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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1009a8ab3aa4af84af47b4e849bd9a61a5449cc455197cc3bb7107e4ddf3f08
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e1786c9b17412fed4de73e791589ed625f5c5d804b7fbcb4efb2c00d18aa000
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47734b2516fc466c430e23dc38c8ea31e77752a6e4a2fbc01d594fe3a67a524e
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b2e53b22a002ff74a1d8ddd8bee1bc3ee84061e62d2af29b86b8dde26dd6aa5
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -129,3 +129,67 @@
|
|
129 |
{"current_steps": 1280, "total_steps": 1938, "loss": 0.7755, "lr": 5e-06, "epoch": 1.9789371980676327, "percentage": 66.05, "elapsed_time": "20:47:01", "remaining_time": "10:41:02"}
|
130 |
{"current_steps": 1290, "total_steps": 1938, "loss": 0.7709, "lr": 5e-06, "epoch": 1.9943961352657005, "percentage": 66.56, "elapsed_time": "20:56:39", "remaining_time": "10:31:15"}
|
131 |
{"current_steps": 1293, "total_steps": 1938, "eval_loss": 0.8051349520683289, "epoch": 1.9990338164251207, "percentage": 66.72, "elapsed_time": "21:11:26", "remaining_time": "10:34:14"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
{"current_steps": 1280, "total_steps": 1938, "loss": 0.7755, "lr": 5e-06, "epoch": 1.9789371980676327, "percentage": 66.05, "elapsed_time": "20:47:01", "remaining_time": "10:41:02"}
|
130 |
{"current_steps": 1290, "total_steps": 1938, "loss": 0.7709, "lr": 5e-06, "epoch": 1.9943961352657005, "percentage": 66.56, "elapsed_time": "20:56:39", "remaining_time": "10:31:15"}
|
131 |
{"current_steps": 1293, "total_steps": 1938, "eval_loss": 0.8051349520683289, "epoch": 1.9990338164251207, "percentage": 66.72, "elapsed_time": "21:11:26", "remaining_time": "10:34:14"}
|
132 |
+
{"current_steps": 1300, "total_steps": 1938, "loss": 0.7604, "lr": 5e-06, "epoch": 2.0100483091787438, "percentage": 67.08, "elapsed_time": "21:19:00", "remaining_time": "10:27:41"}
|
133 |
+
{"current_steps": 1310, "total_steps": 1938, "loss": 0.7299, "lr": 5e-06, "epoch": 2.0255072463768116, "percentage": 67.6, "elapsed_time": "21:28:40", "remaining_time": "10:17:46"}
|
134 |
+
{"current_steps": 1320, "total_steps": 1938, "loss": 0.7254, "lr": 5e-06, "epoch": 2.0409661835748794, "percentage": 68.11, "elapsed_time": "21:38:19", "remaining_time": "10:07:51"}
|
135 |
+
{"current_steps": 1330, "total_steps": 1938, "loss": 0.7312, "lr": 5e-06, "epoch": 2.0564251207729467, "percentage": 68.63, "elapsed_time": "21:47:58", "remaining_time": "9:57:55"}
|
136 |
+
{"current_steps": 1340, "total_steps": 1938, "loss": 0.7283, "lr": 5e-06, "epoch": 2.0718840579710145, "percentage": 69.14, "elapsed_time": "21:57:37", "remaining_time": "9:48:00"}
|
137 |
+
{"current_steps": 1350, "total_steps": 1938, "loss": 0.7322, "lr": 5e-06, "epoch": 2.0873429951690823, "percentage": 69.66, "elapsed_time": "22:07:17", "remaining_time": "9:38:06"}
|
138 |
+
{"current_steps": 1360, "total_steps": 1938, "loss": 0.7317, "lr": 5e-06, "epoch": 2.1028019323671496, "percentage": 70.18, "elapsed_time": "22:16:56", "remaining_time": "9:28:12"}
|
139 |
+
{"current_steps": 1370, "total_steps": 1938, "loss": 0.7331, "lr": 5e-06, "epoch": 2.1182608695652174, "percentage": 70.69, "elapsed_time": "22:26:35", "remaining_time": "9:18:17"}
|
140 |
+
{"current_steps": 1380, "total_steps": 1938, "loss": 0.7346, "lr": 5e-06, "epoch": 2.133719806763285, "percentage": 71.21, "elapsed_time": "22:36:15", "remaining_time": "9:08:23"}
|
141 |
+
{"current_steps": 1390, "total_steps": 1938, "loss": 0.7336, "lr": 5e-06, "epoch": 2.1491787439613526, "percentage": 71.72, "elapsed_time": "22:45:54", "remaining_time": "8:58:29"}
|
142 |
+
{"current_steps": 1400, "total_steps": 1938, "loss": 0.7299, "lr": 5e-06, "epoch": 2.1646376811594203, "percentage": 72.24, "elapsed_time": "22:55:33", "remaining_time": "8:48:36"}
|
143 |
+
{"current_steps": 1410, "total_steps": 1938, "loss": 0.7333, "lr": 5e-06, "epoch": 2.1800966183574877, "percentage": 72.76, "elapsed_time": "23:05:13", "remaining_time": "8:38:43"}
|
144 |
+
{"current_steps": 1420, "total_steps": 1938, "loss": 0.7371, "lr": 5e-06, "epoch": 2.1955555555555555, "percentage": 73.27, "elapsed_time": "23:14:53", "remaining_time": "8:28:50"}
|
145 |
+
{"current_steps": 1430, "total_steps": 1938, "loss": 0.7314, "lr": 5e-06, "epoch": 2.2110144927536233, "percentage": 73.79, "elapsed_time": "23:24:34", "remaining_time": "8:18:57"}
|
146 |
+
{"current_steps": 1440, "total_steps": 1938, "loss": 0.7322, "lr": 5e-06, "epoch": 2.2264734299516906, "percentage": 74.3, "elapsed_time": "23:34:14", "remaining_time": "8:09:05"}
|
147 |
+
{"current_steps": 1450, "total_steps": 1938, "loss": 0.7356, "lr": 5e-06, "epoch": 2.2419323671497584, "percentage": 74.82, "elapsed_time": "23:43:54", "remaining_time": "7:59:13"}
|
148 |
+
{"current_steps": 1460, "total_steps": 1938, "loss": 0.7418, "lr": 5e-06, "epoch": 2.257391304347826, "percentage": 75.34, "elapsed_time": "23:53:34", "remaining_time": "7:49:20"}
|
149 |
+
{"current_steps": 1470, "total_steps": 1938, "loss": 0.7319, "lr": 5e-06, "epoch": 2.2728502415458935, "percentage": 75.85, "elapsed_time": "1 day, 0:03:14", "remaining_time": "7:39:28"}
|
150 |
+
{"current_steps": 1480, "total_steps": 1938, "loss": 0.7332, "lr": 5e-06, "epoch": 2.2883091787439613, "percentage": 76.37, "elapsed_time": "1 day, 0:12:55", "remaining_time": "7:29:37"}
|
151 |
+
{"current_steps": 1490, "total_steps": 1938, "loss": 0.7342, "lr": 5e-06, "epoch": 2.303768115942029, "percentage": 76.88, "elapsed_time": "1 day, 0:22:35", "remaining_time": "7:19:45"}
|
152 |
+
{"current_steps": 1500, "total_steps": 1938, "loss": 0.7345, "lr": 5e-06, "epoch": 2.3192270531400965, "percentage": 77.4, "elapsed_time": "1 day, 0:32:14", "remaining_time": "7:09:53"}
|
153 |
+
{"current_steps": 1510, "total_steps": 1938, "loss": 0.7357, "lr": 5e-06, "epoch": 2.3346859903381643, "percentage": 77.92, "elapsed_time": "1 day, 0:41:55", "remaining_time": "7:00:02"}
|
154 |
+
{"current_steps": 1520, "total_steps": 1938, "loss": 0.7339, "lr": 5e-06, "epoch": 2.350144927536232, "percentage": 78.43, "elapsed_time": "1 day, 0:51:35", "remaining_time": "6:50:11"}
|
155 |
+
{"current_steps": 1530, "total_steps": 1938, "loss": 0.7297, "lr": 5e-06, "epoch": 2.3656038647342994, "percentage": 78.95, "elapsed_time": "1 day, 1:01:14", "remaining_time": "6:40:19"}
|
156 |
+
{"current_steps": 1540, "total_steps": 1938, "loss": 0.7298, "lr": 5e-06, "epoch": 2.381062801932367, "percentage": 79.46, "elapsed_time": "1 day, 1:10:55", "remaining_time": "6:30:29"}
|
157 |
+
{"current_steps": 1550, "total_steps": 1938, "loss": 0.7368, "lr": 5e-06, "epoch": 2.396521739130435, "percentage": 79.98, "elapsed_time": "1 day, 1:20:35", "remaining_time": "6:20:38"}
|
158 |
+
{"current_steps": 1560, "total_steps": 1938, "loss": 0.7353, "lr": 5e-06, "epoch": 2.4119806763285023, "percentage": 80.5, "elapsed_time": "1 day, 1:30:15", "remaining_time": "6:10:47"}
|
159 |
+
{"current_steps": 1570, "total_steps": 1938, "loss": 0.7338, "lr": 5e-06, "epoch": 2.42743961352657, "percentage": 81.01, "elapsed_time": "1 day, 1:39:55", "remaining_time": "6:00:57"}
|
160 |
+
{"current_steps": 1580, "total_steps": 1938, "loss": 0.7329, "lr": 5e-06, "epoch": 2.442898550724638, "percentage": 81.53, "elapsed_time": "1 day, 1:49:35", "remaining_time": "5:51:06"}
|
161 |
+
{"current_steps": 1590, "total_steps": 1938, "loss": 0.7367, "lr": 5e-06, "epoch": 2.4583574879227053, "percentage": 82.04, "elapsed_time": "1 day, 1:59:15", "remaining_time": "5:41:16"}
|
162 |
+
{"current_steps": 1600, "total_steps": 1938, "loss": 0.733, "lr": 5e-06, "epoch": 2.473816425120773, "percentage": 82.56, "elapsed_time": "1 day, 2:08:55", "remaining_time": "5:31:26"}
|
163 |
+
{"current_steps": 1610, "total_steps": 1938, "loss": 0.7375, "lr": 5e-06, "epoch": 2.4892753623188404, "percentage": 83.08, "elapsed_time": "1 day, 2:18:35", "remaining_time": "5:21:36"}
|
164 |
+
{"current_steps": 1620, "total_steps": 1938, "loss": 0.7374, "lr": 5e-06, "epoch": 2.504734299516908, "percentage": 83.59, "elapsed_time": "1 day, 2:28:15", "remaining_time": "5:11:46"}
|
165 |
+
{"current_steps": 1630, "total_steps": 1938, "loss": 0.7311, "lr": 5e-06, "epoch": 2.520193236714976, "percentage": 84.11, "elapsed_time": "1 day, 2:37:54", "remaining_time": "5:01:56"}
|
166 |
+
{"current_steps": 1640, "total_steps": 1938, "loss": 0.7308, "lr": 5e-06, "epoch": 2.5356521739130433, "percentage": 84.62, "elapsed_time": "1 day, 2:47:34", "remaining_time": "4:52:06"}
|
167 |
+
{"current_steps": 1650, "total_steps": 1938, "loss": 0.7337, "lr": 5e-06, "epoch": 2.551111111111111, "percentage": 85.14, "elapsed_time": "1 day, 2:57:14", "remaining_time": "4:42:16"}
|
168 |
+
{"current_steps": 1660, "total_steps": 1938, "loss": 0.7318, "lr": 5e-06, "epoch": 2.566570048309179, "percentage": 85.66, "elapsed_time": "1 day, 3:06:53", "remaining_time": "4:32:27"}
|
169 |
+
{"current_steps": 1670, "total_steps": 1938, "loss": 0.736, "lr": 5e-06, "epoch": 2.5820289855072462, "percentage": 86.17, "elapsed_time": "1 day, 3:16:34", "remaining_time": "4:22:38"}
|
170 |
+
{"current_steps": 1680, "total_steps": 1938, "loss": 0.7325, "lr": 5e-06, "epoch": 2.597487922705314, "percentage": 86.69, "elapsed_time": "1 day, 3:26:15", "remaining_time": "4:12:49"}
|
171 |
+
{"current_steps": 1690, "total_steps": 1938, "loss": 0.7375, "lr": 5e-06, "epoch": 2.6129468599033814, "percentage": 87.2, "elapsed_time": "1 day, 3:35:55", "remaining_time": "4:03:00"}
|
172 |
+
{"current_steps": 1700, "total_steps": 1938, "loss": 0.7366, "lr": 5e-06, "epoch": 2.628405797101449, "percentage": 87.72, "elapsed_time": "1 day, 3:45:34", "remaining_time": "3:53:10"}
|
173 |
+
{"current_steps": 1710, "total_steps": 1938, "loss": 0.7372, "lr": 5e-06, "epoch": 2.643864734299517, "percentage": 88.24, "elapsed_time": "1 day, 3:55:14", "remaining_time": "3:43:21"}
|
174 |
+
{"current_steps": 1720, "total_steps": 1938, "loss": 0.7351, "lr": 5e-06, "epoch": 2.6593236714975843, "percentage": 88.75, "elapsed_time": "1 day, 4:04:54", "remaining_time": "3:33:33"}
|
175 |
+
{"current_steps": 1730, "total_steps": 1938, "loss": 0.7384, "lr": 5e-06, "epoch": 2.674782608695652, "percentage": 89.27, "elapsed_time": "1 day, 4:14:34", "remaining_time": "3:23:44"}
|
176 |
+
{"current_steps": 1740, "total_steps": 1938, "loss": 0.7361, "lr": 5e-06, "epoch": 2.69024154589372, "percentage": 89.78, "elapsed_time": "1 day, 4:24:13", "remaining_time": "3:13:55"}
|
177 |
+
{"current_steps": 1750, "total_steps": 1938, "loss": 0.7309, "lr": 5e-06, "epoch": 2.7057004830917872, "percentage": 90.3, "elapsed_time": "1 day, 4:33:53", "remaining_time": "3:04:07"}
|
178 |
+
{"current_steps": 1760, "total_steps": 1938, "loss": 0.7296, "lr": 5e-06, "epoch": 2.721159420289855, "percentage": 90.82, "elapsed_time": "1 day, 4:43:32", "remaining_time": "2:54:18"}
|
179 |
+
{"current_steps": 1770, "total_steps": 1938, "loss": 0.7406, "lr": 5e-06, "epoch": 2.736618357487923, "percentage": 91.33, "elapsed_time": "1 day, 4:53:11", "remaining_time": "2:44:30"}
|
180 |
+
{"current_steps": 1780, "total_steps": 1938, "loss": 0.7324, "lr": 5e-06, "epoch": 2.75207729468599, "percentage": 91.85, "elapsed_time": "1 day, 5:02:50", "remaining_time": "2:34:42"}
|
181 |
+
{"current_steps": 1790, "total_steps": 1938, "loss": 0.7331, "lr": 5e-06, "epoch": 2.767536231884058, "percentage": 92.36, "elapsed_time": "1 day, 5:12:29", "remaining_time": "2:24:53"}
|
182 |
+
{"current_steps": 1800, "total_steps": 1938, "loss": 0.7372, "lr": 5e-06, "epoch": 2.7829951690821257, "percentage": 92.88, "elapsed_time": "1 day, 5:22:08", "remaining_time": "2:15:05"}
|
183 |
+
{"current_steps": 1810, "total_steps": 1938, "loss": 0.7359, "lr": 5e-06, "epoch": 2.798454106280193, "percentage": 93.4, "elapsed_time": "1 day, 5:31:47", "remaining_time": "2:05:17"}
|
184 |
+
{"current_steps": 1820, "total_steps": 1938, "loss": 0.7384, "lr": 5e-06, "epoch": 2.813913043478261, "percentage": 93.91, "elapsed_time": "1 day, 5:41:27", "remaining_time": "1:55:30"}
|
185 |
+
{"current_steps": 1830, "total_steps": 1938, "loss": 0.7324, "lr": 5e-06, "epoch": 2.8293719806763287, "percentage": 94.43, "elapsed_time": "1 day, 5:51:07", "remaining_time": "1:45:42"}
|
186 |
+
{"current_steps": 1840, "total_steps": 1938, "loss": 0.736, "lr": 5e-06, "epoch": 2.844830917874396, "percentage": 94.94, "elapsed_time": "1 day, 6:00:47", "remaining_time": "1:35:54"}
|
187 |
+
{"current_steps": 1850, "total_steps": 1938, "loss": 0.7327, "lr": 5e-06, "epoch": 2.860289855072464, "percentage": 95.46, "elapsed_time": "1 day, 6:10:26", "remaining_time": "1:26:07"}
|
188 |
+
{"current_steps": 1860, "total_steps": 1938, "loss": 0.7374, "lr": 5e-06, "epoch": 2.8757487922705316, "percentage": 95.98, "elapsed_time": "1 day, 6:20:06", "remaining_time": "1:16:19"}
|
189 |
+
{"current_steps": 1870, "total_steps": 1938, "loss": 0.7351, "lr": 5e-06, "epoch": 2.891207729468599, "percentage": 96.49, "elapsed_time": "1 day, 6:29:47", "remaining_time": "1:06:32"}
|
190 |
+
{"current_steps": 1880, "total_steps": 1938, "loss": 0.7326, "lr": 5e-06, "epoch": 2.9066666666666667, "percentage": 97.01, "elapsed_time": "1 day, 6:39:27", "remaining_time": "0:56:44"}
|
191 |
+
{"current_steps": 1890, "total_steps": 1938, "loss": 0.7321, "lr": 5e-06, "epoch": 2.9221256038647345, "percentage": 97.52, "elapsed_time": "1 day, 6:49:07", "remaining_time": "0:46:57"}
|
192 |
+
{"current_steps": 1900, "total_steps": 1938, "loss": 0.7395, "lr": 5e-06, "epoch": 2.937584541062802, "percentage": 98.04, "elapsed_time": "1 day, 6:58:47", "remaining_time": "0:37:10"}
|
193 |
+
{"current_steps": 1910, "total_steps": 1938, "loss": 0.7368, "lr": 5e-06, "epoch": 2.9530434782608697, "percentage": 98.56, "elapsed_time": "1 day, 7:08:27", "remaining_time": "0:27:23"}
|
194 |
+
{"current_steps": 1920, "total_steps": 1938, "loss": 0.7339, "lr": 5e-06, "epoch": 2.9685024154589374, "percentage": 99.07, "elapsed_time": "1 day, 7:18:07", "remaining_time": "0:17:36"}
|
195 |
+
{"current_steps": 1930, "total_steps": 1938, "loss": 0.7386, "lr": 5e-06, "epoch": 2.983961352657005, "percentage": 99.59, "elapsed_time": "1 day, 7:27:47", "remaining_time": "0:07:49"}
|