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:b550a9fcb975da00add15a47b18bcd50a726475e85e96cbcca00af9102b18899
|
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:f211fca67b2ff5752105526fa56b49dc88f40464a0b27e3e46c22e23c36e7078
|
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 sha256:18b4448d0449089d33285c5e9866f0c022edff3c6141e2d9b0ed01a5a7f45fd6
|
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:e76769720b57016f36742f5460c8e2dd5efc57b3112422c697272c2ca53668c4
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -121,3 +121,64 @@
|
|
121 |
{"current_steps": 121, "total_steps": 183, "loss": 0.3784, "lr": 2.504731712636925e-05, "epoch": 1.9685279187817257, "percentage": 66.12, "elapsed_time": "7:26:06", "remaining_time": "3:48:35"}
|
122 |
{"current_steps": 122, "total_steps": 183, "loss": 0.3809, "lr": 2.4339412547218845e-05, "epoch": 1.984771573604061, "percentage": 66.67, "elapsed_time": "7:29:49", "remaining_time": "3:44:54"}
|
123 |
{"current_steps": 123, "total_steps": 183, "loss": 0.606, "lr": 2.3637254513146406e-05, "epoch": 2.0040609137055836, "percentage": 67.21, "elapsed_time": "7:35:05", "remaining_time": "3:41:59"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
121 |
{"current_steps": 121, "total_steps": 183, "loss": 0.3784, "lr": 2.504731712636925e-05, "epoch": 1.9685279187817257, "percentage": 66.12, "elapsed_time": "7:26:06", "remaining_time": "3:48:35"}
|
122 |
{"current_steps": 122, "total_steps": 183, "loss": 0.3809, "lr": 2.4339412547218845e-05, "epoch": 1.984771573604061, "percentage": 66.67, "elapsed_time": "7:29:49", "remaining_time": "3:44:54"}
|
123 |
{"current_steps": 123, "total_steps": 183, "loss": 0.606, "lr": 2.3637254513146406e-05, "epoch": 2.0040609137055836, "percentage": 67.21, "elapsed_time": "7:35:05", "remaining_time": "3:41:59"}
|
124 |
+
{"current_steps": 124, "total_steps": 183, "loss": 0.3647, "lr": 2.294110067622321e-05, "epoch": 2.020304568527919, "percentage": 67.76, "elapsed_time": "7:38:46", "remaining_time": "3:38:17"}
|
125 |
+
{"current_steps": 125, "total_steps": 183, "loss": 0.3608, "lr": 2.225120648532161e-05, "epoch": 2.0365482233502537, "percentage": 68.31, "elapsed_time": "7:42:27", "remaining_time": "3:34:34"}
|
126 |
+
{"current_steps": 126, "total_steps": 183, "loss": 0.3614, "lr": 2.1567825092379807e-05, "epoch": 2.052791878172589, "percentage": 68.85, "elapsed_time": "7:46:07", "remaining_time": "3:30:52"}
|
127 |
+
{"current_steps": 127, "total_steps": 183, "loss": 0.3682, "lr": 2.089120725950948e-05, "epoch": 2.0690355329949237, "percentage": 69.4, "elapsed_time": "7:49:48", "remaining_time": "3:27:09"}
|
128 |
+
{"current_steps": 128, "total_steps": 183, "loss": 0.3548, "lr": 2.0221601266980383e-05, "epoch": 2.085279187817259, "percentage": 69.95, "elapsed_time": "7:53:28", "remaining_time": "3:23:26"}
|
129 |
+
{"current_steps": 129, "total_steps": 183, "loss": 0.3552, "lr": 1.955925282211558e-05, "epoch": 2.1015228426395938, "percentage": 70.49, "elapsed_time": "7:57:08", "remaining_time": "3:19:44"}
|
130 |
+
{"current_steps": 130, "total_steps": 183, "loss": 0.3641, "lr": 1.890440496913083e-05, "epoch": 2.117766497461929, "percentage": 71.04, "elapsed_time": "8:00:48", "remaining_time": "3:16:01"}
|
131 |
+
{"current_steps": 131, "total_steps": 183, "loss": 0.3641, "lr": 1.825729799995116e-05, "epoch": 2.134010152284264, "percentage": 71.58, "elapsed_time": "8:04:29", "remaining_time": "3:12:19"}
|
132 |
+
{"current_steps": 132, "total_steps": 183, "loss": 0.3618, "lr": 1.761816936603744e-05, "epoch": 2.150253807106599, "percentage": 72.13, "elapsed_time": "8:08:10", "remaining_time": "3:08:36"}
|
133 |
+
{"current_steps": 133, "total_steps": 183, "loss": 0.3546, "lr": 1.6987253591255178e-05, "epoch": 2.166497461928934, "percentage": 72.68, "elapsed_time": "8:11:50", "remaining_time": "3:04:54"}
|
134 |
+
{"current_steps": 134, "total_steps": 183, "loss": 0.3549, "lr": 1.6364782185817592e-05, "epoch": 2.182741116751269, "percentage": 73.22, "elapsed_time": "8:15:30", "remaining_time": "3:01:11"}
|
135 |
+
{"current_steps": 135, "total_steps": 183, "loss": 0.3586, "lr": 1.5750983561334493e-05, "epoch": 2.198984771573604, "percentage": 73.77, "elapsed_time": "8:19:10", "remaining_time": "2:57:29"}
|
136 |
+
{"current_steps": 136, "total_steps": 183, "loss": 0.3559, "lr": 1.5146082946998286e-05, "epoch": 2.215228426395939, "percentage": 74.32, "elapsed_time": "8:22:51", "remaining_time": "2:53:46"}
|
137 |
+
{"current_steps": 137, "total_steps": 183, "loss": 0.3639, "lr": 1.4550302306937619e-05, "epoch": 2.231472081218274, "percentage": 74.86, "elapsed_time": "8:26:30", "remaining_time": "2:50:04"}
|
138 |
+
{"current_steps": 138, "total_steps": 183, "loss": 0.355, "lr": 1.396386025876916e-05, "epoch": 2.2477157360406093, "percentage": 75.41, "elapsed_time": "8:30:11", "remaining_time": "2:46:21"}
|
139 |
+
{"current_steps": 139, "total_steps": 183, "loss": 0.3549, "lr": 1.338697199337739e-05, "epoch": 2.263959390862944, "percentage": 75.96, "elapsed_time": "8:33:51", "remaining_time": "2:42:39"}
|
140 |
+
{"current_steps": 140, "total_steps": 183, "loss": 0.3586, "lr": 1.2819849195951778e-05, "epoch": 2.2802030456852793, "percentage": 76.5, "elapsed_time": "8:37:31", "remaining_time": "2:38:57"}
|
141 |
+
{"current_steps": 141, "total_steps": 183, "loss": 0.3604, "lr": 1.2262699968310336e-05, "epoch": 2.296446700507614, "percentage": 77.05, "elapsed_time": "8:41:11", "remaining_time": "2:35:14"}
|
142 |
+
{"current_steps": 142, "total_steps": 183, "loss": 0.3551, "lr": 1.1715728752538103e-05, "epoch": 2.3126903553299494, "percentage": 77.6, "elapsed_time": "8:44:51", "remaining_time": "2:31:32"}
|
143 |
+
{"current_steps": 143, "total_steps": 183, "loss": 0.3563, "lr": 1.1179136255968523e-05, "epoch": 2.328934010152284, "percentage": 78.14, "elapsed_time": "8:48:31", "remaining_time": "2:27:50"}
|
144 |
+
{"current_steps": 144, "total_steps": 183, "loss": 0.359, "lr": 1.065311937753526e-05, "epoch": 2.3451776649746194, "percentage": 78.69, "elapsed_time": "8:52:11", "remaining_time": "2:24:08"}
|
145 |
+
{"current_steps": 145, "total_steps": 183, "loss": 0.3548, "lr": 1.0137871135521493e-05, "epoch": 2.3614213197969542, "percentage": 79.23, "elapsed_time": "8:55:52", "remaining_time": "2:20:26"}
|
146 |
+
{"current_steps": 146, "total_steps": 183, "loss": 0.3523, "lr": 9.633580596733179e-06, "epoch": 2.3776649746192895, "percentage": 79.78, "elapsed_time": "8:59:32", "remaining_time": "2:16:43"}
|
147 |
+
{"current_steps": 147, "total_steps": 183, "loss": 0.359, "lr": 9.140432807122282e-06, "epoch": 2.3939086294416243, "percentage": 80.33, "elapsed_time": "9:03:12", "remaining_time": "2:13:01"}
|
148 |
+
{"current_steps": 148, "total_steps": 183, "loss": 0.3518, "lr": 8.658608723885433e-06, "epoch": 2.4101522842639596, "percentage": 80.87, "elapsed_time": "9:06:52", "remaining_time": "2:09:19"}
|
149 |
+
{"current_steps": 149, "total_steps": 183, "loss": 0.3535, "lr": 8.18828514906294e-06, "epoch": 2.4263959390862944, "percentage": 81.42, "elapsed_time": "9:10:33", "remaining_time": "2:05:37"}
|
150 |
+
{"current_steps": 150, "total_steps": 183, "loss": 0.3534, "lr": 7.729634664662469e-06, "epoch": 2.4426395939086296, "percentage": 81.97, "elapsed_time": "9:14:13", "remaining_time": "2:01:55"}
|
151 |
+
{"current_steps": 151, "total_steps": 183, "loss": 0.3596, "lr": 7.282825569331296e-06, "epoch": 2.4588832487309644, "percentage": 82.51, "elapsed_time": "9:17:54", "remaining_time": "1:58:13"}
|
152 |
+
{"current_steps": 152, "total_steps": 183, "loss": 0.361, "lr": 6.848021816600221e-06, "epoch": 2.4751269035532997, "percentage": 83.06, "elapsed_time": "9:21:35", "remaining_time": "1:54:32"}
|
153 |
+
{"current_steps": 153, "total_steps": 183, "loss": 0.3614, "lr": 6.425382954722002e-06, "epoch": 2.4913705583756345, "percentage": 83.61, "elapsed_time": "9:25:15", "remaining_time": "1:50:50"}
|
154 |
+
{"current_steps": 154, "total_steps": 183, "loss": 0.3575, "lr": 6.015064068126188e-06, "epoch": 2.5076142131979697, "percentage": 84.15, "elapsed_time": "9:28:56", "remaining_time": "1:47:08"}
|
155 |
+
{"current_steps": 155, "total_steps": 183, "loss": 0.351, "lr": 5.617215720511962e-06, "epoch": 2.5238578680203045, "percentage": 84.7, "elapsed_time": "9:32:37", "remaining_time": "1:43:26"}
|
156 |
+
{"current_steps": 156, "total_steps": 183, "loss": 0.3543, "lr": 5.231983899599798e-06, "epoch": 2.5401015228426393, "percentage": 85.25, "elapsed_time": "9:36:18", "remaining_time": "1:39:44"}
|
157 |
+
{"current_steps": 157, "total_steps": 183, "loss": 0.3646, "lr": 4.859509963562313e-06, "epoch": 2.5563451776649746, "percentage": 85.79, "elapsed_time": "9:39:58", "remaining_time": "1:36:02"}
|
158 |
+
{"current_steps": 158, "total_steps": 183, "loss": 0.3546, "lr": 4.4999305891538294e-06, "epoch": 2.57258883248731, "percentage": 86.34, "elapsed_time": "9:43:39", "remaining_time": "1:32:21"}
|
159 |
+
{"current_steps": 159, "total_steps": 183, "loss": 0.3579, "lr": 4.153377721557781e-06, "epoch": 2.5888324873096447, "percentage": 86.89, "elapsed_time": "9:47:20", "remaining_time": "1:28:39"}
|
160 |
+
{"current_steps": 160, "total_steps": 183, "loss": 0.3565, "lr": 3.819978525970336e-06, "epoch": 2.6050761421319795, "percentage": 87.43, "elapsed_time": "9:51:00", "remaining_time": "1:24:57"}
|
161 |
+
{"current_steps": 161, "total_steps": 183, "loss": 0.3553, "lr": 3.499855340938001e-06, "epoch": 2.6213197969543147, "percentage": 87.98, "elapsed_time": "9:54:40", "remaining_time": "1:21:15"}
|
162 |
+
{"current_steps": 162, "total_steps": 183, "loss": 0.3545, "lr": 3.19312563346633e-06, "epoch": 2.63756345177665, "percentage": 88.52, "elapsed_time": "9:58:21", "remaining_time": "1:17:33"}
|
163 |
+
{"current_steps": 163, "total_steps": 183, "loss": 0.3552, "lr": 2.8999019559162156e-06, "epoch": 2.6538071065989848, "percentage": 89.07, "elapsed_time": "10:02:01", "remaining_time": "1:13:52"}
|
164 |
+
{"current_steps": 164, "total_steps": 183, "loss": 0.3468, "lr": 2.6202919047035604e-06, "epoch": 2.6700507614213196, "percentage": 89.62, "elapsed_time": "10:05:41", "remaining_time": "1:10:10"}
|
165 |
+
{"current_steps": 165, "total_steps": 183, "loss": 0.3562, "lr": 2.3543980808175393e-06, "epoch": 2.686294416243655, "percentage": 90.16, "elapsed_time": "10:09:21", "remaining_time": "1:06:28"}
|
166 |
+
{"current_steps": 166, "total_steps": 183, "loss": 0.3556, "lr": 2.10231805217183e-06, "epoch": 2.70253807106599, "percentage": 90.71, "elapsed_time": "10:13:02", "remaining_time": "1:02:46"}
|
167 |
+
{"current_steps": 167, "total_steps": 183, "loss": 0.354, "lr": 1.8641443178027784e-06, "epoch": 2.718781725888325, "percentage": 91.26, "elapsed_time": "10:16:42", "remaining_time": "0:59:05"}
|
168 |
+
{"current_steps": 168, "total_steps": 183, "loss": 0.3534, "lr": 1.6399642739274791e-06, "epoch": 2.7350253807106597, "percentage": 91.8, "elapsed_time": "10:20:23", "remaining_time": "0:55:23"}
|
169 |
+
{"current_steps": 169, "total_steps": 183, "loss": 0.3585, "lr": 1.4298601818743607e-06, "epoch": 2.751269035532995, "percentage": 92.35, "elapsed_time": "10:24:03", "remaining_time": "0:51:41"}
|
170 |
+
{"current_steps": 170, "total_steps": 183, "loss": 0.3632, "lr": 1.233909137897924e-06, "epoch": 2.76751269035533, "percentage": 92.9, "elapsed_time": "10:27:43", "remaining_time": "0:48:00"}
|
171 |
+
{"current_steps": 171, "total_steps": 183, "loss": 0.3581, "lr": 1.0521830448888414e-06, "epoch": 2.783756345177665, "percentage": 93.44, "elapsed_time": "10:31:24", "remaining_time": "0:44:18"}
|
172 |
+
{"current_steps": 172, "total_steps": 183, "loss": 0.3502, "lr": 8.847485859896365e-07, "epoch": 2.8, "percentage": 93.99, "elapsed_time": "10:35:04", "remaining_time": "0:40:36"}
|
173 |
+
{"current_steps": 173, "total_steps": 183, "loss": 0.3567, "lr": 7.31667200125803e-07, "epoch": 2.816243654822335, "percentage": 94.54, "elapsed_time": "10:38:44", "remaining_time": "0:36:55"}
|
174 |
+
{"current_steps": 174, "total_steps": 183, "loss": 0.3554, "lr": 5.929950594612032e-07, "epoch": 2.8324873096446703, "percentage": 95.08, "elapsed_time": "10:42:24", "remaining_time": "0:33:13"}
|
175 |
+
{"current_steps": 175, "total_steps": 183, "loss": 0.3563, "lr": 4.687830487860634e-07, "epoch": 2.848730964467005, "percentage": 95.63, "elapsed_time": "10:46:05", "remaining_time": "0:29:32"}
|
176 |
+
{"current_steps": 176, "total_steps": 183, "loss": 0.3505, "lr": 3.590767468451528e-07, "epoch": 2.86497461928934, "percentage": 96.17, "elapsed_time": "10:49:44", "remaining_time": "0:25:50"}
|
177 |
+
{"current_steps": 177, "total_steps": 183, "loss": 0.3541, "lr": 2.639164096129987e-07, "epoch": 2.881218274111675, "percentage": 96.72, "elapsed_time": "10:53:25", "remaining_time": "0:22:08"}
|
178 |
+
{"current_steps": 178, "total_steps": 183, "loss": 0.356, "lr": 1.833369555222042e-07, "epoch": 2.89746192893401, "percentage": 97.27, "elapsed_time": "10:57:05", "remaining_time": "0:18:27"}
|
179 |
+
{"current_steps": 179, "total_steps": 183, "loss": 0.3602, "lr": 1.1736795265038237e-07, "epoch": 2.9137055837563453, "percentage": 97.81, "elapsed_time": "11:00:45", "remaining_time": "0:14:45"}
|
180 |
+
{"current_steps": 180, "total_steps": 183, "loss": 0.3592, "lr": 6.603360787035495e-08, "epoch": 2.92994923857868, "percentage": 98.36, "elapsed_time": "11:04:25", "remaining_time": "0:11:04"}
|
181 |
+
{"current_steps": 181, "total_steps": 183, "loss": 0.3495, "lr": 2.9352757967600064e-08, "epoch": 2.9461928934010153, "percentage": 98.91, "elapsed_time": "11:08:05", "remaining_time": "0:07:22"}
|
182 |
+
{"current_steps": 182, "total_steps": 183, "loss": 0.3571, "lr": 7.338862728225593e-09, "epoch": 2.96243654822335, "percentage": 99.45, "elapsed_time": "11:11:45", "remaining_time": "0:03:41"}
|
183 |
+
{"current_steps": 183, "total_steps": 183, "loss": 0.3592, "lr": 0.0, "epoch": 2.9786802030456854, "percentage": 100.0, "elapsed_time": "11:15:26", "remaining_time": "0:00:00"}
|
184 |
+
{"current_steps": 183, "total_steps": 183, "epoch": 2.9786802030456854, "percentage": 100.0, "elapsed_time": "11:16:57", "remaining_time": "0:00:00"}
|