Training in progress, epoch 2
Browse files- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- trainer_log.jsonl +100 -0
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8634408ab318a46c965a8d386e493cd3c41bdc44e2e256b1f8bdcf8290c63641
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b966bdcfe25bb67d730f601a528cd8d5353d7ee3f026a7147be03f3676b235f3
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0986a97cdbe21d3e550522107622bd1bad0fa64e59c0d7bfce528bcbb5e10b0f
|
3 |
size 4540516344
|
trainer_log.jsonl
CHANGED
@@ -98,3 +98,103 @@
|
|
98 |
{"current_steps": 980, "total_steps": 2961, "loss": 0.5515, "learning_rate": 5e-06, "epoch": 0.9924050632911392, "percentage": 33.1, "elapsed_time": "7:35:41", "remaining_time": "15:21:07"}
|
99 |
{"current_steps": 987, "total_steps": 2961, "eval_loss": 0.13834980130195618, "epoch": 0.999493670886076, "percentage": 33.33, "elapsed_time": "7:47:37", "remaining_time": "15:35:14"}
|
100 |
{"current_steps": 990, "total_steps": 2961, "loss": 0.5308, "learning_rate": 5e-06, "epoch": 1.0025316455696203, "percentage": 33.43, "elapsed_time": "7:49:52", "remaining_time": "15:35:28"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
{"current_steps": 980, "total_steps": 2961, "loss": 0.5515, "learning_rate": 5e-06, "epoch": 0.9924050632911392, "percentage": 33.1, "elapsed_time": "7:35:41", "remaining_time": "15:21:07"}
|
99 |
{"current_steps": 987, "total_steps": 2961, "eval_loss": 0.13834980130195618, "epoch": 0.999493670886076, "percentage": 33.33, "elapsed_time": "7:47:37", "remaining_time": "15:35:14"}
|
100 |
{"current_steps": 990, "total_steps": 2961, "loss": 0.5308, "learning_rate": 5e-06, "epoch": 1.0025316455696203, "percentage": 33.43, "elapsed_time": "7:49:52", "remaining_time": "15:35:28"}
|
101 |
+
{"current_steps": 1000, "total_steps": 2961, "loss": 0.4633, "learning_rate": 5e-06, "epoch": 1.0126582278481013, "percentage": 33.77, "elapsed_time": "7:54:31", "remaining_time": "15:30:32"}
|
102 |
+
{"current_steps": 1010, "total_steps": 2961, "loss": 0.4634, "learning_rate": 5e-06, "epoch": 1.0227848101265822, "percentage": 34.11, "elapsed_time": "7:59:10", "remaining_time": "15:25:37"}
|
103 |
+
{"current_steps": 1020, "total_steps": 2961, "loss": 0.4435, "learning_rate": 5e-06, "epoch": 1.0329113924050632, "percentage": 34.45, "elapsed_time": "8:03:50", "remaining_time": "15:20:42"}
|
104 |
+
{"current_steps": 1030, "total_steps": 2961, "loss": 0.4503, "learning_rate": 5e-06, "epoch": 1.0430379746835443, "percentage": 34.79, "elapsed_time": "8:08:29", "remaining_time": "15:15:47"}
|
105 |
+
{"current_steps": 1040, "total_steps": 2961, "loss": 0.4506, "learning_rate": 5e-06, "epoch": 1.0531645569620254, "percentage": 35.12, "elapsed_time": "8:13:08", "remaining_time": "15:10:52"}
|
106 |
+
{"current_steps": 1050, "total_steps": 2961, "loss": 0.4591, "learning_rate": 5e-06, "epoch": 1.0632911392405062, "percentage": 35.46, "elapsed_time": "8:17:47", "remaining_time": "15:05:58"}
|
107 |
+
{"current_steps": 1060, "total_steps": 2961, "loss": 0.4498, "learning_rate": 5e-06, "epoch": 1.0734177215189873, "percentage": 35.8, "elapsed_time": "8:22:26", "remaining_time": "15:01:04"}
|
108 |
+
{"current_steps": 1070, "total_steps": 2961, "loss": 0.4521, "learning_rate": 5e-06, "epoch": 1.0835443037974684, "percentage": 36.14, "elapsed_time": "8:27:05", "remaining_time": "14:56:11"}
|
109 |
+
{"current_steps": 1080, "total_steps": 2961, "loss": 0.4537, "learning_rate": 5e-06, "epoch": 1.0936708860759494, "percentage": 36.47, "elapsed_time": "8:31:44", "remaining_time": "14:51:17"}
|
110 |
+
{"current_steps": 1090, "total_steps": 2961, "loss": 0.4591, "learning_rate": 5e-06, "epoch": 1.1037974683544305, "percentage": 36.81, "elapsed_time": "8:36:24", "remaining_time": "14:46:24"}
|
111 |
+
{"current_steps": 1100, "total_steps": 2961, "loss": 0.451, "learning_rate": 5e-06, "epoch": 1.1139240506329113, "percentage": 37.15, "elapsed_time": "8:41:03", "remaining_time": "14:41:32"}
|
112 |
+
{"current_steps": 1110, "total_steps": 2961, "loss": 0.4545, "learning_rate": 5e-06, "epoch": 1.1240506329113924, "percentage": 37.49, "elapsed_time": "8:45:42", "remaining_time": "14:36:39"}
|
113 |
+
{"current_steps": 1120, "total_steps": 2961, "loss": 0.4511, "learning_rate": 5e-06, "epoch": 1.1341772151898735, "percentage": 37.83, "elapsed_time": "8:50:22", "remaining_time": "14:31:47"}
|
114 |
+
{"current_steps": 1130, "total_steps": 2961, "loss": 0.4597, "learning_rate": 5e-06, "epoch": 1.1443037974683543, "percentage": 38.16, "elapsed_time": "8:55:01", "remaining_time": "14:26:55"}
|
115 |
+
{"current_steps": 1140, "total_steps": 2961, "loss": 0.4587, "learning_rate": 5e-06, "epoch": 1.1544303797468354, "percentage": 38.5, "elapsed_time": "8:59:40", "remaining_time": "14:22:04"}
|
116 |
+
{"current_steps": 1150, "total_steps": 2961, "loss": 0.457, "learning_rate": 5e-06, "epoch": 1.1645569620253164, "percentage": 38.84, "elapsed_time": "9:04:20", "remaining_time": "14:17:12"}
|
117 |
+
{"current_steps": 1160, "total_steps": 2961, "loss": 0.4582, "learning_rate": 5e-06, "epoch": 1.1746835443037975, "percentage": 39.18, "elapsed_time": "9:08:59", "remaining_time": "14:12:21"}
|
118 |
+
{"current_steps": 1170, "total_steps": 2961, "loss": 0.4478, "learning_rate": 5e-06, "epoch": 1.1848101265822786, "percentage": 39.51, "elapsed_time": "9:13:38", "remaining_time": "14:07:30"}
|
119 |
+
{"current_steps": 1180, "total_steps": 2961, "loss": 0.4561, "learning_rate": 5e-06, "epoch": 1.1949367088607594, "percentage": 39.85, "elapsed_time": "9:18:18", "remaining_time": "14:02:39"}
|
120 |
+
{"current_steps": 1190, "total_steps": 2961, "loss": 0.463, "learning_rate": 5e-06, "epoch": 1.2050632911392405, "percentage": 40.19, "elapsed_time": "9:22:57", "remaining_time": "13:57:49"}
|
121 |
+
{"current_steps": 1200, "total_steps": 2961, "loss": 0.4557, "learning_rate": 5e-06, "epoch": 1.2151898734177216, "percentage": 40.53, "elapsed_time": "9:27:37", "remaining_time": "13:52:58"}
|
122 |
+
{"current_steps": 1210, "total_steps": 2961, "loss": 0.4616, "learning_rate": 5e-06, "epoch": 1.2253164556962026, "percentage": 40.86, "elapsed_time": "9:32:16", "remaining_time": "13:48:08"}
|
123 |
+
{"current_steps": 1220, "total_steps": 2961, "loss": 0.4492, "learning_rate": 5e-06, "epoch": 1.2354430379746835, "percentage": 41.2, "elapsed_time": "9:36:55", "remaining_time": "13:43:18"}
|
124 |
+
{"current_steps": 1230, "total_steps": 2961, "loss": 0.4623, "learning_rate": 5e-06, "epoch": 1.2455696202531645, "percentage": 41.54, "elapsed_time": "9:41:35", "remaining_time": "13:38:28"}
|
125 |
+
{"current_steps": 1240, "total_steps": 2961, "loss": 0.4576, "learning_rate": 5e-06, "epoch": 1.2556962025316456, "percentage": 41.88, "elapsed_time": "9:46:14", "remaining_time": "13:33:38"}
|
126 |
+
{"current_steps": 1250, "total_steps": 2961, "loss": 0.4581, "learning_rate": 5e-06, "epoch": 1.2658227848101267, "percentage": 42.22, "elapsed_time": "9:50:53", "remaining_time": "13:28:49"}
|
127 |
+
{"current_steps": 1260, "total_steps": 2961, "loss": 0.4613, "learning_rate": 5e-06, "epoch": 1.2759493670886077, "percentage": 42.55, "elapsed_time": "9:55:33", "remaining_time": "13:23:59"}
|
128 |
+
{"current_steps": 1270, "total_steps": 2961, "loss": 0.4546, "learning_rate": 5e-06, "epoch": 1.2860759493670886, "percentage": 42.89, "elapsed_time": "10:00:12", "remaining_time": "13:19:10"}
|
129 |
+
{"current_steps": 1280, "total_steps": 2961, "loss": 0.4638, "learning_rate": 5e-06, "epoch": 1.2962025316455696, "percentage": 43.23, "elapsed_time": "10:04:51", "remaining_time": "13:14:20"}
|
130 |
+
{"current_steps": 1290, "total_steps": 2961, "loss": 0.4605, "learning_rate": 5e-06, "epoch": 1.3063291139240507, "percentage": 43.57, "elapsed_time": "10:09:30", "remaining_time": "13:09:31"}
|
131 |
+
{"current_steps": 1300, "total_steps": 2961, "loss": 0.4656, "learning_rate": 5e-06, "epoch": 1.3164556962025316, "percentage": 43.9, "elapsed_time": "10:14:09", "remaining_time": "13:04:42"}
|
132 |
+
{"current_steps": 1310, "total_steps": 2961, "loss": 0.4546, "learning_rate": 5e-06, "epoch": 1.3265822784810126, "percentage": 44.24, "elapsed_time": "10:18:48", "remaining_time": "12:59:53"}
|
133 |
+
{"current_steps": 1320, "total_steps": 2961, "loss": 0.4509, "learning_rate": 5e-06, "epoch": 1.3367088607594937, "percentage": 44.58, "elapsed_time": "10:23:28", "remaining_time": "12:55:05"}
|
134 |
+
{"current_steps": 1330, "total_steps": 2961, "loss": 0.4592, "learning_rate": 5e-06, "epoch": 1.3468354430379748, "percentage": 44.92, "elapsed_time": "10:28:07", "remaining_time": "12:50:16"}
|
135 |
+
{"current_steps": 1340, "total_steps": 2961, "loss": 0.4731, "learning_rate": 5e-06, "epoch": 1.3569620253164558, "percentage": 45.25, "elapsed_time": "10:32:46", "remaining_time": "12:45:28"}
|
136 |
+
{"current_steps": 1350, "total_steps": 2961, "loss": 0.4614, "learning_rate": 5e-06, "epoch": 1.3670886075949367, "percentage": 45.59, "elapsed_time": "10:37:25", "remaining_time": "12:40:39"}
|
137 |
+
{"current_steps": 1360, "total_steps": 2961, "loss": 0.4642, "learning_rate": 5e-06, "epoch": 1.3772151898734177, "percentage": 45.93, "elapsed_time": "10:42:04", "remaining_time": "12:35:51"}
|
138 |
+
{"current_steps": 1370, "total_steps": 2961, "loss": 0.4599, "learning_rate": 5e-06, "epoch": 1.3873417721518988, "percentage": 46.27, "elapsed_time": "10:46:43", "remaining_time": "12:31:03"}
|
139 |
+
{"current_steps": 1380, "total_steps": 2961, "loss": 0.4635, "learning_rate": 5e-06, "epoch": 1.3974683544303796, "percentage": 46.61, "elapsed_time": "10:51:22", "remaining_time": "12:26:15"}
|
140 |
+
{"current_steps": 1390, "total_steps": 2961, "loss": 0.4581, "learning_rate": 5e-06, "epoch": 1.4075949367088607, "percentage": 46.94, "elapsed_time": "10:56:01", "remaining_time": "12:21:27"}
|
141 |
+
{"current_steps": 1400, "total_steps": 2961, "loss": 0.4602, "learning_rate": 5e-06, "epoch": 1.4177215189873418, "percentage": 47.28, "elapsed_time": "11:00:40", "remaining_time": "12:16:39"}
|
142 |
+
{"current_steps": 1410, "total_steps": 2961, "loss": 0.4602, "learning_rate": 5e-06, "epoch": 1.4278481012658228, "percentage": 47.62, "elapsed_time": "11:05:19", "remaining_time": "12:11:51"}
|
143 |
+
{"current_steps": 1420, "total_steps": 2961, "loss": 0.4687, "learning_rate": 5e-06, "epoch": 1.437974683544304, "percentage": 47.96, "elapsed_time": "11:09:58", "remaining_time": "12:07:04"}
|
144 |
+
{"current_steps": 1430, "total_steps": 2961, "loss": 0.4651, "learning_rate": 5e-06, "epoch": 1.4481012658227848, "percentage": 48.29, "elapsed_time": "11:14:37", "remaining_time": "12:02:16"}
|
145 |
+
{"current_steps": 1440, "total_steps": 2961, "loss": 0.4643, "learning_rate": 5e-06, "epoch": 1.4582278481012658, "percentage": 48.63, "elapsed_time": "11:19:16", "remaining_time": "11:57:29"}
|
146 |
+
{"current_steps": 1450, "total_steps": 2961, "loss": 0.467, "learning_rate": 5e-06, "epoch": 1.4683544303797469, "percentage": 48.97, "elapsed_time": "11:23:56", "remaining_time": "11:52:42"}
|
147 |
+
{"current_steps": 1460, "total_steps": 2961, "loss": 0.4692, "learning_rate": 5e-06, "epoch": 1.4784810126582277, "percentage": 49.31, "elapsed_time": "11:28:35", "remaining_time": "11:47:55"}
|
148 |
+
{"current_steps": 1470, "total_steps": 2961, "loss": 0.4606, "learning_rate": 5e-06, "epoch": 1.4886075949367088, "percentage": 49.65, "elapsed_time": "11:33:14", "remaining_time": "11:43:08"}
|
149 |
+
{"current_steps": 1480, "total_steps": 2961, "loss": 0.4607, "learning_rate": 5e-06, "epoch": 1.4987341772151899, "percentage": 49.98, "elapsed_time": "11:37:53", "remaining_time": "11:38:21"}
|
150 |
+
{"current_steps": 1490, "total_steps": 2961, "loss": 0.4603, "learning_rate": 5e-06, "epoch": 1.508860759493671, "percentage": 50.32, "elapsed_time": "11:42:32", "remaining_time": "11:33:35"}
|
151 |
+
{"current_steps": 1500, "total_steps": 2961, "loss": 0.4671, "learning_rate": 5e-06, "epoch": 1.518987341772152, "percentage": 50.66, "elapsed_time": "11:47:11", "remaining_time": "11:28:48"}
|
152 |
+
{"current_steps": 1510, "total_steps": 2961, "loss": 0.4642, "learning_rate": 5e-06, "epoch": 1.529113924050633, "percentage": 51.0, "elapsed_time": "11:51:50", "remaining_time": "11:24:02"}
|
153 |
+
{"current_steps": 1520, "total_steps": 2961, "loss": 0.4654, "learning_rate": 5e-06, "epoch": 1.539240506329114, "percentage": 51.33, "elapsed_time": "11:56:29", "remaining_time": "11:19:15"}
|
154 |
+
{"current_steps": 1530, "total_steps": 2961, "loss": 0.4623, "learning_rate": 5e-06, "epoch": 1.549367088607595, "percentage": 51.67, "elapsed_time": "12:01:09", "remaining_time": "11:14:29"}
|
155 |
+
{"current_steps": 1540, "total_steps": 2961, "loss": 0.4644, "learning_rate": 5e-06, "epoch": 1.5594936708860758, "percentage": 52.01, "elapsed_time": "12:05:49", "remaining_time": "11:09:44"}
|
156 |
+
{"current_steps": 1550, "total_steps": 2961, "loss": 0.4699, "learning_rate": 5e-06, "epoch": 1.5696202531645569, "percentage": 52.35, "elapsed_time": "12:10:28", "remaining_time": "11:04:58"}
|
157 |
+
{"current_steps": 1560, "total_steps": 2961, "loss": 0.4585, "learning_rate": 5e-06, "epoch": 1.579746835443038, "percentage": 52.68, "elapsed_time": "12:15:08", "remaining_time": "11:00:12"}
|
158 |
+
{"current_steps": 1570, "total_steps": 2961, "loss": 0.4674, "learning_rate": 5e-06, "epoch": 1.589873417721519, "percentage": 53.02, "elapsed_time": "12:19:47", "remaining_time": "10:55:27"}
|
159 |
+
{"current_steps": 1580, "total_steps": 2961, "loss": 0.4659, "learning_rate": 5e-06, "epoch": 1.6, "percentage": 53.36, "elapsed_time": "12:24:27", "remaining_time": "10:50:41"}
|
160 |
+
{"current_steps": 1590, "total_steps": 2961, "loss": 0.4582, "learning_rate": 5e-06, "epoch": 1.6101265822784812, "percentage": 53.7, "elapsed_time": "12:29:06", "remaining_time": "10:45:55"}
|
161 |
+
{"current_steps": 1600, "total_steps": 2961, "loss": 0.4676, "learning_rate": 5e-06, "epoch": 1.620253164556962, "percentage": 54.04, "elapsed_time": "12:33:46", "remaining_time": "10:41:10"}
|
162 |
+
{"current_steps": 1610, "total_steps": 2961, "loss": 0.4612, "learning_rate": 5e-06, "epoch": 1.630379746835443, "percentage": 54.37, "elapsed_time": "12:38:25", "remaining_time": "10:36:24"}
|
163 |
+
{"current_steps": 1620, "total_steps": 2961, "loss": 0.4506, "learning_rate": 5e-06, "epoch": 1.640506329113924, "percentage": 54.71, "elapsed_time": "12:43:04", "remaining_time": "10:31:39"}
|
164 |
+
{"current_steps": 1630, "total_steps": 2961, "loss": 0.4611, "learning_rate": 5e-06, "epoch": 1.650632911392405, "percentage": 55.05, "elapsed_time": "12:47:43", "remaining_time": "10:26:54"}
|
165 |
+
{"current_steps": 1640, "total_steps": 2961, "loss": 0.4699, "learning_rate": 5e-06, "epoch": 1.660759493670886, "percentage": 55.39, "elapsed_time": "12:52:23", "remaining_time": "10:22:08"}
|
166 |
+
{"current_steps": 1650, "total_steps": 2961, "loss": 0.4612, "learning_rate": 5e-06, "epoch": 1.6708860759493671, "percentage": 55.72, "elapsed_time": "12:57:02", "remaining_time": "10:17:23"}
|
167 |
+
{"current_steps": 1660, "total_steps": 2961, "loss": 0.4623, "learning_rate": 5e-06, "epoch": 1.6810126582278482, "percentage": 56.06, "elapsed_time": "13:01:41", "remaining_time": "10:12:38"}
|
168 |
+
{"current_steps": 1670, "total_steps": 2961, "loss": 0.4625, "learning_rate": 5e-06, "epoch": 1.6911392405063292, "percentage": 56.4, "elapsed_time": "13:06:21", "remaining_time": "10:07:53"}
|
169 |
+
{"current_steps": 1680, "total_steps": 2961, "loss": 0.4627, "learning_rate": 5e-06, "epoch": 1.70126582278481, "percentage": 56.74, "elapsed_time": "13:11:00", "remaining_time": "10:03:08"}
|
170 |
+
{"current_steps": 1690, "total_steps": 2961, "loss": 0.4646, "learning_rate": 5e-06, "epoch": 1.7113924050632912, "percentage": 57.08, "elapsed_time": "13:15:40", "remaining_time": "9:58:23"}
|
171 |
+
{"current_steps": 1700, "total_steps": 2961, "loss": 0.4648, "learning_rate": 5e-06, "epoch": 1.721518987341772, "percentage": 57.41, "elapsed_time": "13:20:19", "remaining_time": "9:53:39"}
|
172 |
+
{"current_steps": 1710, "total_steps": 2961, "loss": 0.4708, "learning_rate": 5e-06, "epoch": 1.731645569620253, "percentage": 57.75, "elapsed_time": "13:24:58", "remaining_time": "9:48:54"}
|
173 |
+
{"current_steps": 1720, "total_steps": 2961, "loss": 0.4591, "learning_rate": 5e-06, "epoch": 1.7417721518987341, "percentage": 58.09, "elapsed_time": "13:29:38", "remaining_time": "9:44:09"}
|
174 |
+
{"current_steps": 1730, "total_steps": 2961, "loss": 0.4651, "learning_rate": 5e-06, "epoch": 1.7518987341772152, "percentage": 58.43, "elapsed_time": "13:34:17", "remaining_time": "9:39:25"}
|
175 |
+
{"current_steps": 1740, "total_steps": 2961, "loss": 0.4714, "learning_rate": 5e-06, "epoch": 1.7620253164556963, "percentage": 58.76, "elapsed_time": "13:38:56", "remaining_time": "9:34:40"}
|
176 |
+
{"current_steps": 1750, "total_steps": 2961, "loss": 0.466, "learning_rate": 5e-06, "epoch": 1.7721518987341773, "percentage": 59.1, "elapsed_time": "13:43:36", "remaining_time": "9:29:56"}
|
177 |
+
{"current_steps": 1760, "total_steps": 2961, "loss": 0.4727, "learning_rate": 5e-06, "epoch": 1.7822784810126582, "percentage": 59.44, "elapsed_time": "13:48:15", "remaining_time": "9:25:11"}
|
178 |
+
{"current_steps": 1770, "total_steps": 2961, "loss": 0.4679, "learning_rate": 5e-06, "epoch": 1.7924050632911392, "percentage": 59.78, "elapsed_time": "13:52:54", "remaining_time": "9:20:27"}
|
179 |
+
{"current_steps": 1780, "total_steps": 2961, "loss": 0.4647, "learning_rate": 5e-06, "epoch": 1.80253164556962, "percentage": 60.11, "elapsed_time": "13:57:34", "remaining_time": "9:15:42"}
|
180 |
+
{"current_steps": 1790, "total_steps": 2961, "loss": 0.4644, "learning_rate": 5e-06, "epoch": 1.8126582278481012, "percentage": 60.45, "elapsed_time": "14:02:13", "remaining_time": "9:10:58"}
|
181 |
+
{"current_steps": 1800, "total_steps": 2961, "loss": 0.4675, "learning_rate": 5e-06, "epoch": 1.8227848101265822, "percentage": 60.79, "elapsed_time": "14:06:53", "remaining_time": "9:06:14"}
|
182 |
+
{"current_steps": 1810, "total_steps": 2961, "loss": 0.4624, "learning_rate": 5e-06, "epoch": 1.8329113924050633, "percentage": 61.13, "elapsed_time": "14:11:32", "remaining_time": "9:01:30"}
|
183 |
+
{"current_steps": 1820, "total_steps": 2961, "loss": 0.4739, "learning_rate": 5e-06, "epoch": 1.8430379746835444, "percentage": 61.47, "elapsed_time": "14:16:11", "remaining_time": "8:56:46"}
|
184 |
+
{"current_steps": 1830, "total_steps": 2961, "loss": 0.4655, "learning_rate": 5e-06, "epoch": 1.8531645569620254, "percentage": 61.8, "elapsed_time": "14:20:51", "remaining_time": "8:52:02"}
|
185 |
+
{"current_steps": 1840, "total_steps": 2961, "loss": 0.4678, "learning_rate": 5e-06, "epoch": 1.8632911392405065, "percentage": 62.14, "elapsed_time": "14:25:30", "remaining_time": "8:47:17"}
|
186 |
+
{"current_steps": 1850, "total_steps": 2961, "loss": 0.4609, "learning_rate": 5e-06, "epoch": 1.8734177215189873, "percentage": 62.48, "elapsed_time": "14:30:09", "remaining_time": "8:42:33"}
|
187 |
+
{"current_steps": 1860, "total_steps": 2961, "loss": 0.4663, "learning_rate": 5e-06, "epoch": 1.8835443037974684, "percentage": 62.82, "elapsed_time": "14:34:48", "remaining_time": "8:37:49"}
|
188 |
+
{"current_steps": 1870, "total_steps": 2961, "loss": 0.4665, "learning_rate": 5e-06, "epoch": 1.8936708860759492, "percentage": 63.15, "elapsed_time": "14:39:27", "remaining_time": "8:33:05"}
|
189 |
+
{"current_steps": 1880, "total_steps": 2961, "loss": 0.4676, "learning_rate": 5e-06, "epoch": 1.9037974683544303, "percentage": 63.49, "elapsed_time": "14:44:06", "remaining_time": "8:28:22"}
|
190 |
+
{"current_steps": 1890, "total_steps": 2961, "loss": 0.4669, "learning_rate": 5e-06, "epoch": 1.9139240506329114, "percentage": 63.83, "elapsed_time": "14:48:46", "remaining_time": "8:23:38"}
|
191 |
+
{"current_steps": 1900, "total_steps": 2961, "loss": 0.4701, "learning_rate": 5e-06, "epoch": 1.9240506329113924, "percentage": 64.17, "elapsed_time": "14:53:25", "remaining_time": "8:18:54"}
|
192 |
+
{"current_steps": 1910, "total_steps": 2961, "loss": 0.4693, "learning_rate": 5e-06, "epoch": 1.9341772151898735, "percentage": 64.51, "elapsed_time": "14:58:04", "remaining_time": "8:14:10"}
|
193 |
+
{"current_steps": 1920, "total_steps": 2961, "loss": 0.4763, "learning_rate": 5e-06, "epoch": 1.9443037974683546, "percentage": 64.84, "elapsed_time": "15:02:44", "remaining_time": "8:09:27"}
|
194 |
+
{"current_steps": 1930, "total_steps": 2961, "loss": 0.4756, "learning_rate": 5e-06, "epoch": 1.9544303797468354, "percentage": 65.18, "elapsed_time": "15:07:23", "remaining_time": "8:04:43"}
|
195 |
+
{"current_steps": 1940, "total_steps": 2961, "loss": 0.4667, "learning_rate": 5e-06, "epoch": 1.9645569620253165, "percentage": 65.52, "elapsed_time": "15:12:02", "remaining_time": "8:00:00"}
|
196 |
+
{"current_steps": 1950, "total_steps": 2961, "loss": 0.469, "learning_rate": 5e-06, "epoch": 1.9746835443037973, "percentage": 65.86, "elapsed_time": "15:16:42", "remaining_time": "7:55:16"}
|
197 |
+
{"current_steps": 1960, "total_steps": 2961, "loss": 0.4748, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.19, "elapsed_time": "15:21:21", "remaining_time": "7:50:33"}
|
198 |
+
{"current_steps": 1970, "total_steps": 2961, "loss": 0.468, "learning_rate": 5e-06, "epoch": 1.9949367088607595, "percentage": 66.53, "elapsed_time": "15:26:00", "remaining_time": "7:45:49"}
|
199 |
+
{"current_steps": 1975, "total_steps": 2961, "eval_loss": 0.1398227959871292, "epoch": 2.0, "percentage": 66.7, "elapsed_time": "15:36:44", "remaining_time": "7:47:39"}
|
200 |
+
{"current_steps": 1980, "total_steps": 2961, "loss": 0.4085, "learning_rate": 5e-06, "epoch": 2.0050632911392405, "percentage": 66.87, "elapsed_time": "15:40:11", "remaining_time": "7:45:49"}
|