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 sha256:9547be591a2d337bb4e756b0ddae956b8db0ad422ac7c63aa908a5dd982e43d0
|
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 sha256:50598356b27d2b2eda58970d06cadb5fdf26b3042a4c8a5a8d7aa2208c223e70
|
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:efb0724feedb3c2753825ba62a9f2ea0ef1d64d5ea6cd297d89bff46c67495d4
|
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 sha256:00d6c2a0c6f9cfe5231e6831d6315a52d9e738f23a38581c212a11b5ef9362b7
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -165,3 +165,71 @@
|
|
165 |
{"current_steps": 165, "total_steps": 234, "loss": 0.8232, "lr": 2.43550361297047e-06, "epoch": 2.106382978723404, "percentage": 70.51, "elapsed_time": "0:40:42", "remaining_time": "0:17:01"}
|
166 |
{"current_steps": 166, "total_steps": 234, "loss": 0.6172, "lr": 2.371581150947476e-06, "epoch": 2.119148936170213, "percentage": 70.94, "elapsed_time": "0:40:56", "remaining_time": "0:16:46"}
|
167 |
{"current_steps": 167, "total_steps": 234, "loss": 0.7489, "lr": 2.3082469195465893e-06, "epoch": 2.1319148936170214, "percentage": 71.37, "elapsed_time": "0:41:12", "remaining_time": "0:16:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
165 |
{"current_steps": 165, "total_steps": 234, "loss": 0.8232, "lr": 2.43550361297047e-06, "epoch": 2.106382978723404, "percentage": 70.51, "elapsed_time": "0:40:42", "remaining_time": "0:17:01"}
|
166 |
{"current_steps": 166, "total_steps": 234, "loss": 0.6172, "lr": 2.371581150947476e-06, "epoch": 2.119148936170213, "percentage": 70.94, "elapsed_time": "0:40:56", "remaining_time": "0:16:46"}
|
167 |
{"current_steps": 167, "total_steps": 234, "loss": 0.7489, "lr": 2.3082469195465893e-06, "epoch": 2.1319148936170214, "percentage": 71.37, "elapsed_time": "0:41:12", "remaining_time": "0:16:32"}
|
168 |
+
{"current_steps": 168, "total_steps": 234, "loss": 0.6874, "lr": 2.245515092739488e-06, "epoch": 2.1446808510638298, "percentage": 71.79, "elapsed_time": "0:41:28", "remaining_time": "0:16:17"}
|
169 |
+
{"current_steps": 169, "total_steps": 234, "loss": 0.6266, "lr": 2.1833997096818897e-06, "epoch": 2.157446808510638, "percentage": 72.22, "elapsed_time": "0:41:40", "remaining_time": "0:16:01"}
|
170 |
+
{"current_steps": 170, "total_steps": 234, "loss": 0.6489, "lr": 2.1219146715716332e-06, "epoch": 2.1702127659574466, "percentage": 72.65, "elapsed_time": "0:41:53", "remaining_time": "0:15:46"}
|
171 |
+
{"current_steps": 171, "total_steps": 234, "loss": 0.763, "lr": 2.061073738537635e-06, "epoch": 2.1829787234042555, "percentage": 73.08, "elapsed_time": "0:42:04", "remaining_time": "0:15:29"}
|
172 |
+
{"current_steps": 172, "total_steps": 234, "loss": 0.6465, "lr": 2.0008905265604316e-06, "epoch": 2.195744680851064, "percentage": 73.5, "elapsed_time": "0:42:17", "remaining_time": "0:15:14"}
|
173 |
+
{"current_steps": 173, "total_steps": 234, "loss": 0.6834, "lr": 1.941378504424968e-06, "epoch": 2.2085106382978723, "percentage": 73.93, "elapsed_time": "0:42:31", "remaining_time": "0:14:59"}
|
174 |
+
{"current_steps": 174, "total_steps": 234, "loss": 0.7395, "lr": 1.8825509907063328e-06, "epoch": 2.2212765957446807, "percentage": 74.36, "elapsed_time": "0:42:46", "remaining_time": "0:14:44"}
|
175 |
+
{"current_steps": 175, "total_steps": 234, "loss": 0.7249, "lr": 1.8244211507891064e-06, "epoch": 2.2340425531914896, "percentage": 74.79, "elapsed_time": "0:43:02", "remaining_time": "0:14:30"}
|
176 |
+
{"current_steps": 176, "total_steps": 234, "loss": 0.7169, "lr": 1.7670019939210025e-06, "epoch": 2.246808510638298, "percentage": 75.21, "elapsed_time": "0:43:15", "remaining_time": "0:14:15"}
|
177 |
+
{"current_steps": 177, "total_steps": 234, "loss": 0.7966, "lr": 1.7103063703014372e-06, "epoch": 2.2595744680851064, "percentage": 75.64, "elapsed_time": "0:43:29", "remaining_time": "0:14:00"}
|
178 |
+
{"current_steps": 178, "total_steps": 234, "loss": 0.6413, "lr": 1.6543469682057105e-06, "epoch": 2.272340425531915, "percentage": 76.07, "elapsed_time": "0:43:42", "remaining_time": "0:13:45"}
|
179 |
+
{"current_steps": 179, "total_steps": 234, "loss": 0.6976, "lr": 1.5991363111454023e-06, "epoch": 2.2851063829787233, "percentage": 76.5, "elapsed_time": "0:43:57", "remaining_time": "0:13:30"}
|
180 |
+
{"current_steps": 180, "total_steps": 234, "loss": 0.6723, "lr": 1.544686755065677e-06, "epoch": 2.297872340425532, "percentage": 76.92, "elapsed_time": "0:44:12", "remaining_time": "0:13:15"}
|
181 |
+
{"current_steps": 181, "total_steps": 234, "loss": 0.7238, "lr": 1.4910104855800429e-06, "epoch": 2.3106382978723405, "percentage": 77.35, "elapsed_time": "0:44:28", "remaining_time": "0:13:01"}
|
182 |
+
{"current_steps": 182, "total_steps": 234, "loss": 0.7487, "lr": 1.438119515243277e-06, "epoch": 2.323404255319149, "percentage": 77.78, "elapsed_time": "0:44:43", "remaining_time": "0:12:46"}
|
183 |
+
{"current_steps": 183, "total_steps": 234, "loss": 0.6416, "lr": 1.3860256808630429e-06, "epoch": 2.3361702127659574, "percentage": 78.21, "elapsed_time": "0:44:59", "remaining_time": "0:12:32"}
|
184 |
+
{"current_steps": 184, "total_steps": 234, "loss": 0.7321, "lr": 1.3347406408508695e-06, "epoch": 2.348936170212766, "percentage": 78.63, "elapsed_time": "0:45:15", "remaining_time": "0:12:18"}
|
185 |
+
{"current_steps": 185, "total_steps": 234, "loss": 0.7622, "lr": 1.2842758726130283e-06, "epoch": 2.3617021276595747, "percentage": 79.06, "elapsed_time": "0:45:31", "remaining_time": "0:12:03"}
|
186 |
+
{"current_steps": 186, "total_steps": 234, "loss": 0.6713, "lr": 1.234642669981946e-06, "epoch": 2.374468085106383, "percentage": 79.49, "elapsed_time": "0:45:43", "remaining_time": "0:11:48"}
|
187 |
+
{"current_steps": 187, "total_steps": 234, "loss": 0.7533, "lr": 1.1858521406886674e-06, "epoch": 2.3872340425531915, "percentage": 79.91, "elapsed_time": "0:45:59", "remaining_time": "0:11:33"}
|
188 |
+
{"current_steps": 188, "total_steps": 234, "loss": 0.6469, "lr": 1.137915203877003e-06, "epoch": 2.4, "percentage": 80.34, "elapsed_time": "0:46:10", "remaining_time": "0:11:17"}
|
189 |
+
{"current_steps": 189, "total_steps": 234, "loss": 0.6918, "lr": 1.0908425876598512e-06, "epoch": 2.4127659574468083, "percentage": 80.77, "elapsed_time": "0:46:24", "remaining_time": "0:11:02"}
|
190 |
+
{"current_steps": 190, "total_steps": 234, "loss": 0.6792, "lr": 1.044644826718295e-06, "epoch": 2.425531914893617, "percentage": 81.2, "elapsed_time": "0:46:38", "remaining_time": "0:10:48"}
|
191 |
+
{"current_steps": 191, "total_steps": 234, "loss": 0.7389, "lr": 9.993322599439692e-07, "epoch": 2.4382978723404256, "percentage": 81.62, "elapsed_time": "0:46:50", "remaining_time": "0:10:32"}
|
192 |
+
{"current_steps": 192, "total_steps": 234, "loss": 0.6471, "lr": 9.549150281252633e-07, "epoch": 2.451063829787234, "percentage": 82.05, "elapsed_time": "0:47:01", "remaining_time": "0:10:17"}
|
193 |
+
{"current_steps": 193, "total_steps": 234, "loss": 0.7413, "lr": 9.114030716778433e-07, "epoch": 2.4638297872340424, "percentage": 82.48, "elapsed_time": "0:47:14", "remaining_time": "0:10:02"}
|
194 |
+
{"current_steps": 194, "total_steps": 234, "loss": 0.6261, "lr": 8.688061284200266e-07, "epoch": 2.476595744680851, "percentage": 82.91, "elapsed_time": "0:47:30", "remaining_time": "0:09:47"}
|
195 |
+
{"current_steps": 195, "total_steps": 234, "loss": 0.6867, "lr": 8.271337313934869e-07, "epoch": 2.4893617021276597, "percentage": 83.33, "elapsed_time": "0:47:41", "remaining_time": "0:09:32"}
|
196 |
+
{"current_steps": 196, "total_steps": 234, "loss": 0.7692, "lr": 7.863952067298042e-07, "epoch": 2.502127659574468, "percentage": 83.76, "elapsed_time": "0:47:55", "remaining_time": "0:09:17"}
|
197 |
+
{"current_steps": 197, "total_steps": 234, "loss": 0.6737, "lr": 7.465996715633028e-07, "epoch": 2.5148936170212766, "percentage": 84.19, "elapsed_time": "0:48:11", "remaining_time": "0:09:03"}
|
198 |
+
{"current_steps": 198, "total_steps": 234, "loss": 0.7463, "lr": 7.077560319906696e-07, "epoch": 2.527659574468085, "percentage": 84.62, "elapsed_time": "0:48:26", "remaining_time": "0:08:48"}
|
199 |
+
{"current_steps": 199, "total_steps": 234, "loss": 0.7835, "lr": 6.698729810778065e-07, "epoch": 2.5404255319148934, "percentage": 85.04, "elapsed_time": "0:48:41", "remaining_time": "0:08:33"}
|
200 |
+
{"current_steps": 200, "total_steps": 234, "loss": 0.7075, "lr": 6.329589969143518e-07, "epoch": 2.5531914893617023, "percentage": 85.47, "elapsed_time": "0:48:54", "remaining_time": "0:08:18"}
|
201 |
+
{"current_steps": 201, "total_steps": 234, "loss": 0.7195, "lr": 5.9702234071631e-07, "epoch": 2.5659574468085107, "percentage": 85.9, "elapsed_time": "0:49:06", "remaining_time": "0:08:03"}
|
202 |
+
{"current_steps": 202, "total_steps": 234, "loss": 0.6318, "lr": 5.620710549772295e-07, "epoch": 2.578723404255319, "percentage": 86.32, "elapsed_time": "0:49:20", "remaining_time": "0:07:49"}
|
203 |
+
{"current_steps": 203, "total_steps": 234, "loss": 0.7642, "lr": 5.281129616683167e-07, "epoch": 2.5914893617021275, "percentage": 86.75, "elapsed_time": "0:49:37", "remaining_time": "0:07:34"}
|
204 |
+
{"current_steps": 204, "total_steps": 234, "loss": 0.7023, "lr": 4.951556604879049e-07, "epoch": 2.604255319148936, "percentage": 87.18, "elapsed_time": "0:49:51", "remaining_time": "0:07:19"}
|
205 |
+
{"current_steps": 205, "total_steps": 234, "loss": 0.7142, "lr": 4.632065271606756e-07, "epoch": 2.617021276595745, "percentage": 87.61, "elapsed_time": "0:50:06", "remaining_time": "0:07:05"}
|
206 |
+
{"current_steps": 206, "total_steps": 234, "loss": 0.6562, "lr": 4.322727117869951e-07, "epoch": 2.629787234042553, "percentage": 88.03, "elapsed_time": "0:50:19", "remaining_time": "0:06:50"}
|
207 |
+
{"current_steps": 207, "total_steps": 234, "loss": 0.7008, "lr": 4.0236113724274716e-07, "epoch": 2.6425531914893616, "percentage": 88.46, "elapsed_time": "0:50:31", "remaining_time": "0:06:35"}
|
208 |
+
{"current_steps": 208, "total_steps": 234, "loss": 0.7654, "lr": 3.734784976300165e-07, "epoch": 2.65531914893617, "percentage": 88.89, "elapsed_time": "0:50:47", "remaining_time": "0:06:20"}
|
209 |
+
{"current_steps": 209, "total_steps": 234, "loss": 0.6106, "lr": 3.4563125677897936e-07, "epoch": 2.6680851063829785, "percentage": 89.32, "elapsed_time": "0:51:00", "remaining_time": "0:06:06"}
|
210 |
+
{"current_steps": 210, "total_steps": 234, "loss": 0.8295, "lr": 3.18825646801314e-07, "epoch": 2.6808510638297873, "percentage": 89.74, "elapsed_time": "0:51:11", "remaining_time": "0:05:51"}
|
211 |
+
{"current_steps": 211, "total_steps": 234, "loss": 0.6481, "lr": 2.930676666954846e-07, "epoch": 2.6936170212765957, "percentage": 90.17, "elapsed_time": "0:51:27", "remaining_time": "0:05:36"}
|
212 |
+
{"current_steps": 212, "total_steps": 234, "loss": 0.642, "lr": 2.6836308100417874e-07, "epoch": 2.706382978723404, "percentage": 90.6, "elapsed_time": "0:51:39", "remaining_time": "0:05:21"}
|
213 |
+
{"current_steps": 213, "total_steps": 234, "loss": 0.7463, "lr": 2.447174185242324e-07, "epoch": 2.719148936170213, "percentage": 91.03, "elapsed_time": "0:51:52", "remaining_time": "0:05:06"}
|
214 |
+
{"current_steps": 214, "total_steps": 234, "loss": 0.6347, "lr": 2.2213597106929608e-07, "epoch": 2.731914893617021, "percentage": 91.45, "elapsed_time": "0:52:06", "remaining_time": "0:04:52"}
|
215 |
+
{"current_steps": 215, "total_steps": 234, "loss": 0.8141, "lr": 2.006237922855553e-07, "epoch": 2.74468085106383, "percentage": 91.88, "elapsed_time": "0:52:21", "remaining_time": "0:04:37"}
|
216 |
+
{"current_steps": 216, "total_steps": 234, "loss": 0.6098, "lr": 1.801856965207338e-07, "epoch": 2.7574468085106383, "percentage": 92.31, "elapsed_time": "0:52:32", "remaining_time": "0:04:22"}
|
217 |
+
{"current_steps": 217, "total_steps": 234, "loss": 0.7974, "lr": 1.6082625774666793e-07, "epoch": 2.7702127659574467, "percentage": 92.74, "elapsed_time": "0:52:47", "remaining_time": "0:04:08"}
|
218 |
+
{"current_steps": 218, "total_steps": 234, "loss": 0.6051, "lr": 1.4254980853566248e-07, "epoch": 2.7829787234042556, "percentage": 93.16, "elapsed_time": "0:53:00", "remaining_time": "0:03:53"}
|
219 |
+
{"current_steps": 219, "total_steps": 234, "loss": 0.7594, "lr": 1.253604390908819e-07, "epoch": 2.795744680851064, "percentage": 93.59, "elapsed_time": "0:53:17", "remaining_time": "0:03:38"}
|
220 |
+
{"current_steps": 220, "total_steps": 234, "loss": 0.6206, "lr": 1.0926199633097156e-07, "epoch": 2.8085106382978724, "percentage": 94.02, "elapsed_time": "0:53:29", "remaining_time": "0:03:24"}
|
221 |
+
{"current_steps": 221, "total_steps": 234, "loss": 0.8591, "lr": 9.42580830291373e-08, "epoch": 2.821276595744681, "percentage": 94.44, "elapsed_time": "0:53:42", "remaining_time": "0:03:09"}
|
222 |
+
{"current_steps": 222, "total_steps": 234, "loss": 0.6012, "lr": 8.035205700685167e-08, "epoch": 2.8340425531914892, "percentage": 94.87, "elapsed_time": "0:53:59", "remaining_time": "0:02:55"}
|
223 |
+
{"current_steps": 223, "total_steps": 234, "loss": 0.6869, "lr": 6.75470303823933e-08, "epoch": 2.846808510638298, "percentage": 95.3, "elapsed_time": "0:54:12", "remaining_time": "0:02:40"}
|
224 |
+
{"current_steps": 224, "total_steps": 234, "loss": 0.6985, "lr": 5.584586887435739e-08, "epoch": 2.8595744680851065, "percentage": 95.73, "elapsed_time": "0:54:23", "remaining_time": "0:02:25"}
|
225 |
+
{"current_steps": 225, "total_steps": 234, "loss": 0.7723, "lr": 4.52511911603265e-08, "epoch": 2.872340425531915, "percentage": 96.15, "elapsed_time": "0:54:38", "remaining_time": "0:02:11"}
|
226 |
+
{"current_steps": 226, "total_steps": 234, "loss": 0.6751, "lr": 3.576536829081323e-08, "epoch": 2.8851063829787233, "percentage": 96.58, "elapsed_time": "0:54:49", "remaining_time": "0:01:56"}
|
227 |
+
{"current_steps": 227, "total_steps": 234, "loss": 0.6796, "lr": 2.7390523158633552e-08, "epoch": 2.8978723404255318, "percentage": 97.01, "elapsed_time": "0:55:02", "remaining_time": "0:01:41"}
|
228 |
+
{"current_steps": 228, "total_steps": 234, "loss": 0.7351, "lr": 2.012853002380466e-08, "epoch": 2.9106382978723406, "percentage": 97.44, "elapsed_time": "0:55:14", "remaining_time": "0:01:27"}
|
229 |
+
{"current_steps": 229, "total_steps": 234, "loss": 0.6504, "lr": 1.3981014094099354e-08, "epoch": 2.923404255319149, "percentage": 97.86, "elapsed_time": "0:55:27", "remaining_time": "0:01:12"}
|
230 |
+
{"current_steps": 230, "total_steps": 234, "loss": 0.6921, "lr": 8.949351161324227e-09, "epoch": 2.9361702127659575, "percentage": 98.29, "elapsed_time": "0:55:44", "remaining_time": "0:00:58"}
|
231 |
+
{"current_steps": 231, "total_steps": 234, "loss": 0.7357, "lr": 5.034667293427053e-09, "epoch": 2.948936170212766, "percentage": 98.72, "elapsed_time": "0:56:00", "remaining_time": "0:00:43"}
|
232 |
+
{"current_steps": 232, "total_steps": 234, "loss": 0.6568, "lr": 2.237838582483387e-09, "epoch": 2.9617021276595743, "percentage": 99.15, "elapsed_time": "0:56:15", "remaining_time": "0:00:29"}
|
233 |
+
{"current_steps": 233, "total_steps": 234, "loss": 0.6961, "lr": 5.594909486328348e-10, "epoch": 2.974468085106383, "percentage": 99.57, "elapsed_time": "0:56:26", "remaining_time": "0:00:14"}
|
234 |
+
{"current_steps": 234, "total_steps": 234, "loss": 0.6174, "lr": 0.0, "epoch": 2.9872340425531916, "percentage": 100.0, "elapsed_time": "0:56:37", "remaining_time": "0:00:00"}
|
235 |
+
{"current_steps": 234, "total_steps": 234, "epoch": 2.9872340425531916, "percentage": 100.0, "elapsed_time": "0:58:46", "remaining_time": "0:00:00"}
|