sedrickkeh commited on
Commit
2a87ee0
·
verified ·
1 Parent(s): 0e5faad

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:fbed3a95a23542fde6274aed9329d62c687e9e51e2a7c12433db3d84eba8bd9c
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b7a3ccd9cfb29e79a7b58616a42fc9720e98c7a3d18be7e0396c9e710038ed
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:461569734e10f3f1ee497f5b4a91bf468f525fb0032666b625eca2a71d6d5dd4
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86d52ea0730dbdd1c9b7438f83bd8a7b57321dcbf2a648ecf28f2d8867df569
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:aa467bbc0c0cc72928f6812861f481c7bd432d6a8cf84142c88609ec150fdd7e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9006154c9b0b93413f8ff4b718efa20c349d08f6b795fd530feff89a411a5f4
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0047785afb9f5bb807f15cea25b24cdf96e4ce6ebfe0d8eb755b36c6131f7cd6
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48bdf6f2b5aaa50149cbb4d9e3689d36014623256c5f8482478df4f7a4d5ce96
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -116,3 +116,42 @@
116
  {"current_steps": 116, "total_steps": 156, "loss": 0.5989, "lr": 1.8825509907063328e-06, "epoch": 2.21656050955414, "percentage": 74.36, "elapsed_time": "0:26:11", "remaining_time": "0:09:01"}
117
  {"current_steps": 117, "total_steps": 156, "loss": 0.6264, "lr": 1.7956219300748796e-06, "epoch": 2.2356687898089174, "percentage": 75.0, "elapsed_time": "0:26:25", "remaining_time": "0:08:48"}
118
  {"current_steps": 118, "total_steps": 156, "loss": 0.5717, "lr": 1.7103063703014372e-06, "epoch": 2.254777070063694, "percentage": 75.64, "elapsed_time": "0:26:37", "remaining_time": "0:08:34"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
  {"current_steps": 116, "total_steps": 156, "loss": 0.5989, "lr": 1.8825509907063328e-06, "epoch": 2.21656050955414, "percentage": 74.36, "elapsed_time": "0:26:11", "remaining_time": "0:09:01"}
117
  {"current_steps": 117, "total_steps": 156, "loss": 0.6264, "lr": 1.7956219300748796e-06, "epoch": 2.2356687898089174, "percentage": 75.0, "elapsed_time": "0:26:25", "remaining_time": "0:08:48"}
118
  {"current_steps": 118, "total_steps": 156, "loss": 0.5717, "lr": 1.7103063703014372e-06, "epoch": 2.254777070063694, "percentage": 75.64, "elapsed_time": "0:26:37", "remaining_time": "0:08:34"}
119
+ {"current_steps": 119, "total_steps": 156, "loss": 0.608, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:26:49", "remaining_time": "0:08:20"}
120
+ {"current_steps": 120, "total_steps": 156, "loss": 0.6242, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:26:59", "remaining_time": "0:08:05"}
121
+ {"current_steps": 121, "total_steps": 156, "loss": 0.5927, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:27:08", "remaining_time": "0:07:50"}
122
+ {"current_steps": 122, "total_steps": 156, "loss": 0.5857, "lr": 1.3860256808630429e-06, "epoch": 2.3312101910828025, "percentage": 78.21, "elapsed_time": "0:27:21", "remaining_time": "0:07:37"}
123
+ {"current_steps": 123, "total_steps": 156, "loss": 0.6115, "lr": 1.3094050125632973e-06, "epoch": 2.3503184713375798, "percentage": 78.85, "elapsed_time": "0:27:36", "remaining_time": "0:07:24"}
124
+ {"current_steps": 124, "total_steps": 156, "loss": 0.5559, "lr": 1.234642669981946e-06, "epoch": 2.3694267515923566, "percentage": 79.49, "elapsed_time": "0:27:51", "remaining_time": "0:07:11"}
125
+ {"current_steps": 125, "total_steps": 156, "loss": 0.6358, "lr": 1.1617762982099446e-06, "epoch": 2.388535031847134, "percentage": 80.13, "elapsed_time": "0:28:04", "remaining_time": "0:06:57"}
126
+ {"current_steps": 126, "total_steps": 156, "loss": 0.5673, "lr": 1.0908425876598512e-06, "epoch": 2.4076433121019107, "percentage": 80.77, "elapsed_time": "0:28:15", "remaining_time": "0:06:43"}
127
+ {"current_steps": 127, "total_steps": 156, "loss": 0.603, "lr": 1.0218772555910955e-06, "epoch": 2.426751592356688, "percentage": 81.41, "elapsed_time": "0:28:26", "remaining_time": "0:06:29"}
128
+ {"current_steps": 128, "total_steps": 156, "loss": 0.6113, "lr": 9.549150281252633e-07, "epoch": 2.445859872611465, "percentage": 82.05, "elapsed_time": "0:28:40", "remaining_time": "0:06:16"}
129
+ {"current_steps": 129, "total_steps": 156, "loss": 0.601, "lr": 8.899896227604509e-07, "epoch": 2.464968152866242, "percentage": 82.69, "elapsed_time": "0:28:59", "remaining_time": "0:06:04"}
130
+ {"current_steps": 130, "total_steps": 156, "loss": 0.5505, "lr": 8.271337313934869e-07, "epoch": 2.484076433121019, "percentage": 83.33, "elapsed_time": "0:29:07", "remaining_time": "0:05:49"}
131
+ {"current_steps": 131, "total_steps": 156, "loss": 0.6827, "lr": 7.663790038585794e-07, "epoch": 2.5031847133757963, "percentage": 83.97, "elapsed_time": "0:29:19", "remaining_time": "0:05:35"}
132
+ {"current_steps": 132, "total_steps": 156, "loss": 0.5709, "lr": 7.077560319906696e-07, "epoch": 2.522292993630573, "percentage": 84.62, "elapsed_time": "0:29:32", "remaining_time": "0:05:22"}
133
+ {"current_steps": 133, "total_steps": 156, "loss": 0.6091, "lr": 6.512943342215234e-07, "epoch": 2.5414012738853504, "percentage": 85.26, "elapsed_time": "0:29:45", "remaining_time": "0:05:08"}
134
+ {"current_steps": 134, "total_steps": 156, "loss": 0.5609, "lr": 5.9702234071631e-07, "epoch": 2.5605095541401273, "percentage": 85.9, "elapsed_time": "0:29:55", "remaining_time": "0:04:54"}
135
+ {"current_steps": 135, "total_steps": 156, "loss": 0.5865, "lr": 5.449673790581611e-07, "epoch": 2.5796178343949046, "percentage": 86.54, "elapsed_time": "0:30:05", "remaining_time": "0:04:40"}
136
+ {"current_steps": 136, "total_steps": 156, "loss": 0.5847, "lr": 4.951556604879049e-07, "epoch": 2.5987261146496814, "percentage": 87.18, "elapsed_time": "0:30:17", "remaining_time": "0:04:27"}
137
+ {"current_steps": 137, "total_steps": 156, "loss": 0.5941, "lr": 4.4761226670592074e-07, "epoch": 2.6178343949044587, "percentage": 87.82, "elapsed_time": "0:30:26", "remaining_time": "0:04:13"}
138
+ {"current_steps": 138, "total_steps": 156, "loss": 0.6, "lr": 4.0236113724274716e-07, "epoch": 2.6369426751592355, "percentage": 88.46, "elapsed_time": "0:30:37", "remaining_time": "0:03:59"}
139
+ {"current_steps": 139, "total_steps": 156, "loss": 0.5928, "lr": 3.5942505740480583e-07, "epoch": 2.656050955414013, "percentage": 89.1, "elapsed_time": "0:30:48", "remaining_time": "0:03:46"}
140
+ {"current_steps": 140, "total_steps": 156, "loss": 0.5801, "lr": 3.18825646801314e-07, "epoch": 2.6751592356687897, "percentage": 89.74, "elapsed_time": "0:30:58", "remaining_time": "0:03:32"}
141
+ {"current_steps": 141, "total_steps": 156, "loss": 0.6199, "lr": 2.8058334845816214e-07, "epoch": 2.694267515923567, "percentage": 90.38, "elapsed_time": "0:31:10", "remaining_time": "0:03:19"}
142
+ {"current_steps": 142, "total_steps": 156, "loss": 0.6229, "lr": 2.447174185242324e-07, "epoch": 2.713375796178344, "percentage": 91.03, "elapsed_time": "0:31:21", "remaining_time": "0:03:05"}
143
+ {"current_steps": 143, "total_steps": 156, "loss": 0.6053, "lr": 2.1124591657534776e-07, "epoch": 2.732484076433121, "percentage": 91.67, "elapsed_time": "0:31:35", "remaining_time": "0:02:52"}
144
+ {"current_steps": 144, "total_steps": 156, "loss": 0.5444, "lr": 1.801856965207338e-07, "epoch": 2.7515923566878984, "percentage": 92.31, "elapsed_time": "0:31:47", "remaining_time": "0:02:38"}
145
+ {"current_steps": 145, "total_steps": 156, "loss": 0.5756, "lr": 1.5155239811656562e-07, "epoch": 2.770700636942675, "percentage": 92.95, "elapsed_time": "0:31:57", "remaining_time": "0:02:25"}
146
+ {"current_steps": 146, "total_steps": 156, "loss": 0.6188, "lr": 1.253604390908819e-07, "epoch": 2.789808917197452, "percentage": 93.59, "elapsed_time": "0:32:13", "remaining_time": "0:02:12"}
147
+ {"current_steps": 147, "total_steps": 156, "loss": 0.6433, "lr": 1.0162300788382263e-07, "epoch": 2.8089171974522293, "percentage": 94.23, "elapsed_time": "0:32:26", "remaining_time": "0:01:59"}
148
+ {"current_steps": 148, "total_steps": 156, "loss": 0.5587, "lr": 8.035205700685167e-08, "epoch": 2.8280254777070066, "percentage": 94.87, "elapsed_time": "0:32:39", "remaining_time": "0:01:45"}
149
+ {"current_steps": 149, "total_steps": 156, "loss": 0.5927, "lr": 6.15582970243117e-08, "epoch": 2.8471337579617835, "percentage": 95.51, "elapsed_time": "0:33:06", "remaining_time": "0:01:33"}
150
+ {"current_steps": 150, "total_steps": 156, "loss": 0.5883, "lr": 4.52511911603265e-08, "epoch": 2.8662420382165603, "percentage": 96.15, "elapsed_time": "0:33:20", "remaining_time": "0:01:20"}
151
+ {"current_steps": 151, "total_steps": 156, "loss": 0.5976, "lr": 3.143895053378698e-08, "epoch": 2.8853503184713376, "percentage": 96.79, "elapsed_time": "0:33:30", "remaining_time": "0:01:06"}
152
+ {"current_steps": 152, "total_steps": 156, "loss": 0.5732, "lr": 2.012853002380466e-08, "epoch": 2.904458598726115, "percentage": 97.44, "elapsed_time": "0:33:43", "remaining_time": "0:00:53"}
153
+ {"current_steps": 153, "total_steps": 156, "loss": 0.6537, "lr": 1.132562476771959e-08, "epoch": 2.9235668789808917, "percentage": 98.08, "elapsed_time": "0:34:14", "remaining_time": "0:00:40"}
154
+ {"current_steps": 154, "total_steps": 156, "loss": 0.5774, "lr": 5.034667293427053e-09, "epoch": 2.9426751592356686, "percentage": 98.72, "elapsed_time": "0:34:25", "remaining_time": "0:00:26"}
155
+ {"current_steps": 155, "total_steps": 156, "loss": 0.58, "lr": 1.2588252874673469e-09, "epoch": 2.961783439490446, "percentage": 99.36, "elapsed_time": "0:34:34", "remaining_time": "0:00:13"}
156
+ {"current_steps": 156, "total_steps": 156, "loss": 0.6071, "lr": 0.0, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:34:44", "remaining_time": "0:00:00"}
157
+ {"current_steps": 156, "total_steps": 156, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:36:14", "remaining_time": "0:00:00"}