neginr commited on
Commit
9bbd630
·
verified ·
1 Parent(s): 3adfa21

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:867c09ca7488e0b53538e07ece7910f9cddc709326924ee3b0c789cd87c95a68
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52091116c1e7702d425c3d524995efb2fbe7adc769cec142067fc484cef4deda
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:669af510ccf69863b7ec7644cdc314b812cd337e7e206544b178543efa45b86e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d369e6ec1fc0fc49cc17dbabba6c9878762cbd5987bea4786f343979afd68c13
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:e76ce8056b9c5bf2e510baaf8052a73dd11c6a107437b7fb84cc1bae53526a99
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a92d421ca1615160f5ad9631cc025d185684fbde161523f42e180e871bcbf1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1110f99ec37c558504d1be8a822f8f10edde50601c68700dd7c0586642810245
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e40e3b9f5fcb7613df1f8485e62a8181cc1ee81267d148e5d85dc9f30a0e7f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -134,3 +134,58 @@
134
  {"current_steps": 134, "total_steps": 364, "loss": 0.3283, "lr": 1.5963020014335437e-05, "epoch": 2.5605095541401273, "percentage": 36.81, "elapsed_time": "0:15:15", "remaining_time": "0:26:11"}
135
  {"current_steps": 135, "total_steps": 364, "loss": 0.3597, "lr": 1.588562229179443e-05, "epoch": 2.5796178343949046, "percentage": 37.09, "elapsed_time": "0:15:20", "remaining_time": "0:26:00"}
136
  {"current_steps": 136, "total_steps": 364, "loss": 0.361, "lr": 1.5807681327318372e-05, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:15:24", "remaining_time": "0:25:49"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  {"current_steps": 134, "total_steps": 364, "loss": 0.3283, "lr": 1.5963020014335437e-05, "epoch": 2.5605095541401273, "percentage": 36.81, "elapsed_time": "0:15:15", "remaining_time": "0:26:11"}
135
  {"current_steps": 135, "total_steps": 364, "loss": 0.3597, "lr": 1.588562229179443e-05, "epoch": 2.5796178343949046, "percentage": 37.09, "elapsed_time": "0:15:20", "remaining_time": "0:26:00"}
136
  {"current_steps": 136, "total_steps": 364, "loss": 0.361, "lr": 1.5807681327318372e-05, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:15:24", "remaining_time": "0:25:49"}
137
+ {"current_steps": 137, "total_steps": 364, "loss": 0.3604, "lr": 1.5729204314845002e-05, "epoch": 2.6178343949044587, "percentage": 37.64, "elapsed_time": "0:15:28", "remaining_time": "0:25:38"}
138
+ {"current_steps": 138, "total_steps": 364, "loss": 0.3523, "lr": 1.56501984977892e-05, "epoch": 2.6369426751592355, "percentage": 37.91, "elapsed_time": "0:15:32", "remaining_time": "0:25:27"}
139
+ {"current_steps": 139, "total_steps": 364, "loss": 0.299, "lr": 1.557067116837444e-05, "epoch": 2.656050955414013, "percentage": 38.19, "elapsed_time": "0:15:36", "remaining_time": "0:25:15"}
140
+ {"current_steps": 140, "total_steps": 364, "loss": 0.3457, "lr": 1.5490629666959668e-05, "epoch": 2.6751592356687897, "percentage": 38.46, "elapsed_time": "0:15:40", "remaining_time": "0:25:04"}
141
+ {"current_steps": 141, "total_steps": 364, "loss": 0.3444, "lr": 1.541008138136183e-05, "epoch": 2.694267515923567, "percentage": 38.74, "elapsed_time": "0:15:44", "remaining_time": "0:24:54"}
142
+ {"current_steps": 142, "total_steps": 364, "loss": 0.3729, "lr": 1.5329033746173975e-05, "epoch": 2.713375796178344, "percentage": 39.01, "elapsed_time": "0:15:50", "remaining_time": "0:24:45"}
143
+ {"current_steps": 143, "total_steps": 364, "loss": 0.326, "lr": 1.5247494242079024e-05, "epoch": 2.732484076433121, "percentage": 39.29, "elapsed_time": "0:15:55", "remaining_time": "0:24:36"}
144
+ {"current_steps": 144, "total_steps": 364, "loss": 0.3256, "lr": 1.5165470395159314e-05, "epoch": 2.7515923566878984, "percentage": 39.56, "elapsed_time": "0:15:59", "remaining_time": "0:24:25"}
145
+ {"current_steps": 145, "total_steps": 364, "loss": 0.3161, "lr": 1.5082969776201948e-05, "epoch": 2.770700636942675, "percentage": 39.84, "elapsed_time": "0:16:03", "remaining_time": "0:24:15"}
146
+ {"current_steps": 146, "total_steps": 364, "loss": 0.3379, "lr": 1.5000000000000002e-05, "epoch": 2.789808917197452, "percentage": 40.11, "elapsed_time": "0:16:07", "remaining_time": "0:24:04"}
147
+ {"current_steps": 147, "total_steps": 364, "loss": 0.3501, "lr": 1.4916568724649688e-05, "epoch": 2.8089171974522293, "percentage": 40.38, "elapsed_time": "0:16:11", "remaining_time": "0:23:54"}
148
+ {"current_steps": 148, "total_steps": 364, "loss": 0.3216, "lr": 1.483268365084351e-05, "epoch": 2.8280254777070066, "percentage": 40.66, "elapsed_time": "0:16:15", "remaining_time": "0:23:44"}
149
+ {"current_steps": 149, "total_steps": 364, "loss": 0.3653, "lr": 1.4748352521159492e-05, "epoch": 2.8471337579617835, "percentage": 40.93, "elapsed_time": "0:16:20", "remaining_time": "0:23:34"}
150
+ {"current_steps": 150, "total_steps": 364, "loss": 0.3613, "lr": 1.466358311934654e-05, "epoch": 2.8662420382165603, "percentage": 41.21, "elapsed_time": "0:16:24", "remaining_time": "0:23:25"}
151
+ {"current_steps": 151, "total_steps": 364, "loss": 0.3194, "lr": 1.4578383269606004e-05, "epoch": 2.8853503184713376, "percentage": 41.48, "elapsed_time": "0:16:28", "remaining_time": "0:23:14"}
152
+ {"current_steps": 152, "total_steps": 364, "loss": 0.3425, "lr": 1.4492760835869504e-05, "epoch": 2.904458598726115, "percentage": 41.76, "elapsed_time": "0:16:32", "remaining_time": "0:23:04"}
153
+ {"current_steps": 153, "total_steps": 364, "loss": 0.3483, "lr": 1.4406723721073088e-05, "epoch": 2.9235668789808917, "percentage": 42.03, "elapsed_time": "0:16:41", "remaining_time": "0:23:00"}
154
+ {"current_steps": 154, "total_steps": 364, "loss": 0.3504, "lr": 1.4320279866427798e-05, "epoch": 2.9426751592356686, "percentage": 42.31, "elapsed_time": "0:16:47", "remaining_time": "0:22:53"}
155
+ {"current_steps": 155, "total_steps": 364, "loss": 0.3707, "lr": 1.4233437250686695e-05, "epoch": 2.961783439490446, "percentage": 42.58, "elapsed_time": "0:16:53", "remaining_time": "0:22:45"}
156
+ {"current_steps": 156, "total_steps": 364, "loss": 0.3321, "lr": 1.4146203889408418e-05, "epoch": 2.980891719745223, "percentage": 42.86, "elapsed_time": "0:17:01", "remaining_time": "0:22:41"}
157
+ {"current_steps": 157, "total_steps": 364, "loss": 0.3053, "lr": 1.4058587834217356e-05, "epoch": 3.0, "percentage": 43.13, "elapsed_time": "0:17:06", "remaining_time": "0:22:33"}
158
+ {"current_steps": 158, "total_steps": 364, "loss": 0.2188, "lr": 1.3970597172060482e-05, "epoch": 3.0191082802547773, "percentage": 43.41, "elapsed_time": "0:18:50", "remaining_time": "0:24:33"}
159
+ {"current_steps": 159, "total_steps": 364, "loss": 0.1843, "lr": 1.3882240024460928e-05, "epoch": 3.038216560509554, "percentage": 43.68, "elapsed_time": "0:18:54", "remaining_time": "0:24:22"}
160
+ {"current_steps": 160, "total_steps": 364, "loss": 0.201, "lr": 1.3793524546768358e-05, "epoch": 3.0573248407643314, "percentage": 43.96, "elapsed_time": "0:18:59", "remaining_time": "0:24:13"}
161
+ {"current_steps": 161, "total_steps": 364, "loss": 0.2039, "lr": 1.3704458927406261e-05, "epoch": 3.0764331210191083, "percentage": 44.23, "elapsed_time": "0:19:05", "remaining_time": "0:24:04"}
162
+ {"current_steps": 162, "total_steps": 364, "loss": 0.2, "lr": 1.3615051387116131e-05, "epoch": 3.0955414012738856, "percentage": 44.51, "elapsed_time": "0:19:09", "remaining_time": "0:23:53"}
163
+ {"current_steps": 163, "total_steps": 364, "loss": 0.2408, "lr": 1.3525310178198707e-05, "epoch": 3.1146496815286624, "percentage": 44.78, "elapsed_time": "0:19:13", "remaining_time": "0:23:42"}
164
+ {"current_steps": 164, "total_steps": 364, "loss": 0.2229, "lr": 1.3435243583752294e-05, "epoch": 3.1337579617834397, "percentage": 45.05, "elapsed_time": "0:19:20", "remaining_time": "0:23:35"}
165
+ {"current_steps": 165, "total_steps": 364, "loss": 0.2032, "lr": 1.3344859916908206e-05, "epoch": 3.1528662420382165, "percentage": 45.33, "elapsed_time": "0:19:27", "remaining_time": "0:23:28"}
166
+ {"current_steps": 166, "total_steps": 364, "loss": 0.2025, "lr": 1.325416752006351e-05, "epoch": 3.171974522292994, "percentage": 45.6, "elapsed_time": "0:19:34", "remaining_time": "0:23:21"}
167
+ {"current_steps": 167, "total_steps": 364, "loss": 0.1829, "lr": 1.3163174764110985e-05, "epoch": 3.1910828025477707, "percentage": 45.88, "elapsed_time": "0:19:38", "remaining_time": "0:23:10"}
168
+ {"current_steps": 168, "total_steps": 364, "loss": 0.227, "lr": 1.3071890047666498e-05, "epoch": 3.210191082802548, "percentage": 46.15, "elapsed_time": "0:19:44", "remaining_time": "0:23:01"}
169
+ {"current_steps": 169, "total_steps": 364, "loss": 0.2156, "lr": 1.2980321796293838e-05, "epoch": 3.229299363057325, "percentage": 46.43, "elapsed_time": "0:19:48", "remaining_time": "0:22:51"}
170
+ {"current_steps": 170, "total_steps": 364, "loss": 0.2216, "lr": 1.288847846172701e-05, "epoch": 3.248407643312102, "percentage": 46.7, "elapsed_time": "0:19:52", "remaining_time": "0:22:40"}
171
+ {"current_steps": 171, "total_steps": 364, "loss": 0.2107, "lr": 1.2796368521090143e-05, "epoch": 3.267515923566879, "percentage": 46.98, "elapsed_time": "0:19:57", "remaining_time": "0:22:31"}
172
+ {"current_steps": 172, "total_steps": 364, "loss": 0.2395, "lr": 1.2704000476115079e-05, "epoch": 3.286624203821656, "percentage": 47.25, "elapsed_time": "0:20:01", "remaining_time": "0:22:21"}
173
+ {"current_steps": 173, "total_steps": 364, "loss": 0.2083, "lr": 1.2611382852356632e-05, "epoch": 3.305732484076433, "percentage": 47.53, "elapsed_time": "0:20:08", "remaining_time": "0:22:14"}
174
+ {"current_steps": 174, "total_steps": 364, "loss": 0.2076, "lr": 1.2518524198405699e-05, "epoch": 3.3248407643312103, "percentage": 47.8, "elapsed_time": "0:20:12", "remaining_time": "0:22:04"}
175
+ {"current_steps": 175, "total_steps": 364, "loss": 0.1926, "lr": 1.2425433085100224e-05, "epoch": 3.343949044585987, "percentage": 48.08, "elapsed_time": "0:20:16", "remaining_time": "0:21:53"}
176
+ {"current_steps": 176, "total_steps": 364, "loss": 0.2096, "lr": 1.233211810473411e-05, "epoch": 3.3630573248407645, "percentage": 48.35, "elapsed_time": "0:20:23", "remaining_time": "0:21:46"}
177
+ {"current_steps": 177, "total_steps": 364, "loss": 0.1926, "lr": 1.2238587870264152e-05, "epoch": 3.3821656050955413, "percentage": 48.63, "elapsed_time": "0:20:28", "remaining_time": "0:21:38"}
178
+ {"current_steps": 178, "total_steps": 364, "loss": 0.194, "lr": 1.2144851014515055e-05, "epoch": 3.4012738853503186, "percentage": 48.9, "elapsed_time": "0:20:32", "remaining_time": "0:21:27"}
179
+ {"current_steps": 179, "total_steps": 364, "loss": 0.2237, "lr": 1.2050916189382646e-05, "epoch": 3.4203821656050954, "percentage": 49.18, "elapsed_time": "0:20:41", "remaining_time": "0:21:23"}
180
+ {"current_steps": 180, "total_steps": 364, "loss": 0.1652, "lr": 1.1956792065035281e-05, "epoch": 3.4394904458598727, "percentage": 49.45, "elapsed_time": "0:20:45", "remaining_time": "0:21:12"}
181
+ {"current_steps": 181, "total_steps": 364, "loss": 0.239, "lr": 1.1862487329113606e-05, "epoch": 3.4585987261146496, "percentage": 49.73, "elapsed_time": "0:20:49", "remaining_time": "0:21:03"}
182
+ {"current_steps": 182, "total_steps": 364, "loss": 0.1775, "lr": 1.1768010685928686e-05, "epoch": 3.477707006369427, "percentage": 50.0, "elapsed_time": "0:20:53", "remaining_time": "0:20:53"}
183
+ {"current_steps": 183, "total_steps": 364, "loss": 0.2222, "lr": 1.1673370855658592e-05, "epoch": 3.4968152866242037, "percentage": 50.27, "elapsed_time": "0:20:59", "remaining_time": "0:20:45"}
184
+ {"current_steps": 184, "total_steps": 364, "loss": 0.1812, "lr": 1.1578576573543541e-05, "epoch": 3.515923566878981, "percentage": 50.55, "elapsed_time": "0:21:05", "remaining_time": "0:20:38"}
185
+ {"current_steps": 185, "total_steps": 364, "loss": 0.1933, "lr": 1.1483636589079627e-05, "epoch": 3.535031847133758, "percentage": 50.82, "elapsed_time": "0:21:10", "remaining_time": "0:20:28"}
186
+ {"current_steps": 186, "total_steps": 364, "loss": 0.2232, "lr": 1.1388559665211241e-05, "epoch": 3.554140127388535, "percentage": 51.1, "elapsed_time": "0:21:16", "remaining_time": "0:20:21"}
187
+ {"current_steps": 187, "total_steps": 364, "loss": 0.2141, "lr": 1.1293354577522264e-05, "epoch": 3.573248407643312, "percentage": 51.37, "elapsed_time": "0:21:20", "remaining_time": "0:20:12"}
188
+ {"current_steps": 188, "total_steps": 364, "loss": 0.1982, "lr": 1.1198030113426074e-05, "epoch": 3.5923566878980893, "percentage": 51.65, "elapsed_time": "0:21:24", "remaining_time": "0:20:02"}
189
+ {"current_steps": 189, "total_steps": 364, "loss": 0.18, "lr": 1.1102595071354471e-05, "epoch": 3.611464968152866, "percentage": 51.92, "elapsed_time": "0:21:28", "remaining_time": "0:19:53"}
190
+ {"current_steps": 190, "total_steps": 364, "loss": 0.228, "lr": 1.1007058259945584e-05, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:21:32", "remaining_time": "0:19:43"}
191
+ {"current_steps": 191, "total_steps": 364, "loss": 0.2184, "lr": 1.0911428497230834e-05, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:21:37", "remaining_time": "0:19:35"}