sedrickkeh commited on
Commit
69e3448
·
verified ·
1 Parent(s): 0df405d

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 sha256:23e1febe08632b91f6577f6eee889397e3f5291bb21995418b7c9c89ae4e9302
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d808dc4c78854c14b828a1c3a60482f5b5c63fd1917bc1ced53bb39104dc8284
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16c3ab5e9d7eaff3c6b55a511752416294e3557448da4c6278d81951efc2e00f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6e3d0affdd6361909a6f17af31b50b0c806e7bcbdf470181326c70e99981df
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:f9946600f7020c757ce53f636916ad5ff6fee20c29449d7d1439f50791ab6bf1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9918978a827dbb7cc8e02ab5a69468714343f4f03fad192379942599311135e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53bb995d017074067b5a5457d68704a5c4b0972d98265bacd50d695e1d64441c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39550a156071d86485f513bf62d6bd054606b0cdb88dfe8955d1a1a977df5adc
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -119,3 +119,39 @@
119
  {"current_steps": 119, "total_steps": 156, "loss": 0.6113, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:23:03", "remaining_time": "0:07:10"}
120
  {"current_steps": 120, "total_steps": 156, "loss": 0.6283, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:23:11", "remaining_time": "0:06:57"}
121
  {"current_steps": 121, "total_steps": 156, "loss": 0.5991, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:23:18", "remaining_time": "0:06:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119
  {"current_steps": 119, "total_steps": 156, "loss": 0.6113, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:23:03", "remaining_time": "0:07:10"}
120
  {"current_steps": 120, "total_steps": 156, "loss": 0.6283, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:23:11", "remaining_time": "0:06:57"}
121
  {"current_steps": 121, "total_steps": 156, "loss": 0.5991, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:23:18", "remaining_time": "0:06:44"}
122
+ {"current_steps": 122, "total_steps": 156, "loss": 0.5943, "lr": 1.3860256808630429e-06, "epoch": 2.3312101910828025, "percentage": 78.21, "elapsed_time": "0:23:29", "remaining_time": "0:06:32"}
123
+ {"current_steps": 123, "total_steps": 156, "loss": 0.61, "lr": 1.3094050125632973e-06, "epoch": 2.3503184713375798, "percentage": 78.85, "elapsed_time": "0:23:43", "remaining_time": "0:06:21"}
124
+ {"current_steps": 124, "total_steps": 156, "loss": 0.5619, "lr": 1.234642669981946e-06, "epoch": 2.3694267515923566, "percentage": 79.49, "elapsed_time": "0:23:56", "remaining_time": "0:06:10"}
125
+ {"current_steps": 125, "total_steps": 156, "loss": 0.6469, "lr": 1.1617762982099446e-06, "epoch": 2.388535031847134, "percentage": 80.13, "elapsed_time": "0:24:06", "remaining_time": "0:05:58"}
126
+ {"current_steps": 126, "total_steps": 156, "loss": 0.5711, "lr": 1.0908425876598512e-06, "epoch": 2.4076433121019107, "percentage": 80.77, "elapsed_time": "0:24:15", "remaining_time": "0:05:46"}
127
+ {"current_steps": 127, "total_steps": 156, "loss": 0.6099, "lr": 1.0218772555910955e-06, "epoch": 2.426751592356688, "percentage": 81.41, "elapsed_time": "0:24:24", "remaining_time": "0:05:34"}
128
+ {"current_steps": 128, "total_steps": 156, "loss": 0.6232, "lr": 9.549150281252633e-07, "epoch": 2.445859872611465, "percentage": 82.05, "elapsed_time": "0:24:36", "remaining_time": "0:05:22"}
129
+ {"current_steps": 129, "total_steps": 156, "loss": 0.6051, "lr": 8.899896227604509e-07, "epoch": 2.464968152866242, "percentage": 82.69, "elapsed_time": "0:24:53", "remaining_time": "0:05:12"}
130
+ {"current_steps": 130, "total_steps": 156, "loss": 0.5551, "lr": 8.271337313934869e-07, "epoch": 2.484076433121019, "percentage": 83.33, "elapsed_time": "0:24:59", "remaining_time": "0:04:59"}
131
+ {"current_steps": 131, "total_steps": 156, "loss": 0.6801, "lr": 7.663790038585794e-07, "epoch": 2.5031847133757963, "percentage": 83.97, "elapsed_time": "0:25:09", "remaining_time": "0:04:48"}
132
+ {"current_steps": 132, "total_steps": 156, "loss": 0.5733, "lr": 7.077560319906696e-07, "epoch": 2.522292993630573, "percentage": 84.62, "elapsed_time": "0:25:19", "remaining_time": "0:04:36"}
133
+ {"current_steps": 133, "total_steps": 156, "loss": 0.6124, "lr": 6.512943342215234e-07, "epoch": 2.5414012738853504, "percentage": 85.26, "elapsed_time": "0:25:30", "remaining_time": "0:04:24"}
134
+ {"current_steps": 134, "total_steps": 156, "loss": 0.5694, "lr": 5.9702234071631e-07, "epoch": 2.5605095541401273, "percentage": 85.9, "elapsed_time": "0:25:38", "remaining_time": "0:04:12"}
135
+ {"current_steps": 135, "total_steps": 156, "loss": 0.5906, "lr": 5.449673790581611e-07, "epoch": 2.5796178343949046, "percentage": 86.54, "elapsed_time": "0:25:47", "remaining_time": "0:04:00"}
136
+ {"current_steps": 136, "total_steps": 156, "loss": 0.596, "lr": 4.951556604879049e-07, "epoch": 2.5987261146496814, "percentage": 87.18, "elapsed_time": "0:25:57", "remaining_time": "0:03:48"}
137
+ {"current_steps": 137, "total_steps": 156, "loss": 0.6075, "lr": 4.4761226670592074e-07, "epoch": 2.6178343949044587, "percentage": 87.82, "elapsed_time": "0:26:04", "remaining_time": "0:03:36"}
138
+ {"current_steps": 138, "total_steps": 156, "loss": 0.6073, "lr": 4.0236113724274716e-07, "epoch": 2.6369426751592355, "percentage": 88.46, "elapsed_time": "0:26:12", "remaining_time": "0:03:25"}
139
+ {"current_steps": 139, "total_steps": 156, "loss": 0.5987, "lr": 3.5942505740480583e-07, "epoch": 2.656050955414013, "percentage": 89.1, "elapsed_time": "0:26:22", "remaining_time": "0:03:13"}
140
+ {"current_steps": 140, "total_steps": 156, "loss": 0.5869, "lr": 3.18825646801314e-07, "epoch": 2.6751592356687897, "percentage": 89.74, "elapsed_time": "0:26:30", "remaining_time": "0:03:01"}
141
+ {"current_steps": 141, "total_steps": 156, "loss": 0.6231, "lr": 2.8058334845816214e-07, "epoch": 2.694267515923567, "percentage": 90.38, "elapsed_time": "0:26:40", "remaining_time": "0:02:50"}
142
+ {"current_steps": 142, "total_steps": 156, "loss": 0.6306, "lr": 2.447174185242324e-07, "epoch": 2.713375796178344, "percentage": 91.03, "elapsed_time": "0:26:48", "remaining_time": "0:02:38"}
143
+ {"current_steps": 143, "total_steps": 156, "loss": 0.6098, "lr": 2.1124591657534776e-07, "epoch": 2.732484076433121, "percentage": 91.67, "elapsed_time": "0:27:01", "remaining_time": "0:02:27"}
144
+ {"current_steps": 144, "total_steps": 156, "loss": 0.5506, "lr": 1.801856965207338e-07, "epoch": 2.7515923566878984, "percentage": 92.31, "elapsed_time": "0:27:11", "remaining_time": "0:02:15"}
145
+ {"current_steps": 145, "total_steps": 156, "loss": 0.5764, "lr": 1.5155239811656562e-07, "epoch": 2.770700636942675, "percentage": 92.95, "elapsed_time": "0:27:19", "remaining_time": "0:02:04"}
146
+ {"current_steps": 146, "total_steps": 156, "loss": 0.6209, "lr": 1.253604390908819e-07, "epoch": 2.789808917197452, "percentage": 93.59, "elapsed_time": "0:27:32", "remaining_time": "0:01:53"}
147
+ {"current_steps": 147, "total_steps": 156, "loss": 0.6466, "lr": 1.0162300788382263e-07, "epoch": 2.8089171974522293, "percentage": 94.23, "elapsed_time": "0:27:43", "remaining_time": "0:01:41"}
148
+ {"current_steps": 148, "total_steps": 156, "loss": 0.5619, "lr": 8.035205700685167e-08, "epoch": 2.8280254777070066, "percentage": 94.87, "elapsed_time": "0:27:54", "remaining_time": "0:01:30"}
149
+ {"current_steps": 149, "total_steps": 156, "loss": 0.6001, "lr": 6.15582970243117e-08, "epoch": 2.8471337579617835, "percentage": 95.51, "elapsed_time": "0:28:17", "remaining_time": "0:01:19"}
150
+ {"current_steps": 150, "total_steps": 156, "loss": 0.5876, "lr": 4.52511911603265e-08, "epoch": 2.8662420382165603, "percentage": 96.15, "elapsed_time": "0:28:30", "remaining_time": "0:01:08"}
151
+ {"current_steps": 151, "total_steps": 156, "loss": 0.6018, "lr": 3.143895053378698e-08, "epoch": 2.8853503184713376, "percentage": 96.79, "elapsed_time": "0:28:37", "remaining_time": "0:00:56"}
152
+ {"current_steps": 152, "total_steps": 156, "loss": 0.5735, "lr": 2.012853002380466e-08, "epoch": 2.904458598726115, "percentage": 97.44, "elapsed_time": "0:28:48", "remaining_time": "0:00:45"}
153
+ {"current_steps": 153, "total_steps": 156, "loss": 0.6618, "lr": 1.132562476771959e-08, "epoch": 2.9235668789808917, "percentage": 98.08, "elapsed_time": "0:29:16", "remaining_time": "0:00:34"}
154
+ {"current_steps": 154, "total_steps": 156, "loss": 0.582, "lr": 5.034667293427053e-09, "epoch": 2.9426751592356686, "percentage": 98.72, "elapsed_time": "0:29:25", "remaining_time": "0:00:22"}
155
+ {"current_steps": 155, "total_steps": 156, "loss": 0.5935, "lr": 1.2588252874673469e-09, "epoch": 2.961783439490446, "percentage": 99.36, "elapsed_time": "0:29:32", "remaining_time": "0:00:11"}
156
+ {"current_steps": 156, "total_steps": 156, "loss": 0.6098, "lr": 0.0, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:29:39", "remaining_time": "0:00:00"}
157
+ {"current_steps": 156, "total_steps": 156, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:31:10", "remaining_time": "0:00:00"}