Training in progress, epoch 3
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:c4c4563a40cf3188259e755b71e2015e0c86e38514b56e9ef1ae980c263f6f7d
|
| 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 sha256:4bcf1394601ce44846f521f823d9ec756d670f3333c3c202f57e1f7bd1ddbf43
|
| 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:f270e8abb93ae60cf2dd7097c595c212b1be6b4d69707a73b58ff5d82889030d
|
| 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 sha256:4edad43b4912e125f512b78fdd127ceeffb87131d0d20d4c1cee839715910ec5
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -149,3 +149,75 @@
|
|
| 149 |
{"current_steps": 149, "total_steps": 222, "loss": 0.7376, "lr": 2.968720740881056e-06, "epoch": 2.0135135135135136, "percentage": 67.12, "elapsed_time": "1:16:45", "remaining_time": "0:37:36"}
|
| 150 |
{"current_steps": 150, "total_steps": 222, "loss": 0.6356, "lr": 2.8968497269310803e-06, "epoch": 2.027027027027027, "percentage": 67.57, "elapsed_time": "1:17:16", "remaining_time": "0:37:05"}
|
| 151 |
{"current_steps": 151, "total_steps": 222, "loss": 0.6941, "lr": 2.825502862121036e-06, "epoch": 2.0405405405405403, "percentage": 68.02, "elapsed_time": "1:17:42", "remaining_time": "0:36:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 149 |
{"current_steps": 149, "total_steps": 222, "loss": 0.7376, "lr": 2.968720740881056e-06, "epoch": 2.0135135135135136, "percentage": 67.12, "elapsed_time": "1:16:45", "remaining_time": "0:37:36"}
|
| 150 |
{"current_steps": 150, "total_steps": 222, "loss": 0.6356, "lr": 2.8968497269310803e-06, "epoch": 2.027027027027027, "percentage": 67.57, "elapsed_time": "1:17:16", "remaining_time": "0:37:05"}
|
| 151 |
{"current_steps": 151, "total_steps": 222, "loss": 0.6941, "lr": 2.825502862121036e-06, "epoch": 2.0405405405405403, "percentage": 68.02, "elapsed_time": "1:17:42", "remaining_time": "0:36:32"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 222, "loss": 0.7393, "lr": 2.754697927585399e-06, "epoch": 2.054054054054054, "percentage": 68.47, "elapsed_time": "1:18:15", "remaining_time": "0:36:02"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 222, "loss": 0.648, "lr": 2.6844525693982614e-06, "epoch": 2.0675675675675675, "percentage": 68.92, "elapsed_time": "1:18:47", "remaining_time": "0:35:31"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 222, "loss": 0.7293, "lr": 2.6147842941755543e-06, "epoch": 2.081081081081081, "percentage": 69.37, "elapsed_time": "1:19:20", "remaining_time": "0:35:02"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 222, "loss": 0.7275, "lr": 2.5457104647120323e-06, "epoch": 2.0945945945945947, "percentage": 69.82, "elapsed_time": "1:19:48", "remaining_time": "0:34:29"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 222, "loss": 0.6401, "lr": 2.4772482956541133e-06, "epoch": 2.108108108108108, "percentage": 70.27, "elapsed_time": "1:20:17", "remaining_time": "0:33:58"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 222, "loss": 0.6813, "lr": 2.4094148492096124e-06, "epoch": 2.1216216216216215, "percentage": 70.72, "elapsed_time": "1:20:49", "remaining_time": "0:33:27"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 222, "loss": 0.7284, "lr": 2.3422270308954936e-06, "epoch": 2.135135135135135, "percentage": 71.17, "elapsed_time": "1:21:21", "remaining_time": "0:32:57"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 222, "loss": 0.7205, "lr": 2.2757015853246493e-06, "epoch": 2.1486486486486487, "percentage": 71.62, "elapsed_time": "1:21:54", "remaining_time": "0:32:27"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 222, "loss": 0.7288, "lr": 2.2098550920328e-06, "epoch": 2.1621621621621623, "percentage": 72.07, "elapsed_time": "1:22:30", "remaining_time": "0:31:58"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 222, "loss": 0.7027, "lr": 2.1447039613465265e-06, "epoch": 2.175675675675676, "percentage": 72.52, "elapsed_time": "1:23:02", "remaining_time": "0:31:27"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 222, "loss": 0.7266, "lr": 2.0802644302934683e-06, "epoch": 2.189189189189189, "percentage": 72.97, "elapsed_time": "1:23:30", "remaining_time": "0:30:55"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 222, "loss": 0.7287, "lr": 2.0165525585557205e-06, "epoch": 2.2027027027027026, "percentage": 73.42, "elapsed_time": "1:23:57", "remaining_time": "0:30:23"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 222, "loss": 0.6899, "lr": 1.953584224467418e-06, "epoch": 2.2162162162162162, "percentage": 73.87, "elapsed_time": "1:24:26", "remaining_time": "0:29:51"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 222, "loss": 0.6905, "lr": 1.8913751210575248e-06, "epoch": 2.22972972972973, "percentage": 74.32, "elapsed_time": "1:24:58", "remaining_time": "0:29:21"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 222, "loss": 0.7061, "lr": 1.8299407521388067e-06, "epoch": 2.2432432432432434, "percentage": 74.77, "elapsed_time": "1:25:26", "remaining_time": "0:28:49"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 222, "loss": 0.6592, "lr": 1.7692964284439506e-06, "epoch": 2.2567567567567566, "percentage": 75.23, "elapsed_time": "1:25:52", "remaining_time": "0:28:16"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 222, "loss": 0.6191, "lr": 1.7094572638098122e-06, "epoch": 2.27027027027027, "percentage": 75.68, "elapsed_time": "1:26:18", "remaining_time": "0:27:44"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 222, "loss": 0.7861, "lr": 1.6504381714107254e-06, "epoch": 2.2837837837837838, "percentage": 76.13, "elapsed_time": "1:26:49", "remaining_time": "0:27:13"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 222, "loss": 0.6756, "lr": 1.5922538600418319e-06, "epoch": 2.2972972972972974, "percentage": 76.58, "elapsed_time": "1:27:23", "remaining_time": "0:26:43"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 222, "loss": 0.6965, "lr": 1.5349188304533414e-06, "epoch": 2.310810810810811, "percentage": 77.03, "elapsed_time": "1:27:52", "remaining_time": "0:26:12"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 222, "loss": 0.6178, "lr": 1.4784473717366388e-06, "epoch": 2.3243243243243246, "percentage": 77.48, "elapsed_time": "1:28:18", "remaining_time": "0:25:40"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 222, "loss": 0.7379, "lr": 1.4228535577631442e-06, "epoch": 2.3378378378378377, "percentage": 77.93, "elapsed_time": "1:28:43", "remaining_time": "0:25:07"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 222, "loss": 0.6727, "lr": 1.3681512436768047e-06, "epoch": 2.3513513513513513, "percentage": 78.38, "elapsed_time": "1:29:16", "remaining_time": "0:24:37"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 222, "loss": 0.6992, "lr": 1.314354062441106e-06, "epoch": 2.364864864864865, "percentage": 78.83, "elapsed_time": "1:29:50", "remaining_time": "0:24:07"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 222, "loss": 0.6942, "lr": 1.261475421441455e-06, "epoch": 2.3783783783783785, "percentage": 79.28, "elapsed_time": "1:30:21", "remaining_time": "0:23:36"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 222, "loss": 0.7095, "lr": 1.2095284991437734e-06, "epoch": 2.391891891891892, "percentage": 79.73, "elapsed_time": "1:30:53", "remaining_time": "0:23:06"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 222, "loss": 0.7001, "lr": 1.1585262418101468e-06, "epoch": 2.4054054054054053, "percentage": 80.18, "elapsed_time": "1:31:34", "remaining_time": "0:22:38"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 222, "loss": 0.6289, "lr": 1.1084813602723516e-06, "epoch": 2.418918918918919, "percentage": 80.63, "elapsed_time": "1:32:02", "remaining_time": "0:22:06"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 222, "loss": 0.6646, "lr": 1.0594063267640386e-06, "epoch": 2.4324324324324325, "percentage": 81.08, "elapsed_time": "1:32:27", "remaining_time": "0:21:34"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 222, "loss": 0.7526, "lr": 1.0113133718124036e-06, "epoch": 2.445945945945946, "percentage": 81.53, "elapsed_time": "1:33:00", "remaining_time": "0:21:03"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 222, "loss": 0.7304, "lr": 9.64214481190074e-07, "epoch": 2.4594594594594597, "percentage": 81.98, "elapsed_time": "1:33:29", "remaining_time": "0:20:32"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 222, "loss": 0.7122, "lr": 9.181213929280047e-07, "epoch": 2.472972972972973, "percentage": 82.43, "elapsed_time": "1:33:55", "remaining_time": "0:20:01"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 222, "loss": 0.6884, "lr": 8.7304559439012e-07, "epoch": 2.4864864864864864, "percentage": 82.88, "elapsed_time": "1:34:22", "remaining_time": "0:19:29"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 222, "loss": 0.6515, "lr": 8.289983194104128e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:34:48", "remaining_time": "0:18:57"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 222, "loss": 0.7365, "lr": 7.859905454932471e-07, "epoch": 2.5135135135135136, "percentage": 83.78, "elapsed_time": "1:35:17", "remaining_time": "0:18:26"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 222, "loss": 0.7368, "lr": 7.440329910775274e-07, "epoch": 2.527027027027027, "percentage": 84.23, "elapsed_time": "1:35:46", "remaining_time": "0:17:55"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 222, "loss": 0.7144, "lr": 7.031361128654402e-07, "epoch": 2.5405405405405403, "percentage": 84.68, "elapsed_time": "1:36:13", "remaining_time": "0:17:24"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 222, "loss": 0.6884, "lr": 6.633101032164274e-07, "epoch": 2.554054054054054, "percentage": 85.14, "elapsed_time": "1:36:37", "remaining_time": "0:16:52"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 222, "loss": 0.7383, "lr": 6.24564887607032e-07, "epoch": 2.5675675675675675, "percentage": 85.59, "elapsed_time": "1:37:11", "remaining_time": "0:16:22"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 222, "loss": 0.7095, "lr": 5.869101221572653e-07, "epoch": 2.581081081081081, "percentage": 86.04, "elapsed_time": "1:37:49", "remaining_time": "0:15:52"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 222, "loss": 0.6647, "lr": 5.50355191224099e-07, "epoch": 2.5945945945945947, "percentage": 86.49, "elapsed_time": "1:38:23", "remaining_time": "0:15:22"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 222, "loss": 0.7085, "lr": 5.149092050626825e-07, "epoch": 2.608108108108108, "percentage": 86.94, "elapsed_time": "1:38:50", "remaining_time": "0:14:51"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 222, "loss": 0.6722, "lr": 4.805809975558828e-07, "epoch": 2.6216216216216215, "percentage": 87.39, "elapsed_time": "1:39:23", "remaining_time": "0:14:20"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 222, "loss": 0.689, "lr": 4.47379124012689e-07, "epoch": 2.635135135135135, "percentage": 87.84, "elapsed_time": "1:39:48", "remaining_time": "0:13:49"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 222, "loss": 0.7396, "lr": 4.1531185903605607e-07, "epoch": 2.6486486486486487, "percentage": 88.29, "elapsed_time": "1:40:20", "remaining_time": "0:13:18"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 222, "loss": 0.6984, "lr": 3.8438719446069693e-07, "epoch": 2.6621621621621623, "percentage": 88.74, "elapsed_time": "1:40:51", "remaining_time": "0:12:48"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 222, "loss": 0.676, "lr": 3.546128373613472e-07, "epoch": 2.6756756756756754, "percentage": 89.19, "elapsed_time": "1:41:19", "remaining_time": "0:12:16"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 222, "loss": 0.6387, "lr": 3.259962081320084e-07, "epoch": 2.689189189189189, "percentage": 89.64, "elapsed_time": "1:41:49", "remaining_time": "0:11:46"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 222, "loss": 0.6955, "lr": 2.9854443863662263e-07, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "1:42:19", "remaining_time": "0:11:15"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 222, "loss": 0.7018, "lr": 2.722643704316652e-07, "epoch": 2.7162162162162162, "percentage": 90.54, "elapsed_time": "1:42:52", "remaining_time": "0:10:44"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 222, "loss": 0.6882, "lr": 2.4716255306108605e-07, "epoch": 2.72972972972973, "percentage": 90.99, "elapsed_time": "1:43:24", "remaining_time": "0:10:14"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 222, "loss": 0.6018, "lr": 2.232452424240261e-07, "epoch": 2.743243243243243, "percentage": 91.44, "elapsed_time": "1:43:46", "remaining_time": "0:09:42"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 222, "loss": 0.7123, "lr": 2.0051839921571448e-07, "epoch": 2.756756756756757, "percentage": 91.89, "elapsed_time": "1:44:20", "remaining_time": "0:09:12"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 222, "loss": 0.684, "lr": 1.7898768744194163e-07, "epoch": 2.77027027027027, "percentage": 92.34, "elapsed_time": "1:44:51", "remaining_time": "0:08:41"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 222, "loss": 0.6959, "lr": 1.5865847300746417e-07, "epoch": 2.7837837837837838, "percentage": 92.79, "elapsed_time": "1:45:14", "remaining_time": "0:08:10"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 222, "loss": 0.6353, "lr": 1.395358223787152e-07, "epoch": 2.7972972972972974, "percentage": 93.24, "elapsed_time": "1:45:39", "remaining_time": "0:07:39"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 222, "loss": 0.6685, "lr": 1.2162450132113202e-07, "epoch": 2.810810810810811, "percentage": 93.69, "elapsed_time": "1:46:10", "remaining_time": "0:07:08"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 222, "loss": 0.6556, "lr": 1.049289737114273e-07, "epoch": 2.8243243243243246, "percentage": 94.14, "elapsed_time": "1:46:37", "remaining_time": "0:06:37"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 222, "loss": 0.6669, "lr": 8.945340042509799e-08, "epoch": 2.8378378378378377, "percentage": 94.59, "elapsed_time": "1:47:04", "remaining_time": "0:06:07"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 222, "loss": 0.6401, "lr": 7.520163829944805e-08, "epoch": 2.8513513513513513, "percentage": 95.05, "elapsed_time": "1:47:31", "remaining_time": "0:05:36"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 222, "loss": 0.6644, "lr": 6.217723917238127e-08, "epoch": 2.864864864864865, "percentage": 95.5, "elapsed_time": "1:48:01", "remaining_time": "0:05:05"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 222, "loss": 0.702, "lr": 5.038344899721437e-08, "epoch": 2.8783783783783785, "percentage": 95.95, "elapsed_time": "1:48:31", "remaining_time": "0:04:35"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 222, "loss": 0.7573, "lr": 3.9823207033710676e-08, "epoch": 2.891891891891892, "percentage": 96.4, "elapsed_time": "1:49:07", "remaining_time": "0:04:04"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 222, "loss": 0.632, "lr": 3.049914511556118e-08, "epoch": 2.9054054054054053, "percentage": 96.85, "elapsed_time": "1:49:32", "remaining_time": "0:03:33"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 222, "loss": 0.673, "lr": 2.2413586994470826e-08, "epoch": 2.918918918918919, "percentage": 97.3, "elapsed_time": "1:50:01", "remaining_time": "0:03:03"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 222, "loss": 0.666, "lr": 1.5568547761034003e-08, "epoch": 2.9324324324324325, "percentage": 97.75, "elapsed_time": "1:50:27", "remaining_time": "0:02:32"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 222, "loss": 0.7365, "lr": 9.965733342532925e-09, "epoch": 2.945945945945946, "percentage": 98.2, "elapsed_time": "1:51:04", "remaining_time": "0:02:02"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 222, "loss": 0.7352, "lr": 5.606540077782164e-09, "epoch": 2.9594594594594597, "percentage": 98.65, "elapsed_time": "1:51:38", "remaining_time": "0:01:31"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 222, "loss": 0.6517, "lr": 2.492054369130914e-09, "epoch": 2.972972972972973, "percentage": 99.1, "elapsed_time": "1:52:06", "remaining_time": "0:01:01"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 222, "loss": 0.6425, "lr": 6.23052411713454e-10, "epoch": 2.9864864864864864, "percentage": 99.55, "elapsed_time": "1:52:35", "remaining_time": "0:00:30"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 222, "loss": 0.6743, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:53:08", "remaining_time": "0:00:00"}
|
| 223 |
+
{"current_steps": 222, "total_steps": 222, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:54:54", "remaining_time": "0:00:00"}
|