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:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:813d1a484436656f654bbceb452732d2c1fd058f261409b026740ebb9de41bc3
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cfbda9b593b29de61f86e4a941ee4173f8f94bcfaa1693f565ec6c5ba93b261
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bcc403aefbae09b5a1f3a684273adb568af34de458928c6d035ff4526e15821
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5960ad85fe9f96152eac252b79a40acd56e155b7e85de4ea94db0fe6e12b59bb
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -110,3 +110,59 @@
|
|
110 |
{"current_steps": 1090, "total_steps": 4392, "loss": 0.7148, "lr": 5e-06, "epoch": 1.9845243513882567, "percentage": 24.82, "elapsed_time": "9:51:24", "remaining_time": "1 day, 5:51:36"}
|
111 |
{"current_steps": 1098, "total_steps": 4392, "eval_loss": 0.7494105696678162, "epoch": 1.9990896677287209, "percentage": 25.0, "elapsed_time": "10:02:05", "remaining_time": "1 day, 6:06:16"}
|
112 |
{"current_steps": 1100, "total_steps": 4392, "loss": 0.7534, "lr": 5e-06, "epoch": 2.002730996813837, "percentage": 25.05, "elapsed_time": "10:04:14", "remaining_time": "1 day, 6:08:19"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
110 |
{"current_steps": 1090, "total_steps": 4392, "loss": 0.7148, "lr": 5e-06, "epoch": 1.9845243513882567, "percentage": 24.82, "elapsed_time": "9:51:24", "remaining_time": "1 day, 5:51:36"}
|
111 |
{"current_steps": 1098, "total_steps": 4392, "eval_loss": 0.7494105696678162, "epoch": 1.9990896677287209, "percentage": 25.0, "elapsed_time": "10:02:05", "remaining_time": "1 day, 6:06:16"}
|
112 |
{"current_steps": 1100, "total_steps": 4392, "loss": 0.7534, "lr": 5e-06, "epoch": 2.002730996813837, "percentage": 25.05, "elapsed_time": "10:04:14", "remaining_time": "1 day, 6:08:19"}
|
113 |
+
{"current_steps": 1110, "total_steps": 4392, "loss": 0.6594, "lr": 5e-06, "epoch": 2.020937642239417, "percentage": 25.27, "elapsed_time": "10:09:34", "remaining_time": "1 day, 6:02:22"}
|
114 |
+
{"current_steps": 1120, "total_steps": 4392, "loss": 0.6665, "lr": 5e-06, "epoch": 2.039144287664998, "percentage": 25.5, "elapsed_time": "10:14:55", "remaining_time": "1 day, 5:56:28"}
|
115 |
+
{"current_steps": 1130, "total_steps": 4392, "loss": 0.6641, "lr": 5e-06, "epoch": 2.057350933090578, "percentage": 25.73, "elapsed_time": "10:20:15", "remaining_time": "1 day, 5:50:29"}
|
116 |
+
{"current_steps": 1140, "total_steps": 4392, "loss": 0.6611, "lr": 5e-06, "epoch": 2.0755575785161584, "percentage": 25.96, "elapsed_time": "10:25:36", "remaining_time": "1 day, 5:44:38"}
|
117 |
+
{"current_steps": 1150, "total_steps": 4392, "loss": 0.6631, "lr": 5e-06, "epoch": 2.0937642239417387, "percentage": 26.18, "elapsed_time": "10:30:58", "remaining_time": "1 day, 5:38:49"}
|
118 |
+
{"current_steps": 1160, "total_steps": 4392, "loss": 0.6631, "lr": 5e-06, "epoch": 2.111970869367319, "percentage": 26.41, "elapsed_time": "10:36:21", "remaining_time": "1 day, 5:33:01"}
|
119 |
+
{"current_steps": 1170, "total_steps": 4392, "loss": 0.6641, "lr": 5e-06, "epoch": 2.1301775147928996, "percentage": 26.64, "elapsed_time": "10:41:42", "remaining_time": "1 day, 5:27:10"}
|
120 |
+
{"current_steps": 1180, "total_steps": 4392, "loss": 0.6644, "lr": 5e-06, "epoch": 2.14838416021848, "percentage": 26.87, "elapsed_time": "10:47:05", "remaining_time": "1 day, 5:21:23"}
|
121 |
+
{"current_steps": 1190, "total_steps": 4392, "loss": 0.6711, "lr": 5e-06, "epoch": 2.16659080564406, "percentage": 27.09, "elapsed_time": "10:52:28", "remaining_time": "1 day, 5:15:37"}
|
122 |
+
{"current_steps": 1200, "total_steps": 4392, "loss": 0.6668, "lr": 5e-06, "epoch": 2.1847974510696404, "percentage": 27.32, "elapsed_time": "10:57:47", "remaining_time": "1 day, 5:09:44"}
|
123 |
+
{"current_steps": 1210, "total_steps": 4392, "loss": 0.6717, "lr": 5e-06, "epoch": 2.2030040964952207, "percentage": 27.55, "elapsed_time": "11:03:09", "remaining_time": "1 day, 5:03:55"}
|
124 |
+
{"current_steps": 1220, "total_steps": 4392, "loss": 0.6689, "lr": 5e-06, "epoch": 2.221210741920801, "percentage": 27.78, "elapsed_time": "11:08:28", "remaining_time": "1 day, 4:58:01"}
|
125 |
+
{"current_steps": 1230, "total_steps": 4392, "loss": 0.6628, "lr": 5e-06, "epoch": 2.2394173873463816, "percentage": 28.01, "elapsed_time": "11:13:50", "remaining_time": "1 day, 4:52:15"}
|
126 |
+
{"current_steps": 1240, "total_steps": 4392, "loss": 0.6651, "lr": 5e-06, "epoch": 2.257624032771962, "percentage": 28.23, "elapsed_time": "11:19:11", "remaining_time": "1 day, 4:46:27"}
|
127 |
+
{"current_steps": 1250, "total_steps": 4392, "loss": 0.6677, "lr": 5e-06, "epoch": 2.275830678197542, "percentage": 28.46, "elapsed_time": "11:24:33", "remaining_time": "1 day, 4:40:41"}
|
128 |
+
{"current_steps": 1260, "total_steps": 4392, "loss": 0.6649, "lr": 5e-06, "epoch": 2.2940373236231224, "percentage": 28.69, "elapsed_time": "11:29:51", "remaining_time": "1 day, 4:34:46"}
|
129 |
+
{"current_steps": 1270, "total_steps": 4392, "loss": 0.6661, "lr": 5e-06, "epoch": 2.3122439690487027, "percentage": 28.92, "elapsed_time": "11:35:13", "remaining_time": "1 day, 4:29:02"}
|
130 |
+
{"current_steps": 1280, "total_steps": 4392, "loss": 0.6706, "lr": 5e-06, "epoch": 2.330450614474283, "percentage": 29.14, "elapsed_time": "11:40:36", "remaining_time": "1 day, 4:23:20"}
|
131 |
+
{"current_steps": 1290, "total_steps": 4392, "loss": 0.6642, "lr": 5e-06, "epoch": 2.3486572598998636, "percentage": 29.37, "elapsed_time": "11:45:58", "remaining_time": "1 day, 4:17:38"}
|
132 |
+
{"current_steps": 1300, "total_steps": 4392, "loss": 0.6675, "lr": 5e-06, "epoch": 2.366863905325444, "percentage": 29.6, "elapsed_time": "11:51:20", "remaining_time": "1 day, 4:11:54"}
|
133 |
+
{"current_steps": 1310, "total_steps": 4392, "loss": 0.6658, "lr": 5e-06, "epoch": 2.385070550751024, "percentage": 29.83, "elapsed_time": "11:56:42", "remaining_time": "1 day, 4:06:11"}
|
134 |
+
{"current_steps": 1320, "total_steps": 4392, "loss": 0.6693, "lr": 5e-06, "epoch": 2.4032771961766044, "percentage": 30.05, "elapsed_time": "12:02:02", "remaining_time": "1 day, 4:00:22"}
|
135 |
+
{"current_steps": 1330, "total_steps": 4392, "loss": 0.6667, "lr": 5e-06, "epoch": 2.4214838416021847, "percentage": 30.28, "elapsed_time": "12:07:24", "remaining_time": "1 day, 3:54:40"}
|
136 |
+
{"current_steps": 1340, "total_steps": 4392, "loss": 0.6693, "lr": 5e-06, "epoch": 2.4396904870277654, "percentage": 30.51, "elapsed_time": "12:12:46", "remaining_time": "1 day, 3:48:58"}
|
137 |
+
{"current_steps": 1350, "total_steps": 4392, "loss": 0.6691, "lr": 5e-06, "epoch": 2.4578971324533456, "percentage": 30.74, "elapsed_time": "12:18:07", "remaining_time": "1 day, 3:43:15"}
|
138 |
+
{"current_steps": 1360, "total_steps": 4392, "loss": 0.6697, "lr": 5e-06, "epoch": 2.476103777878926, "percentage": 30.97, "elapsed_time": "12:23:30", "remaining_time": "1 day, 3:37:34"}
|
139 |
+
{"current_steps": 1370, "total_steps": 4392, "loss": 0.6659, "lr": 5e-06, "epoch": 2.494310423304506, "percentage": 31.19, "elapsed_time": "12:28:53", "remaining_time": "1 day, 3:31:55"}
|
140 |
+
{"current_steps": 1380, "total_steps": 4392, "loss": 0.6689, "lr": 5e-06, "epoch": 2.5125170687300864, "percentage": 31.42, "elapsed_time": "12:34:15", "remaining_time": "1 day, 3:26:15"}
|
141 |
+
{"current_steps": 1390, "total_steps": 4392, "loss": 0.6713, "lr": 5e-06, "epoch": 2.5307237141556667, "percentage": 31.65, "elapsed_time": "12:39:38", "remaining_time": "1 day, 3:20:35"}
|
142 |
+
{"current_steps": 1400, "total_steps": 4392, "loss": 0.6702, "lr": 5e-06, "epoch": 2.548930359581247, "percentage": 31.88, "elapsed_time": "12:44:59", "remaining_time": "1 day, 3:14:53"}
|
143 |
+
{"current_steps": 1410, "total_steps": 4392, "loss": 0.6729, "lr": 5e-06, "epoch": 2.5671370050068276, "percentage": 32.1, "elapsed_time": "12:50:21", "remaining_time": "1 day, 3:09:12"}
|
144 |
+
{"current_steps": 1420, "total_steps": 4392, "loss": 0.6727, "lr": 5e-06, "epoch": 2.585343650432408, "percentage": 32.33, "elapsed_time": "12:55:42", "remaining_time": "1 day, 3:03:31"}
|
145 |
+
{"current_steps": 1430, "total_steps": 4392, "loss": 0.6638, "lr": 5e-06, "epoch": 2.603550295857988, "percentage": 32.56, "elapsed_time": "13:01:04", "remaining_time": "1 day, 2:57:52"}
|
146 |
+
{"current_steps": 1440, "total_steps": 4392, "loss": 0.6687, "lr": 5e-06, "epoch": 2.6217569412835684, "percentage": 32.79, "elapsed_time": "13:06:24", "remaining_time": "1 day, 2:52:08"}
|
147 |
+
{"current_steps": 1450, "total_steps": 4392, "loss": 0.6673, "lr": 5e-06, "epoch": 2.6399635867091487, "percentage": 33.01, "elapsed_time": "13:11:44", "remaining_time": "1 day, 2:46:24"}
|
148 |
+
{"current_steps": 1460, "total_steps": 4392, "loss": 0.6723, "lr": 5e-06, "epoch": 2.6581702321347294, "percentage": 33.24, "elapsed_time": "13:17:05", "remaining_time": "1 day, 2:40:44"}
|
149 |
+
{"current_steps": 1470, "total_steps": 4392, "loss": 0.6697, "lr": 5e-06, "epoch": 2.6763768775603096, "percentage": 33.47, "elapsed_time": "13:22:24", "remaining_time": "1 day, 2:34:59"}
|
150 |
+
{"current_steps": 1480, "total_steps": 4392, "loss": 0.6726, "lr": 5e-06, "epoch": 2.69458352298589, "percentage": 33.7, "elapsed_time": "13:27:46", "remaining_time": "1 day, 2:29:20"}
|
151 |
+
{"current_steps": 1490, "total_steps": 4392, "loss": 0.6697, "lr": 5e-06, "epoch": 2.71279016841147, "percentage": 33.93, "elapsed_time": "13:33:09", "remaining_time": "1 day, 2:23:45"}
|
152 |
+
{"current_steps": 1500, "total_steps": 4392, "loss": 0.6713, "lr": 5e-06, "epoch": 2.7309968138370504, "percentage": 34.15, "elapsed_time": "13:38:31", "remaining_time": "1 day, 2:18:06"}
|
153 |
+
{"current_steps": 1510, "total_steps": 4392, "loss": 0.6713, "lr": 5e-06, "epoch": 2.749203459262631, "percentage": 34.38, "elapsed_time": "13:43:52", "remaining_time": "1 day, 2:12:27"}
|
154 |
+
{"current_steps": 1520, "total_steps": 4392, "loss": 0.6711, "lr": 5e-06, "epoch": 2.7674101046882114, "percentage": 34.61, "elapsed_time": "13:49:14", "remaining_time": "1 day, 2:06:49"}
|
155 |
+
{"current_steps": 1530, "total_steps": 4392, "loss": 0.6679, "lr": 5e-06, "epoch": 2.7856167501137916, "percentage": 34.84, "elapsed_time": "13:54:36", "remaining_time": "1 day, 2:01:11"}
|
156 |
+
{"current_steps": 1540, "total_steps": 4392, "loss": 0.6705, "lr": 5e-06, "epoch": 2.803823395539372, "percentage": 35.06, "elapsed_time": "13:59:57", "remaining_time": "1 day, 1:55:33"}
|
157 |
+
{"current_steps": 1550, "total_steps": 4392, "loss": 0.6714, "lr": 5e-06, "epoch": 2.822030040964952, "percentage": 35.29, "elapsed_time": "14:05:19", "remaining_time": "1 day, 1:49:56"}
|
158 |
+
{"current_steps": 1560, "total_steps": 4392, "loss": 0.6678, "lr": 5e-06, "epoch": 2.8402366863905324, "percentage": 35.52, "elapsed_time": "14:10:40", "remaining_time": "1 day, 1:44:18"}
|
159 |
+
{"current_steps": 1570, "total_steps": 4392, "loss": 0.6738, "lr": 5e-06, "epoch": 2.8584433318161127, "percentage": 35.75, "elapsed_time": "14:16:01", "remaining_time": "1 day, 1:38:39"}
|
160 |
+
{"current_steps": 1580, "total_steps": 4392, "loss": 0.6682, "lr": 5e-06, "epoch": 2.8766499772416934, "percentage": 35.97, "elapsed_time": "14:21:22", "remaining_time": "1 day, 1:33:02"}
|
161 |
+
{"current_steps": 1590, "total_steps": 4392, "loss": 0.6689, "lr": 5e-06, "epoch": 2.8948566226672736, "percentage": 36.2, "elapsed_time": "14:26:45", "remaining_time": "1 day, 1:27:27"}
|
162 |
+
{"current_steps": 1600, "total_steps": 4392, "loss": 0.6654, "lr": 5e-06, "epoch": 2.913063268092854, "percentage": 36.43, "elapsed_time": "14:32:06", "remaining_time": "1 day, 1:21:50"}
|
163 |
+
{"current_steps": 1610, "total_steps": 4392, "loss": 0.6648, "lr": 5e-06, "epoch": 2.931269913518434, "percentage": 36.66, "elapsed_time": "14:37:29", "remaining_time": "1 day, 1:16:15"}
|
164 |
+
{"current_steps": 1620, "total_steps": 4392, "loss": 0.6674, "lr": 5e-06, "epoch": 2.9494765589440144, "percentage": 36.89, "elapsed_time": "14:42:50", "remaining_time": "1 day, 1:10:38"}
|
165 |
+
{"current_steps": 1630, "total_steps": 4392, "loss": 0.6748, "lr": 5e-06, "epoch": 2.967683204369595, "percentage": 37.11, "elapsed_time": "14:48:11", "remaining_time": "1 day, 1:05:01"}
|
166 |
+
{"current_steps": 1640, "total_steps": 4392, "loss": 0.6707, "lr": 5e-06, "epoch": 2.9858898497951754, "percentage": 37.34, "elapsed_time": "14:53:34", "remaining_time": "1 day, 0:59:27"}
|
167 |
+
{"current_steps": 1647, "total_steps": 4392, "eval_loss": 0.7486923933029175, "epoch": 2.9986345015930813, "percentage": 37.5, "elapsed_time": "15:03:50", "remaining_time": "1 day, 1:06:24"}
|
168 |
+
{"current_steps": 1650, "total_steps": 4392, "loss": 0.7123, "lr": 5e-06, "epoch": 3.0040964952207556, "percentage": 37.57, "elapsed_time": "15:06:24", "remaining_time": "1 day, 1:06:16"}
|