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 sha256:9a2dad390580a127756de1c771b07c4383a26eba93887e3c070a85b8632cda93
|
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 sha256:5ffd59c619a50632888ad684929907ca8d0816d3b38537b8f9df0eb2a5b05b9d
|
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 sha256:962d2fe21d7e215c29d1eaf5eecb4d3be9445ce9187cf745ce2276d1f1709374
|
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 sha256:8abe487ad40b0fbe9de896d84a07fdccdee7bf5e33234f52d42d64c98dd15fa2
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -137,3 +137,71 @@
|
|
137 |
{"current_steps": 1360, "total_steps": 2052, "loss": 0.7681, "lr": 5e-06, "epoch": 1.9857638255156052, "percentage": 66.28, "elapsed_time": "22:03:22", "remaining_time": "11:13:21"}
|
138 |
{"current_steps": 1369, "total_steps": 2052, "eval_loss": 0.8045554161071777, "epoch": 1.9989049096550464, "percentage": 66.72, "elapsed_time": "22:24:50", "remaining_time": "11:10:56"}
|
139 |
{"current_steps": 1370, "total_steps": 2052, "loss": 0.7813, "lr": 5e-06, "epoch": 2.0003650301149847, "percentage": 66.76, "elapsed_time": "22:26:21", "remaining_time": "11:10:13"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
137 |
{"current_steps": 1360, "total_steps": 2052, "loss": 0.7681, "lr": 5e-06, "epoch": 1.9857638255156052, "percentage": 66.28, "elapsed_time": "22:03:22", "remaining_time": "11:13:21"}
|
138 |
{"current_steps": 1369, "total_steps": 2052, "eval_loss": 0.8045554161071777, "epoch": 1.9989049096550464, "percentage": 66.72, "elapsed_time": "22:24:50", "remaining_time": "11:10:56"}
|
139 |
{"current_steps": 1370, "total_steps": 2052, "loss": 0.7813, "lr": 5e-06, "epoch": 2.0003650301149847, "percentage": 66.76, "elapsed_time": "22:26:21", "remaining_time": "11:10:13"}
|
140 |
+
{"current_steps": 1380, "total_steps": 2052, "loss": 0.7275, "lr": 5e-06, "epoch": 2.0149662347143638, "percentage": 67.25, "elapsed_time": "22:36:00", "remaining_time": "11:00:18"}
|
141 |
+
{"current_steps": 1390, "total_steps": 2052, "loss": 0.7301, "lr": 5e-06, "epoch": 2.0295674393137433, "percentage": 67.74, "elapsed_time": "22:45:38", "remaining_time": "10:50:24"}
|
142 |
+
{"current_steps": 1400, "total_steps": 2052, "loss": 0.7279, "lr": 5e-06, "epoch": 2.044168643913123, "percentage": 68.23, "elapsed_time": "22:55:18", "remaining_time": "10:40:29"}
|
143 |
+
{"current_steps": 1410, "total_steps": 2052, "loss": 0.732, "lr": 5e-06, "epoch": 2.0587698485125023, "percentage": 68.71, "elapsed_time": "23:04:56", "remaining_time": "10:30:35"}
|
144 |
+
{"current_steps": 1420, "total_steps": 2052, "loss": 0.7327, "lr": 5e-06, "epoch": 2.073371053111882, "percentage": 69.2, "elapsed_time": "23:14:35", "remaining_time": "10:20:41"}
|
145 |
+
{"current_steps": 1430, "total_steps": 2052, "loss": 0.7289, "lr": 5e-06, "epoch": 2.0879722577112614, "percentage": 69.69, "elapsed_time": "23:24:14", "remaining_time": "10:10:47"}
|
146 |
+
{"current_steps": 1440, "total_steps": 2052, "loss": 0.729, "lr": 5e-06, "epoch": 2.1025734623106405, "percentage": 70.18, "elapsed_time": "23:33:53", "remaining_time": "10:00:54"}
|
147 |
+
{"current_steps": 1450, "total_steps": 2052, "loss": 0.7321, "lr": 5e-06, "epoch": 2.11717466691002, "percentage": 70.66, "elapsed_time": "23:43:33", "remaining_time": "9:51:01"}
|
148 |
+
{"current_steps": 1460, "total_steps": 2052, "loss": 0.7283, "lr": 5e-06, "epoch": 2.1317758715093995, "percentage": 71.15, "elapsed_time": "23:53:13", "remaining_time": "9:41:08"}
|
149 |
+
{"current_steps": 1470, "total_steps": 2052, "loss": 0.7341, "lr": 5e-06, "epoch": 2.146377076108779, "percentage": 71.64, "elapsed_time": "1 day, 0:02:51", "remaining_time": "9:31:15"}
|
150 |
+
{"current_steps": 1480, "total_steps": 2052, "loss": 0.7273, "lr": 5e-06, "epoch": 2.1609782807081586, "percentage": 72.12, "elapsed_time": "1 day, 0:12:30", "remaining_time": "9:21:22"}
|
151 |
+
{"current_steps": 1490, "total_steps": 2052, "loss": 0.7327, "lr": 5e-06, "epoch": 2.175579485307538, "percentage": 72.61, "elapsed_time": "1 day, 0:22:09", "remaining_time": "9:11:30"}
|
152 |
+
{"current_steps": 1500, "total_steps": 2052, "loss": 0.7259, "lr": 5e-06, "epoch": 2.190180689906917, "percentage": 73.1, "elapsed_time": "1 day, 0:31:48", "remaining_time": "9:01:37"}
|
153 |
+
{"current_steps": 1510, "total_steps": 2052, "loss": 0.7309, "lr": 5e-06, "epoch": 2.2047818945062967, "percentage": 73.59, "elapsed_time": "1 day, 0:41:26", "remaining_time": "8:51:44"}
|
154 |
+
{"current_steps": 1520, "total_steps": 2052, "loss": 0.7351, "lr": 5e-06, "epoch": 2.219383099105676, "percentage": 74.07, "elapsed_time": "1 day, 0:51:04", "remaining_time": "8:41:52"}
|
155 |
+
{"current_steps": 1530, "total_steps": 2052, "loss": 0.7319, "lr": 5e-06, "epoch": 2.2339843037050557, "percentage": 74.56, "elapsed_time": "1 day, 1:00:43", "remaining_time": "8:32:00"}
|
156 |
+
{"current_steps": 1540, "total_steps": 2052, "loss": 0.7331, "lr": 5e-06, "epoch": 2.2485855083044353, "percentage": 75.05, "elapsed_time": "1 day, 1:10:22", "remaining_time": "8:22:09"}
|
157 |
+
{"current_steps": 1550, "total_steps": 2052, "loss": 0.7364, "lr": 5e-06, "epoch": 2.2631867129038143, "percentage": 75.54, "elapsed_time": "1 day, 1:20:01", "remaining_time": "8:12:17"}
|
158 |
+
{"current_steps": 1560, "total_steps": 2052, "loss": 0.7336, "lr": 5e-06, "epoch": 2.277787917503194, "percentage": 76.02, "elapsed_time": "1 day, 1:29:39", "remaining_time": "8:02:25"}
|
159 |
+
{"current_steps": 1570, "total_steps": 2052, "loss": 0.7335, "lr": 5e-06, "epoch": 2.2923891221025734, "percentage": 76.51, "elapsed_time": "1 day, 1:39:18", "remaining_time": "7:52:34"}
|
160 |
+
{"current_steps": 1580, "total_steps": 2052, "loss": 0.7315, "lr": 5e-06, "epoch": 2.306990326701953, "percentage": 77.0, "elapsed_time": "1 day, 1:48:57", "remaining_time": "7:42:43"}
|
161 |
+
{"current_steps": 1590, "total_steps": 2052, "loss": 0.7322, "lr": 5e-06, "epoch": 2.3215915313013324, "percentage": 77.49, "elapsed_time": "1 day, 1:58:37", "remaining_time": "7:32:52"}
|
162 |
+
{"current_steps": 1600, "total_steps": 2052, "loss": 0.7345, "lr": 5e-06, "epoch": 2.336192735900712, "percentage": 77.97, "elapsed_time": "1 day, 2:08:16", "remaining_time": "7:23:02"}
|
163 |
+
{"current_steps": 1610, "total_steps": 2052, "loss": 0.7344, "lr": 5e-06, "epoch": 2.3507939405000915, "percentage": 78.46, "elapsed_time": "1 day, 2:17:55", "remaining_time": "7:13:11"}
|
164 |
+
{"current_steps": 1620, "total_steps": 2052, "loss": 0.7359, "lr": 5e-06, "epoch": 2.3653951450994706, "percentage": 78.95, "elapsed_time": "1 day, 2:27:34", "remaining_time": "7:03:21"}
|
165 |
+
{"current_steps": 1630, "total_steps": 2052, "loss": 0.7368, "lr": 5e-06, "epoch": 2.37999634969885, "percentage": 79.43, "elapsed_time": "1 day, 2:37:11", "remaining_time": "6:53:30"}
|
166 |
+
{"current_steps": 1640, "total_steps": 2052, "loss": 0.7355, "lr": 5e-06, "epoch": 2.3945975542982296, "percentage": 79.92, "elapsed_time": "1 day, 2:46:50", "remaining_time": "6:43:40"}
|
167 |
+
{"current_steps": 1650, "total_steps": 2052, "loss": 0.7355, "lr": 5e-06, "epoch": 2.409198758897609, "percentage": 80.41, "elapsed_time": "1 day, 2:56:27", "remaining_time": "6:33:49"}
|
168 |
+
{"current_steps": 1660, "total_steps": 2052, "loss": 0.7343, "lr": 5e-06, "epoch": 2.4237999634969887, "percentage": 80.9, "elapsed_time": "1 day, 3:06:07", "remaining_time": "6:23:59"}
|
169 |
+
{"current_steps": 1670, "total_steps": 2052, "loss": 0.7348, "lr": 5e-06, "epoch": 2.4384011680963678, "percentage": 81.38, "elapsed_time": "1 day, 3:15:44", "remaining_time": "6:14:09"}
|
170 |
+
{"current_steps": 1680, "total_steps": 2052, "loss": 0.7384, "lr": 5e-06, "epoch": 2.4530023726957473, "percentage": 81.87, "elapsed_time": "1 day, 3:25:22", "remaining_time": "6:04:20"}
|
171 |
+
{"current_steps": 1690, "total_steps": 2052, "loss": 0.7319, "lr": 5e-06, "epoch": 2.467603577295127, "percentage": 82.36, "elapsed_time": "1 day, 3:35:01", "remaining_time": "5:54:30"}
|
172 |
+
{"current_steps": 1700, "total_steps": 2052, "loss": 0.7344, "lr": 5e-06, "epoch": 2.4822047818945063, "percentage": 82.85, "elapsed_time": "1 day, 3:44:41", "remaining_time": "5:44:41"}
|
173 |
+
{"current_steps": 1710, "total_steps": 2052, "loss": 0.7348, "lr": 5e-06, "epoch": 2.496805986493886, "percentage": 83.33, "elapsed_time": "1 day, 3:54:19", "remaining_time": "5:34:51"}
|
174 |
+
{"current_steps": 1720, "total_steps": 2052, "loss": 0.7335, "lr": 5e-06, "epoch": 2.511407191093265, "percentage": 83.82, "elapsed_time": "1 day, 4:03:58", "remaining_time": "5:25:02"}
|
175 |
+
{"current_steps": 1730, "total_steps": 2052, "loss": 0.7341, "lr": 5e-06, "epoch": 2.526008395692645, "percentage": 84.31, "elapsed_time": "1 day, 4:13:37", "remaining_time": "5:15:13"}
|
176 |
+
{"current_steps": 1740, "total_steps": 2052, "loss": 0.7345, "lr": 5e-06, "epoch": 2.540609600292024, "percentage": 84.8, "elapsed_time": "1 day, 4:23:15", "remaining_time": "5:05:24"}
|
177 |
+
{"current_steps": 1750, "total_steps": 2052, "loss": 0.7364, "lr": 5e-06, "epoch": 2.5552108048914035, "percentage": 85.28, "elapsed_time": "1 day, 4:32:54", "remaining_time": "4:55:35"}
|
178 |
+
{"current_steps": 1760, "total_steps": 2052, "loss": 0.7327, "lr": 5e-06, "epoch": 2.569812009490783, "percentage": 85.77, "elapsed_time": "1 day, 4:42:33", "remaining_time": "4:45:47"}
|
179 |
+
{"current_steps": 1770, "total_steps": 2052, "loss": 0.734, "lr": 5e-06, "epoch": 2.5844132140901626, "percentage": 86.26, "elapsed_time": "1 day, 4:52:12", "remaining_time": "4:35:58"}
|
180 |
+
{"current_steps": 1780, "total_steps": 2052, "loss": 0.7309, "lr": 5e-06, "epoch": 2.599014418689542, "percentage": 86.74, "elapsed_time": "1 day, 5:01:51", "remaining_time": "4:26:10"}
|
181 |
+
{"current_steps": 1790, "total_steps": 2052, "loss": 0.7352, "lr": 5e-06, "epoch": 2.613615623288921, "percentage": 87.23, "elapsed_time": "1 day, 5:11:31", "remaining_time": "4:16:22"}
|
182 |
+
{"current_steps": 1800, "total_steps": 2052, "loss": 0.7356, "lr": 5e-06, "epoch": 2.6282168278883007, "percentage": 87.72, "elapsed_time": "1 day, 5:21:11", "remaining_time": "4:06:33"}
|
183 |
+
{"current_steps": 1810, "total_steps": 2052, "loss": 0.7353, "lr": 5e-06, "epoch": 2.64281803248768, "percentage": 88.21, "elapsed_time": "1 day, 5:30:51", "remaining_time": "3:56:45"}
|
184 |
+
{"current_steps": 1820, "total_steps": 2052, "loss": 0.7347, "lr": 5e-06, "epoch": 2.6574192370870597, "percentage": 88.69, "elapsed_time": "1 day, 5:40:30", "remaining_time": "3:46:57"}
|
185 |
+
{"current_steps": 1830, "total_steps": 2052, "loss": 0.7354, "lr": 5e-06, "epoch": 2.6720204416864393, "percentage": 89.18, "elapsed_time": "1 day, 5:50:10", "remaining_time": "3:37:10"}
|
186 |
+
{"current_steps": 1840, "total_steps": 2052, "loss": 0.7391, "lr": 5e-06, "epoch": 2.6866216462858183, "percentage": 89.67, "elapsed_time": "1 day, 5:59:49", "remaining_time": "3:27:22"}
|
187 |
+
{"current_steps": 1850, "total_steps": 2052, "loss": 0.7388, "lr": 5e-06, "epoch": 2.701222850885198, "percentage": 90.16, "elapsed_time": "1 day, 6:09:27", "remaining_time": "3:17:34"}
|
188 |
+
{"current_steps": 1860, "total_steps": 2052, "loss": 0.737, "lr": 5e-06, "epoch": 2.7158240554845774, "percentage": 90.64, "elapsed_time": "1 day, 6:19:07", "remaining_time": "3:07:46"}
|
189 |
+
{"current_steps": 1870, "total_steps": 2052, "loss": 0.7359, "lr": 5e-06, "epoch": 2.730425260083957, "percentage": 91.13, "elapsed_time": "1 day, 6:28:46", "remaining_time": "2:57:59"}
|
190 |
+
{"current_steps": 1880, "total_steps": 2052, "loss": 0.7349, "lr": 5e-06, "epoch": 2.7450264646833364, "percentage": 91.62, "elapsed_time": "1 day, 6:38:24", "remaining_time": "2:48:11"}
|
191 |
+
{"current_steps": 1890, "total_steps": 2052, "loss": 0.7363, "lr": 5e-06, "epoch": 2.759627669282716, "percentage": 92.11, "elapsed_time": "1 day, 6:48:03", "remaining_time": "2:38:24"}
|
192 |
+
{"current_steps": 1900, "total_steps": 2052, "loss": 0.7359, "lr": 5e-06, "epoch": 2.7742288738820955, "percentage": 92.59, "elapsed_time": "1 day, 6:57:41", "remaining_time": "2:28:36"}
|
193 |
+
{"current_steps": 1910, "total_steps": 2052, "loss": 0.7383, "lr": 5e-06, "epoch": 2.7888300784814746, "percentage": 93.08, "elapsed_time": "1 day, 7:07:20", "remaining_time": "2:18:49"}
|
194 |
+
{"current_steps": 1920, "total_steps": 2052, "loss": 0.7344, "lr": 5e-06, "epoch": 2.803431283080854, "percentage": 93.57, "elapsed_time": "1 day, 7:16:58", "remaining_time": "2:09:02"}
|
195 |
+
{"current_steps": 1930, "total_steps": 2052, "loss": 0.7382, "lr": 5e-06, "epoch": 2.8180324876802336, "percentage": 94.05, "elapsed_time": "1 day, 7:26:37", "remaining_time": "1:59:15"}
|
196 |
+
{"current_steps": 1940, "total_steps": 2052, "loss": 0.7356, "lr": 5e-06, "epoch": 2.832633692279613, "percentage": 94.54, "elapsed_time": "1 day, 7:36:16", "remaining_time": "1:49:28"}
|
197 |
+
{"current_steps": 1950, "total_steps": 2052, "loss": 0.7377, "lr": 5e-06, "epoch": 2.8472348968789927, "percentage": 95.03, "elapsed_time": "1 day, 7:45:55", "remaining_time": "1:39:41"}
|
198 |
+
{"current_steps": 1960, "total_steps": 2052, "loss": 0.7337, "lr": 5e-06, "epoch": 2.8618361014783718, "percentage": 95.52, "elapsed_time": "1 day, 7:55:32", "remaining_time": "1:29:54"}
|
199 |
+
{"current_steps": 1970, "total_steps": 2052, "loss": 0.7362, "lr": 5e-06, "epoch": 2.8764373060777513, "percentage": 96.0, "elapsed_time": "1 day, 8:05:11", "remaining_time": "1:20:08"}
|
200 |
+
{"current_steps": 1980, "total_steps": 2052, "loss": 0.7359, "lr": 5e-06, "epoch": 2.891038510677131, "percentage": 96.49, "elapsed_time": "1 day, 8:14:49", "remaining_time": "1:10:21"}
|
201 |
+
{"current_steps": 1990, "total_steps": 2052, "loss": 0.7331, "lr": 5e-06, "epoch": 2.9056397152765103, "percentage": 96.98, "elapsed_time": "1 day, 8:24:27", "remaining_time": "1:00:34"}
|
202 |
+
{"current_steps": 2000, "total_steps": 2052, "loss": 0.7341, "lr": 5e-06, "epoch": 2.92024091987589, "percentage": 97.47, "elapsed_time": "1 day, 8:34:05", "remaining_time": "0:50:48"}
|
203 |
+
{"current_steps": 2010, "total_steps": 2052, "loss": 0.7404, "lr": 5e-06, "epoch": 2.9348421244752694, "percentage": 97.95, "elapsed_time": "1 day, 8:43:44", "remaining_time": "0:41:01"}
|
204 |
+
{"current_steps": 2020, "total_steps": 2052, "loss": 0.7337, "lr": 5e-06, "epoch": 2.949443329074649, "percentage": 98.44, "elapsed_time": "1 day, 8:53:21", "remaining_time": "0:31:15"}
|
205 |
+
{"current_steps": 2030, "total_steps": 2052, "loss": 0.7348, "lr": 5e-06, "epoch": 2.964044533674028, "percentage": 98.93, "elapsed_time": "1 day, 9:03:00", "remaining_time": "0:21:29"}
|
206 |
+
{"current_steps": 2040, "total_steps": 2052, "loss": 0.7354, "lr": 5e-06, "epoch": 2.9786457382734075, "percentage": 99.42, "elapsed_time": "1 day, 9:12:39", "remaining_time": "0:11:43"}
|
207 |
+
{"current_steps": 2050, "total_steps": 2052, "loss": 0.7372, "lr": 5e-06, "epoch": 2.993246942872787, "percentage": 99.9, "elapsed_time": "1 day, 9:22:18", "remaining_time": "0:01:57"}
|