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:abf805490768585f25a30bf8705f244d4ea2c8457266e1cc2b6be064836564bf
|
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 sha256:070a2c85bd9ff401c279e1aaf53a0ffa36001741ba5058afe221502e8a7e54a2
|
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 sha256:742f8a117e2b90cc39463a8bf06285bbed7ede73acfa14e36799da8dd590ef2e
|
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:e570a4c034ba256c39ed7a09a57631cdc6c03c18c6480c36f1d164f689883ad0
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -157,3 +157,79 @@
|
|
157 |
{"current_steps": 157, "total_steps": 234, "loss": 1.2703, "lr": 2.966316784621e-06, "epoch": 2.008528784648188, "percentage": 67.09, "elapsed_time": "1:41:43", "remaining_time": "0:49:53"}
|
158 |
{"current_steps": 158, "total_steps": 234, "loss": 0.7064, "lr": 2.8982138584521734e-06, "epoch": 2.021321961620469, "percentage": 67.52, "elapsed_time": "1:42:21", "remaining_time": "0:49:14"}
|
159 |
{"current_steps": 159, "total_steps": 234, "loss": 0.7061, "lr": 2.83058130441221e-06, "epoch": 2.0341151385927505, "percentage": 67.95, "elapsed_time": "1:43:01", "remaining_time": "0:48:35"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
{"current_steps": 157, "total_steps": 234, "loss": 1.2703, "lr": 2.966316784621e-06, "epoch": 2.008528784648188, "percentage": 67.09, "elapsed_time": "1:41:43", "remaining_time": "0:49:53"}
|
158 |
{"current_steps": 158, "total_steps": 234, "loss": 0.7064, "lr": 2.8982138584521734e-06, "epoch": 2.021321961620469, "percentage": 67.52, "elapsed_time": "1:42:21", "remaining_time": "0:49:14"}
|
159 |
{"current_steps": 159, "total_steps": 234, "loss": 0.7061, "lr": 2.83058130441221e-06, "epoch": 2.0341151385927505, "percentage": 67.95, "elapsed_time": "1:43:01", "remaining_time": "0:48:35"}
|
160 |
+
{"current_steps": 160, "total_steps": 234, "loss": 0.7014, "lr": 2.7634342584218364e-06, "epoch": 2.046908315565032, "percentage": 68.38, "elapsed_time": "1:43:37", "remaining_time": "0:47:55"}
|
161 |
+
{"current_steps": 161, "total_steps": 234, "loss": 0.6972, "lr": 2.6967877477468394e-06, "epoch": 2.0597014925373136, "percentage": 68.8, "elapsed_time": "1:44:14", "remaining_time": "0:47:15"}
|
162 |
+
{"current_steps": 162, "total_steps": 234, "loss": 0.6418, "lr": 2.6306566876350072e-06, "epoch": 2.0724946695095947, "percentage": 69.23, "elapsed_time": "1:44:52", "remaining_time": "0:46:36"}
|
163 |
+
{"current_steps": 163, "total_steps": 234, "loss": 0.7516, "lr": 2.5650558779781635e-06, "epoch": 2.0852878464818763, "percentage": 69.66, "elapsed_time": "1:45:31", "remaining_time": "0:45:57"}
|
164 |
+
{"current_steps": 164, "total_steps": 234, "loss": 0.7129, "lr": 2.5000000000000015e-06, "epoch": 2.098081023454158, "percentage": 70.09, "elapsed_time": "1:46:09", "remaining_time": "0:45:18"}
|
165 |
+
{"current_steps": 165, "total_steps": 234, "loss": 0.7031, "lr": 2.43550361297047e-06, "epoch": 2.1108742004264394, "percentage": 70.51, "elapsed_time": "1:46:48", "remaining_time": "0:44:40"}
|
166 |
+
{"current_steps": 166, "total_steps": 234, "loss": 0.7059, "lr": 2.371581150947476e-06, "epoch": 2.1236673773987205, "percentage": 70.94, "elapsed_time": "1:47:24", "remaining_time": "0:43:59"}
|
167 |
+
{"current_steps": 167, "total_steps": 234, "loss": 0.6921, "lr": 2.3082469195465893e-06, "epoch": 2.136460554371002, "percentage": 71.37, "elapsed_time": "1:48:02", "remaining_time": "0:43:20"}
|
168 |
+
{"current_steps": 168, "total_steps": 234, "loss": 0.6459, "lr": 2.245515092739488e-06, "epoch": 2.1492537313432836, "percentage": 71.79, "elapsed_time": "1:48:34", "remaining_time": "0:42:39"}
|
169 |
+
{"current_steps": 169, "total_steps": 234, "loss": 0.6815, "lr": 2.1833997096818897e-06, "epoch": 2.162046908315565, "percentage": 72.22, "elapsed_time": "1:49:13", "remaining_time": "0:42:00"}
|
170 |
+
{"current_steps": 170, "total_steps": 234, "loss": 0.6917, "lr": 2.1219146715716332e-06, "epoch": 2.1748400852878467, "percentage": 72.65, "elapsed_time": "1:49:56", "remaining_time": "0:41:23"}
|
171 |
+
{"current_steps": 171, "total_steps": 234, "loss": 0.6415, "lr": 2.061073738537635e-06, "epoch": 2.1876332622601278, "percentage": 73.08, "elapsed_time": "1:50:35", "remaining_time": "0:40:44"}
|
172 |
+
{"current_steps": 172, "total_steps": 234, "loss": 0.6476, "lr": 2.0008905265604316e-06, "epoch": 2.2004264392324093, "percentage": 73.5, "elapsed_time": "1:51:12", "remaining_time": "0:40:05"}
|
173 |
+
{"current_steps": 173, "total_steps": 234, "loss": 0.8098, "lr": 1.941378504424968e-06, "epoch": 2.213219616204691, "percentage": 73.93, "elapsed_time": "1:51:52", "remaining_time": "0:39:26"}
|
174 |
+
{"current_steps": 174, "total_steps": 234, "loss": 0.6996, "lr": 1.8825509907063328e-06, "epoch": 2.2260127931769724, "percentage": 74.36, "elapsed_time": "1:52:31", "remaining_time": "0:38:48"}
|
175 |
+
{"current_steps": 175, "total_steps": 234, "loss": 0.6946, "lr": 1.8244211507891064e-06, "epoch": 2.2388059701492535, "percentage": 74.79, "elapsed_time": "1:53:09", "remaining_time": "0:38:09"}
|
176 |
+
{"current_steps": 176, "total_steps": 234, "loss": 0.7051, "lr": 1.7670019939210025e-06, "epoch": 2.251599147121535, "percentage": 75.21, "elapsed_time": "1:53:47", "remaining_time": "0:37:29"}
|
177 |
+
{"current_steps": 177, "total_steps": 234, "loss": 0.6582, "lr": 1.7103063703014372e-06, "epoch": 2.2643923240938166, "percentage": 75.64, "elapsed_time": "1:54:25", "remaining_time": "0:36:50"}
|
178 |
+
{"current_steps": 178, "total_steps": 234, "loss": 0.6591, "lr": 1.6543469682057105e-06, "epoch": 2.277185501066098, "percentage": 76.07, "elapsed_time": "1:55:04", "remaining_time": "0:36:12"}
|
179 |
+
{"current_steps": 179, "total_steps": 234, "loss": 0.6544, "lr": 1.5991363111454023e-06, "epoch": 2.2899786780383797, "percentage": 76.5, "elapsed_time": "1:55:37", "remaining_time": "0:35:31"}
|
180 |
+
{"current_steps": 180, "total_steps": 234, "loss": 0.6695, "lr": 1.544686755065677e-06, "epoch": 2.302771855010661, "percentage": 76.92, "elapsed_time": "1:56:16", "remaining_time": "0:34:53"}
|
181 |
+
{"current_steps": 181, "total_steps": 234, "loss": 0.6983, "lr": 1.4910104855800429e-06, "epoch": 2.3155650319829424, "percentage": 77.35, "elapsed_time": "1:56:58", "remaining_time": "0:34:15"}
|
182 |
+
{"current_steps": 182, "total_steps": 234, "loss": 0.6253, "lr": 1.438119515243277e-06, "epoch": 2.328358208955224, "percentage": 77.78, "elapsed_time": "1:57:33", "remaining_time": "0:33:35"}
|
183 |
+
{"current_steps": 183, "total_steps": 234, "loss": 0.6788, "lr": 1.3860256808630429e-06, "epoch": 2.3411513859275055, "percentage": 78.21, "elapsed_time": "1:58:07", "remaining_time": "0:32:55"}
|
184 |
+
{"current_steps": 184, "total_steps": 234, "loss": 0.7431, "lr": 1.3347406408508695e-06, "epoch": 2.3539445628997866, "percentage": 78.63, "elapsed_time": "1:58:50", "remaining_time": "0:32:17"}
|
185 |
+
{"current_steps": 185, "total_steps": 234, "loss": 0.6587, "lr": 1.2842758726130283e-06, "epoch": 2.366737739872068, "percentage": 79.06, "elapsed_time": "1:59:28", "remaining_time": "0:31:38"}
|
186 |
+
{"current_steps": 186, "total_steps": 234, "loss": 0.7, "lr": 1.234642669981946e-06, "epoch": 2.3795309168443497, "percentage": 79.49, "elapsed_time": "2:00:07", "remaining_time": "0:31:00"}
|
187 |
+
{"current_steps": 187, "total_steps": 234, "loss": 0.7007, "lr": 1.1858521406886674e-06, "epoch": 2.3923240938166312, "percentage": 79.91, "elapsed_time": "2:00:45", "remaining_time": "0:30:21"}
|
188 |
+
{"current_steps": 188, "total_steps": 234, "loss": 0.7469, "lr": 1.137915203877003e-06, "epoch": 2.405117270788913, "percentage": 80.34, "elapsed_time": "2:01:22", "remaining_time": "0:29:41"}
|
189 |
+
{"current_steps": 189, "total_steps": 234, "loss": 0.6608, "lr": 1.0908425876598512e-06, "epoch": 2.417910447761194, "percentage": 80.77, "elapsed_time": "2:01:58", "remaining_time": "0:29:02"}
|
190 |
+
{"current_steps": 190, "total_steps": 234, "loss": 0.7566, "lr": 1.044644826718295e-06, "epoch": 2.4307036247334755, "percentage": 81.2, "elapsed_time": "2:02:37", "remaining_time": "0:28:23"}
|
191 |
+
{"current_steps": 191, "total_steps": 234, "loss": 0.6596, "lr": 9.993322599439692e-07, "epoch": 2.443496801705757, "percentage": 81.62, "elapsed_time": "2:03:13", "remaining_time": "0:27:44"}
|
192 |
+
{"current_steps": 192, "total_steps": 234, "loss": 0.7325, "lr": 9.549150281252633e-07, "epoch": 2.4562899786780386, "percentage": 82.05, "elapsed_time": "2:03:50", "remaining_time": "0:27:05"}
|
193 |
+
{"current_steps": 193, "total_steps": 234, "loss": 0.6592, "lr": 9.114030716778433e-07, "epoch": 2.4690831556503197, "percentage": 82.48, "elapsed_time": "2:04:29", "remaining_time": "0:26:26"}
|
194 |
+
{"current_steps": 194, "total_steps": 234, "loss": 0.7221, "lr": 8.688061284200266e-07, "epoch": 2.481876332622601, "percentage": 82.91, "elapsed_time": "2:05:05", "remaining_time": "0:25:47"}
|
195 |
+
{"current_steps": 195, "total_steps": 234, "loss": 0.6698, "lr": 8.271337313934869e-07, "epoch": 2.4946695095948828, "percentage": 83.33, "elapsed_time": "2:05:45", "remaining_time": "0:25:09"}
|
196 |
+
{"current_steps": 196, "total_steps": 234, "loss": 0.691, "lr": 7.863952067298042e-07, "epoch": 2.5074626865671643, "percentage": 83.76, "elapsed_time": "2:06:27", "remaining_time": "0:24:30"}
|
197 |
+
{"current_steps": 197, "total_steps": 234, "loss": 0.7766, "lr": 7.465996715633028e-07, "epoch": 2.520255863539446, "percentage": 84.19, "elapsed_time": "2:07:07", "remaining_time": "0:23:52"}
|
198 |
+
{"current_steps": 198, "total_steps": 234, "loss": 0.7563, "lr": 7.077560319906696e-07, "epoch": 2.533049040511727, "percentage": 84.62, "elapsed_time": "2:07:45", "remaining_time": "0:23:13"}
|
199 |
+
{"current_steps": 199, "total_steps": 234, "loss": 0.7013, "lr": 6.698729810778065e-07, "epoch": 2.5458422174840085, "percentage": 85.04, "elapsed_time": "2:08:22", "remaining_time": "0:22:34"}
|
200 |
+
{"current_steps": 200, "total_steps": 234, "loss": 0.6536, "lr": 6.329589969143518e-07, "epoch": 2.55863539445629, "percentage": 85.47, "elapsed_time": "2:08:59", "remaining_time": "0:21:55"}
|
201 |
+
{"current_steps": 201, "total_steps": 234, "loss": 0.7274, "lr": 5.9702234071631e-07, "epoch": 2.571428571428571, "percentage": 85.9, "elapsed_time": "2:09:41", "remaining_time": "0:21:17"}
|
202 |
+
{"current_steps": 202, "total_steps": 234, "loss": 0.6523, "lr": 5.620710549772295e-07, "epoch": 2.5842217484008527, "percentage": 86.32, "elapsed_time": "2:10:18", "remaining_time": "0:20:38"}
|
203 |
+
{"current_steps": 203, "total_steps": 234, "loss": 0.7254, "lr": 5.281129616683167e-07, "epoch": 2.5970149253731343, "percentage": 86.75, "elapsed_time": "2:10:58", "remaining_time": "0:20:00"}
|
204 |
+
{"current_steps": 204, "total_steps": 234, "loss": 0.6832, "lr": 4.951556604879049e-07, "epoch": 2.609808102345416, "percentage": 87.18, "elapsed_time": "2:11:37", "remaining_time": "0:19:21"}
|
205 |
+
{"current_steps": 205, "total_steps": 234, "loss": 0.7226, "lr": 4.632065271606756e-07, "epoch": 2.6226012793176974, "percentage": 87.61, "elapsed_time": "2:12:13", "remaining_time": "0:18:42"}
|
206 |
+
{"current_steps": 206, "total_steps": 234, "loss": 0.6507, "lr": 4.322727117869951e-07, "epoch": 2.635394456289979, "percentage": 88.03, "elapsed_time": "2:12:55", "remaining_time": "0:18:04"}
|
207 |
+
{"current_steps": 207, "total_steps": 234, "loss": 0.6371, "lr": 4.0236113724274716e-07, "epoch": 2.64818763326226, "percentage": 88.46, "elapsed_time": "2:13:33", "remaining_time": "0:17:25"}
|
208 |
+
{"current_steps": 208, "total_steps": 234, "loss": 0.7792, "lr": 3.734784976300165e-07, "epoch": 2.6609808102345416, "percentage": 88.89, "elapsed_time": "2:14:16", "remaining_time": "0:16:47"}
|
209 |
+
{"current_steps": 209, "total_steps": 234, "loss": 0.5887, "lr": 3.4563125677897936e-07, "epoch": 2.673773987206823, "percentage": 89.32, "elapsed_time": "2:14:46", "remaining_time": "0:16:07"}
|
210 |
+
{"current_steps": 210, "total_steps": 234, "loss": 0.6793, "lr": 3.18825646801314e-07, "epoch": 2.6865671641791042, "percentage": 89.74, "elapsed_time": "2:15:23", "remaining_time": "0:15:28"}
|
211 |
+
{"current_steps": 211, "total_steps": 234, "loss": 0.6553, "lr": 2.930676666954846e-07, "epoch": 2.699360341151386, "percentage": 90.17, "elapsed_time": "2:16:00", "remaining_time": "0:14:49"}
|
212 |
+
{"current_steps": 212, "total_steps": 234, "loss": 0.7101, "lr": 2.6836308100417874e-07, "epoch": 2.7121535181236673, "percentage": 90.6, "elapsed_time": "2:16:41", "remaining_time": "0:14:11"}
|
213 |
+
{"current_steps": 213, "total_steps": 234, "loss": 0.7189, "lr": 2.447174185242324e-07, "epoch": 2.724946695095949, "percentage": 91.03, "elapsed_time": "2:17:18", "remaining_time": "0:13:32"}
|
214 |
+
{"current_steps": 214, "total_steps": 234, "loss": 0.6076, "lr": 2.2213597106929608e-07, "epoch": 2.7377398720682304, "percentage": 91.45, "elapsed_time": "2:17:55", "remaining_time": "0:12:53"}
|
215 |
+
{"current_steps": 215, "total_steps": 234, "loss": 0.7334, "lr": 2.006237922855553e-07, "epoch": 2.750533049040512, "percentage": 91.88, "elapsed_time": "2:18:35", "remaining_time": "0:12:14"}
|
216 |
+
{"current_steps": 216, "total_steps": 234, "loss": 0.7144, "lr": 1.801856965207338e-07, "epoch": 2.763326226012793, "percentage": 92.31, "elapsed_time": "2:19:12", "remaining_time": "0:11:36"}
|
217 |
+
{"current_steps": 217, "total_steps": 234, "loss": 0.6139, "lr": 1.6082625774666793e-07, "epoch": 2.7761194029850746, "percentage": 92.74, "elapsed_time": "2:19:47", "remaining_time": "0:10:57"}
|
218 |
+
{"current_steps": 218, "total_steps": 234, "loss": 0.7111, "lr": 1.4254980853566248e-07, "epoch": 2.788912579957356, "percentage": 93.16, "elapsed_time": "2:20:24", "remaining_time": "0:10:18"}
|
219 |
+
{"current_steps": 219, "total_steps": 234, "loss": 0.6719, "lr": 1.253604390908819e-07, "epoch": 2.8017057569296373, "percentage": 93.59, "elapsed_time": "2:21:04", "remaining_time": "0:09:39"}
|
220 |
+
{"current_steps": 220, "total_steps": 234, "loss": 0.7834, "lr": 1.0926199633097156e-07, "epoch": 2.814498933901919, "percentage": 94.02, "elapsed_time": "2:21:45", "remaining_time": "0:09:01"}
|
221 |
+
{"current_steps": 221, "total_steps": 234, "loss": 0.6486, "lr": 9.42580830291373e-08, "epoch": 2.8272921108742004, "percentage": 94.44, "elapsed_time": "2:22:26", "remaining_time": "0:08:22"}
|
222 |
+
{"current_steps": 222, "total_steps": 234, "loss": 0.6523, "lr": 8.035205700685167e-08, "epoch": 2.840085287846482, "percentage": 94.87, "elapsed_time": "2:23:00", "remaining_time": "0:07:43"}
|
223 |
+
{"current_steps": 223, "total_steps": 234, "loss": 0.708, "lr": 6.75470303823933e-08, "epoch": 2.8528784648187635, "percentage": 95.3, "elapsed_time": "2:23:39", "remaining_time": "0:07:05"}
|
224 |
+
{"current_steps": 224, "total_steps": 234, "loss": 0.7025, "lr": 5.584586887435739e-08, "epoch": 2.8656716417910446, "percentage": 95.73, "elapsed_time": "2:24:17", "remaining_time": "0:06:26"}
|
225 |
+
{"current_steps": 225, "total_steps": 234, "loss": 0.7003, "lr": 4.52511911603265e-08, "epoch": 2.878464818763326, "percentage": 96.15, "elapsed_time": "2:24:52", "remaining_time": "0:05:47"}
|
226 |
+
{"current_steps": 226, "total_steps": 234, "loss": 0.7252, "lr": 3.576536829081323e-08, "epoch": 2.8912579957356077, "percentage": 96.58, "elapsed_time": "2:25:32", "remaining_time": "0:05:09"}
|
227 |
+
{"current_steps": 227, "total_steps": 234, "loss": 0.7079, "lr": 2.7390523158633552e-08, "epoch": 2.9040511727078893, "percentage": 97.01, "elapsed_time": "2:26:10", "remaining_time": "0:04:30"}
|
228 |
+
{"current_steps": 228, "total_steps": 234, "loss": 0.6701, "lr": 2.012853002380466e-08, "epoch": 2.9168443496801704, "percentage": 97.44, "elapsed_time": "2:26:44", "remaining_time": "0:03:51"}
|
229 |
+
{"current_steps": 229, "total_steps": 234, "loss": 0.6388, "lr": 1.3981014094099354e-08, "epoch": 2.929637526652452, "percentage": 97.86, "elapsed_time": "2:27:27", "remaining_time": "0:03:13"}
|
230 |
+
{"current_steps": 230, "total_steps": 234, "loss": 0.7613, "lr": 8.949351161324227e-09, "epoch": 2.9424307036247335, "percentage": 98.29, "elapsed_time": "2:28:05", "remaining_time": "0:02:34"}
|
231 |
+
{"current_steps": 231, "total_steps": 234, "loss": 0.6471, "lr": 5.034667293427053e-09, "epoch": 2.955223880597015, "percentage": 98.72, "elapsed_time": "2:28:41", "remaining_time": "0:01:55"}
|
232 |
+
{"current_steps": 232, "total_steps": 234, "loss": 0.7412, "lr": 2.237838582483387e-09, "epoch": 2.9680170575692966, "percentage": 99.15, "elapsed_time": "2:29:19", "remaining_time": "0:01:17"}
|
233 |
+
{"current_steps": 233, "total_steps": 234, "loss": 0.6572, "lr": 5.594909486328348e-10, "epoch": 2.9808102345415777, "percentage": 99.57, "elapsed_time": "2:29:58", "remaining_time": "0:00:38"}
|
234 |
+
{"current_steps": 234, "total_steps": 234, "loss": 0.7006, "lr": 0.0, "epoch": 2.9936034115138592, "percentage": 100.0, "elapsed_time": "2:30:37", "remaining_time": "0:00:00"}
|
235 |
+
{"current_steps": 234, "total_steps": 234, "epoch": 2.9936034115138592, "percentage": 100.0, "elapsed_time": "2:32:24", "remaining_time": "0:00:00"}
|