sedrickkeh commited on
Commit
cfaad29
·
verified ·
1 Parent(s): a17e0c8

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:b40baa79e355f518385f2f71be7e6a9951642e8e39a1d7b72e0b0658dac4e50c
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6163a7aaa3d2f6d276305db90b18d820129c62ee122da08b20afdd033c46210
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26a0a2f1ea5ba7a783d9838fb0c53d4480e3b1b6d136633ebf783f041c61e0e4
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f0d14f52310afbe4f6032dab226bac2da93dc4324bc3bc3b7f58d2ceaa2031
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:796cc19851ee8a9ea39b107e7004ca271d3ba982ffe54a9a5b224919885caf33
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b5cd4c969a1691d6303e25ad547f860944230180943af68fefd68d9359a949
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00bed98febbca8d425f5042b8c97f35251780f38a86a3266fb5d0348efbb611d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89da067a82fb5ea5adefeb89fbb82e6ba2e38880ea91d36c1a0ca55f5513c01
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -125,3 +125,128 @@
125
  {"current_steps": 125, "total_steps": 375, "loss": 0.8512, "lr": 8.443744651324828e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:54:26", "remaining_time": "3:48:52"}
126
  {"current_steps": 126, "total_steps": 375, "loss": 0.8784, "lr": 8.409802411019962e-06, "epoch": 1.008, "percentage": 33.6, "elapsed_time": "1:56:22", "remaining_time": "3:49:58"}
127
  {"current_steps": 127, "total_steps": 375, "loss": 0.8431, "lr": 8.375563847271506e-06, "epoch": 1.016, "percentage": 33.87, "elapsed_time": "1:57:17", "remaining_time": "3:49:03"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
125
  {"current_steps": 125, "total_steps": 375, "loss": 0.8512, "lr": 8.443744651324828e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:54:26", "remaining_time": "3:48:52"}
126
  {"current_steps": 126, "total_steps": 375, "loss": 0.8784, "lr": 8.409802411019962e-06, "epoch": 1.008, "percentage": 33.6, "elapsed_time": "1:56:22", "remaining_time": "3:49:58"}
127
  {"current_steps": 127, "total_steps": 375, "loss": 0.8431, "lr": 8.375563847271506e-06, "epoch": 1.016, "percentage": 33.87, "elapsed_time": "1:57:17", "remaining_time": "3:49:03"}
128
+ {"current_steps": 128, "total_steps": 375, "loss": 0.8489, "lr": 8.341031935527267e-06, "epoch": 1.024, "percentage": 34.13, "elapsed_time": "1:58:10", "remaining_time": "3:48:02"}
129
+ {"current_steps": 129, "total_steps": 375, "loss": 0.8586, "lr": 8.306209676727994e-06, "epoch": 1.032, "percentage": 34.4, "elapsed_time": "1:59:10", "remaining_time": "3:47:15"}
130
+ {"current_steps": 130, "total_steps": 375, "loss": 0.8498, "lr": 8.271100097046585e-06, "epoch": 1.04, "percentage": 34.67, "elapsed_time": "2:00:15", "remaining_time": "3:46:38"}
131
+ {"current_steps": 131, "total_steps": 375, "loss": 0.8249, "lr": 8.235706247625098e-06, "epoch": 1.048, "percentage": 34.93, "elapsed_time": "2:01:05", "remaining_time": "3:45:31"}
132
+ {"current_steps": 132, "total_steps": 375, "loss": 0.8051, "lr": 8.200031204309604e-06, "epoch": 1.056, "percentage": 35.2, "elapsed_time": "2:01:52", "remaining_time": "3:44:22"}
133
+ {"current_steps": 133, "total_steps": 375, "loss": 0.8263, "lr": 8.16407806738288e-06, "epoch": 1.064, "percentage": 35.47, "elapsed_time": "2:02:53", "remaining_time": "3:43:35"}
134
+ {"current_steps": 134, "total_steps": 375, "loss": 0.801, "lr": 8.127849961294984e-06, "epoch": 1.072, "percentage": 35.73, "elapsed_time": "2:03:43", "remaining_time": "3:42:31"}
135
+ {"current_steps": 135, "total_steps": 375, "loss": 0.8507, "lr": 8.091350034391732e-06, "epoch": 1.08, "percentage": 36.0, "elapsed_time": "2:04:41", "remaining_time": "3:41:40"}
136
+ {"current_steps": 136, "total_steps": 375, "loss": 0.836, "lr": 8.05458145864109e-06, "epoch": 1.088, "percentage": 36.27, "elapsed_time": "2:05:34", "remaining_time": "3:40:40"}
137
+ {"current_steps": 137, "total_steps": 375, "loss": 0.846, "lr": 8.017547429357532e-06, "epoch": 1.096, "percentage": 36.53, "elapsed_time": "2:06:25", "remaining_time": "3:39:37"}
138
+ {"current_steps": 138, "total_steps": 375, "loss": 0.8489, "lr": 7.980251164924342e-06, "epoch": 1.104, "percentage": 36.8, "elapsed_time": "2:07:23", "remaining_time": "3:38:47"}
139
+ {"current_steps": 139, "total_steps": 375, "loss": 0.8149, "lr": 7.94269590651393e-06, "epoch": 1.112, "percentage": 37.07, "elapsed_time": "2:08:11", "remaining_time": "3:37:38"}
140
+ {"current_steps": 140, "total_steps": 375, "loss": 0.8401, "lr": 7.904884917806174e-06, "epoch": 1.12, "percentage": 37.33, "elapsed_time": "2:09:05", "remaining_time": "3:36:41"}
141
+ {"current_steps": 141, "total_steps": 375, "loss": 0.8379, "lr": 7.866821484704777e-06, "epoch": 1.1280000000000001, "percentage": 37.6, "elapsed_time": "2:10:01", "remaining_time": "3:35:47"}
142
+ {"current_steps": 142, "total_steps": 375, "loss": 0.817, "lr": 7.828508915051724e-06, "epoch": 1.1360000000000001, "percentage": 37.87, "elapsed_time": "2:10:51", "remaining_time": "3:34:42"}
143
+ {"current_steps": 143, "total_steps": 375, "loss": 0.8452, "lr": 7.789950538339813e-06, "epoch": 1.144, "percentage": 38.13, "elapsed_time": "2:11:42", "remaining_time": "3:33:40"}
144
+ {"current_steps": 144, "total_steps": 375, "loss": 0.8404, "lr": 7.751149705423313e-06, "epoch": 1.152, "percentage": 38.4, "elapsed_time": "2:12:44", "remaining_time": "3:32:56"}
145
+ {"current_steps": 145, "total_steps": 375, "loss": 0.8142, "lr": 7.712109788226763e-06, "epoch": 1.16, "percentage": 38.67, "elapsed_time": "2:13:38", "remaining_time": "3:31:58"}
146
+ {"current_steps": 146, "total_steps": 375, "loss": 0.8746, "lr": 7.672834179451943e-06, "epoch": 1.168, "percentage": 38.93, "elapsed_time": "2:14:33", "remaining_time": "3:31:03"}
147
+ {"current_steps": 147, "total_steps": 375, "loss": 0.8469, "lr": 7.633326292283028e-06, "epoch": 1.176, "percentage": 39.2, "elapsed_time": "2:15:30", "remaining_time": "3:30:10"}
148
+ {"current_steps": 148, "total_steps": 375, "loss": 0.8328, "lr": 7.593589560089984e-06, "epoch": 1.184, "percentage": 39.47, "elapsed_time": "2:16:26", "remaining_time": "3:29:16"}
149
+ {"current_steps": 149, "total_steps": 375, "loss": 0.8582, "lr": 7.553627436130183e-06, "epoch": 1.192, "percentage": 39.73, "elapsed_time": "2:17:15", "remaining_time": "3:28:10"}
150
+ {"current_steps": 150, "total_steps": 375, "loss": 0.8558, "lr": 7.513443393248312e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "2:18:10", "remaining_time": "3:27:16"}
151
+ {"current_steps": 151, "total_steps": 375, "loss": 0.8549, "lr": 7.473040923574567e-06, "epoch": 1.208, "percentage": 40.27, "elapsed_time": "2:19:03", "remaining_time": "3:26:17"}
152
+ {"current_steps": 152, "total_steps": 375, "loss": 0.8473, "lr": 7.432423538221179e-06, "epoch": 1.216, "percentage": 40.53, "elapsed_time": "2:20:04", "remaining_time": "3:25:29"}
153
+ {"current_steps": 153, "total_steps": 375, "loss": 0.8281, "lr": 7.391594766977277e-06, "epoch": 1.224, "percentage": 40.8, "elapsed_time": "2:21:04", "remaining_time": "3:24:41"}
154
+ {"current_steps": 154, "total_steps": 375, "loss": 0.8419, "lr": 7.350558158002154e-06, "epoch": 1.232, "percentage": 41.07, "elapsed_time": "2:21:55", "remaining_time": "3:23:39"}
155
+ {"current_steps": 155, "total_steps": 375, "loss": 0.8408, "lr": 7.3093172775169e-06, "epoch": 1.24, "percentage": 41.33, "elapsed_time": "2:22:43", "remaining_time": "3:22:35"}
156
+ {"current_steps": 156, "total_steps": 375, "loss": 0.8345, "lr": 7.2678757094945e-06, "epoch": 1.248, "percentage": 41.6, "elapsed_time": "2:23:41", "remaining_time": "3:21:43"}
157
+ {"current_steps": 157, "total_steps": 375, "loss": 0.8654, "lr": 7.226237055348369e-06, "epoch": 1.256, "percentage": 41.87, "elapsed_time": "2:24:36", "remaining_time": "3:20:47"}
158
+ {"current_steps": 158, "total_steps": 375, "loss": 0.8387, "lr": 7.184404933619377e-06, "epoch": 1.264, "percentage": 42.13, "elapsed_time": "2:25:29", "remaining_time": "3:19:48"}
159
+ {"current_steps": 159, "total_steps": 375, "loss": 0.8317, "lr": 7.142382979661386e-06, "epoch": 1.272, "percentage": 42.4, "elapsed_time": "2:26:18", "remaining_time": "3:18:45"}
160
+ {"current_steps": 160, "total_steps": 375, "loss": 0.8281, "lr": 7.100174845325327e-06, "epoch": 1.28, "percentage": 42.67, "elapsed_time": "2:27:18", "remaining_time": "3:17:56"}
161
+ {"current_steps": 161, "total_steps": 375, "loss": 0.8646, "lr": 7.057784198641835e-06, "epoch": 1.288, "percentage": 42.93, "elapsed_time": "2:28:15", "remaining_time": "3:17:03"}
162
+ {"current_steps": 162, "total_steps": 375, "loss": 0.8293, "lr": 7.015214723502496e-06, "epoch": 1.296, "percentage": 43.2, "elapsed_time": "2:29:07", "remaining_time": "3:16:04"}
163
+ {"current_steps": 163, "total_steps": 375, "loss": 0.8097, "lr": 6.972470119339692e-06, "epoch": 1.304, "percentage": 43.47, "elapsed_time": "2:30:02", "remaining_time": "3:15:09"}
164
+ {"current_steps": 164, "total_steps": 375, "loss": 0.85, "lr": 6.929554100805118e-06, "epoch": 1.312, "percentage": 43.73, "elapsed_time": "2:31:00", "remaining_time": "3:14:16"}
165
+ {"current_steps": 165, "total_steps": 375, "loss": 0.8343, "lr": 6.886470397446958e-06, "epoch": 1.32, "percentage": 44.0, "elapsed_time": "2:31:57", "remaining_time": "3:13:24"}
166
+ {"current_steps": 166, "total_steps": 375, "loss": 0.7749, "lr": 6.843222753385785e-06, "epoch": 1.328, "percentage": 44.27, "elapsed_time": "2:32:50", "remaining_time": "3:12:26"}
167
+ {"current_steps": 167, "total_steps": 375, "loss": 0.8165, "lr": 6.799814926989171e-06, "epoch": 1.336, "percentage": 44.53, "elapsed_time": "2:33:42", "remaining_time": "3:11:26"}
168
+ {"current_steps": 168, "total_steps": 375, "loss": 0.8349, "lr": 6.756250690545079e-06, "epoch": 1.3439999999999999, "percentage": 44.8, "elapsed_time": "2:34:50", "remaining_time": "3:10:46"}
169
+ {"current_steps": 169, "total_steps": 375, "loss": 0.8224, "lr": 6.712533829934042e-06, "epoch": 1.3519999999999999, "percentage": 45.07, "elapsed_time": "2:35:51", "remaining_time": "3:09:59"}
170
+ {"current_steps": 170, "total_steps": 375, "loss": 0.8518, "lr": 6.6686681443001485e-06, "epoch": 1.3599999999999999, "percentage": 45.33, "elapsed_time": "2:36:55", "remaining_time": "3:09:14"}
171
+ {"current_steps": 171, "total_steps": 375, "loss": 0.8736, "lr": 6.62465744572089e-06, "epoch": 1.3679999999999999, "percentage": 45.6, "elapsed_time": "2:37:47", "remaining_time": "3:08:14"}
172
+ {"current_steps": 172, "total_steps": 375, "loss": 0.8171, "lr": 6.580505558875878e-06, "epoch": 1.376, "percentage": 45.87, "elapsed_time": "2:38:38", "remaining_time": "3:07:14"}
173
+ {"current_steps": 173, "total_steps": 375, "loss": 0.8325, "lr": 6.536216320714466e-06, "epoch": 1.384, "percentage": 46.13, "elapsed_time": "2:39:34", "remaining_time": "3:06:19"}
174
+ {"current_steps": 174, "total_steps": 375, "loss": 0.8348, "lr": 6.491793580122301e-06, "epoch": 1.392, "percentage": 46.4, "elapsed_time": "2:40:22", "remaining_time": "3:05:15"}
175
+ {"current_steps": 175, "total_steps": 375, "loss": 0.8679, "lr": 6.447241197586847e-06, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "2:41:24", "remaining_time": "3:04:28"}
176
+ {"current_steps": 176, "total_steps": 375, "loss": 0.8414, "lr": 6.402563044861899e-06, "epoch": 1.408, "percentage": 46.93, "elapsed_time": "2:42:21", "remaining_time": "3:03:34"}
177
+ {"current_steps": 177, "total_steps": 375, "loss": 0.7706, "lr": 6.357763004631104e-06, "epoch": 1.416, "percentage": 47.2, "elapsed_time": "2:43:06", "remaining_time": "3:02:27"}
178
+ {"current_steps": 178, "total_steps": 375, "loss": 0.8145, "lr": 6.312844970170551e-06, "epoch": 1.424, "percentage": 47.47, "elapsed_time": "2:43:55", "remaining_time": "3:01:25"}
179
+ {"current_steps": 179, "total_steps": 375, "loss": 0.8071, "lr": 6.267812845010431e-06, "epoch": 1.432, "percentage": 47.73, "elapsed_time": "2:44:53", "remaining_time": "3:00:33"}
180
+ {"current_steps": 180, "total_steps": 375, "loss": 0.8338, "lr": 6.2226705425958e-06, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "2:45:53", "remaining_time": "2:59:42"}
181
+ {"current_steps": 181, "total_steps": 375, "loss": 0.856, "lr": 6.177421985946499e-06, "epoch": 1.448, "percentage": 48.27, "elapsed_time": "2:47:01", "remaining_time": "2:59:00"}
182
+ {"current_steps": 182, "total_steps": 375, "loss": 0.8405, "lr": 6.132071107316221e-06, "epoch": 1.456, "percentage": 48.53, "elapsed_time": "2:48:01", "remaining_time": "2:58:10"}
183
+ {"current_steps": 183, "total_steps": 375, "loss": 0.848, "lr": 6.0866218478507875e-06, "epoch": 1.464, "percentage": 48.8, "elapsed_time": "2:49:05", "remaining_time": "2:57:24"}
184
+ {"current_steps": 184, "total_steps": 375, "loss": 0.8139, "lr": 6.041078157245649e-06, "epoch": 1.472, "percentage": 49.07, "elapsed_time": "2:50:02", "remaining_time": "2:56:31"}
185
+ {"current_steps": 185, "total_steps": 375, "loss": 0.8267, "lr": 5.995443993402647e-06, "epoch": 1.48, "percentage": 49.33, "elapsed_time": "2:50:59", "remaining_time": "2:55:36"}
186
+ {"current_steps": 186, "total_steps": 375, "loss": 0.8011, "lr": 5.949723322086053e-06, "epoch": 1.488, "percentage": 49.6, "elapsed_time": "2:51:53", "remaining_time": "2:54:39"}
187
+ {"current_steps": 187, "total_steps": 375, "loss": 0.786, "lr": 5.9039201165779315e-06, "epoch": 1.496, "percentage": 49.87, "elapsed_time": "2:52:45", "remaining_time": "2:53:40"}
188
+ {"current_steps": 188, "total_steps": 375, "loss": 0.8083, "lr": 5.858038357332851e-06, "epoch": 1.504, "percentage": 50.13, "elapsed_time": "2:53:43", "remaining_time": "2:52:48"}
189
+ {"current_steps": 189, "total_steps": 375, "loss": 0.8421, "lr": 5.812082031631966e-06, "epoch": 1.512, "percentage": 50.4, "elapsed_time": "2:54:32", "remaining_time": "2:51:45"}
190
+ {"current_steps": 190, "total_steps": 375, "loss": 0.823, "lr": 5.766055133236513e-06, "epoch": 1.52, "percentage": 50.67, "elapsed_time": "2:55:27", "remaining_time": "2:50:50"}
191
+ {"current_steps": 191, "total_steps": 375, "loss": 0.8309, "lr": 5.7199616620407325e-06, "epoch": 1.528, "percentage": 50.93, "elapsed_time": "2:56:24", "remaining_time": "2:49:56"}
192
+ {"current_steps": 192, "total_steps": 375, "loss": 0.8088, "lr": 5.673805623724272e-06, "epoch": 1.536, "percentage": 51.2, "elapsed_time": "2:57:27", "remaining_time": "2:49:08"}
193
+ {"current_steps": 193, "total_steps": 375, "loss": 0.8199, "lr": 5.627591029404072e-06, "epoch": 1.544, "percentage": 51.47, "elapsed_time": "2:58:24", "remaining_time": "2:48:14"}
194
+ {"current_steps": 194, "total_steps": 375, "loss": 0.8194, "lr": 5.581321895285787e-06, "epoch": 1.552, "percentage": 51.73, "elapsed_time": "2:59:11", "remaining_time": "2:47:10"}
195
+ {"current_steps": 195, "total_steps": 375, "loss": 0.8176, "lr": 5.535002242314772e-06, "epoch": 1.56, "percentage": 52.0, "elapsed_time": "3:00:07", "remaining_time": "2:46:16"}
196
+ {"current_steps": 196, "total_steps": 375, "loss": 0.8078, "lr": 5.488636095826636e-06, "epoch": 1.568, "percentage": 52.27, "elapsed_time": "3:00:57", "remaining_time": "2:45:15"}
197
+ {"current_steps": 197, "total_steps": 375, "loss": 0.8397, "lr": 5.4422274851974356e-06, "epoch": 1.576, "percentage": 52.53, "elapsed_time": "3:02:00", "remaining_time": "2:44:27"}
198
+ {"current_steps": 198, "total_steps": 375, "loss": 0.8549, "lr": 5.395780443493508e-06, "epoch": 1.584, "percentage": 52.8, "elapsed_time": "3:02:56", "remaining_time": "2:43:32"}
199
+ {"current_steps": 199, "total_steps": 375, "loss": 0.7686, "lr": 5.34929900712098e-06, "epoch": 1.592, "percentage": 53.07, "elapsed_time": "3:03:39", "remaining_time": "2:42:25"}
200
+ {"current_steps": 200, "total_steps": 375, "loss": 0.8329, "lr": 5.302787215474992e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "3:04:33", "remaining_time": "2:41:29"}
201
+ {"current_steps": 201, "total_steps": 375, "loss": 0.833, "lr": 5.256249110588659e-06, "epoch": 1.608, "percentage": 53.6, "elapsed_time": "3:05:37", "remaining_time": "2:40:41"}
202
+ {"current_steps": 202, "total_steps": 375, "loss": 0.812, "lr": 5.209688736781811e-06, "epoch": 1.616, "percentage": 53.87, "elapsed_time": "3:06:30", "remaining_time": "2:39:43"}
203
+ {"current_steps": 203, "total_steps": 375, "loss": 0.8408, "lr": 5.163110140309518e-06, "epoch": 1.624, "percentage": 54.13, "elapsed_time": "3:07:26", "remaining_time": "2:38:48"}
204
+ {"current_steps": 204, "total_steps": 375, "loss": 0.8294, "lr": 5.116517369010467e-06, "epoch": 1.6320000000000001, "percentage": 54.4, "elapsed_time": "3:08:14", "remaining_time": "2:37:47"}
205
+ {"current_steps": 205, "total_steps": 375, "loss": 0.7811, "lr": 5.069914471955179e-06, "epoch": 1.6400000000000001, "percentage": 54.67, "elapsed_time": "3:09:05", "remaining_time": "2:36:48"}
206
+ {"current_steps": 206, "total_steps": 375, "loss": 0.8307, "lr": 5.023305499094145e-06, "epoch": 1.6480000000000001, "percentage": 54.93, "elapsed_time": "3:10:07", "remaining_time": "2:35:58"}
207
+ {"current_steps": 207, "total_steps": 375, "loss": 0.8046, "lr": 4.976694500905858e-06, "epoch": 1.6560000000000001, "percentage": 55.2, "elapsed_time": "3:10:56", "remaining_time": "2:34:57"}
208
+ {"current_steps": 208, "total_steps": 375, "loss": 0.8315, "lr": 4.930085528044823e-06, "epoch": 1.6640000000000001, "percentage": 55.47, "elapsed_time": "3:11:51", "remaining_time": "2:34:02"}
209
+ {"current_steps": 209, "total_steps": 375, "loss": 0.8472, "lr": 4.883482630989536e-06, "epoch": 1.6720000000000002, "percentage": 55.73, "elapsed_time": "3:12:44", "remaining_time": "2:33:05"}
210
+ {"current_steps": 210, "total_steps": 375, "loss": 0.8163, "lr": 4.8368898596904834e-06, "epoch": 1.6800000000000002, "percentage": 56.0, "elapsed_time": "3:13:36", "remaining_time": "2:32:07"}
211
+ {"current_steps": 211, "total_steps": 375, "loss": 0.8362, "lr": 4.790311263218191e-06, "epoch": 1.688, "percentage": 56.27, "elapsed_time": "3:14:29", "remaining_time": "2:31:09"}
212
+ {"current_steps": 212, "total_steps": 375, "loss": 0.8364, "lr": 4.743750889411342e-06, "epoch": 1.696, "percentage": 56.53, "elapsed_time": "3:15:29", "remaining_time": "2:30:18"}
213
+ {"current_steps": 213, "total_steps": 375, "loss": 0.8156, "lr": 4.697212784525009e-06, "epoch": 1.704, "percentage": 56.8, "elapsed_time": "3:16:28", "remaining_time": "2:29:25"}
214
+ {"current_steps": 214, "total_steps": 375, "loss": 0.8363, "lr": 4.65070099287902e-06, "epoch": 1.712, "percentage": 57.07, "elapsed_time": "3:17:29", "remaining_time": "2:28:35"}
215
+ {"current_steps": 215, "total_steps": 375, "loss": 0.8252, "lr": 4.604219556506492e-06, "epoch": 1.72, "percentage": 57.33, "elapsed_time": "3:18:26", "remaining_time": "2:27:40"}
216
+ {"current_steps": 216, "total_steps": 375, "loss": 0.8188, "lr": 4.557772514802564e-06, "epoch": 1.728, "percentage": 57.6, "elapsed_time": "3:19:24", "remaining_time": "2:26:47"}
217
+ {"current_steps": 217, "total_steps": 375, "loss": 0.835, "lr": 4.511363904173366e-06, "epoch": 1.736, "percentage": 57.87, "elapsed_time": "3:20:23", "remaining_time": "2:25:54"}
218
+ {"current_steps": 218, "total_steps": 375, "loss": 0.8072, "lr": 4.46499775768523e-06, "epoch": 1.744, "percentage": 58.13, "elapsed_time": "3:21:17", "remaining_time": "2:24:58"}
219
+ {"current_steps": 219, "total_steps": 375, "loss": 0.8331, "lr": 4.418678104714214e-06, "epoch": 1.752, "percentage": 58.4, "elapsed_time": "3:22:09", "remaining_time": "2:24:00"}
220
+ {"current_steps": 220, "total_steps": 375, "loss": 0.8031, "lr": 4.372408970595931e-06, "epoch": 1.76, "percentage": 58.67, "elapsed_time": "3:23:05", "remaining_time": "2:23:05"}
221
+ {"current_steps": 221, "total_steps": 375, "loss": 0.8117, "lr": 4.326194376275729e-06, "epoch": 1.768, "percentage": 58.93, "elapsed_time": "3:24:06", "remaining_time": "2:22:13"}
222
+ {"current_steps": 222, "total_steps": 375, "loss": 0.8137, "lr": 4.280038337959268e-06, "epoch": 1.776, "percentage": 59.2, "elapsed_time": "3:24:56", "remaining_time": "2:21:14"}
223
+ {"current_steps": 223, "total_steps": 375, "loss": 0.7834, "lr": 4.2339448667634885e-06, "epoch": 1.784, "percentage": 59.47, "elapsed_time": "3:25:48", "remaining_time": "2:20:16"}
224
+ {"current_steps": 224, "total_steps": 375, "loss": 0.8227, "lr": 4.187917968368036e-06, "epoch": 1.792, "percentage": 59.73, "elapsed_time": "3:26:44", "remaining_time": "2:19:22"}
225
+ {"current_steps": 225, "total_steps": 375, "loss": 0.8526, "lr": 4.141961642667152e-06, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "3:27:46", "remaining_time": "2:18:31"}
226
+ {"current_steps": 226, "total_steps": 375, "loss": 0.8529, "lr": 4.09607988342207e-06, "epoch": 1.808, "percentage": 60.27, "elapsed_time": "3:28:44", "remaining_time": "2:17:37"}
227
+ {"current_steps": 227, "total_steps": 375, "loss": 0.8142, "lr": 4.0502766779139485e-06, "epoch": 1.8159999999999998, "percentage": 60.53, "elapsed_time": "3:29:38", "remaining_time": "2:16:41"}
228
+ {"current_steps": 228, "total_steps": 375, "loss": 0.8127, "lr": 4.0045560065973535e-06, "epoch": 1.8239999999999998, "percentage": 60.8, "elapsed_time": "3:30:41", "remaining_time": "2:15:50"}
229
+ {"current_steps": 229, "total_steps": 375, "loss": 0.8405, "lr": 3.958921842754351e-06, "epoch": 1.8319999999999999, "percentage": 61.07, "elapsed_time": "3:31:36", "remaining_time": "2:14:54"}
230
+ {"current_steps": 230, "total_steps": 375, "loss": 0.7938, "lr": 3.913378152149214e-06, "epoch": 1.8399999999999999, "percentage": 61.33, "elapsed_time": "3:32:22", "remaining_time": "2:13:53"}
231
+ {"current_steps": 231, "total_steps": 375, "loss": 0.8237, "lr": 3.86792889268378e-06, "epoch": 1.8479999999999999, "percentage": 61.6, "elapsed_time": "3:33:23", "remaining_time": "2:13:01"}
232
+ {"current_steps": 232, "total_steps": 375, "loss": 0.8157, "lr": 3.8225780140535025e-06, "epoch": 1.8559999999999999, "percentage": 61.87, "elapsed_time": "3:34:15", "remaining_time": "2:12:03"}
233
+ {"current_steps": 233, "total_steps": 375, "loss": 0.8471, "lr": 3.777329457404202e-06, "epoch": 1.8639999999999999, "percentage": 62.13, "elapsed_time": "3:35:04", "remaining_time": "2:11:04"}
234
+ {"current_steps": 234, "total_steps": 375, "loss": 0.8184, "lr": 3.7321871549895715e-06, "epoch": 1.8719999999999999, "percentage": 62.4, "elapsed_time": "3:36:00", "remaining_time": "2:10:09"}
235
+ {"current_steps": 235, "total_steps": 375, "loss": 0.8048, "lr": 3.68715502982945e-06, "epoch": 1.88, "percentage": 62.67, "elapsed_time": "3:36:52", "remaining_time": "2:09:12"}
236
+ {"current_steps": 236, "total_steps": 375, "loss": 0.8462, "lr": 3.6422369953688973e-06, "epoch": 1.888, "percentage": 62.93, "elapsed_time": "3:37:50", "remaining_time": "2:08:18"}
237
+ {"current_steps": 237, "total_steps": 375, "loss": 0.814, "lr": 3.5974369551381023e-06, "epoch": 1.896, "percentage": 63.2, "elapsed_time": "3:38:41", "remaining_time": "2:07:20"}
238
+ {"current_steps": 238, "total_steps": 375, "loss": 0.8076, "lr": 3.5527588024131542e-06, "epoch": 1.904, "percentage": 63.47, "elapsed_time": "3:39:47", "remaining_time": "2:06:31"}
239
+ {"current_steps": 239, "total_steps": 375, "loss": 0.8063, "lr": 3.5082064198777e-06, "epoch": 1.912, "percentage": 63.73, "elapsed_time": "3:40:42", "remaining_time": "2:05:35"}
240
+ {"current_steps": 240, "total_steps": 375, "loss": 0.8212, "lr": 3.463783679285535e-06, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "3:41:36", "remaining_time": "2:04:39"}
241
+ {"current_steps": 241, "total_steps": 375, "loss": 0.8087, "lr": 3.4194944411241213e-06, "epoch": 1.928, "percentage": 64.27, "elapsed_time": "3:42:30", "remaining_time": "2:03:43"}
242
+ {"current_steps": 242, "total_steps": 375, "loss": 0.8116, "lr": 3.3753425542791106e-06, "epoch": 1.936, "percentage": 64.53, "elapsed_time": "3:43:22", "remaining_time": "2:02:45"}
243
+ {"current_steps": 243, "total_steps": 375, "loss": 0.8062, "lr": 3.3313318556998523e-06, "epoch": 1.944, "percentage": 64.8, "elapsed_time": "3:44:14", "remaining_time": "2:01:48"}
244
+ {"current_steps": 244, "total_steps": 375, "loss": 0.8428, "lr": 3.2874661700659586e-06, "epoch": 1.952, "percentage": 65.07, "elapsed_time": "3:45:09", "remaining_time": "2:00:52"}
245
+ {"current_steps": 245, "total_steps": 375, "loss": 0.8268, "lr": 3.2437493094549223e-06, "epoch": 1.96, "percentage": 65.33, "elapsed_time": "3:46:05", "remaining_time": "1:59:58"}
246
+ {"current_steps": 246, "total_steps": 375, "loss": 0.8086, "lr": 3.200185073010831e-06, "epoch": 1.968, "percentage": 65.6, "elapsed_time": "3:46:58", "remaining_time": "1:59:01"}
247
+ {"current_steps": 247, "total_steps": 375, "loss": 0.8212, "lr": 3.1567772466142156e-06, "epoch": 1.976, "percentage": 65.87, "elapsed_time": "3:47:54", "remaining_time": "1:58:06"}
248
+ {"current_steps": 248, "total_steps": 375, "loss": 0.8217, "lr": 3.1135296025530426e-06, "epoch": 1.984, "percentage": 66.13, "elapsed_time": "3:48:59", "remaining_time": "1:57:15"}
249
+ {"current_steps": 249, "total_steps": 375, "loss": 0.8394, "lr": 3.070445899194885e-06, "epoch": 1.992, "percentage": 66.4, "elapsed_time": "3:49:53", "remaining_time": "1:56:19"}
250
+ {"current_steps": 250, "total_steps": 375, "loss": 0.8254, "lr": 3.0275298806603102e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:50:41", "remaining_time": "1:55:20"}
251
+ {"current_steps": 251, "total_steps": 375, "loss": 0.7948, "lr": 2.984785276497507e-06, "epoch": 2.008, "percentage": 66.93, "elapsed_time": "3:52:43", "remaining_time": "1:54:58"}
252
+ {"current_steps": 252, "total_steps": 375, "loss": 0.7709, "lr": 2.9422158013581658e-06, "epoch": 2.016, "percentage": 67.2, "elapsed_time": "3:53:34", "remaining_time": "1:54:00"}