Training in progress, step 1500
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +51 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100059752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b434372cd13b8123950c7cf96d3f396bf051c39dbe0e9c9873a07adedda412
|
3 |
size 100059752
|
trainer_log.jsonl
CHANGED
@@ -100,3 +100,54 @@
|
|
100 |
{"current_steps": 990, "total_steps": 1770, "loss": 1.2163, "accuracy": 0.6312500238418579, "learning_rate": 2.0369703571452387e-06, "epoch": 1.676545300592718, "percentage": 55.93, "elapsed_time": "3:36:53", "remaining_time": "2:50:53"}
|
101 |
{"current_steps": 1000, "total_steps": 1770, "loss": 1.3103, "accuracy": 0.59375, "learning_rate": 1.993438056859441e-06, "epoch": 1.6934801016088061, "percentage": 56.5, "elapsed_time": "3:39:04", "remaining_time": "2:48:41"}
|
102 |
{"current_steps": 1000, "total_steps": 1770, "eval_loss": 1.3313392400741577, "epoch": 1.6934801016088061, "percentage": 56.5, "elapsed_time": "3:42:46", "remaining_time": "2:51:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
{"current_steps": 990, "total_steps": 1770, "loss": 1.2163, "accuracy": 0.6312500238418579, "learning_rate": 2.0369703571452387e-06, "epoch": 1.676545300592718, "percentage": 55.93, "elapsed_time": "3:36:53", "remaining_time": "2:50:53"}
|
101 |
{"current_steps": 1000, "total_steps": 1770, "loss": 1.3103, "accuracy": 0.59375, "learning_rate": 1.993438056859441e-06, "epoch": 1.6934801016088061, "percentage": 56.5, "elapsed_time": "3:39:04", "remaining_time": "2:48:41"}
|
102 |
{"current_steps": 1000, "total_steps": 1770, "eval_loss": 1.3313392400741577, "epoch": 1.6934801016088061, "percentage": 56.5, "elapsed_time": "3:42:46", "remaining_time": "2:51:32"}
|
103 |
+
{"current_steps": 1010, "total_steps": 1770, "loss": 1.2981, "accuracy": 0.5625, "learning_rate": 1.9500653531031917e-06, "epoch": 1.710414902624894, "percentage": 57.06, "elapsed_time": "3:44:59", "remaining_time": "2:49:18"}
|
104 |
+
{"current_steps": 1020, "total_steps": 1770, "loss": 1.3076, "accuracy": 0.5625, "learning_rate": 1.9068659108055117e-06, "epoch": 1.7273497036409822, "percentage": 57.63, "elapsed_time": "3:47:23", "remaining_time": "2:47:11"}
|
105 |
+
{"current_steps": 1030, "total_steps": 1770, "loss": 1.1465, "accuracy": 0.606249988079071, "learning_rate": 1.863853340307962e-06, "epoch": 1.7442845046570703, "percentage": 58.19, "elapsed_time": "3:49:32", "remaining_time": "2:44:55"}
|
106 |
+
{"current_steps": 1040, "total_steps": 1770, "loss": 1.3013, "accuracy": 0.612500011920929, "learning_rate": 1.8210411930766019e-06, "epoch": 1.7612193056731584, "percentage": 58.76, "elapsed_time": "3:51:44", "remaining_time": "2:42:39"}
|
107 |
+
{"current_steps": 1050, "total_steps": 1770, "loss": 1.2597, "accuracy": 0.625, "learning_rate": 1.7784429574324803e-06, "epoch": 1.7781541066892466, "percentage": 59.32, "elapsed_time": "3:53:55", "remaining_time": "2:40:24"}
|
108 |
+
{"current_steps": 1060, "total_steps": 1770, "loss": 1.2883, "accuracy": 0.5375000238418579, "learning_rate": 1.7360720543020327e-06, "epoch": 1.7950889077053345, "percentage": 59.89, "elapsed_time": "3:56:05", "remaining_time": "2:38:07"}
|
109 |
+
{"current_steps": 1070, "total_steps": 1770, "loss": 1.3393, "accuracy": 0.574999988079071, "learning_rate": 1.6939418329887042e-06, "epoch": 1.8120237087214224, "percentage": 60.45, "elapsed_time": "3:58:16", "remaining_time": "2:35:52"}
|
110 |
+
{"current_steps": 1080, "total_steps": 1770, "loss": 1.3404, "accuracy": 0.4937500059604645, "learning_rate": 1.6520655669671467e-06, "epoch": 1.8289585097375105, "percentage": 61.02, "elapsed_time": "4:00:24", "remaining_time": "2:33:35"}
|
111 |
+
{"current_steps": 1090, "total_steps": 1770, "loss": 1.356, "accuracy": 0.5375000238418579, "learning_rate": 1.610456449701294e-06, "epoch": 1.8458933107535986, "percentage": 61.58, "elapsed_time": "4:02:30", "remaining_time": "2:31:17"}
|
112 |
+
{"current_steps": 1100, "total_steps": 1770, "loss": 1.3787, "accuracy": 0.6187499761581421, "learning_rate": 1.5691275904876545e-06, "epoch": 1.8628281117696868, "percentage": 62.15, "elapsed_time": "4:04:34", "remaining_time": "2:28:58"}
|
113 |
+
{"current_steps": 1110, "total_steps": 1770, "loss": 1.2855, "accuracy": 0.543749988079071, "learning_rate": 1.5280920103251235e-06, "epoch": 1.879762912785775, "percentage": 62.71, "elapsed_time": "4:06:41", "remaining_time": "2:26:41"}
|
114 |
+
{"current_steps": 1120, "total_steps": 1770, "loss": 1.3108, "accuracy": 0.59375, "learning_rate": 1.4873626378126015e-06, "epoch": 1.8966977138018628, "percentage": 63.28, "elapsed_time": "4:08:47", "remaining_time": "2:24:23"}
|
115 |
+
{"current_steps": 1130, "total_steps": 1770, "loss": 1.2889, "accuracy": 0.5687500238418579, "learning_rate": 1.446952305075738e-06, "epoch": 1.913632514817951, "percentage": 63.84, "elapsed_time": "4:10:51", "remaining_time": "2:22:04"}
|
116 |
+
{"current_steps": 1140, "total_steps": 1770, "loss": 1.3124, "accuracy": 0.606249988079071, "learning_rate": 1.406873743724065e-06, "epoch": 1.9305673158340388, "percentage": 64.41, "elapsed_time": "4:13:02", "remaining_time": "2:19:50"}
|
117 |
+
{"current_steps": 1150, "total_steps": 1770, "loss": 1.212, "accuracy": 0.543749988079071, "learning_rate": 1.3671395808397898e-06, "epoch": 1.947502116850127, "percentage": 64.97, "elapsed_time": "4:15:16", "remaining_time": "2:17:37"}
|
118 |
+
{"current_steps": 1160, "total_steps": 1770, "loss": 1.2708, "accuracy": 0.5562499761581421, "learning_rate": 1.3277623349995418e-06, "epoch": 1.964436917866215, "percentage": 65.54, "elapsed_time": "4:17:14", "remaining_time": "2:15:16"}
|
119 |
+
{"current_steps": 1170, "total_steps": 1770, "loss": 1.3554, "accuracy": 0.48750001192092896, "learning_rate": 1.2887544123302781e-06, "epoch": 1.9813717188823032, "percentage": 66.1, "elapsed_time": "4:19:15", "remaining_time": "2:12:57"}
|
120 |
+
{"current_steps": 1180, "total_steps": 1770, "loss": 1.2795, "accuracy": 0.4937500059604645, "learning_rate": 1.2501281026006393e-06, "epoch": 1.9983065198983911, "percentage": 66.67, "elapsed_time": "4:21:15", "remaining_time": "2:10:37"}
|
121 |
+
{"current_steps": 1190, "total_steps": 1770, "loss": 1.3511, "accuracy": 0.5687500238418579, "learning_rate": 1.2118955753489523e-06, "epoch": 2.015241320914479, "percentage": 67.23, "elapsed_time": "4:23:27", "remaining_time": "2:08:24"}
|
122 |
+
{"current_steps": 1200, "total_steps": 1770, "loss": 1.3467, "accuracy": 0.5562499761581421, "learning_rate": 1.1740688760491189e-06, "epoch": 2.032176121930567, "percentage": 67.8, "elapsed_time": "4:25:35", "remaining_time": "2:06:09"}
|
123 |
+
{"current_steps": 1210, "total_steps": 1770, "loss": 1.2695, "accuracy": 0.5625, "learning_rate": 1.1366599223155847e-06, "epoch": 2.0491109229466553, "percentage": 68.36, "elapsed_time": "4:27:41", "remaining_time": "2:03:53"}
|
124 |
+
{"current_steps": 1220, "total_steps": 1770, "loss": 1.306, "accuracy": 0.53125, "learning_rate": 1.0996805001486067e-06, "epoch": 2.0660457239627434, "percentage": 68.93, "elapsed_time": "4:29:48", "remaining_time": "2:01:38"}
|
125 |
+
{"current_steps": 1230, "total_steps": 1770, "loss": 1.3487, "accuracy": 0.574999988079071, "learning_rate": 1.0631422602209608e-06, "epoch": 2.0829805249788316, "percentage": 69.49, "elapsed_time": "4:32:01", "remaining_time": "1:59:25"}
|
126 |
+
{"current_steps": 1240, "total_steps": 1770, "loss": 1.3792, "accuracy": 0.581250011920929, "learning_rate": 1.027056714207319e-06, "epoch": 2.0999153259949197, "percentage": 70.06, "elapsed_time": "4:34:20", "remaining_time": "1:57:15"}
|
127 |
+
{"current_steps": 1250, "total_steps": 1770, "loss": 1.1253, "accuracy": 0.581250011920929, "learning_rate": 9.914352311573838e-07, "epoch": 2.116850127011008, "percentage": 70.62, "elapsed_time": "4:36:27", "remaining_time": "1:55:00"}
|
128 |
+
{"current_steps": 1260, "total_steps": 1770, "loss": 1.2498, "accuracy": 0.550000011920929, "learning_rate": 9.562890339139877e-07, "epoch": 2.1337849280270955, "percentage": 71.19, "elapsed_time": "4:38:31", "remaining_time": "1:52:44"}
|
129 |
+
{"current_steps": 1270, "total_steps": 1770, "loss": 1.2522, "accuracy": 0.59375, "learning_rate": 9.216291955772374e-07, "epoch": 2.1507197290431836, "percentage": 71.75, "elapsed_time": "4:40:32", "remaining_time": "1:50:26"}
|
130 |
+
{"current_steps": 1280, "total_steps": 1770, "loss": 1.2333, "accuracy": 0.5062500238418579, "learning_rate": 8.874666360158457e-07, "epoch": 2.167654530059272, "percentage": 72.32, "elapsed_time": "4:42:45", "remaining_time": "1:48:14"}
|
131 |
+
{"current_steps": 1290, "total_steps": 1770, "loss": 1.1702, "accuracy": 0.550000011920929, "learning_rate": 8.538121184267315e-07, "epoch": 2.18458933107536, "percentage": 72.88, "elapsed_time": "4:44:48", "remaining_time": "1:45:58"}
|
132 |
+
{"current_steps": 1300, "total_steps": 1770, "loss": 1.2819, "accuracy": 0.574999988079071, "learning_rate": 8.206762459439907e-07, "epoch": 2.201524132091448, "percentage": 73.45, "elapsed_time": "4:46:55", "remaining_time": "1:43:44"}
|
133 |
+
{"current_steps": 1310, "total_steps": 1770, "loss": 1.3177, "accuracy": 0.5687500238418579, "learning_rate": 7.880694582982898e-07, "epoch": 2.218458933107536, "percentage": 74.01, "elapsed_time": "4:49:05", "remaining_time": "1:41:30"}
|
134 |
+
{"current_steps": 1320, "total_steps": 1770, "loss": 1.2905, "accuracy": 0.5062500238418579, "learning_rate": 7.560020285277401e-07, "epoch": 2.235393734123624, "percentage": 74.58, "elapsed_time": "4:51:06", "remaining_time": "1:39:14"}
|
135 |
+
{"current_steps": 1330, "total_steps": 1770, "loss": 1.3196, "accuracy": 0.5249999761581421, "learning_rate": 7.244840597412956e-07, "epoch": 2.252328535139712, "percentage": 75.14, "elapsed_time": "4:53:13", "remaining_time": "1:37:00"}
|
136 |
+
{"current_steps": 1340, "total_steps": 1770, "loss": 1.2872, "accuracy": 0.5562499761581421, "learning_rate": 6.935254819356796e-07, "epoch": 2.2692633361558, "percentage": 75.71, "elapsed_time": "4:55:18", "remaining_time": "1:34:45"}
|
137 |
+
{"current_steps": 1350, "total_steps": 1770, "loss": 1.1808, "accuracy": 0.625, "learning_rate": 6.631360488668662e-07, "epoch": 2.2861981371718882, "percentage": 76.27, "elapsed_time": "4:57:23", "remaining_time": "1:32:31"}
|
138 |
+
{"current_steps": 1360, "total_steps": 1770, "loss": 1.3274, "accuracy": 0.574999988079071, "learning_rate": 6.333253349770672e-07, "epoch": 2.3031329381879764, "percentage": 76.84, "elapsed_time": "4:59:30", "remaining_time": "1:30:17"}
|
139 |
+
{"current_steps": 1370, "total_steps": 1770, "loss": 1.2175, "accuracy": 0.6187499761581421, "learning_rate": 6.041027323782364e-07, "epoch": 2.3200677392040645, "percentage": 77.4, "elapsed_time": "5:01:42", "remaining_time": "1:28:05"}
|
140 |
+
{"current_steps": 1380, "total_steps": 1770, "loss": 1.2822, "accuracy": 0.5625, "learning_rate": 5.754774478929969e-07, "epoch": 2.337002540220152, "percentage": 77.97, "elapsed_time": "5:03:59", "remaining_time": "1:25:54"}
|
141 |
+
{"current_steps": 1390, "total_steps": 1770, "loss": 1.2119, "accuracy": 0.5562499761581421, "learning_rate": 5.474585001539634e-07, "epoch": 2.3539373412362403, "percentage": 78.53, "elapsed_time": "5:06:06", "remaining_time": "1:23:40"}
|
142 |
+
{"current_steps": 1400, "total_steps": 1770, "loss": 1.2975, "accuracy": 0.5874999761581421, "learning_rate": 5.200547167623424e-07, "epoch": 2.3708721422523285, "percentage": 79.1, "elapsed_time": "5:08:14", "remaining_time": "1:21:27"}
|
143 |
+
{"current_steps": 1410, "total_steps": 1770, "loss": 1.2494, "accuracy": 0.59375, "learning_rate": 4.932747315067271e-07, "epoch": 2.3878069432684166, "percentage": 79.66, "elapsed_time": "5:10:29", "remaining_time": "1:19:16"}
|
144 |
+
{"current_steps": 1420, "total_steps": 1770, "loss": 1.2374, "accuracy": 0.59375, "learning_rate": 4.6712698164294553e-07, "epoch": 2.4047417442845047, "percentage": 80.23, "elapsed_time": "5:12:42", "remaining_time": "1:17:04"}
|
145 |
+
{"current_steps": 1430, "total_steps": 1770, "loss": 1.3027, "accuracy": 0.637499988079071, "learning_rate": 4.41619705235842e-07, "epoch": 2.421676545300593, "percentage": 80.79, "elapsed_time": "5:14:55", "remaining_time": "1:14:52"}
|
146 |
+
{"current_steps": 1440, "total_steps": 1770, "loss": 1.3255, "accuracy": 0.581250011920929, "learning_rate": 4.167609385637961e-07, "epoch": 2.438611346316681, "percentage": 81.36, "elapsed_time": "5:17:04", "remaining_time": "1:12:39"}
|
147 |
+
{"current_steps": 1450, "total_steps": 1770, "loss": 1.2391, "accuracy": 0.5249999761581421, "learning_rate": 3.9255851358683567e-07, "epoch": 2.4555461473327687, "percentage": 81.92, "elapsed_time": "5:19:17", "remaining_time": "1:10:27"}
|
148 |
+
{"current_steps": 1460, "total_steps": 1770, "loss": 1.2682, "accuracy": 0.574999988079071, "learning_rate": 3.690200554791082e-07, "epoch": 2.472480948348857, "percentage": 82.49, "elapsed_time": "5:21:21", "remaining_time": "1:08:13"}
|
149 |
+
{"current_steps": 1470, "total_steps": 1770, "loss": 1.2931, "accuracy": 0.5249999761581421, "learning_rate": 3.461529802265079e-07, "epoch": 2.489415749364945, "percentage": 83.05, "elapsed_time": "5:23:31", "remaining_time": "1:06:01"}
|
150 |
+
{"current_steps": 1480, "total_steps": 1770, "loss": 1.3096, "accuracy": 0.581250011920929, "learning_rate": 3.2396449229020883e-07, "epoch": 2.506350550381033, "percentage": 83.62, "elapsed_time": "5:25:41", "remaining_time": "1:03:49"}
|
151 |
+
{"current_steps": 1490, "total_steps": 1770, "loss": 1.2608, "accuracy": 0.574999988079071, "learning_rate": 3.024615823368371e-07, "epoch": 2.523285351397121, "percentage": 84.18, "elapsed_time": "5:27:34", "remaining_time": "1:01:33"}
|
152 |
+
{"current_steps": 1500, "total_steps": 1770, "loss": 1.2057, "accuracy": 0.5625, "learning_rate": 2.8165102503600716e-07, "epoch": 2.5402201524132093, "percentage": 84.75, "elapsed_time": "5:29:42", "remaining_time": "0:59:20"}
|
153 |
+
{"current_steps": 1500, "total_steps": 1770, "eval_loss": 1.3159173727035522, "epoch": 2.5402201524132093, "percentage": 84.75, "elapsed_time": "5:33:24", "remaining_time": "1:00:00"}
|