Training in progress, epoch 1
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 sha256:305fb7cdd5cd6972716e748371d7b24c5d4fe0bc1f56ae33757c35250d6f523d
|
| 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 sha256:0b9ebbb34052296046a3b49311bb1c4941423b209bfec2d10f9a82e4a852264e
|
| 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:dbcdd9febc81b421a60165e0e873bd43ae07b1f7e9d82456c2ab198018d824c3
|
| 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:aad7527e4ee1e5477f241618b65846165b23caaf1a68566da209deb1a67262f5
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -99,3 +99,103 @@
|
|
| 99 |
{"current_steps": 990, "total_steps": 3984, "loss": 0.7336, "lr": 5e-06, "epoch": 0.9936018065487392, "percentage": 24.85, "elapsed_time": "8:46:00", "remaining_time": "1 day, 2:30:45"}
|
| 100 |
{"current_steps": 996, "total_steps": 3984, "eval_loss": 0.7306540608406067, "epoch": 0.9996236356793377, "percentage": 25.0, "elapsed_time": "9:01:12", "remaining_time": "1 day, 3:03:37"}
|
| 101 |
{"current_steps": 1000, "total_steps": 3984, "loss": 0.7631, "lr": 5e-06, "epoch": 1.0036381884330698, "percentage": 25.1, "elapsed_time": "9:04:27", "remaining_time": "1 day, 3:04:41"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
{"current_steps": 990, "total_steps": 3984, "loss": 0.7336, "lr": 5e-06, "epoch": 0.9936018065487392, "percentage": 24.85, "elapsed_time": "8:46:00", "remaining_time": "1 day, 2:30:45"}
|
| 100 |
{"current_steps": 996, "total_steps": 3984, "eval_loss": 0.7306540608406067, "epoch": 0.9996236356793377, "percentage": 25.0, "elapsed_time": "9:01:12", "remaining_time": "1 day, 3:03:37"}
|
| 101 |
{"current_steps": 1000, "total_steps": 3984, "loss": 0.7631, "lr": 5e-06, "epoch": 1.0036381884330698, "percentage": 25.1, "elapsed_time": "9:04:27", "remaining_time": "1 day, 3:04:41"}
|
| 102 |
+
{"current_steps": 1010, "total_steps": 3984, "loss": 0.6949, "lr": 5e-06, "epoch": 1.0136745703174006, "percentage": 25.35, "elapsed_time": "9:09:46", "remaining_time": "1 day, 2:58:49"}
|
| 103 |
+
{"current_steps": 1020, "total_steps": 3984, "loss": 0.6968, "lr": 5e-06, "epoch": 1.0237109522017314, "percentage": 25.6, "elapsed_time": "9:15:04", "remaining_time": "1 day, 2:52:57"}
|
| 104 |
+
{"current_steps": 1030, "total_steps": 3984, "loss": 0.6905, "lr": 5e-06, "epoch": 1.033747334086062, "percentage": 25.85, "elapsed_time": "9:20:22", "remaining_time": "1 day, 2:47:08"}
|
| 105 |
+
{"current_steps": 1040, "total_steps": 3984, "loss": 0.6922, "lr": 5e-06, "epoch": 1.0437837159703927, "percentage": 26.1, "elapsed_time": "9:25:41", "remaining_time": "1 day, 2:41:20"}
|
| 106 |
+
{"current_steps": 1050, "total_steps": 3984, "loss": 0.6901, "lr": 5e-06, "epoch": 1.0538200978547234, "percentage": 26.36, "elapsed_time": "9:31:00", "remaining_time": "1 day, 2:35:34"}
|
| 107 |
+
{"current_steps": 1060, "total_steps": 3984, "loss": 0.6922, "lr": 5e-06, "epoch": 1.0638564797390542, "percentage": 26.61, "elapsed_time": "9:36:19", "remaining_time": "1 day, 2:29:47"}
|
| 108 |
+
{"current_steps": 1070, "total_steps": 3984, "loss": 0.6979, "lr": 5e-06, "epoch": 1.0738928616233847, "percentage": 26.86, "elapsed_time": "9:41:39", "remaining_time": "1 day, 2:24:03"}
|
| 109 |
+
{"current_steps": 1080, "total_steps": 3984, "loss": 0.6958, "lr": 5e-06, "epoch": 1.0839292435077155, "percentage": 27.11, "elapsed_time": "9:46:59", "remaining_time": "1 day, 2:18:21"}
|
| 110 |
+
{"current_steps": 1090, "total_steps": 3984, "loss": 0.6931, "lr": 5e-06, "epoch": 1.0939656253920462, "percentage": 27.36, "elapsed_time": "9:52:18", "remaining_time": "1 day, 2:12:37"}
|
| 111 |
+
{"current_steps": 1100, "total_steps": 3984, "loss": 0.6937, "lr": 5e-06, "epoch": 1.1040020072763768, "percentage": 27.61, "elapsed_time": "9:57:38", "remaining_time": "1 day, 2:06:55"}
|
| 112 |
+
{"current_steps": 1110, "total_steps": 3984, "loss": 0.6917, "lr": 5e-06, "epoch": 1.1140383891607075, "percentage": 27.86, "elapsed_time": "10:02:57", "remaining_time": "1 day, 2:01:09"}
|
| 113 |
+
{"current_steps": 1120, "total_steps": 3984, "loss": 0.6972, "lr": 5e-06, "epoch": 1.1240747710450383, "percentage": 28.11, "elapsed_time": "10:08:15", "remaining_time": "1 day, 1:55:24"}
|
| 114 |
+
{"current_steps": 1130, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.134111152929369, "percentage": 28.36, "elapsed_time": "10:13:34", "remaining_time": "1 day, 1:49:41"}
|
| 115 |
+
{"current_steps": 1140, "total_steps": 3984, "loss": 0.6934, "lr": 5e-06, "epoch": 1.1441475348136996, "percentage": 28.61, "elapsed_time": "10:18:54", "remaining_time": "1 day, 1:44:01"}
|
| 116 |
+
{"current_steps": 1150, "total_steps": 3984, "loss": 0.6966, "lr": 5e-06, "epoch": 1.1541839166980303, "percentage": 28.87, "elapsed_time": "10:24:13", "remaining_time": "1 day, 1:38:18"}
|
| 117 |
+
{"current_steps": 1160, "total_steps": 3984, "loss": 0.6905, "lr": 5e-06, "epoch": 1.164220298582361, "percentage": 29.12, "elapsed_time": "10:29:32", "remaining_time": "1 day, 1:32:36"}
|
| 118 |
+
{"current_steps": 1170, "total_steps": 3984, "loss": 0.6949, "lr": 5e-06, "epoch": 1.1742566804666918, "percentage": 29.37, "elapsed_time": "10:34:51", "remaining_time": "1 day, 1:26:54"}
|
| 119 |
+
{"current_steps": 1180, "total_steps": 3984, "loss": 0.6982, "lr": 5e-06, "epoch": 1.1842930623510224, "percentage": 29.62, "elapsed_time": "10:40:10", "remaining_time": "1 day, 1:21:13"}
|
| 120 |
+
{"current_steps": 1190, "total_steps": 3984, "loss": 0.6975, "lr": 5e-06, "epoch": 1.1943294442353531, "percentage": 29.87, "elapsed_time": "10:45:29", "remaining_time": "1 day, 1:15:32"}
|
| 121 |
+
{"current_steps": 1200, "total_steps": 3984, "loss": 0.6938, "lr": 5e-06, "epoch": 1.204365826119684, "percentage": 30.12, "elapsed_time": "10:50:48", "remaining_time": "1 day, 1:09:53"}
|
| 122 |
+
{"current_steps": 1210, "total_steps": 3984, "loss": 0.6928, "lr": 5e-06, "epoch": 1.2144022080040147, "percentage": 30.37, "elapsed_time": "10:56:08", "remaining_time": "1 day, 1:04:14"}
|
| 123 |
+
{"current_steps": 1220, "total_steps": 3984, "loss": 0.6966, "lr": 5e-06, "epoch": 1.2244385898883452, "percentage": 30.62, "elapsed_time": "11:01:28", "remaining_time": "1 day, 0:58:36"}
|
| 124 |
+
{"current_steps": 1230, "total_steps": 3984, "loss": 0.6923, "lr": 5e-06, "epoch": 1.234474971772676, "percentage": 30.87, "elapsed_time": "11:06:47", "remaining_time": "1 day, 0:52:58"}
|
| 125 |
+
{"current_steps": 1240, "total_steps": 3984, "loss": 0.6945, "lr": 5e-06, "epoch": 1.2445113536570067, "percentage": 31.12, "elapsed_time": "11:12:06", "remaining_time": "1 day, 0:47:19"}
|
| 126 |
+
{"current_steps": 1250, "total_steps": 3984, "loss": 0.6944, "lr": 5e-06, "epoch": 1.2545477355413372, "percentage": 31.38, "elapsed_time": "11:17:25", "remaining_time": "1 day, 0:41:40"}
|
| 127 |
+
{"current_steps": 1260, "total_steps": 3984, "loss": 0.6959, "lr": 5e-06, "epoch": 1.264584117425668, "percentage": 31.63, "elapsed_time": "11:22:41", "remaining_time": "1 day, 0:35:53"}
|
| 128 |
+
{"current_steps": 1270, "total_steps": 3984, "loss": 0.6957, "lr": 5e-06, "epoch": 1.2746204993099988, "percentage": 31.88, "elapsed_time": "11:27:58", "remaining_time": "1 day, 0:30:13"}
|
| 129 |
+
{"current_steps": 1280, "total_steps": 3984, "loss": 0.6919, "lr": 5e-06, "epoch": 1.2846568811943295, "percentage": 32.13, "elapsed_time": "11:33:17", "remaining_time": "1 day, 0:24:35"}
|
| 130 |
+
{"current_steps": 1290, "total_steps": 3984, "loss": 0.6886, "lr": 5e-06, "epoch": 1.29469326307866, "percentage": 32.38, "elapsed_time": "11:38:37", "remaining_time": "1 day, 0:18:58"}
|
| 131 |
+
{"current_steps": 1300, "total_steps": 3984, "loss": 0.6962, "lr": 5e-06, "epoch": 1.3047296449629908, "percentage": 32.63, "elapsed_time": "11:43:56", "remaining_time": "1 day, 0:13:22"}
|
| 132 |
+
{"current_steps": 1310, "total_steps": 3984, "loss": 0.6972, "lr": 5e-06, "epoch": 1.3147660268473216, "percentage": 32.88, "elapsed_time": "11:49:15", "remaining_time": "1 day, 0:07:45"}
|
| 133 |
+
{"current_steps": 1320, "total_steps": 3984, "loss": 0.6929, "lr": 5e-06, "epoch": 1.3248024087316521, "percentage": 33.13, "elapsed_time": "11:54:32", "remaining_time": "1 day, 0:02:04"}
|
| 134 |
+
{"current_steps": 1330, "total_steps": 3984, "loss": 0.6879, "lr": 5e-06, "epoch": 1.3348387906159829, "percentage": 33.38, "elapsed_time": "11:59:51", "remaining_time": "23:56:27"}
|
| 135 |
+
{"current_steps": 1340, "total_steps": 3984, "loss": 0.6963, "lr": 5e-06, "epoch": 1.3448751725003136, "percentage": 33.63, "elapsed_time": "12:05:08", "remaining_time": "23:50:48"}
|
| 136 |
+
{"current_steps": 1350, "total_steps": 3984, "loss": 0.6879, "lr": 5e-06, "epoch": 1.3549115543846444, "percentage": 33.89, "elapsed_time": "12:10:25", "remaining_time": "23:45:08"}
|
| 137 |
+
{"current_steps": 1360, "total_steps": 3984, "loss": 0.6976, "lr": 5e-06, "epoch": 1.3649479362689751, "percentage": 34.14, "elapsed_time": "12:15:43", "remaining_time": "23:39:30"}
|
| 138 |
+
{"current_steps": 1370, "total_steps": 3984, "loss": 0.6852, "lr": 5e-06, "epoch": 1.3749843181533057, "percentage": 34.39, "elapsed_time": "12:21:00", "remaining_time": "23:33:51"}
|
| 139 |
+
{"current_steps": 1380, "total_steps": 3984, "loss": 0.6948, "lr": 5e-06, "epoch": 1.3850207000376364, "percentage": 34.64, "elapsed_time": "12:26:17", "remaining_time": "23:28:13"}
|
| 140 |
+
{"current_steps": 1390, "total_steps": 3984, "loss": 0.6954, "lr": 5e-06, "epoch": 1.3950570819219672, "percentage": 34.89, "elapsed_time": "12:31:34", "remaining_time": "23:22:34"}
|
| 141 |
+
{"current_steps": 1400, "total_steps": 3984, "loss": 0.6921, "lr": 5e-06, "epoch": 1.4050934638062977, "percentage": 35.14, "elapsed_time": "12:36:54", "remaining_time": "23:17:01"}
|
| 142 |
+
{"current_steps": 1410, "total_steps": 3984, "loss": 0.6907, "lr": 5e-06, "epoch": 1.4151298456906285, "percentage": 35.39, "elapsed_time": "12:42:10", "remaining_time": "23:11:23"}
|
| 143 |
+
{"current_steps": 1420, "total_steps": 3984, "loss": 0.6924, "lr": 5e-06, "epoch": 1.4251662275749593, "percentage": 35.64, "elapsed_time": "12:47:27", "remaining_time": "23:05:45"}
|
| 144 |
+
{"current_steps": 1430, "total_steps": 3984, "loss": 0.696, "lr": 5e-06, "epoch": 1.43520260945929, "percentage": 35.89, "elapsed_time": "12:52:44", "remaining_time": "23:00:07"}
|
| 145 |
+
{"current_steps": 1440, "total_steps": 3984, "loss": 0.6902, "lr": 5e-06, "epoch": 1.4452389913436205, "percentage": 36.14, "elapsed_time": "12:58:03", "remaining_time": "22:54:34"}
|
| 146 |
+
{"current_steps": 1450, "total_steps": 3984, "loss": 0.6921, "lr": 5e-06, "epoch": 1.4552753732279513, "percentage": 36.4, "elapsed_time": "13:03:22", "remaining_time": "22:49:01"}
|
| 147 |
+
{"current_steps": 1460, "total_steps": 3984, "loss": 0.6926, "lr": 5e-06, "epoch": 1.465311755112282, "percentage": 36.65, "elapsed_time": "13:08:41", "remaining_time": "22:43:28"}
|
| 148 |
+
{"current_steps": 1470, "total_steps": 3984, "loss": 0.6924, "lr": 5e-06, "epoch": 1.4753481369966126, "percentage": 36.9, "elapsed_time": "13:14:01", "remaining_time": "22:37:55"}
|
| 149 |
+
{"current_steps": 1480, "total_steps": 3984, "loss": 0.6889, "lr": 5e-06, "epoch": 1.4853845188809434, "percentage": 37.15, "elapsed_time": "13:19:15", "remaining_time": "22:32:15"}
|
| 150 |
+
{"current_steps": 1490, "total_steps": 3984, "loss": 0.6895, "lr": 5e-06, "epoch": 1.4954209007652741, "percentage": 37.4, "elapsed_time": "13:24:32", "remaining_time": "22:26:39"}
|
| 151 |
+
{"current_steps": 1500, "total_steps": 3984, "loss": 0.6955, "lr": 5e-06, "epoch": 1.5054572826496049, "percentage": 37.65, "elapsed_time": "13:29:51", "remaining_time": "22:21:08"}
|
| 152 |
+
{"current_steps": 1510, "total_steps": 3984, "loss": 0.6971, "lr": 5e-06, "epoch": 1.5154936645339356, "percentage": 37.9, "elapsed_time": "13:35:11", "remaining_time": "22:15:36"}
|
| 153 |
+
{"current_steps": 1520, "total_steps": 3984, "loss": 0.695, "lr": 5e-06, "epoch": 1.5255300464182662, "percentage": 38.15, "elapsed_time": "13:40:30", "remaining_time": "22:10:05"}
|
| 154 |
+
{"current_steps": 1530, "total_steps": 3984, "loss": 0.6917, "lr": 5e-06, "epoch": 1.535566428302597, "percentage": 38.4, "elapsed_time": "13:45:49", "remaining_time": "22:04:33"}
|
| 155 |
+
{"current_steps": 1540, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.5456028101869275, "percentage": 38.65, "elapsed_time": "13:51:08", "remaining_time": "21:59:01"}
|
| 156 |
+
{"current_steps": 1550, "total_steps": 3984, "loss": 0.6864, "lr": 5e-06, "epoch": 1.5556391920712582, "percentage": 38.91, "elapsed_time": "13:56:27", "remaining_time": "21:53:30"}
|
| 157 |
+
{"current_steps": 1560, "total_steps": 3984, "loss": 0.6936, "lr": 5e-06, "epoch": 1.565675573955589, "percentage": 39.16, "elapsed_time": "14:01:45", "remaining_time": "21:47:58"}
|
| 158 |
+
{"current_steps": 1570, "total_steps": 3984, "loss": 0.6894, "lr": 5e-06, "epoch": 1.5757119558399197, "percentage": 39.41, "elapsed_time": "14:07:04", "remaining_time": "21:42:26"}
|
| 159 |
+
{"current_steps": 1580, "total_steps": 3984, "loss": 0.693, "lr": 5e-06, "epoch": 1.5857483377242505, "percentage": 39.66, "elapsed_time": "14:12:21", "remaining_time": "21:36:52"}
|
| 160 |
+
{"current_steps": 1590, "total_steps": 3984, "loss": 0.692, "lr": 5e-06, "epoch": 1.5957847196085813, "percentage": 39.91, "elapsed_time": "14:17:37", "remaining_time": "21:31:17"}
|
| 161 |
+
{"current_steps": 1600, "total_steps": 3984, "loss": 0.6916, "lr": 5e-06, "epoch": 1.6058211014929118, "percentage": 40.16, "elapsed_time": "14:22:55", "remaining_time": "21:25:45"}
|
| 162 |
+
{"current_steps": 1610, "total_steps": 3984, "loss": 0.6867, "lr": 5e-06, "epoch": 1.6158574833772426, "percentage": 40.41, "elapsed_time": "14:28:14", "remaining_time": "21:20:15"}
|
| 163 |
+
{"current_steps": 1620, "total_steps": 3984, "loss": 0.6897, "lr": 5e-06, "epoch": 1.625893865261573, "percentage": 40.66, "elapsed_time": "14:33:33", "remaining_time": "21:14:44"}
|
| 164 |
+
{"current_steps": 1630, "total_steps": 3984, "loss": 0.6921, "lr": 5e-06, "epoch": 1.6359302471459038, "percentage": 40.91, "elapsed_time": "14:38:49", "remaining_time": "21:09:10"}
|
| 165 |
+
{"current_steps": 1640, "total_steps": 3984, "loss": 0.6848, "lr": 5e-06, "epoch": 1.6459666290302346, "percentage": 41.16, "elapsed_time": "14:44:07", "remaining_time": "21:03:39"}
|
| 166 |
+
{"current_steps": 1650, "total_steps": 3984, "loss": 0.69, "lr": 5e-06, "epoch": 1.6560030109145654, "percentage": 41.42, "elapsed_time": "14:49:27", "remaining_time": "20:58:10"}
|
| 167 |
+
{"current_steps": 1660, "total_steps": 3984, "loss": 0.6986, "lr": 5e-06, "epoch": 1.6660393927988961, "percentage": 41.67, "elapsed_time": "14:54:47", "remaining_time": "20:52:42"}
|
| 168 |
+
{"current_steps": 1670, "total_steps": 3984, "loss": 0.6908, "lr": 5e-06, "epoch": 1.6760757746832267, "percentage": 41.92, "elapsed_time": "15:00:05", "remaining_time": "20:47:11"}
|
| 169 |
+
{"current_steps": 1680, "total_steps": 3984, "loss": 0.6914, "lr": 5e-06, "epoch": 1.6861121565675574, "percentage": 42.17, "elapsed_time": "15:05:23", "remaining_time": "20:41:40"}
|
| 170 |
+
{"current_steps": 1690, "total_steps": 3984, "loss": 0.6921, "lr": 5e-06, "epoch": 1.696148538451888, "percentage": 42.42, "elapsed_time": "15:10:42", "remaining_time": "20:36:11"}
|
| 171 |
+
{"current_steps": 1700, "total_steps": 3984, "loss": 0.6906, "lr": 5e-06, "epoch": 1.7061849203362187, "percentage": 42.67, "elapsed_time": "15:16:02", "remaining_time": "20:30:44"}
|
| 172 |
+
{"current_steps": 1710, "total_steps": 3984, "loss": 0.6943, "lr": 5e-06, "epoch": 1.7162213022205495, "percentage": 42.92, "elapsed_time": "15:21:19", "remaining_time": "20:25:12"}
|
| 173 |
+
{"current_steps": 1720, "total_steps": 3984, "loss": 0.69, "lr": 5e-06, "epoch": 1.7262576841048802, "percentage": 43.17, "elapsed_time": "15:26:37", "remaining_time": "20:19:41"}
|
| 174 |
+
{"current_steps": 1730, "total_steps": 3984, "loss": 0.6892, "lr": 5e-06, "epoch": 1.736294065989211, "percentage": 43.42, "elapsed_time": "15:31:55", "remaining_time": "20:14:11"}
|
| 175 |
+
{"current_steps": 1740, "total_steps": 3984, "loss": 0.6915, "lr": 5e-06, "epoch": 1.7463304478735417, "percentage": 43.67, "elapsed_time": "15:37:13", "remaining_time": "20:08:42"}
|
| 176 |
+
{"current_steps": 1750, "total_steps": 3984, "loss": 0.6946, "lr": 5e-06, "epoch": 1.7563668297578723, "percentage": 43.93, "elapsed_time": "15:42:32", "remaining_time": "20:03:13"}
|
| 177 |
+
{"current_steps": 1760, "total_steps": 3984, "loss": 0.6888, "lr": 5e-06, "epoch": 1.7664032116422028, "percentage": 44.18, "elapsed_time": "15:47:51", "remaining_time": "19:57:45"}
|
| 178 |
+
{"current_steps": 1770, "total_steps": 3984, "loss": 0.687, "lr": 5e-06, "epoch": 1.7764395935265336, "percentage": 44.43, "elapsed_time": "15:53:08", "remaining_time": "19:52:14"}
|
| 179 |
+
{"current_steps": 1780, "total_steps": 3984, "loss": 0.6888, "lr": 5e-06, "epoch": 1.7864759754108643, "percentage": 44.68, "elapsed_time": "15:58:26", "remaining_time": "19:46:45"}
|
| 180 |
+
{"current_steps": 1790, "total_steps": 3984, "loss": 0.697, "lr": 5e-06, "epoch": 1.796512357295195, "percentage": 44.93, "elapsed_time": "16:03:46", "remaining_time": "19:41:18"}
|
| 181 |
+
{"current_steps": 1800, "total_steps": 3984, "loss": 0.6939, "lr": 5e-06, "epoch": 1.8065487391795259, "percentage": 45.18, "elapsed_time": "16:09:06", "remaining_time": "19:35:50"}
|
| 182 |
+
{"current_steps": 1810, "total_steps": 3984, "loss": 0.6904, "lr": 5e-06, "epoch": 1.8165851210638566, "percentage": 45.43, "elapsed_time": "16:14:26", "remaining_time": "19:30:23"}
|
| 183 |
+
{"current_steps": 1820, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.8266215029481871, "percentage": 45.68, "elapsed_time": "16:19:45", "remaining_time": "19:24:56"}
|
| 184 |
+
{"current_steps": 1830, "total_steps": 3984, "loss": 0.6882, "lr": 5e-06, "epoch": 1.836657884832518, "percentage": 45.93, "elapsed_time": "16:25:03", "remaining_time": "19:19:28"}
|
| 185 |
+
{"current_steps": 1840, "total_steps": 3984, "loss": 0.6922, "lr": 5e-06, "epoch": 1.8466942667168484, "percentage": 46.18, "elapsed_time": "16:30:23", "remaining_time": "19:14:01"}
|
| 186 |
+
{"current_steps": 1850, "total_steps": 3984, "loss": 0.6922, "lr": 5e-06, "epoch": 1.8567306486011792, "percentage": 46.44, "elapsed_time": "16:35:43", "remaining_time": "19:08:34"}
|
| 187 |
+
{"current_steps": 1860, "total_steps": 3984, "loss": 0.6885, "lr": 5e-06, "epoch": 1.86676703048551, "percentage": 46.69, "elapsed_time": "16:41:02", "remaining_time": "19:03:07"}
|
| 188 |
+
{"current_steps": 1870, "total_steps": 3984, "loss": 0.6881, "lr": 5e-06, "epoch": 1.8768034123698407, "percentage": 46.94, "elapsed_time": "16:46:23", "remaining_time": "18:57:42"}
|
| 189 |
+
{"current_steps": 1880, "total_steps": 3984, "loss": 0.6862, "lr": 5e-06, "epoch": 1.8868397942541715, "percentage": 47.19, "elapsed_time": "16:51:41", "remaining_time": "18:52:13"}
|
| 190 |
+
{"current_steps": 1890, "total_steps": 3984, "loss": 0.6917, "lr": 5e-06, "epoch": 1.8968761761385022, "percentage": 47.44, "elapsed_time": "16:57:01", "remaining_time": "18:46:47"}
|
| 191 |
+
{"current_steps": 1900, "total_steps": 3984, "loss": 0.6888, "lr": 5e-06, "epoch": 1.9069125580228328, "percentage": 47.69, "elapsed_time": "17:02:20", "remaining_time": "18:41:20"}
|
| 192 |
+
{"current_steps": 1910, "total_steps": 3984, "loss": 0.6872, "lr": 5e-06, "epoch": 1.9169489399071633, "percentage": 47.94, "elapsed_time": "17:07:38", "remaining_time": "18:35:52"}
|
| 193 |
+
{"current_steps": 1920, "total_steps": 3984, "loss": 0.6947, "lr": 5e-06, "epoch": 1.926985321791494, "percentage": 48.19, "elapsed_time": "17:12:58", "remaining_time": "18:30:26"}
|
| 194 |
+
{"current_steps": 1930, "total_steps": 3984, "loss": 0.6888, "lr": 5e-06, "epoch": 1.9370217036758248, "percentage": 48.44, "elapsed_time": "17:18:17", "remaining_time": "18:25:00"}
|
| 195 |
+
{"current_steps": 1940, "total_steps": 3984, "loss": 0.6884, "lr": 5e-06, "epoch": 1.9470580855601556, "percentage": 48.69, "elapsed_time": "17:23:37", "remaining_time": "18:19:34"}
|
| 196 |
+
{"current_steps": 1950, "total_steps": 3984, "loss": 0.6886, "lr": 5e-06, "epoch": 1.9570944674444863, "percentage": 48.95, "elapsed_time": "17:28:56", "remaining_time": "18:14:07"}
|
| 197 |
+
{"current_steps": 1960, "total_steps": 3984, "loss": 0.6873, "lr": 5e-06, "epoch": 1.967130849328817, "percentage": 49.2, "elapsed_time": "17:34:15", "remaining_time": "18:08:41"}
|
| 198 |
+
{"current_steps": 1970, "total_steps": 3984, "loss": 0.6895, "lr": 5e-06, "epoch": 1.9771672312131476, "percentage": 49.45, "elapsed_time": "17:39:32", "remaining_time": "18:03:12"}
|
| 199 |
+
{"current_steps": 1980, "total_steps": 3984, "loss": 0.6886, "lr": 5e-06, "epoch": 1.9872036130974784, "percentage": 49.7, "elapsed_time": "17:44:50", "remaining_time": "17:57:44"}
|
| 200 |
+
{"current_steps": 1990, "total_steps": 3984, "loss": 0.6923, "lr": 5e-06, "epoch": 1.997239994981809, "percentage": 49.95, "elapsed_time": "17:50:07", "remaining_time": "17:52:16"}
|
| 201 |
+
{"current_steps": 1992, "total_steps": 3984, "eval_loss": 0.7167317867279053, "epoch": 1.999247271358675, "percentage": 50.0, "elapsed_time": "18:02:52", "remaining_time": "18:02:52"}
|