352235e-05, "epoch": 1.9774436090225564, "percentage": 66.67, "elapsed_time": "4:10:34", "remaining_time": "2:05:17"}
99
  {"current_steps": 99, "total_steps": 147, "loss": 0.984, "lr": 2.338339947992455e-05, "epoch": 2.0100250626566414, "percentage": 67.35, "elapsed_time": "4:14:41", "remaining_time": "2:03:29"}
100
+ {"current_steps": 100, "total_steps": 147, "loss": 0.5472, "lr": 2.2522219505225627e-05, "epoch": 2.030075187969925, "percentage": 68.03, "elapsed_time": "4:17:13", "remaining_time": "2:00:53"}
101
+ {"current_steps": 101, "total_steps": 147, "loss": 0.5246, "lr": 2.1670939130903585e-05, "epoch": 2.050125313283208, "percentage": 68.71, "elapsed_time": "4:19:46", "remaining_time": "1:58:18"}
102
+ {"current_steps": 102, "total_steps": 147, "loss": 0.5333, "lr": 2.0830040531197744e-05, "epoch": 2.0701754385964914, "percentage": 69.39, "elapsed_time": "4:22:18", "remaining_time": "1:55:43"}
103
+ {"current_steps": 103, "total_steps": 147, "loss": 0.5232, "lr": 2.0000000000000012e-05, "epoch": 2.090225563909774, "percentage": 70.07, "elapsed_time": "4:24:50", "remaining_time": "1:53:07"}
104
+ {"current_steps": 104, "total_steps": 147, "loss": 0.5299, "lr": 1.9181287681077116e-05, "epoch": 2.110275689223058, "percentage": 70.75, "elapsed_time": "4:27:22", "remaining_time": "1:50:32"}
105
+ {"current_steps": 105, "total_steps": 147, "loss": 0.5193, "lr": 1.8374367301776112e-05, "epoch": 2.1303258145363406, "percentage": 71.43, "elapsed_time": "4:29:53", "remaining_time": "1:47:57"}
106
+ {"current_steps": 106, "total_steps": 147, "loss": 0.5342, "lr": 1.7579695910364235e-05, "epoch": 2.1503759398496243, "percentage": 72.11, "elapsed_time": "4:32:24", "remaining_time": "1:45:22"}
107
+ {"current_steps": 107, "total_steps": 147, "loss": 0.5361, "lr": 1.679772361715208e-05, "epoch": 2.170426065162907, "percentage": 72.79, "elapsed_time": "4:34:55", "remaining_time": "1:42:46"}
108
+ {"current_steps": 108, "total_steps": 147, "loss": 0.5331, "lr": 1.6028893339546122e-05, "epoch": 2.1904761904761907, "percentage": 73.47, "elapsed_time": "4:37:26", "remaining_time": "1:40:11"}
109
+ {"current_steps": 109, "total_steps": 147, "loss": 0.5329, "lr": 1.527364055117579e-05, "epoch": 2.2105263157894735, "percentage": 74.15, "elapsed_time": "4:39:58", "remaining_time": "1:37:36"}
110
+ {"current_steps": 110, "total_steps": 147, "loss": 0.5323, "lr": 1.4532393035236477e-05, "epoch": 2.230576441102757, "percentage": 74.83, "elapsed_time": "4:42:31", "remaining_time": "1:35:01"}
111
+ {"current_steps": 111, "total_steps": 147, "loss": 0.5162, "lr": 1.3805570642188602e-05, "epoch": 2.25062656641604, "percentage": 75.51, "elapsed_time": "4:45:03", "remaining_time": "1:32:27"}
112
+ {"current_steps": 112, "total_steps": 147, "loss": 0.5258, "lr": 1.30935850519499e-05, "epoch": 2.2706766917293235, "percentage": 76.19, "elapsed_time": "4:47:35", "remaining_time": "1:29:52"}
113
+ {"current_steps": 113, "total_steps": 147, "loss": 0.5249, "lr": 1.2396839540715528e-05, "epoch": 2.2907268170426063, "percentage": 76.87, "elapsed_time": "4:50:05", "remaining_time": "1:27:17"}
114
+ {"current_steps": 114, "total_steps": 147, "loss": 0.5283, "lr": 1.1715728752538103e-05, "epoch": 2.31077694235589, "percentage": 77.55, "elapsed_time": "4:52:37", "remaining_time": "1:24:42"}
115
+ {"current_steps": 115, "total_steps": 147, "loss": 0.5264, "lr": 1.1050638475797193e-05, "epoch": 2.3308270676691727, "percentage": 78.23, "elapsed_time": "4:55:09", "remaining_time": "1:22:07"}
116
+ {"current_steps": 116, "total_steps": 147, "loss": 0.5258, "lr": 1.0401945424684653e-05, "epoch": 2.3508771929824563, "percentage": 78.91, "elapsed_time": "4:57:41", "remaining_time": "1:19:33"}
117
+ {"current_steps": 117, "total_steps": 147, "loss": 0.5125, "lr": 9.770017025829675e-06, "epoch": 2.370927318295739, "percentage": 79.59, "elapsed_time": "5:00:13", "remaining_time": "1:16:58"}
118
+ {"current_steps": 118, "total_steps": 147, "loss": 0.5215, "lr": 9.155211210184495e-06, "epoch": 2.3909774436090228, "percentage": 80.27, "elapsed_time": "5:02:46", "remaining_time": "1:14:24"}
119
+ {"current_steps": 119, "total_steps": 147, "loss": 0.5162, "lr": 8.55787621028851e-06, "epoch": 2.4110275689223055, "percentage": 80.95, "elapsed_time": "5:05:17", "remaining_time": "1:11:50"}
120
+ {"current_steps": 120, "total_steps": 147, "loss": 0.5343, "lr": 7.978350363025588e-06, "epoch": 2.431077694235589, "percentage": 81.63, "elapsed_time": "5:07:49", "remaining_time": "1:09:15"}
121
+ {"current_steps": 121, "total_steps": 147, "loss": 0.5219, "lr": 7.416961917986572e-06, "epoch": 2.451127819548872, "percentage": 82.31, "elapsed_time": "5:10:22", "remaining_time": "1:06:41"}
122
+ {"current_steps": 122, "total_steps": 147, "loss": 0.5212, "lr": 6.874028851545174e-06, "epoch": 2.4711779448621556, "percentage": 82.99, "elapsed_time": "5:12:58", "remaining_time": "1:04:07"}
123
+ {"current_steps": 123, "total_steps": 147, "loss": 0.5328, "lr": 6.349858686752748e-06, "epoch": 2.4912280701754383, "percentage": 83.67, "elapsed_time": "5:15:34", "remaining_time": "1:01:34"}
124
+ {"current_steps": 124, "total_steps": 147, "loss": 0.5282, "lr": 5.8447483191540784e-06, "epoch": 2.511278195488722, "percentage": 84.35, "elapsed_time": "5:18:09", "remaining_time": "0:59:00"}
125
+ {"current_steps": 125, "total_steps": 147, "loss": 0.5291, "lr": 5.358983848622452e-06, "epoch": 2.5313283208020048, "percentage": 85.03, "elapsed_time": "5:20:43", "remaining_time": "0:56:26"}
126
+ {"current_steps": 126, "total_steps": 147, "loss": 0.5174, "lr": 4.892840417309775e-06, "epoch": 2.5513784461152884, "percentage": 85.71, "elapsed_time": "5:23:16", "remaining_time": "0:53:52"}
127
+ {"current_steps": 127, "total_steps": 147, "loss": 0.5269, "lr": 4.446582053803066e-06, "epoch": 2.571428571428571, "percentage": 86.39, "elapsed_time": "5:25:48", "remaining_time": "0:51:18"}
128
+ {"current_steps": 128, "total_steps": 147, "loss": 0.5404, "lr": 4.020461523575873e-06, "epoch": 2.591478696741855, "percentage": 87.07, "elapsed_time": "5:28:19", "remaining_time": "0:48:44"}
129
+ {"current_steps": 129, "total_steps": 147, "loss": 0.5297, "lr": 3.6147201858192627e-06, "epoch": 2.6115288220551376, "percentage": 87.76, "elapsed_time": "5:30:53", "remaining_time": "0:46:10"}
130
+ {"current_steps": 130, "total_steps": 147, "loss": 0.5347, "lr": 3.2295878567333784e-06, "epoch": 2.6315789473684212, "percentage": 88.44, "elapsed_time": "5:33:26", "remaining_time": "0:43:36"}
131
+ {"current_steps": 131, "total_steps": 147, "loss": 0.5309, "lr": 2.8652826793570975e-06, "epoch": 2.651629072681704, "percentage": 89.12, "elapsed_time": "5:35:57", "remaining_time": "0:41:01"}
132
+ {"current_steps": 132, "total_steps": 147, "loss": 0.529, "lr": 2.5220110000095366e-06, "epoch": 2.6716791979949877, "percentage": 89.8, "elapsed_time": "5:38:30", "remaining_time": "0:38:27"}
133
+ {"current_steps": 133, "total_steps": 147, "loss": 0.526, "lr": 2.199967251413262e-06, "epoch": 2.6917293233082704, "percentage": 90.48, "elapsed_time": "5:41:01", "remaining_time": "0:35:53"}
134
+ {"current_steps": 134, "total_steps": 147, "loss": 0.5291, "lr": 1.8993338425655805e-06, "epoch": 2.711779448621554, "percentage": 91.16, "elapsed_time": "5:43:32", "remaining_time": "0:33:19"}
135
+ {"current_steps": 135, "total_steps": 147, "loss": 0.5287, "lr": 1.6202810554201099e-06, "epoch": 2.731829573934837, "percentage": 91.84, "elapsed_time": "5:46:04", "remaining_time": "0:30:45"}
136
+ {"current_steps": 136, "total_steps": 147, "loss": 0.519, "lr": 1.3629669484372722e-06, "epoch": 2.7518796992481205, "percentage": 92.52, "elapsed_time": "5:48:35", "remaining_time": "0:28:11"}
137
+ {"current_steps": 137, "total_steps": 147, "loss": 0.5299, "lr": 1.127537267058334e-06, "epoch": 2.7719298245614032, "percentage": 93.2, "elapsed_time": "5:51:06", "remaining_time": "0:25:37"}
138
+ {"current_steps": 138, "total_steps": 147, "loss": 0.5335, "lr": 9.141253611536238e-07, "epoch": 2.791979949874687, "percentage": 93.88, "elapsed_time": "5:53:38", "remaining_time": "0:23:03"}
139
+ {"current_steps": 139, "total_steps": 147, "loss": 0.5156, "lr": 7.228521094917318e-07, "epoch": 2.8120300751879697, "percentage": 94.56, "elapsed_time": "5:56:10", "remaining_time": "0:20:29"}
140
+ {"current_steps": 140, "total_steps": 147, "loss": 0.528, "lr": 5.538258512725403e-07, "epoch": 2.8320802005012533, "percentage": 95.24, "elapsed_time": "5:58:42", "remaining_time": "0:17:56"}
141
+ {"current_steps": 141, "total_steps": 147, "loss": 0.5205, "lr": 4.0714232476269265e-07, "epoch": 2.852130325814536, "percentage": 95.92, "elapsed_time": "6:01:14", "remaining_time": "0:15:22"}
142
+ {"current_steps": 142, "total_steps": 147, "loss": 0.5251, "lr": 2.8288461306846817e-07, "epoch": 2.8721804511278197, "percentage": 96.6, "elapsed_time": "6:03:45", "remaining_time": "0:12:48"}
143
+ {"current_steps": 143, "total_steps": 147, "loss": 0.5326, "lr": 1.8112309707661647e-07, "epoch": 2.8922305764411025, "percentage": 97.28, "elapsed_time": "6:06:16", "remaining_time": "0:10:14"}
144
+ {"current_steps": 144, "total_steps": 147, "loss": 0.5325, "lr": 1.019154155898594e-07, "epoch": 2.912280701754386, "percentage": 97.96, "elapsed_time": "6:08:47", "remaining_time": "0:07:40"}
145
+ {"current_steps": 145, "total_steps": 147, "loss": 0.5283, "lr": 4.530643267968149e-08, "epoch": 2.932330827067669, "percentage": 98.64, "elapsed_time": "6:11:18", "remaining_time": "0:05:07"}
146
+ {"current_steps": 146, "total_steps": 147, "loss": 0.5307, "lr": 1.1328212274839267e-08, "epoch": 2.9523809523809526, "percentage": 99.32, "elapsed_time": "6:13:50", "remaining_time": "0:02:33"}
147
+ {"current_steps": 147, "total_steps": 147, "loss": 0.5333, "lr": 0.0, "epoch": 2.9724310776942353, "percentage": 100.0, "elapsed_time": "6:16:22", "remaining_time": "0:00:00"}
148
+ {"current_steps": 147, "total_steps": 147, "epoch": 2.9724310776942353, "percentage": 100.0, "elapsed_time": "6:17:56", "remaining_time": "0:00:00"}