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 sha256:8ad5b78aa99f0ab2541fb7c7343ce62045d3c32da3d56b66934cfa6432c09b82
|
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 sha256:40d0c4debf39486bc453231de50f90a1584a8555e705c3386fe4612ae2f2b966
|
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 sha256:6fb351c5e56dc22dc31c89e2e5297160c57cf709e09105e405626a6a203dd859
|
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 sha256:967e84a6a9c07b525614c0e0ffa83a31ef4cb47a2d38335fbd3c5651528e68d9
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -162,3 +162,80 @@
|
|
162 |
{"current_steps": 162, "total_steps": 380, "loss": 0.5117, "lr": 5.673804690815845e-05, "epoch": 2.108854589764419, "percentage": 42.63, "elapsed_time": "4:38:37", "remaining_time": "6:14:56"}
|
163 |
{"current_steps": 163, "total_steps": 380, "loss": 0.5039, "lr": 5.6403624023937614e-05, "epoch": 2.121852152721365, "percentage": 42.89, "elapsed_time": "4:40:20", "remaining_time": "6:13:12"}
|
164 |
{"current_steps": 164, "total_steps": 380, "loss": 0.5043, "lr": 5.606781698611879e-05, "epoch": 2.1348497156783104, "percentage": 43.16, "elapsed_time": "4:42:04", "remaining_time": "6:11:30"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
{"current_steps": 162, "total_steps": 380, "loss": 0.5117, "lr": 5.673804690815845e-05, "epoch": 2.108854589764419, "percentage": 42.63, "elapsed_time": "4:38:37", "remaining_time": "6:14:56"}
|
163 |
{"current_steps": 163, "total_steps": 380, "loss": 0.5039, "lr": 5.6403624023937614e-05, "epoch": 2.121852152721365, "percentage": 42.89, "elapsed_time": "4:40:20", "remaining_time": "6:13:12"}
|
164 |
{"current_steps": 164, "total_steps": 380, "loss": 0.5043, "lr": 5.606781698611879e-05, "epoch": 2.1348497156783104, "percentage": 43.16, "elapsed_time": "4:42:04", "remaining_time": "6:11:30"}
|
165 |
+
{"current_steps": 165, "total_steps": 380, "loss": 0.5069, "lr": 5.573065413042333e-05, "epoch": 2.147847278635256, "percentage": 43.42, "elapsed_time": "4:43:46", "remaining_time": "6:09:46"}
|
166 |
+
{"current_steps": 166, "total_steps": 380, "loss": 0.5072, "lr": 5.5392163906977835e-05, "epoch": 2.1608448415922012, "percentage": 43.68, "elapsed_time": "4:45:28", "remaining_time": "6:08:01"}
|
167 |
+
{"current_steps": 167, "total_steps": 380, "loss": 0.5054, "lr": 5.505237487791343e-05, "epoch": 2.173842404549147, "percentage": 43.95, "elapsed_time": "4:47:11", "remaining_time": "6:06:17"}
|
168 |
+
{"current_steps": 168, "total_steps": 380, "loss": 0.5031, "lr": 5.471131571495574e-05, "epoch": 2.1868399675060926, "percentage": 44.21, "elapsed_time": "4:48:53", "remaining_time": "6:04:33"}
|
169 |
+
{"current_steps": 169, "total_steps": 380, "loss": 0.5115, "lr": 5.4369015197005506e-05, "epoch": 2.199837530463038, "percentage": 44.47, "elapsed_time": "4:50:35", "remaining_time": "6:02:48"}
|
170 |
+
{"current_steps": 170, "total_steps": 380, "loss": 0.5073, "lr": 5.4025502207710184e-05, "epoch": 2.212835093419984, "percentage": 44.74, "elapsed_time": "4:52:17", "remaining_time": "6:01:04"}
|
171 |
+
{"current_steps": 171, "total_steps": 380, "loss": 0.5019, "lr": 5.368080573302676e-05, "epoch": 2.2258326563769293, "percentage": 45.0, "elapsed_time": "4:54:00", "remaining_time": "5:59:20"}
|
172 |
+
{"current_steps": 172, "total_steps": 380, "loss": 0.5025, "lr": 5.333495485877583e-05, "epoch": 2.2388302193338747, "percentage": 45.26, "elapsed_time": "4:55:43", "remaining_time": "5:57:37"}
|
173 |
+
{"current_steps": 173, "total_steps": 380, "loss": 0.5025, "lr": 5.298797876818735e-05, "epoch": 2.2518277822908206, "percentage": 45.53, "elapsed_time": "4:57:27", "remaining_time": "5:55:55"}
|
174 |
+
{"current_steps": 174, "total_steps": 380, "loss": 0.5032, "lr": 5.263990673943811e-05, "epoch": 2.264825345247766, "percentage": 45.79, "elapsed_time": "4:59:09", "remaining_time": "5:54:10"}
|
175 |
+
{"current_steps": 175, "total_steps": 380, "loss": 0.5033, "lr": 5.229076814318122e-05, "epoch": 2.2778229082047114, "percentage": 46.05, "elapsed_time": "5:00:51", "remaining_time": "5:52:26"}
|
176 |
+
{"current_steps": 176, "total_steps": 380, "loss": 0.4963, "lr": 5.194059244006779e-05, "epoch": 2.2908204711616573, "percentage": 46.32, "elapsed_time": "5:02:35", "remaining_time": "5:50:43"}
|
177 |
+
{"current_steps": 177, "total_steps": 380, "loss": 0.5049, "lr": 5.158940917826099e-05, "epoch": 2.3038180341186028, "percentage": 46.58, "elapsed_time": "5:04:19", "remaining_time": "5:49:01"}
|
178 |
+
{"current_steps": 178, "total_steps": 380, "loss": 0.4985, "lr": 5.123724799094279e-05, "epoch": 2.316815597075548, "percentage": 46.84, "elapsed_time": "5:06:02", "remaining_time": "5:47:18"}
|
179 |
+
{"current_steps": 179, "total_steps": 380, "loss": 0.4967, "lr": 5.088413859381341e-05, "epoch": 2.329813160032494, "percentage": 47.11, "elapsed_time": "5:07:46", "remaining_time": "5:45:36"}
|
180 |
+
{"current_steps": 180, "total_steps": 380, "loss": 0.4997, "lr": 5.053011078258397e-05, "epoch": 2.3428107229894395, "percentage": 47.37, "elapsed_time": "5:09:29", "remaining_time": "5:43:52"}
|
181 |
+
{"current_steps": 181, "total_steps": 380, "loss": 0.5072, "lr": 5.017519443046226e-05, "epoch": 2.355808285946385, "percentage": 47.63, "elapsed_time": "5:11:12", "remaining_time": "5:42:09"}
|
182 |
+
{"current_steps": 182, "total_steps": 380, "loss": 0.4954, "lr": 4.981941948563197e-05, "epoch": 2.368805848903331, "percentage": 47.89, "elapsed_time": "5:12:56", "remaining_time": "5:40:27"}
|
183 |
+
{"current_steps": 183, "total_steps": 380, "loss": 0.4968, "lr": 4.94628159687257e-05, "epoch": 2.381803411860276, "percentage": 48.16, "elapsed_time": "5:14:40", "remaining_time": "5:38:44"}
|
184 |
+
{"current_steps": 184, "total_steps": 380, "loss": 0.5013, "lr": 4.9105413970291747e-05, "epoch": 2.3948009748172217, "percentage": 48.42, "elapsed_time": "5:16:23", "remaining_time": "5:37:01"}
|
185 |
+
{"current_steps": 185, "total_steps": 380, "loss": 0.506, "lr": 4.874724364825504e-05, "epoch": 2.4077985377741675, "percentage": 48.68, "elapsed_time": "5:18:05", "remaining_time": "5:35:17"}
|
186 |
+
{"current_steps": 186, "total_steps": 380, "loss": 0.5052, "lr": 4.8388335225372416e-05, "epoch": 2.420796100731113, "percentage": 48.95, "elapsed_time": "5:19:48", "remaining_time": "5:33:33"}
|
187 |
+
{"current_steps": 187, "total_steps": 380, "loss": 0.5023, "lr": 4.802871898668237e-05, "epoch": 2.4337936636880584, "percentage": 49.21, "elapsed_time": "5:21:31", "remaining_time": "5:31:50"}
|
188 |
+
{"current_steps": 188, "total_steps": 380, "loss": 0.5057, "lr": 4.7668425276949546e-05, "epoch": 2.4467912266450043, "percentage": 49.47, "elapsed_time": "5:23:12", "remaining_time": "5:30:05"}
|
189 |
+
{"current_steps": 189, "total_steps": 380, "loss": 0.4958, "lr": 4.730748449810429e-05, "epoch": 2.4597887896019497, "percentage": 49.74, "elapsed_time": "5:24:55", "remaining_time": "5:28:21"}
|
190 |
+
{"current_steps": 190, "total_steps": 380, "loss": 0.4963, "lr": 4.694592710667723e-05, "epoch": 2.472786352558895, "percentage": 50.0, "elapsed_time": "5:26:37", "remaining_time": "5:26:37"}
|
191 |
+
{"current_steps": 191, "total_steps": 380, "loss": 0.5002, "lr": 4.658378361122936e-05, "epoch": 2.4857839155158405, "percentage": 50.26, "elapsed_time": "5:28:20", "remaining_time": "5:24:54"}
|
192 |
+
{"current_steps": 192, "total_steps": 380, "loss": 0.5036, "lr": 4.622108456977773e-05, "epoch": 2.4987814784727864, "percentage": 50.53, "elapsed_time": "5:30:04", "remaining_time": "5:23:11"}
|
193 |
+
{"current_steps": 193, "total_steps": 380, "loss": 0.5, "lr": 4.585786058721687e-05, "epoch": 2.511779041429732, "percentage": 50.79, "elapsed_time": "5:31:46", "remaining_time": "5:21:27"}
|
194 |
+
{"current_steps": 194, "total_steps": 380, "loss": 0.5031, "lr": 4.549414231273633e-05, "epoch": 2.5247766043866777, "percentage": 51.05, "elapsed_time": "5:33:28", "remaining_time": "5:19:43"}
|
195 |
+
{"current_steps": 195, "total_steps": 380, "loss": 0.5021, "lr": 4.512996043723453e-05, "epoch": 2.537774167343623, "percentage": 51.32, "elapsed_time": "5:35:10", "remaining_time": "5:17:59"}
|
196 |
+
{"current_steps": 196, "total_steps": 380, "loss": 0.5019, "lr": 4.476534569072895e-05, "epoch": 2.5507717303005686, "percentage": 51.58, "elapsed_time": "5:36:54", "remaining_time": "5:16:17"}
|
197 |
+
{"current_steps": 197, "total_steps": 380, "loss": 0.4991, "lr": 4.440032883976318e-05, "epoch": 2.563769293257514, "percentage": 51.84, "elapsed_time": "5:38:37", "remaining_time": "5:14:33"}
|
198 |
+
{"current_steps": 198, "total_steps": 380, "loss": 0.498, "lr": 4.403494068481074e-05, "epoch": 2.57676685621446, "percentage": 52.11, "elapsed_time": "5:40:19", "remaining_time": "5:12:49"}
|
199 |
+
{"current_steps": 199, "total_steps": 380, "loss": 0.5044, "lr": 4.3669212057676145e-05, "epoch": 2.5897644191714053, "percentage": 52.37, "elapsed_time": "5:42:02", "remaining_time": "5:11:06"}
|
200 |
+
{"current_steps": 200, "total_steps": 380, "loss": 0.4944, "lr": 4.33031738188933e-05, "epoch": 2.602761982128351, "percentage": 52.63, "elapsed_time": "5:43:44", "remaining_time": "5:09:22"}
|
201 |
+
{"current_steps": 201, "total_steps": 380, "loss": 0.4991, "lr": 4.293685685512142e-05, "epoch": 2.6157595450852966, "percentage": 52.89, "elapsed_time": "5:45:25", "remaining_time": "5:07:37"}
|
202 |
+
{"current_steps": 202, "total_steps": 380, "loss": 0.4982, "lr": 4.257029207653881e-05, "epoch": 2.628757108042242, "percentage": 53.16, "elapsed_time": "5:47:07", "remaining_time": "5:05:53"}
|
203 |
+
{"current_steps": 203, "total_steps": 380, "loss": 0.4971, "lr": 4.220351041423462e-05, "epoch": 2.6417546709991875, "percentage": 53.42, "elapsed_time": "5:48:50", "remaining_time": "5:04:09"}
|
204 |
+
{"current_steps": 204, "total_steps": 380, "loss": 0.5074, "lr": 4.183654281759888e-05, "epoch": 2.6547522339561334, "percentage": 53.68, "elapsed_time": "5:50:33", "remaining_time": "5:02:26"}
|
205 |
+
{"current_steps": 205, "total_steps": 380, "loss": 0.5012, "lr": 4.1469420251710905e-05, "epoch": 2.667749796913079, "percentage": 53.95, "elapsed_time": "5:52:16", "remaining_time": "5:00:43"}
|
206 |
+
{"current_steps": 206, "total_steps": 380, "loss": 0.5057, "lr": 4.110217369472649e-05, "epoch": 2.680747359870024, "percentage": 54.21, "elapsed_time": "5:54:00", "remaining_time": "4:59:00"}
|
207 |
+
{"current_steps": 207, "total_steps": 380, "loss": 0.4938, "lr": 4.07348341352639e-05, "epoch": 2.69374492282697, "percentage": 54.47, "elapsed_time": "5:55:44", "remaining_time": "4:57:18"}
|
208 |
+
{"current_steps": 208, "total_steps": 380, "loss": 0.4941, "lr": 4.0367432569789065e-05, "epoch": 2.7067424857839155, "percentage": 54.74, "elapsed_time": "5:57:28", "remaining_time": "4:55:36"}
|
209 |
+
{"current_steps": 209, "total_steps": 380, "loss": 0.4908, "lr": 4e-05, "epoch": 2.719740048740861, "percentage": 55.0, "elapsed_time": "5:59:11", "remaining_time": "4:53:52"}
|
210 |
+
{"current_steps": 210, "total_steps": 380, "loss": 0.4948, "lr": 3.963256743021095e-05, "epoch": 2.732737611697807, "percentage": 55.26, "elapsed_time": "6:00:55", "remaining_time": "4:52:10"}
|
211 |
+
{"current_steps": 211, "total_steps": 380, "loss": 0.4944, "lr": 3.92651658647361e-05, "epoch": 2.7457351746547523, "percentage": 55.53, "elapsed_time": "6:02:38", "remaining_time": "4:50:27"}
|
212 |
+
{"current_steps": 212, "total_steps": 380, "loss": 0.5017, "lr": 3.889782630527353e-05, "epoch": 2.7587327376116977, "percentage": 55.79, "elapsed_time": "6:04:22", "remaining_time": "4:48:45"}
|
213 |
+
{"current_steps": 213, "total_steps": 380, "loss": 0.5034, "lr": 3.853057974828911e-05, "epoch": 2.7717303005686436, "percentage": 56.05, "elapsed_time": "6:06:06", "remaining_time": "4:47:02"}
|
214 |
+
{"current_steps": 214, "total_steps": 380, "loss": 0.4975, "lr": 3.816345718240113e-05, "epoch": 2.784727863525589, "percentage": 56.32, "elapsed_time": "6:07:50", "remaining_time": "4:45:20"}
|
215 |
+
{"current_steps": 215, "total_steps": 380, "loss": 0.4978, "lr": 3.779648958576538e-05, "epoch": 2.7977254264825344, "percentage": 56.58, "elapsed_time": "6:09:33", "remaining_time": "4:43:37"}
|
216 |
+
{"current_steps": 216, "total_steps": 380, "loss": 0.501, "lr": 3.74297079234612e-05, "epoch": 2.81072298943948, "percentage": 56.84, "elapsed_time": "6:11:17", "remaining_time": "4:41:54"}
|
217 |
+
{"current_steps": 217, "total_steps": 380, "loss": 0.5033, "lr": 3.706314314487859e-05, "epoch": 2.8237205523964257, "percentage": 57.11, "elapsed_time": "6:13:02", "remaining_time": "4:40:12"}
|
218 |
+
{"current_steps": 218, "total_steps": 380, "loss": 0.497, "lr": 3.669682618110671e-05, "epoch": 2.836718115353371, "percentage": 57.37, "elapsed_time": "6:14:45", "remaining_time": "4:38:29"}
|
219 |
+
{"current_steps": 219, "total_steps": 380, "loss": 0.4976, "lr": 3.6330787942323855e-05, "epoch": 2.849715678310317, "percentage": 57.63, "elapsed_time": "6:16:28", "remaining_time": "4:36:45"}
|
220 |
+
{"current_steps": 220, "total_steps": 380, "loss": 0.5008, "lr": 3.5965059315189274e-05, "epoch": 2.8627132412672625, "percentage": 57.89, "elapsed_time": "6:18:09", "remaining_time": "4:35:01"}
|
221 |
+
{"current_steps": 221, "total_steps": 380, "loss": 0.5017, "lr": 3.559967116023683e-05, "epoch": 2.875710804224208, "percentage": 58.16, "elapsed_time": "6:19:51", "remaining_time": "4:33:17"}
|
222 |
+
{"current_steps": 222, "total_steps": 380, "loss": 0.4989, "lr": 3.523465430927106e-05, "epoch": 2.8887083671811533, "percentage": 58.42, "elapsed_time": "6:21:34", "remaining_time": "4:31:34"}
|
223 |
+
{"current_steps": 223, "total_steps": 380, "loss": 0.4982, "lr": 3.4870039562765475e-05, "epoch": 2.901705930138099, "percentage": 58.68, "elapsed_time": "6:23:17", "remaining_time": "4:29:51"}
|
224 |
+
{"current_steps": 224, "total_steps": 380, "loss": 0.4928, "lr": 3.4505857687263675e-05, "epoch": 2.9147034930950446, "percentage": 58.95, "elapsed_time": "6:25:00", "remaining_time": "4:28:07"}
|
225 |
+
{"current_steps": 225, "total_steps": 380, "loss": 0.5019, "lr": 3.414213941278314e-05, "epoch": 2.9277010560519905, "percentage": 59.21, "elapsed_time": "6:26:43", "remaining_time": "4:26:24"}
|
226 |
+
{"current_steps": 226, "total_steps": 380, "loss": 0.4969, "lr": 3.377891543022229e-05, "epoch": 2.940698619008936, "percentage": 59.47, "elapsed_time": "6:28:26", "remaining_time": "4:24:41"}
|
227 |
+
{"current_steps": 227, "total_steps": 380, "loss": 0.5033, "lr": 3.341621638877064e-05, "epoch": 2.9536961819658814, "percentage": 59.74, "elapsed_time": "6:30:07", "remaining_time": "4:22:57"}
|
228 |
+
{"current_steps": 228, "total_steps": 380, "loss": 0.4953, "lr": 3.305407289332279e-05, "epoch": 2.966693744922827, "percentage": 60.0, "elapsed_time": "6:31:50", "remaining_time": "4:21:13"}
|
229 |
+
{"current_steps": 229, "total_steps": 380, "loss": 0.4963, "lr": 3.269251550189573e-05, "epoch": 2.9796913078797727, "percentage": 60.26, "elapsed_time": "6:33:34", "remaining_time": "4:19:30"}
|
230 |
+
{"current_steps": 230, "total_steps": 380, "loss": 0.5049, "lr": 3.2331574723050474e-05, "epoch": 2.992688870836718, "percentage": 60.53, "elapsed_time": "6:35:17", "remaining_time": "4:17:47"}
|
231 |
+
{"current_steps": 231, "total_steps": 380, "loss": 0.4795, "lr": 3.197128101331764e-05, "epoch": 3.007311129163282, "percentage": 60.79, "elapsed_time": "6:38:41", "remaining_time": "4:17:10"}
|
232 |
+
{"current_steps": 232, "total_steps": 380, "loss": 0.454, "lr": 3.161166477462759e-05, "epoch": 3.0203086921202273, "percentage": 61.05, "elapsed_time": "6:40:22", "remaining_time": "4:15:24"}
|
233 |
+
{"current_steps": 233, "total_steps": 380, "loss": 0.4578, "lr": 3.125275635174497e-05, "epoch": 3.033306255077173, "percentage": 61.32, "elapsed_time": "6:42:03", "remaining_time": "4:13:39"}
|
234 |
+
{"current_steps": 234, "total_steps": 380, "loss": 0.4508, "lr": 3.089458602970828e-05, "epoch": 3.0463038180341186, "percentage": 61.58, "elapsed_time": "6:43:46", "remaining_time": "4:11:55"}
|
235 |
+
{"current_steps": 235, "total_steps": 380, "loss": 0.4538, "lr": 3.0537184031274306e-05, "epoch": 3.059301380991064, "percentage": 61.84, "elapsed_time": "6:45:27", "remaining_time": "4:10:10"}
|
236 |
+
{"current_steps": 236, "total_steps": 380, "loss": 0.4607, "lr": 3.0180580514368037e-05, "epoch": 3.07229894394801, "percentage": 62.11, "elapsed_time": "6:47:11", "remaining_time": "4:08:27"}
|
237 |
+
{"current_steps": 237, "total_steps": 380, "loss": 0.4503, "lr": 2.9824805569537747e-05, "epoch": 3.0852965069049554, "percentage": 62.37, "elapsed_time": "6:48:52", "remaining_time": "4:06:42"}
|
238 |
+
{"current_steps": 238, "total_steps": 380, "loss": 0.4566, "lr": 2.9469889217416045e-05, "epoch": 3.098294069861901, "percentage": 62.63, "elapsed_time": "6:50:33", "remaining_time": "4:04:57"}
|
239 |
+
{"current_steps": 239, "total_steps": 380, "loss": 0.455, "lr": 2.9115861406186593e-05, "epoch": 3.1112916328188467, "percentage": 62.89, "elapsed_time": "6:52:14", "remaining_time": "4:03:12"}
|
240 |
+
{"current_steps": 240, "total_steps": 380, "loss": 0.4548, "lr": 2.8762752009057232e-05, "epoch": 3.124289195775792, "percentage": 63.16, "elapsed_time": "6:53:54", "remaining_time": "4:01:26"}
|
241 |
+
{"current_steps": 241, "total_steps": 380, "loss": 0.4518, "lr": 2.841059082173902e-05, "epoch": 3.1372867587327375, "percentage": 63.42, "elapsed_time": "6:55:38", "remaining_time": "3:59:43"}
|