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 645976488
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:321755b19ccccc82f2199431da16e1458df733c7525b9527d1219ff07b607267
|
3 |
size 645976488
|
trainer_log.jsonl
CHANGED
@@ -99,3 +99,54 @@
|
|
99 |
{"current_steps": 980, "total_steps": 3573, "loss": 1.3333, "lr": 4.552268682664045e-05, "epoch": 0.8228379513014273, "percentage": 27.43, "elapsed_time": "0:21:19", "remaining_time": "0:56:24"}
|
100 |
{"current_steps": 990, "total_steps": 3573, "loss": 1.3182, "lr": 4.538220366540713e-05, "epoch": 0.8312342569269522, "percentage": 27.71, "elapsed_time": "0:21:31", "remaining_time": "0:56:09"}
|
101 |
{"current_steps": 1000, "total_steps": 3573, "loss": 1.3494, "lr": 4.52397743131194e-05, "epoch": 0.8396305625524769, "percentage": 27.99, "elapsed_time": "0:21:43", "remaining_time": "0:55:53"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
{"current_steps": 980, "total_steps": 3573, "loss": 1.3333, "lr": 4.552268682664045e-05, "epoch": 0.8228379513014273, "percentage": 27.43, "elapsed_time": "0:21:19", "remaining_time": "0:56:24"}
|
100 |
{"current_steps": 990, "total_steps": 3573, "loss": 1.3182, "lr": 4.538220366540713e-05, "epoch": 0.8312342569269522, "percentage": 27.71, "elapsed_time": "0:21:31", "remaining_time": "0:56:09"}
|
101 |
{"current_steps": 1000, "total_steps": 3573, "loss": 1.3494, "lr": 4.52397743131194e-05, "epoch": 0.8396305625524769, "percentage": 27.99, "elapsed_time": "0:21:43", "remaining_time": "0:55:53"}
|
102 |
+
{"current_steps": 1010, "total_steps": 3573, "loss": 1.3372, "lr": 4.509541236961835e-05, "epoch": 0.8480268681780017, "percentage": 28.27, "elapsed_time": "0:22:17", "remaining_time": "0:56:35"}
|
103 |
+
{"current_steps": 1020, "total_steps": 3573, "loss": 1.3459, "lr": 4.4949131619278233e-05, "epoch": 0.8564231738035264, "percentage": 28.55, "elapsed_time": "0:22:30", "remaining_time": "0:56:19"}
|
104 |
+
{"current_steps": 1030, "total_steps": 3573, "loss": 1.3288, "lr": 4.4800946029690205e-05, "epoch": 0.8648194794290512, "percentage": 28.83, "elapsed_time": "0:22:42", "remaining_time": "0:56:03"}
|
105 |
+
{"current_steps": 1040, "total_steps": 3573, "loss": 1.3524, "lr": 4.465086975032866e-05, "epoch": 0.873215785054576, "percentage": 29.11, "elapsed_time": "0:22:54", "remaining_time": "0:55:47"}
|
106 |
+
{"current_steps": 1050, "total_steps": 3573, "loss": 1.3233, "lr": 4.4498917111200154e-05, "epoch": 0.8816120906801007, "percentage": 29.39, "elapsed_time": "0:23:06", "remaining_time": "0:55:31"}
|
107 |
+
{"current_steps": 1060, "total_steps": 3573, "loss": 1.3486, "lr": 4.434510262147514e-05, "epoch": 0.8900083963056256, "percentage": 29.67, "elapsed_time": "0:23:18", "remaining_time": "0:55:15"}
|
108 |
+
{"current_steps": 1070, "total_steps": 3573, "loss": 1.3375, "lr": 4.418944096810253e-05, "epoch": 0.8984047019311503, "percentage": 29.95, "elapsed_time": "0:23:30", "remaining_time": "0:55:00"}
|
109 |
+
{"current_steps": 1080, "total_steps": 3573, "loss": 1.3428, "lr": 4.403194701440733e-05, "epoch": 0.906801007556675, "percentage": 30.23, "elapsed_time": "0:23:42", "remaining_time": "0:54:44"}
|
110 |
+
{"current_steps": 1090, "total_steps": 3573, "loss": 1.3312, "lr": 4.3872635798671384e-05, "epoch": 0.9151973131821999, "percentage": 30.51, "elapsed_time": "0:23:55", "remaining_time": "0:54:29"}
|
111 |
+
{"current_steps": 1100, "total_steps": 3573, "loss": 1.3268, "lr": 4.3711522532697526e-05, "epoch": 0.9235936188077246, "percentage": 30.79, "elapsed_time": "0:24:07", "remaining_time": "0:54:14"}
|
112 |
+
{"current_steps": 1110, "total_steps": 3573, "loss": 1.2904, "lr": 4.354862260035699e-05, "epoch": 0.9319899244332494, "percentage": 31.07, "elapsed_time": "0:24:19", "remaining_time": "0:53:58"}
|
113 |
+
{"current_steps": 1120, "total_steps": 3573, "loss": 1.3352, "lr": 4.338395155612055e-05, "epoch": 0.9403862300587741, "percentage": 31.35, "elapsed_time": "0:24:31", "remaining_time": "0:53:43"}
|
114 |
+
{"current_steps": 1130, "total_steps": 3573, "loss": 1.3327, "lr": 4.321752512357328e-05, "epoch": 0.9487825356842989, "percentage": 31.63, "elapsed_time": "0:24:43", "remaining_time": "0:53:27"}
|
115 |
+
{"current_steps": 1140, "total_steps": 3573, "loss": 1.3293, "lr": 4.304935919391317e-05, "epoch": 0.9571788413098237, "percentage": 31.91, "elapsed_time": "0:24:55", "remaining_time": "0:53:12"}
|
116 |
+
{"current_steps": 1150, "total_steps": 3573, "loss": 1.3171, "lr": 4.2879469824433814e-05, "epoch": 0.9655751469353484, "percentage": 32.19, "elapsed_time": "0:25:08", "remaining_time": "0:52:57"}
|
117 |
+
{"current_steps": 1160, "total_steps": 3573, "loss": 1.3291, "lr": 4.2707873236991116e-05, "epoch": 0.9739714525608733, "percentage": 32.47, "elapsed_time": "0:25:20", "remaining_time": "0:52:42"}
|
118 |
+
{"current_steps": 1170, "total_steps": 3573, "loss": 1.2906, "lr": 4.2534585816454384e-05, "epoch": 0.982367758186398, "percentage": 32.75, "elapsed_time": "0:25:32", "remaining_time": "0:52:27"}
|
119 |
+
{"current_steps": 1180, "total_steps": 3573, "loss": 1.3516, "lr": 4.235962410914185e-05, "epoch": 0.9907640638119227, "percentage": 33.03, "elapsed_time": "0:25:44", "remaining_time": "0:52:12"}
|
120 |
+
{"current_steps": 1190, "total_steps": 3573, "loss": 1.3249, "lr": 4.218300482124069e-05, "epoch": 0.9991603694374476, "percentage": 33.31, "elapsed_time": "0:25:56", "remaining_time": "0:51:57"}
|
121 |
+
{"current_steps": 1200, "total_steps": 3573, "loss": 1.2766, "lr": 4.2004744817211866e-05, "epoch": 1.0075566750629723, "percentage": 33.59, "elapsed_time": "0:26:08", "remaining_time": "0:51:42"}
|
122 |
+
{"current_steps": 1200, "total_steps": 3573, "eval_loss": 1.3506666421890259, "epoch": 1.0075566750629723, "percentage": 33.59, "elapsed_time": "0:26:46", "remaining_time": "0:52:56"}
|
123 |
+
{"current_steps": 1210, "total_steps": 3573, "loss": 1.2816, "lr": 4.182486111817983e-05, "epoch": 1.015952980688497, "percentage": 33.87, "elapsed_time": "0:26:58", "remaining_time": "0:52:40"}
|
124 |
+
{"current_steps": 1220, "total_steps": 3573, "loss": 1.2815, "lr": 4.164337090030727e-05, "epoch": 1.0243492863140218, "percentage": 34.14, "elapsed_time": "0:27:10", "remaining_time": "0:52:24"}
|
125 |
+
{"current_steps": 1230, "total_steps": 3573, "loss": 1.2692, "lr": 4.146029149315502e-05, "epoch": 1.0327455919395465, "percentage": 34.42, "elapsed_time": "0:27:22", "remaining_time": "0:52:08"}
|
126 |
+
{"current_steps": 1240, "total_steps": 3573, "loss": 1.2572, "lr": 4.1275640378027367e-05, "epoch": 1.0411418975650715, "percentage": 34.7, "elapsed_time": "0:27:34", "remaining_time": "0:51:53"}
|
127 |
+
{"current_steps": 1250, "total_steps": 3573, "loss": 1.2636, "lr": 4.108943518630287e-05, "epoch": 1.0495382031905962, "percentage": 34.98, "elapsed_time": "0:27:47", "remaining_time": "0:51:37"}
|
128 |
+
{"current_steps": 1260, "total_steps": 3573, "loss": 1.246, "lr": 4.09016936977508e-05, "epoch": 1.057934508816121, "percentage": 35.26, "elapsed_time": "0:27:59", "remaining_time": "0:51:22"}
|
129 |
+
{"current_steps": 1270, "total_steps": 3573, "loss": 1.2416, "lr": 4.071243383883344e-05, "epoch": 1.0663308144416457, "percentage": 35.54, "elapsed_time": "0:28:11", "remaining_time": "0:51:07"}
|
130 |
+
{"current_steps": 1280, "total_steps": 3573, "loss": 1.2684, "lr": 4.052167368099443e-05, "epoch": 1.0747271200671704, "percentage": 35.82, "elapsed_time": "0:28:23", "remaining_time": "0:50:51"}
|
131 |
+
{"current_steps": 1290, "total_steps": 3573, "loss": 1.2679, "lr": 4.032943143893315e-05, "epoch": 1.0831234256926952, "percentage": 36.1, "elapsed_time": "0:28:35", "remaining_time": "0:50:36"}
|
132 |
+
{"current_steps": 1300, "total_steps": 3573, "loss": 1.2801, "lr": 4.0135725468865545e-05, "epoch": 1.0915197313182199, "percentage": 36.38, "elapsed_time": "0:28:47", "remaining_time": "0:50:21"}
|
133 |
+
{"current_steps": 1310, "total_steps": 3573, "loss": 1.2552, "lr": 3.994057426677135e-05, "epoch": 1.0999160369437448, "percentage": 36.66, "elapsed_time": "0:29:00", "remaining_time": "0:50:05"}
|
134 |
+
{"current_steps": 1320, "total_steps": 3573, "loss": 1.2467, "lr": 3.974399646662804e-05, "epoch": 1.1083123425692696, "percentage": 36.94, "elapsed_time": "0:29:12", "remaining_time": "0:49:50"}
|
135 |
+
{"current_steps": 1330, "total_steps": 3573, "loss": 1.2393, "lr": 3.9546010838631523e-05, "epoch": 1.1167086481947943, "percentage": 37.22, "elapsed_time": "0:29:24", "remaining_time": "0:49:35"}
|
136 |
+
{"current_steps": 1340, "total_steps": 3573, "loss": 1.2413, "lr": 3.9346636287403936e-05, "epoch": 1.125104953820319, "percentage": 37.5, "elapsed_time": "0:29:36", "remaining_time": "0:49:20"}
|
137 |
+
{"current_steps": 1350, "total_steps": 3573, "loss": 1.2344, "lr": 3.9145891850188446e-05, "epoch": 1.1335012594458438, "percentage": 37.78, "elapsed_time": "0:29:48", "remaining_time": "0:49:05"}
|
138 |
+
{"current_steps": 1360, "total_steps": 3573, "loss": 1.2723, "lr": 3.894379669503159e-05, "epoch": 1.1418975650713685, "percentage": 38.06, "elapsed_time": "0:30:00", "remaining_time": "0:48:50"}
|
139 |
+
{"current_steps": 1370, "total_steps": 3573, "loss": 1.2441, "lr": 3.874037011895294e-05, "epoch": 1.1502938706968933, "percentage": 38.34, "elapsed_time": "0:30:12", "remaining_time": "0:48:35"}
|
140 |
+
{"current_steps": 1380, "total_steps": 3573, "loss": 1.2599, "lr": 3.853563154610255e-05, "epoch": 1.1586901763224182, "percentage": 38.62, "elapsed_time": "0:30:25", "remaining_time": "0:48:20"}
|
141 |
+
{"current_steps": 1390, "total_steps": 3573, "loss": 1.2596, "lr": 3.832960052590626e-05, "epoch": 1.167086481947943, "percentage": 38.9, "elapsed_time": "0:30:37", "remaining_time": "0:48:05"}
|
142 |
+
{"current_steps": 1400, "total_steps": 3573, "loss": 1.2679, "lr": 3.812229673119902e-05, "epoch": 1.1754827875734677, "percentage": 39.18, "elapsed_time": "0:30:49", "remaining_time": "0:47:50"}
|
143 |
+
{"current_steps": 1410, "total_steps": 3573, "loss": 1.2893, "lr": 3.791373995634641e-05, "epoch": 1.1838790931989924, "percentage": 39.46, "elapsed_time": "0:31:01", "remaining_time": "0:47:35"}
|
144 |
+
{"current_steps": 1420, "total_steps": 3573, "loss": 1.2858, "lr": 3.770395011535459e-05, "epoch": 1.1922753988245172, "percentage": 39.74, "elapsed_time": "0:31:13", "remaining_time": "0:47:21"}
|
145 |
+
{"current_steps": 1430, "total_steps": 3573, "loss": 1.2544, "lr": 3.749294723996884e-05, "epoch": 1.200671704450042, "percentage": 40.02, "elapsed_time": "0:31:26", "remaining_time": "0:47:06"}
|
146 |
+
{"current_steps": 1440, "total_steps": 3573, "loss": 1.2406, "lr": 3.72807514777608e-05, "epoch": 1.2090680100755669, "percentage": 40.3, "elapsed_time": "0:31:38", "remaining_time": "0:46:51"}
|
147 |
+
{"current_steps": 1450, "total_steps": 3573, "loss": 1.2687, "lr": 3.7067383090204696e-05, "epoch": 1.2174643157010916, "percentage": 40.58, "elapsed_time": "0:31:50", "remaining_time": "0:46:37"}
|
148 |
+
{"current_steps": 1460, "total_steps": 3573, "loss": 1.2529, "lr": 3.6852862450742664e-05, "epoch": 1.2258606213266163, "percentage": 40.86, "elapsed_time": "0:32:02", "remaining_time": "0:46:22"}
|
149 |
+
{"current_steps": 1470, "total_steps": 3573, "loss": 1.2607, "lr": 3.663721004283942e-05, "epoch": 1.234256926952141, "percentage": 41.14, "elapsed_time": "0:32:14", "remaining_time": "0:46:07"}
|
150 |
+
{"current_steps": 1480, "total_steps": 3573, "loss": 1.2633, "lr": 3.642044645802638e-05, "epoch": 1.2426532325776658, "percentage": 41.42, "elapsed_time": "0:32:26", "remaining_time": "0:45:53"}
|
151 |
+
{"current_steps": 1490, "total_steps": 3573, "loss": 1.2631, "lr": 3.620259239393549e-05, "epoch": 1.2510495382031905, "percentage": 41.7, "elapsed_time": "0:32:39", "remaining_time": "0:45:38"}
|
152 |
+
{"current_steps": 1500, "total_steps": 3573, "loss": 1.2323, "lr": 3.5983668652322914e-05, "epoch": 1.2594458438287153, "percentage": 41.98, "elapsed_time": "0:32:51", "remaining_time": "0:45:24"}
|