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 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b6a4235e5e8e50ecc6bfb88b41d601b7e7bb6478a4e469c8e2dbf4ad24a176c
|
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:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:911e0fcb1c23c539871fb6f81a2242a9e8fe387c3eaa40d3d93df62cb4c12eec
|
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:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:998de26341e44535566c5e2f3a9186dcfc8d64300aca35f58925d3a4a701d768
|
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:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69bb297d7873989c1be4b695e492c9c96ccc8341108f65a61f2dfe949657e0a9
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -134,3 +134,138 @@
|
|
134 |
{"current_steps": 1340, "total_steps": 4023, "loss": 0.5404, "lr": 5e-06, "epoch": 0.9992542878448919, "percentage": 33.31, "elapsed_time": "4:55:31", "remaining_time": "9:51:42"}
|
135 |
{"current_steps": 1341, "total_steps": 4023, "eval_loss": 0.5463822484016418, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:01:23", "remaining_time": "10:02:46"}
|
136 |
{"current_steps": 1350, "total_steps": 4023, "loss": 0.4824, "lr": 5e-06, "epoch": 1.0067114093959733, "percentage": 33.56, "elapsed_time": "5:04:27", "remaining_time": "10:02:50"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
{"current_steps": 1340, "total_steps": 4023, "loss": 0.5404, "lr": 5e-06, "epoch": 0.9992542878448919, "percentage": 33.31, "elapsed_time": "4:55:31", "remaining_time": "9:51:42"}
|
135 |
{"current_steps": 1341, "total_steps": 4023, "eval_loss": 0.5463822484016418, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:01:23", "remaining_time": "10:02:46"}
|
136 |
{"current_steps": 1350, "total_steps": 4023, "loss": 0.4824, "lr": 5e-06, "epoch": 1.0067114093959733, "percentage": 33.56, "elapsed_time": "5:04:27", "remaining_time": "10:02:50"}
|
137 |
+
{"current_steps": 1360, "total_steps": 4023, "loss": 0.4797, "lr": 5e-06, "epoch": 1.0141685309470545, "percentage": 33.81, "elapsed_time": "5:06:40", "remaining_time": "10:00:29"}
|
138 |
+
{"current_steps": 1370, "total_steps": 4023, "loss": 0.4686, "lr": 5e-06, "epoch": 1.0216256524981358, "percentage": 34.05, "elapsed_time": "5:08:52", "remaining_time": "9:58:08"}
|
139 |
+
{"current_steps": 1380, "total_steps": 4023, "loss": 0.469, "lr": 5e-06, "epoch": 1.029082774049217, "percentage": 34.3, "elapsed_time": "5:11:05", "remaining_time": "9:55:48"}
|
140 |
+
{"current_steps": 1390, "total_steps": 4023, "loss": 0.4903, "lr": 5e-06, "epoch": 1.0365398956002982, "percentage": 34.55, "elapsed_time": "5:13:17", "remaining_time": "9:53:27"}
|
141 |
+
{"current_steps": 1400, "total_steps": 4023, "loss": 0.4956, "lr": 5e-06, "epoch": 1.0439970171513795, "percentage": 34.8, "elapsed_time": "5:15:30", "remaining_time": "9:51:07"}
|
142 |
+
{"current_steps": 1410, "total_steps": 4023, "loss": 0.4933, "lr": 5e-06, "epoch": 1.0514541387024607, "percentage": 35.05, "elapsed_time": "5:17:42", "remaining_time": "9:48:47"}
|
143 |
+
{"current_steps": 1420, "total_steps": 4023, "loss": 0.486, "lr": 5e-06, "epoch": 1.0589112602535422, "percentage": 35.3, "elapsed_time": "5:19:55", "remaining_time": "9:46:27"}
|
144 |
+
{"current_steps": 1430, "total_steps": 4023, "loss": 0.4968, "lr": 5e-06, "epoch": 1.0663683818046235, "percentage": 35.55, "elapsed_time": "5:22:08", "remaining_time": "9:44:07"}
|
145 |
+
{"current_steps": 1440, "total_steps": 4023, "loss": 0.4902, "lr": 5e-06, "epoch": 1.0738255033557047, "percentage": 35.79, "elapsed_time": "5:24:20", "remaining_time": "9:41:47"}
|
146 |
+
{"current_steps": 1450, "total_steps": 4023, "loss": 0.4703, "lr": 5e-06, "epoch": 1.081282624906786, "percentage": 36.04, "elapsed_time": "5:26:33", "remaining_time": "9:39:28"}
|
147 |
+
{"current_steps": 1460, "total_steps": 4023, "loss": 0.4816, "lr": 5e-06, "epoch": 1.0887397464578672, "percentage": 36.29, "elapsed_time": "5:28:45", "remaining_time": "9:37:08"}
|
148 |
+
{"current_steps": 1470, "total_steps": 4023, "loss": 0.479, "lr": 5e-06, "epoch": 1.0961968680089484, "percentage": 36.54, "elapsed_time": "5:30:58", "remaining_time": "9:34:48"}
|
149 |
+
{"current_steps": 1480, "total_steps": 4023, "loss": 0.4834, "lr": 5e-06, "epoch": 1.10365398956003, "percentage": 36.79, "elapsed_time": "5:33:10", "remaining_time": "9:32:29"}
|
150 |
+
{"current_steps": 1490, "total_steps": 4023, "loss": 0.4807, "lr": 5e-06, "epoch": 1.1111111111111112, "percentage": 37.04, "elapsed_time": "5:35:23", "remaining_time": "9:30:09"}
|
151 |
+
{"current_steps": 1500, "total_steps": 4023, "loss": 0.4945, "lr": 5e-06, "epoch": 1.1185682326621924, "percentage": 37.29, "elapsed_time": "5:37:35", "remaining_time": "9:27:50"}
|
152 |
+
{"current_steps": 1510, "total_steps": 4023, "loss": 0.4756, "lr": 5e-06, "epoch": 1.1260253542132737, "percentage": 37.53, "elapsed_time": "5:39:48", "remaining_time": "9:25:31"}
|
153 |
+
{"current_steps": 1520, "total_steps": 4023, "loss": 0.4753, "lr": 5e-06, "epoch": 1.133482475764355, "percentage": 37.78, "elapsed_time": "5:42:00", "remaining_time": "9:23:11"}
|
154 |
+
{"current_steps": 1530, "total_steps": 4023, "loss": 0.474, "lr": 5e-06, "epoch": 1.1409395973154361, "percentage": 38.03, "elapsed_time": "5:44:13", "remaining_time": "9:20:53"}
|
155 |
+
{"current_steps": 1540, "total_steps": 4023, "loss": 0.4786, "lr": 5e-06, "epoch": 1.1483967188665176, "percentage": 38.28, "elapsed_time": "5:46:26", "remaining_time": "9:18:34"}
|
156 |
+
{"current_steps": 1550, "total_steps": 4023, "loss": 0.4658, "lr": 5e-06, "epoch": 1.1558538404175989, "percentage": 38.53, "elapsed_time": "5:48:39", "remaining_time": "9:16:15"}
|
157 |
+
{"current_steps": 1560, "total_steps": 4023, "loss": 0.4884, "lr": 5e-06, "epoch": 1.1633109619686801, "percentage": 38.78, "elapsed_time": "5:50:51", "remaining_time": "9:13:57"}
|
158 |
+
{"current_steps": 1570, "total_steps": 4023, "loss": 0.4907, "lr": 5e-06, "epoch": 1.1707680835197614, "percentage": 39.03, "elapsed_time": "5:53:04", "remaining_time": "9:11:38"}
|
159 |
+
{"current_steps": 1580, "total_steps": 4023, "loss": 0.4872, "lr": 5e-06, "epoch": 1.1782252050708426, "percentage": 39.27, "elapsed_time": "5:55:17", "remaining_time": "9:09:20"}
|
160 |
+
{"current_steps": 1590, "total_steps": 4023, "loss": 0.4816, "lr": 5e-06, "epoch": 1.1856823266219239, "percentage": 39.52, "elapsed_time": "5:57:29", "remaining_time": "9:07:01"}
|
161 |
+
{"current_steps": 1600, "total_steps": 4023, "loss": 0.4676, "lr": 5e-06, "epoch": 1.1931394481730053, "percentage": 39.77, "elapsed_time": "5:59:42", "remaining_time": "9:04:43"}
|
162 |
+
{"current_steps": 1610, "total_steps": 4023, "loss": 0.4789, "lr": 5e-06, "epoch": 1.2005965697240866, "percentage": 40.02, "elapsed_time": "6:01:54", "remaining_time": "9:02:25"}
|
163 |
+
{"current_steps": 1620, "total_steps": 4023, "loss": 0.4816, "lr": 5e-06, "epoch": 1.2080536912751678, "percentage": 40.27, "elapsed_time": "6:04:07", "remaining_time": "9:00:06"}
|
164 |
+
{"current_steps": 1630, "total_steps": 4023, "loss": 0.4852, "lr": 5e-06, "epoch": 1.215510812826249, "percentage": 40.52, "elapsed_time": "6:06:19", "remaining_time": "8:57:48"}
|
165 |
+
{"current_steps": 1640, "total_steps": 4023, "loss": 0.4986, "lr": 5e-06, "epoch": 1.2229679343773303, "percentage": 40.77, "elapsed_time": "6:08:32", "remaining_time": "8:55:30"}
|
166 |
+
{"current_steps": 1650, "total_steps": 4023, "loss": 0.4811, "lr": 5e-06, "epoch": 1.2304250559284116, "percentage": 41.01, "elapsed_time": "6:10:45", "remaining_time": "8:53:12"}
|
167 |
+
{"current_steps": 1660, "total_steps": 4023, "loss": 0.4886, "lr": 5e-06, "epoch": 1.2378821774794928, "percentage": 41.26, "elapsed_time": "6:12:57", "remaining_time": "8:50:54"}
|
168 |
+
{"current_steps": 1670, "total_steps": 4023, "loss": 0.4656, "lr": 5e-06, "epoch": 1.2453392990305743, "percentage": 41.51, "elapsed_time": "6:15:10", "remaining_time": "8:48:36"}
|
169 |
+
{"current_steps": 1680, "total_steps": 4023, "loss": 0.4715, "lr": 5e-06, "epoch": 1.2527964205816555, "percentage": 41.76, "elapsed_time": "6:17:22", "remaining_time": "8:46:18"}
|
170 |
+
{"current_steps": 1690, "total_steps": 4023, "loss": 0.471, "lr": 5e-06, "epoch": 1.2602535421327368, "percentage": 42.01, "elapsed_time": "6:19:35", "remaining_time": "8:44:00"}
|
171 |
+
{"current_steps": 1700, "total_steps": 4023, "loss": 0.4736, "lr": 5e-06, "epoch": 1.267710663683818, "percentage": 42.26, "elapsed_time": "6:21:47", "remaining_time": "8:41:42"}
|
172 |
+
{"current_steps": 1710, "total_steps": 4023, "loss": 0.4798, "lr": 5e-06, "epoch": 1.2751677852348993, "percentage": 42.51, "elapsed_time": "6:24:00", "remaining_time": "8:39:25"}
|
173 |
+
{"current_steps": 1720, "total_steps": 4023, "loss": 0.4792, "lr": 5e-06, "epoch": 1.2826249067859807, "percentage": 42.75, "elapsed_time": "6:26:12", "remaining_time": "8:37:07"}
|
174 |
+
{"current_steps": 1730, "total_steps": 4023, "loss": 0.4843, "lr": 5e-06, "epoch": 1.290082028337062, "percentage": 43.0, "elapsed_time": "6:28:25", "remaining_time": "8:34:49"}
|
175 |
+
{"current_steps": 1740, "total_steps": 4023, "loss": 0.4869, "lr": 5e-06, "epoch": 1.2975391498881432, "percentage": 43.25, "elapsed_time": "6:30:37", "remaining_time": "8:32:32"}
|
176 |
+
{"current_steps": 1750, "total_steps": 4023, "loss": 0.4838, "lr": 5e-06, "epoch": 1.3049962714392245, "percentage": 43.5, "elapsed_time": "6:32:50", "remaining_time": "8:30:14"}
|
177 |
+
{"current_steps": 1760, "total_steps": 4023, "loss": 0.4746, "lr": 5e-06, "epoch": 1.3124533929903057, "percentage": 43.75, "elapsed_time": "6:35:02", "remaining_time": "8:27:56"}
|
178 |
+
{"current_steps": 1770, "total_steps": 4023, "loss": 0.4931, "lr": 5e-06, "epoch": 1.319910514541387, "percentage": 44.0, "elapsed_time": "6:37:14", "remaining_time": "8:25:39"}
|
179 |
+
{"current_steps": 1780, "total_steps": 4023, "loss": 0.4871, "lr": 5e-06, "epoch": 1.3273676360924682, "percentage": 44.25, "elapsed_time": "6:39:27", "remaining_time": "8:23:21"}
|
180 |
+
{"current_steps": 1790, "total_steps": 4023, "loss": 0.4841, "lr": 5e-06, "epoch": 1.3348247576435495, "percentage": 44.49, "elapsed_time": "6:41:39", "remaining_time": "8:21:04"}
|
181 |
+
{"current_steps": 1800, "total_steps": 4023, "loss": 0.4862, "lr": 5e-06, "epoch": 1.342281879194631, "percentage": 44.74, "elapsed_time": "6:43:52", "remaining_time": "8:18:46"}
|
182 |
+
{"current_steps": 1810, "total_steps": 4023, "loss": 0.4766, "lr": 5e-06, "epoch": 1.3497390007457122, "percentage": 44.99, "elapsed_time": "6:46:04", "remaining_time": "8:16:29"}
|
183 |
+
{"current_steps": 1820, "total_steps": 4023, "loss": 0.4812, "lr": 5e-06, "epoch": 1.3571961222967934, "percentage": 45.24, "elapsed_time": "6:48:16", "remaining_time": "8:14:12"}
|
184 |
+
{"current_steps": 1830, "total_steps": 4023, "loss": 0.4686, "lr": 5e-06, "epoch": 1.3646532438478747, "percentage": 45.49, "elapsed_time": "6:50:29", "remaining_time": "8:11:54"}
|
185 |
+
{"current_steps": 1840, "total_steps": 4023, "loss": 0.477, "lr": 5e-06, "epoch": 1.372110365398956, "percentage": 45.74, "elapsed_time": "6:52:41", "remaining_time": "8:09:37"}
|
186 |
+
{"current_steps": 1850, "total_steps": 4023, "loss": 0.4889, "lr": 5e-06, "epoch": 1.3795674869500374, "percentage": 45.99, "elapsed_time": "6:54:53", "remaining_time": "8:07:20"}
|
187 |
+
{"current_steps": 1860, "total_steps": 4023, "loss": 0.4792, "lr": 5e-06, "epoch": 1.3870246085011186, "percentage": 46.23, "elapsed_time": "6:57:06", "remaining_time": "8:05:03"}
|
188 |
+
{"current_steps": 1870, "total_steps": 4023, "loss": 0.4897, "lr": 5e-06, "epoch": 1.3944817300521999, "percentage": 46.48, "elapsed_time": "6:59:18", "remaining_time": "8:02:46"}
|
189 |
+
{"current_steps": 1880, "total_steps": 4023, "loss": 0.496, "lr": 5e-06, "epoch": 1.4019388516032811, "percentage": 46.73, "elapsed_time": "7:01:31", "remaining_time": "8:00:29"}
|
190 |
+
{"current_steps": 1890, "total_steps": 4023, "loss": 0.4671, "lr": 5e-06, "epoch": 1.4093959731543624, "percentage": 46.98, "elapsed_time": "7:03:44", "remaining_time": "7:58:12"}
|
191 |
+
{"current_steps": 1900, "total_steps": 4023, "loss": 0.4786, "lr": 5e-06, "epoch": 1.4168530947054436, "percentage": 47.23, "elapsed_time": "7:05:56", "remaining_time": "7:55:56"}
|
192 |
+
{"current_steps": 1910, "total_steps": 4023, "loss": 0.4886, "lr": 5e-06, "epoch": 1.4243102162565249, "percentage": 47.48, "elapsed_time": "7:08:09", "remaining_time": "7:53:39"}
|
193 |
+
{"current_steps": 1920, "total_steps": 4023, "loss": 0.497, "lr": 5e-06, "epoch": 1.4317673378076063, "percentage": 47.73, "elapsed_time": "7:10:21", "remaining_time": "7:51:22"}
|
194 |
+
{"current_steps": 1930, "total_steps": 4023, "loss": 0.4899, "lr": 5e-06, "epoch": 1.4392244593586876, "percentage": 47.97, "elapsed_time": "7:12:34", "remaining_time": "7:49:06"}
|
195 |
+
{"current_steps": 1940, "total_steps": 4023, "loss": 0.4775, "lr": 5e-06, "epoch": 1.4466815809097688, "percentage": 48.22, "elapsed_time": "7:14:46", "remaining_time": "7:46:49"}
|
196 |
+
{"current_steps": 1950, "total_steps": 4023, "loss": 0.4907, "lr": 5e-06, "epoch": 1.45413870246085, "percentage": 48.47, "elapsed_time": "7:16:59", "remaining_time": "7:44:33"}
|
197 |
+
{"current_steps": 1960, "total_steps": 4023, "loss": 0.4759, "lr": 5e-06, "epoch": 1.4615958240119313, "percentage": 48.72, "elapsed_time": "7:19:12", "remaining_time": "7:42:16"}
|
198 |
+
{"current_steps": 1970, "total_steps": 4023, "loss": 0.4897, "lr": 5e-06, "epoch": 1.4690529455630128, "percentage": 48.97, "elapsed_time": "7:21:24", "remaining_time": "7:40:00"}
|
199 |
+
{"current_steps": 1980, "total_steps": 4023, "loss": 0.4746, "lr": 5e-06, "epoch": 1.476510067114094, "percentage": 49.22, "elapsed_time": "7:23:37", "remaining_time": "7:37:44"}
|
200 |
+
{"current_steps": 1990, "total_steps": 4023, "loss": 0.4885, "lr": 5e-06, "epoch": 1.4839671886651753, "percentage": 49.47, "elapsed_time": "7:25:49", "remaining_time": "7:35:27"}
|
201 |
+
{"current_steps": 2000, "total_steps": 4023, "loss": 0.4884, "lr": 5e-06, "epoch": 1.4914243102162565, "percentage": 49.71, "elapsed_time": "7:28:02", "remaining_time": "7:33:11"}
|
202 |
+
{"current_steps": 2010, "total_steps": 4023, "loss": 0.4799, "lr": 5e-06, "epoch": 1.4988814317673378, "percentage": 49.96, "elapsed_time": "7:30:15", "remaining_time": "7:30:55"}
|
203 |
+
{"current_steps": 2020, "total_steps": 4023, "loss": 0.4832, "lr": 5e-06, "epoch": 1.506338553318419, "percentage": 50.21, "elapsed_time": "7:32:27", "remaining_time": "7:28:39"}
|
204 |
+
{"current_steps": 2030, "total_steps": 4023, "loss": 0.4765, "lr": 5e-06, "epoch": 1.5137956748695003, "percentage": 50.46, "elapsed_time": "7:34:40", "remaining_time": "7:26:23"}
|
205 |
+
{"current_steps": 2040, "total_steps": 4023, "loss": 0.4876, "lr": 5e-06, "epoch": 1.5212527964205815, "percentage": 50.71, "elapsed_time": "7:36:53", "remaining_time": "7:24:07"}
|
206 |
+
{"current_steps": 2050, "total_steps": 4023, "loss": 0.4867, "lr": 5e-06, "epoch": 1.5287099179716628, "percentage": 50.96, "elapsed_time": "7:39:06", "remaining_time": "7:21:51"}
|
207 |
+
{"current_steps": 2060, "total_steps": 4023, "loss": 0.4952, "lr": 5e-06, "epoch": 1.5361670395227442, "percentage": 51.21, "elapsed_time": "7:41:18", "remaining_time": "7:19:35"}
|
208 |
+
{"current_steps": 2070, "total_steps": 4023, "loss": 0.476, "lr": 5e-06, "epoch": 1.5436241610738255, "percentage": 51.45, "elapsed_time": "7:43:31", "remaining_time": "7:17:19"}
|
209 |
+
{"current_steps": 2080, "total_steps": 4023, "loss": 0.4937, "lr": 5e-06, "epoch": 1.5510812826249067, "percentage": 51.7, "elapsed_time": "7:45:43", "remaining_time": "7:15:03"}
|
210 |
+
{"current_steps": 2090, "total_steps": 4023, "loss": 0.4974, "lr": 5e-06, "epoch": 1.5585384041759882, "percentage": 51.95, "elapsed_time": "7:47:56", "remaining_time": "7:12:47"}
|
211 |
+
{"current_steps": 2100, "total_steps": 4023, "loss": 0.4877, "lr": 5e-06, "epoch": 1.5659955257270695, "percentage": 52.2, "elapsed_time": "7:50:08", "remaining_time": "7:10:31"}
|
212 |
+
{"current_steps": 2110, "total_steps": 4023, "loss": 0.4873, "lr": 5e-06, "epoch": 1.5734526472781507, "percentage": 52.45, "elapsed_time": "7:52:21", "remaining_time": "7:08:15"}
|
213 |
+
{"current_steps": 2120, "total_steps": 4023, "loss": 0.4798, "lr": 5e-06, "epoch": 1.580909768829232, "percentage": 52.7, "elapsed_time": "7:54:33", "remaining_time": "7:05:59"}
|
214 |
+
{"current_steps": 2130, "total_steps": 4023, "loss": 0.4699, "lr": 5e-06, "epoch": 1.5883668903803132, "percentage": 52.95, "elapsed_time": "7:56:46", "remaining_time": "7:03:43"}
|
215 |
+
{"current_steps": 2140, "total_steps": 4023, "loss": 0.4995, "lr": 5e-06, "epoch": 1.5958240119313944, "percentage": 53.19, "elapsed_time": "7:58:58", "remaining_time": "7:01:27"}
|
216 |
+
{"current_steps": 2150, "total_steps": 4023, "loss": 0.4959, "lr": 5e-06, "epoch": 1.6032811334824757, "percentage": 53.44, "elapsed_time": "8:01:11", "remaining_time": "6:59:11"}
|
217 |
+
{"current_steps": 2160, "total_steps": 4023, "loss": 0.4783, "lr": 5e-06, "epoch": 1.610738255033557, "percentage": 53.69, "elapsed_time": "8:03:24", "remaining_time": "6:56:55"}
|
218 |
+
{"current_steps": 2170, "total_steps": 4023, "loss": 0.4823, "lr": 5e-06, "epoch": 1.6181953765846382, "percentage": 53.94, "elapsed_time": "8:05:36", "remaining_time": "6:54:40"}
|
219 |
+
{"current_steps": 2180, "total_steps": 4023, "loss": 0.4761, "lr": 5e-06, "epoch": 1.6256524981357197, "percentage": 54.19, "elapsed_time": "8:07:49", "remaining_time": "6:52:24"}
|
220 |
+
{"current_steps": 2190, "total_steps": 4023, "loss": 0.4823, "lr": 5e-06, "epoch": 1.633109619686801, "percentage": 54.44, "elapsed_time": "8:10:01", "remaining_time": "6:50:09"}
|
221 |
+
{"current_steps": 2200, "total_steps": 4023, "loss": 0.4827, "lr": 5e-06, "epoch": 1.6405667412378822, "percentage": 54.69, "elapsed_time": "8:12:14", "remaining_time": "6:47:53"}
|
222 |
+
{"current_steps": 2210, "total_steps": 4023, "loss": 0.4878, "lr": 5e-06, "epoch": 1.6480238627889636, "percentage": 54.93, "elapsed_time": "8:14:26", "remaining_time": "6:45:37"}
|
223 |
+
{"current_steps": 2220, "total_steps": 4023, "loss": 0.4854, "lr": 5e-06, "epoch": 1.6554809843400449, "percentage": 55.18, "elapsed_time": "8:16:39", "remaining_time": "6:43:21"}
|
224 |
+
{"current_steps": 2230, "total_steps": 4023, "loss": 0.4876, "lr": 5e-06, "epoch": 1.6629381058911261, "percentage": 55.43, "elapsed_time": "8:18:51", "remaining_time": "6:41:06"}
|
225 |
+
{"current_steps": 2240, "total_steps": 4023, "loss": 0.4976, "lr": 5e-06, "epoch": 1.6703952274422074, "percentage": 55.68, "elapsed_time": "8:21:04", "remaining_time": "6:38:50"}
|
226 |
+
{"current_steps": 2250, "total_steps": 4023, "loss": 0.473, "lr": 5e-06, "epoch": 1.6778523489932886, "percentage": 55.93, "elapsed_time": "8:23:16", "remaining_time": "6:36:34"}
|
227 |
+
{"current_steps": 2260, "total_steps": 4023, "loss": 0.4866, "lr": 5e-06, "epoch": 1.6853094705443699, "percentage": 56.18, "elapsed_time": "8:25:28", "remaining_time": "6:34:19"}
|
228 |
+
{"current_steps": 2270, "total_steps": 4023, "loss": 0.4909, "lr": 5e-06, "epoch": 1.692766592095451, "percentage": 56.43, "elapsed_time": "8:27:40", "remaining_time": "6:32:03"}
|
229 |
+
{"current_steps": 2280, "total_steps": 4023, "loss": 0.4914, "lr": 5e-06, "epoch": 1.7002237136465324, "percentage": 56.67, "elapsed_time": "8:29:53", "remaining_time": "6:29:47"}
|
230 |
+
{"current_steps": 2290, "total_steps": 4023, "loss": 0.4804, "lr": 5e-06, "epoch": 1.7076808351976136, "percentage": 56.92, "elapsed_time": "8:32:05", "remaining_time": "6:27:32"}
|
231 |
+
{"current_steps": 2300, "total_steps": 4023, "loss": 0.4925, "lr": 5e-06, "epoch": 1.7151379567486948, "percentage": 57.17, "elapsed_time": "8:34:17", "remaining_time": "6:25:16"}
|
232 |
+
{"current_steps": 2310, "total_steps": 4023, "loss": 0.4913, "lr": 5e-06, "epoch": 1.7225950782997763, "percentage": 57.42, "elapsed_time": "8:36:30", "remaining_time": "6:23:01"}
|
233 |
+
{"current_steps": 2320, "total_steps": 4023, "loss": 0.4769, "lr": 5e-06, "epoch": 1.7300521998508576, "percentage": 57.67, "elapsed_time": "8:38:42", "remaining_time": "6:20:45"}
|
234 |
+
{"current_steps": 2330, "total_steps": 4023, "loss": 0.4898, "lr": 5e-06, "epoch": 1.7375093214019388, "percentage": 57.92, "elapsed_time": "8:40:54", "remaining_time": "6:18:30"}
|
235 |
+
{"current_steps": 2340, "total_steps": 4023, "loss": 0.4826, "lr": 5e-06, "epoch": 1.7449664429530203, "percentage": 58.17, "elapsed_time": "8:43:07", "remaining_time": "6:16:14"}
|
236 |
+
{"current_steps": 2350, "total_steps": 4023, "loss": 0.4777, "lr": 5e-06, "epoch": 1.7524235645041015, "percentage": 58.41, "elapsed_time": "8:45:19", "remaining_time": "6:13:59"}
|
237 |
+
{"current_steps": 2360, "total_steps": 4023, "loss": 0.4934, "lr": 5e-06, "epoch": 1.7598806860551828, "percentage": 58.66, "elapsed_time": "8:47:32", "remaining_time": "6:11:44"}
|
238 |
+
{"current_steps": 2370, "total_steps": 4023, "loss": 0.5053, "lr": 5e-06, "epoch": 1.767337807606264, "percentage": 58.91, "elapsed_time": "8:49:44", "remaining_time": "6:09:29"}
|
239 |
+
{"current_steps": 2380, "total_steps": 4023, "loss": 0.4817, "lr": 5e-06, "epoch": 1.7747949291573453, "percentage": 59.16, "elapsed_time": "8:51:57", "remaining_time": "6:07:13"}
|
240 |
+
{"current_steps": 2390, "total_steps": 4023, "loss": 0.4853, "lr": 5e-06, "epoch": 1.7822520507084265, "percentage": 59.41, "elapsed_time": "8:54:10", "remaining_time": "6:04:58"}
|
241 |
+
{"current_steps": 2400, "total_steps": 4023, "loss": 0.4791, "lr": 5e-06, "epoch": 1.7897091722595078, "percentage": 59.66, "elapsed_time": "8:56:23", "remaining_time": "6:02:43"}
|
242 |
+
{"current_steps": 2410, "total_steps": 4023, "loss": 0.4809, "lr": 5e-06, "epoch": 1.797166293810589, "percentage": 59.91, "elapsed_time": "8:58:35", "remaining_time": "6:00:28"}
|
243 |
+
{"current_steps": 2420, "total_steps": 4023, "loss": 0.4929, "lr": 5e-06, "epoch": 1.8046234153616703, "percentage": 60.15, "elapsed_time": "9:00:48", "remaining_time": "5:58:13"}
|
244 |
+
{"current_steps": 2430, "total_steps": 4023, "loss": 0.4847, "lr": 5e-06, "epoch": 1.8120805369127517, "percentage": 60.4, "elapsed_time": "9:03:01", "remaining_time": "5:55:58"}
|
245 |
+
{"current_steps": 2440, "total_steps": 4023, "loss": 0.4906, "lr": 5e-06, "epoch": 1.819537658463833, "percentage": 60.65, "elapsed_time": "9:05:13", "remaining_time": "5:53:43"}
|
246 |
+
{"current_steps": 2450, "total_steps": 4023, "loss": 0.4975, "lr": 5e-06, "epoch": 1.8269947800149142, "percentage": 60.9, "elapsed_time": "9:07:26", "remaining_time": "5:51:28"}
|
247 |
+
{"current_steps": 2460, "total_steps": 4023, "loss": 0.4814, "lr": 5e-06, "epoch": 1.8344519015659957, "percentage": 61.15, "elapsed_time": "9:09:39", "remaining_time": "5:49:13"}
|
248 |
+
{"current_steps": 2470, "total_steps": 4023, "loss": 0.4811, "lr": 5e-06, "epoch": 1.841909023117077, "percentage": 61.4, "elapsed_time": "9:11:51", "remaining_time": "5:46:58"}
|
249 |
+
{"current_steps": 2480, "total_steps": 4023, "loss": 0.496, "lr": 5e-06, "epoch": 1.8493661446681582, "percentage": 61.65, "elapsed_time": "9:14:04", "remaining_time": "5:44:44"}
|
250 |
+
{"current_steps": 2490, "total_steps": 4023, "loss": 0.4804, "lr": 5e-06, "epoch": 1.8568232662192394, "percentage": 61.89, "elapsed_time": "9:16:17", "remaining_time": "5:42:29"}
|
251 |
+
{"current_steps": 2500, "total_steps": 4023, "loss": 0.4863, "lr": 5e-06, "epoch": 1.8642803877703207, "percentage": 62.14, "elapsed_time": "9:18:29", "remaining_time": "5:40:14"}
|
252 |
+
{"current_steps": 2510, "total_steps": 4023, "loss": 0.4909, "lr": 5e-06, "epoch": 1.871737509321402, "percentage": 62.39, "elapsed_time": "9:20:42", "remaining_time": "5:37:59"}
|
253 |
+
{"current_steps": 2520, "total_steps": 4023, "loss": 0.4831, "lr": 5e-06, "epoch": 1.8791946308724832, "percentage": 62.64, "elapsed_time": "9:22:55", "remaining_time": "5:35:44"}
|
254 |
+
{"current_steps": 2530, "total_steps": 4023, "loss": 0.5042, "lr": 5e-06, "epoch": 1.8866517524235644, "percentage": 62.89, "elapsed_time": "9:25:08", "remaining_time": "5:33:29"}
|
255 |
+
{"current_steps": 2540, "total_steps": 4023, "loss": 0.5004, "lr": 5e-06, "epoch": 1.8941088739746457, "percentage": 63.14, "elapsed_time": "9:27:20", "remaining_time": "5:31:14"}
|
256 |
+
{"current_steps": 2550, "total_steps": 4023, "loss": 0.4802, "lr": 5e-06, "epoch": 1.901565995525727, "percentage": 63.39, "elapsed_time": "9:29:33", "remaining_time": "5:29:00"}
|
257 |
+
{"current_steps": 2560, "total_steps": 4023, "loss": 0.49, "lr": 5e-06, "epoch": 1.9090231170768084, "percentage": 63.63, "elapsed_time": "9:31:46", "remaining_time": "5:26:45"}
|
258 |
+
{"current_steps": 2570, "total_steps": 4023, "loss": 0.4961, "lr": 5e-06, "epoch": 1.9164802386278896, "percentage": 63.88, "elapsed_time": "9:33:58", "remaining_time": "5:24:30"}
|
259 |
+
{"current_steps": 2580, "total_steps": 4023, "loss": 0.493, "lr": 5e-06, "epoch": 1.9239373601789709, "percentage": 64.13, "elapsed_time": "9:36:11", "remaining_time": "5:22:15"}
|
260 |
+
{"current_steps": 2590, "total_steps": 4023, "loss": 0.4788, "lr": 5e-06, "epoch": 1.9313944817300523, "percentage": 64.38, "elapsed_time": "9:38:24", "remaining_time": "5:20:01"}
|
261 |
+
{"current_steps": 2600, "total_steps": 4023, "loss": 0.4944, "lr": 5e-06, "epoch": 1.9388516032811336, "percentage": 64.63, "elapsed_time": "9:40:36", "remaining_time": "5:17:46"}
|
262 |
+
{"current_steps": 2610, "total_steps": 4023, "loss": 0.4924, "lr": 5e-06, "epoch": 1.9463087248322148, "percentage": 64.88, "elapsed_time": "9:42:49", "remaining_time": "5:15:31"}
|
263 |
+
{"current_steps": 2620, "total_steps": 4023, "loss": 0.4909, "lr": 5e-06, "epoch": 1.953765846383296, "percentage": 65.13, "elapsed_time": "9:45:02", "remaining_time": "5:13:17"}
|
264 |
+
{"current_steps": 2630, "total_steps": 4023, "loss": 0.4981, "lr": 5e-06, "epoch": 1.9612229679343773, "percentage": 65.37, "elapsed_time": "9:47:14", "remaining_time": "5:11:02"}
|
265 |
+
{"current_steps": 2640, "total_steps": 4023, "loss": 0.498, "lr": 5e-06, "epoch": 1.9686800894854586, "percentage": 65.62, "elapsed_time": "9:49:27", "remaining_time": "5:08:47"}
|
266 |
+
{"current_steps": 2650, "total_steps": 4023, "loss": 0.4793, "lr": 5e-06, "epoch": 1.9761372110365398, "percentage": 65.87, "elapsed_time": "9:51:40", "remaining_time": "5:06:33"}
|
267 |
+
{"current_steps": 2660, "total_steps": 4023, "loss": 0.4877, "lr": 5e-06, "epoch": 1.983594332587621, "percentage": 66.12, "elapsed_time": "9:53:53", "remaining_time": "5:04:18"}
|
268 |
+
{"current_steps": 2670, "total_steps": 4023, "loss": 0.4852, "lr": 5e-06, "epoch": 1.9910514541387023, "percentage": 66.37, "elapsed_time": "9:56:05", "remaining_time": "5:02:04"}
|
269 |
+
{"current_steps": 2680, "total_steps": 4023, "loss": 0.4804, "lr": 5e-06, "epoch": 1.9985085756897838, "percentage": 66.62, "elapsed_time": "9:58:18", "remaining_time": "4:59:49"}
|
270 |
+
{"current_steps": 2682, "total_steps": 4023, "eval_loss": 0.5512435436248779, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "10:04:26", "remaining_time": "5:02:13"}
|
271 |
+
{"current_steps": 2690, "total_steps": 4023, "loss": 0.4215, "lr": 5e-06, "epoch": 2.005965697240865, "percentage": 66.87, "elapsed_time": "10:07:20", "remaining_time": "5:00:57"}
|