neginr commited on
Commit
79f8846
·
verified ·
1 Parent(s): 0050d4f

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:becfe500848c87be55030cde636635c45e3d75a11954c34e4abf07e4be3a11d0
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f1e82f0e18149023cd69dea9e8f4ede154b33e9057faf1c475a1e5bf32ad2d
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:ed70e0ee295229171ca30453388758ac4e3ba55f47c8646e344500c3b10849cc
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f8b749000e7d3d0f6c857a5cd44afa3498522ecf1eb29f71177d69d9742761
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:b59275f7678a7d8d2b5f34a2afbf8a889cee7c69b92e713df4c858cb2c298f9e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d833e8693095ad70f8a0f50cb5220dc15b556a3e68dcc3b931735a142d09708f
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54a2d4d3b913f3f0b34dd76d4296219c2e9ee9559a4ae8dbea62f204f2b03808
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99397d9a600a9ae9f6950623cae30e88845900572613299d7f3a0896cbd27ba9
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -136,3 +136,57 @@
136
  {"current_steps": 136, "total_steps": 364, "loss": 0.3488, "lr": 1.5807681327318372e-05, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:15:04", "remaining_time": "0:25:16"}
137
  {"current_steps": 137, "total_steps": 364, "loss": 0.3616, "lr": 1.5729204314845002e-05, "epoch": 2.6178343949044587, "percentage": 37.64, "elapsed_time": "0:15:11", "remaining_time": "0:25:09"}
138
  {"current_steps": 138, "total_steps": 364, "loss": 0.3413, "lr": 1.56501984977892e-05, "epoch": 2.6369426751592355, "percentage": 37.91, "elapsed_time": "0:15:14", "remaining_time": "0:24:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  {"current_steps": 136, "total_steps": 364, "loss": 0.3488, "lr": 1.5807681327318372e-05, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:15:04", "remaining_time": "0:25:16"}
137
  {"current_steps": 137, "total_steps": 364, "loss": 0.3616, "lr": 1.5729204314845002e-05, "epoch": 2.6178343949044587, "percentage": 37.64, "elapsed_time": "0:15:11", "remaining_time": "0:25:09"}
138
  {"current_steps": 138, "total_steps": 364, "loss": 0.3413, "lr": 1.56501984977892e-05, "epoch": 2.6369426751592355, "percentage": 37.91, "elapsed_time": "0:15:14", "remaining_time": "0:24:58"}
139
+ {"current_steps": 139, "total_steps": 364, "loss": 0.3049, "lr": 1.557067116837444e-05, "epoch": 2.656050955414013, "percentage": 38.19, "elapsed_time": "0:15:18", "remaining_time": "0:24:46"}
140
+ {"current_steps": 140, "total_steps": 364, "loss": 0.3631, "lr": 1.5490629666959668e-05, "epoch": 2.6751592356687897, "percentage": 38.46, "elapsed_time": "0:15:23", "remaining_time": "0:24:37"}
141
+ {"current_steps": 141, "total_steps": 364, "loss": 0.3233, "lr": 1.541008138136183e-05, "epoch": 2.694267515923567, "percentage": 38.74, "elapsed_time": "0:15:26", "remaining_time": "0:24:26"}
142
+ {"current_steps": 142, "total_steps": 364, "loss": 0.358, "lr": 1.5329033746173975e-05, "epoch": 2.713375796178344, "percentage": 39.01, "elapsed_time": "0:15:34", "remaining_time": "0:24:21"}
143
+ {"current_steps": 143, "total_steps": 364, "loss": 0.37, "lr": 1.5247494242079024e-05, "epoch": 2.732484076433121, "percentage": 39.29, "elapsed_time": "0:15:39", "remaining_time": "0:24:11"}
144
+ {"current_steps": 144, "total_steps": 364, "loss": 0.3301, "lr": 1.5165470395159314e-05, "epoch": 2.7515923566878984, "percentage": 39.56, "elapsed_time": "0:15:43", "remaining_time": "0:24:00"}
145
+ {"current_steps": 145, "total_steps": 364, "loss": 0.3067, "lr": 1.5082969776201948e-05, "epoch": 2.770700636942675, "percentage": 39.84, "elapsed_time": "0:15:46", "remaining_time": "0:23:50"}
146
+ {"current_steps": 146, "total_steps": 364, "loss": 0.3289, "lr": 1.5000000000000002e-05, "epoch": 2.789808917197452, "percentage": 40.11, "elapsed_time": "0:15:50", "remaining_time": "0:23:39"}
147
+ {"current_steps": 147, "total_steps": 364, "loss": 0.3226, "lr": 1.4916568724649688e-05, "epoch": 2.8089171974522293, "percentage": 40.38, "elapsed_time": "0:15:55", "remaining_time": "0:23:30"}
148
+ {"current_steps": 148, "total_steps": 364, "loss": 0.341, "lr": 1.483268365084351e-05, "epoch": 2.8280254777070066, "percentage": 40.66, "elapsed_time": "0:16:01", "remaining_time": "0:23:23"}
149
+ {"current_steps": 149, "total_steps": 364, "loss": 0.3085, "lr": 1.4748352521159492e-05, "epoch": 2.8471337579617835, "percentage": 40.93, "elapsed_time": "0:16:06", "remaining_time": "0:23:14"}
150
+ {"current_steps": 150, "total_steps": 364, "loss": 0.3429, "lr": 1.466358311934654e-05, "epoch": 2.8662420382165603, "percentage": 41.21, "elapsed_time": "0:16:10", "remaining_time": "0:23:04"}
151
+ {"current_steps": 151, "total_steps": 364, "loss": 0.2933, "lr": 1.4578383269606004e-05, "epoch": 2.8853503184713376, "percentage": 41.48, "elapsed_time": "0:16:14", "remaining_time": "0:22:54"}
152
+ {"current_steps": 152, "total_steps": 364, "loss": 0.345, "lr": 1.4492760835869504e-05, "epoch": 2.904458598726115, "percentage": 41.76, "elapsed_time": "0:16:19", "remaining_time": "0:22:46"}
153
+ {"current_steps": 153, "total_steps": 364, "loss": 0.3898, "lr": 1.4406723721073088e-05, "epoch": 2.9235668789808917, "percentage": 42.03, "elapsed_time": "0:16:23", "remaining_time": "0:22:36"}
154
+ {"current_steps": 154, "total_steps": 364, "loss": 0.3674, "lr": 1.4320279866427798e-05, "epoch": 2.9426751592356686, "percentage": 42.31, "elapsed_time": "0:16:31", "remaining_time": "0:22:31"}
155
+ {"current_steps": 155, "total_steps": 364, "loss": 0.3271, "lr": 1.4233437250686695e-05, "epoch": 2.961783439490446, "percentage": 42.58, "elapsed_time": "0:16:34", "remaining_time": "0:22:21"}
156
+ {"current_steps": 156, "total_steps": 364, "loss": 0.3342, "lr": 1.4146203889408418e-05, "epoch": 2.980891719745223, "percentage": 42.86, "elapsed_time": "0:16:39", "remaining_time": "0:22:12"}
157
+ {"current_steps": 157, "total_steps": 364, "loss": 0.3276, "lr": 1.4058587834217356e-05, "epoch": 3.0, "percentage": 43.13, "elapsed_time": "0:16:42", "remaining_time": "0:22:02"}
158
+ {"current_steps": 158, "total_steps": 364, "loss": 0.2086, "lr": 1.3970597172060482e-05, "epoch": 3.0191082802547773, "percentage": 43.41, "elapsed_time": "0:18:35", "remaining_time": "0:24:13"}
159
+ {"current_steps": 159, "total_steps": 364, "loss": 0.2144, "lr": 1.3882240024460928e-05, "epoch": 3.038216560509554, "percentage": 43.68, "elapsed_time": "0:18:40", "remaining_time": "0:24:04"}
160
+ {"current_steps": 160, "total_steps": 364, "loss": 0.1854, "lr": 1.3793524546768358e-05, "epoch": 3.0573248407643314, "percentage": 43.96, "elapsed_time": "0:18:46", "remaining_time": "0:23:55"}
161
+ {"current_steps": 161, "total_steps": 364, "loss": 0.1979, "lr": 1.3704458927406261e-05, "epoch": 3.0764331210191083, "percentage": 44.23, "elapsed_time": "0:18:50", "remaining_time": "0:23:45"}
162
+ {"current_steps": 162, "total_steps": 364, "loss": 0.2177, "lr": 1.3615051387116131e-05, "epoch": 3.0955414012738856, "percentage": 44.51, "elapsed_time": "0:18:54", "remaining_time": "0:23:34"}
163
+ {"current_steps": 163, "total_steps": 364, "loss": 0.2099, "lr": 1.3525310178198707e-05, "epoch": 3.1146496815286624, "percentage": 44.78, "elapsed_time": "0:18:59", "remaining_time": "0:23:24"}
164
+ {"current_steps": 164, "total_steps": 364, "loss": 0.2038, "lr": 1.3435243583752294e-05, "epoch": 3.1337579617834397, "percentage": 45.05, "elapsed_time": "0:19:02", "remaining_time": "0:23:13"}
165
+ {"current_steps": 165, "total_steps": 364, "loss": 0.2378, "lr": 1.3344859916908206e-05, "epoch": 3.1528662420382165, "percentage": 45.33, "elapsed_time": "0:19:07", "remaining_time": "0:23:03"}
166
+ {"current_steps": 166, "total_steps": 364, "loss": 0.1767, "lr": 1.325416752006351e-05, "epoch": 3.171974522292994, "percentage": 45.6, "elapsed_time": "0:19:11", "remaining_time": "0:22:53"}
167
+ {"current_steps": 167, "total_steps": 364, "loss": 0.1753, "lr": 1.3163174764110985e-05, "epoch": 3.1910828025477707, "percentage": 45.88, "elapsed_time": "0:19:15", "remaining_time": "0:22:43"}
168
+ {"current_steps": 168, "total_steps": 364, "loss": 0.2195, "lr": 1.3071890047666498e-05, "epoch": 3.210191082802548, "percentage": 46.15, "elapsed_time": "0:19:19", "remaining_time": "0:22:33"}
169
+ {"current_steps": 169, "total_steps": 364, "loss": 0.2231, "lr": 1.2980321796293838e-05, "epoch": 3.229299363057325, "percentage": 46.43, "elapsed_time": "0:19:25", "remaining_time": "0:22:24"}
170
+ {"current_steps": 170, "total_steps": 364, "loss": 0.233, "lr": 1.288847846172701e-05, "epoch": 3.248407643312102, "percentage": 46.7, "elapsed_time": "0:19:29", "remaining_time": "0:22:14"}
171
+ {"current_steps": 171, "total_steps": 364, "loss": 0.2293, "lr": 1.2796368521090143e-05, "epoch": 3.267515923566879, "percentage": 46.98, "elapsed_time": "0:19:36", "remaining_time": "0:22:07"}
172
+ {"current_steps": 172, "total_steps": 364, "loss": 0.1923, "lr": 1.2704000476115079e-05, "epoch": 3.286624203821656, "percentage": 47.25, "elapsed_time": "0:19:41", "remaining_time": "0:21:59"}
173
+ {"current_steps": 173, "total_steps": 364, "loss": 0.241, "lr": 1.2611382852356632e-05, "epoch": 3.305732484076433, "percentage": 47.53, "elapsed_time": "0:19:46", "remaining_time": "0:21:49"}
174
+ {"current_steps": 174, "total_steps": 364, "loss": 0.227, "lr": 1.2518524198405699e-05, "epoch": 3.3248407643312103, "percentage": 47.8, "elapsed_time": "0:19:49", "remaining_time": "0:21:39"}
175
+ {"current_steps": 175, "total_steps": 364, "loss": 0.1892, "lr": 1.2425433085100224e-05, "epoch": 3.343949044585987, "percentage": 48.08, "elapsed_time": "0:19:54", "remaining_time": "0:21:30"}
176
+ {"current_steps": 176, "total_steps": 364, "loss": 0.2217, "lr": 1.233211810473411e-05, "epoch": 3.3630573248407645, "percentage": 48.35, "elapsed_time": "0:19:58", "remaining_time": "0:21:20"}
177
+ {"current_steps": 177, "total_steps": 364, "loss": 0.2289, "lr": 1.2238587870264152e-05, "epoch": 3.3821656050955413, "percentage": 48.63, "elapsed_time": "0:20:06", "remaining_time": "0:21:14"}
178
+ {"current_steps": 178, "total_steps": 364, "loss": 0.1952, "lr": 1.2144851014515055e-05, "epoch": 3.4012738853503186, "percentage": 48.9, "elapsed_time": "0:20:10", "remaining_time": "0:21:04"}
179
+ {"current_steps": 179, "total_steps": 364, "loss": 0.2116, "lr": 1.2050916189382646e-05, "epoch": 3.4203821656050954, "percentage": 49.18, "elapsed_time": "0:20:17", "remaining_time": "0:20:58"}
180
+ {"current_steps": 180, "total_steps": 364, "loss": 0.1798, "lr": 1.1956792065035281e-05, "epoch": 3.4394904458598727, "percentage": 49.45, "elapsed_time": "0:20:21", "remaining_time": "0:20:48"}
181
+ {"current_steps": 181, "total_steps": 364, "loss": 0.213, "lr": 1.1862487329113606e-05, "epoch": 3.4585987261146496, "percentage": 49.73, "elapsed_time": "0:20:27", "remaining_time": "0:20:41"}
182
+ {"current_steps": 182, "total_steps": 364, "loss": 0.1573, "lr": 1.1768010685928686e-05, "epoch": 3.477707006369427, "percentage": 50.0, "elapsed_time": "0:20:31", "remaining_time": "0:20:31"}
183
+ {"current_steps": 183, "total_steps": 364, "loss": 0.1893, "lr": 1.1673370855658592e-05, "epoch": 3.4968152866242037, "percentage": 50.27, "elapsed_time": "0:20:36", "remaining_time": "0:20:23"}
184
+ {"current_steps": 184, "total_steps": 364, "loss": 0.2159, "lr": 1.1578576573543541e-05, "epoch": 3.515923566878981, "percentage": 50.55, "elapsed_time": "0:20:45", "remaining_time": "0:20:18"}
185
+ {"current_steps": 185, "total_steps": 364, "loss": 0.1904, "lr": 1.1483636589079627e-05, "epoch": 3.535031847133758, "percentage": 50.82, "elapsed_time": "0:20:49", "remaining_time": "0:20:09"}
186
+ {"current_steps": 186, "total_steps": 364, "loss": 0.2147, "lr": 1.1388559665211241e-05, "epoch": 3.554140127388535, "percentage": 51.1, "elapsed_time": "0:20:55", "remaining_time": "0:20:01"}
187
+ {"current_steps": 187, "total_steps": 364, "loss": 0.2162, "lr": 1.1293354577522264e-05, "epoch": 3.573248407643312, "percentage": 51.37, "elapsed_time": "0:20:58", "remaining_time": "0:19:51"}
188
+ {"current_steps": 188, "total_steps": 364, "loss": 0.19, "lr": 1.1198030113426074e-05, "epoch": 3.5923566878980893, "percentage": 51.65, "elapsed_time": "0:21:04", "remaining_time": "0:19:43"}
189
+ {"current_steps": 189, "total_steps": 364, "loss": 0.1852, "lr": 1.1102595071354471e-05, "epoch": 3.611464968152866, "percentage": 51.92, "elapsed_time": "0:21:08", "remaining_time": "0:19:34"}
190
+ {"current_steps": 190, "total_steps": 364, "loss": 0.2172, "lr": 1.1007058259945584e-05, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:21:12", "remaining_time": "0:19:25"}
191
+ {"current_steps": 191, "total_steps": 364, "loss": 0.2218, "lr": 1.0911428497230834e-05, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:21:17", "remaining_time": "0:19:17"}
192
+ {"current_steps": 192, "total_steps": 364, "loss": 0.2033, "lr": 1.0815714609821027e-05, "epoch": 3.6687898089171975, "percentage": 52.75, "elapsed_time": "0:21:21", "remaining_time": "0:19:08"}