Training in progress, step 1500
Browse files
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5cf5d935471f1d9c61271d5f771e3c5787e3663731535adca25a1e6a8ea3df8
|
| 3 |
size 83945296
|
runs/Apr30_19-57-14_8db08970-be1a-4a1c-b5b3-fa94198db698-0/events.out.tfevents.1746043104.8db08970-be1a-4a1c-b5b3-fa94198db698-0.45473.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e67baa421784b1a10a49e46741e9f95546e0023fbc162f92452267ab6e5f4e91
|
| 3 |
+
size 108928
|
trainer_log.jsonl
CHANGED
|
@@ -98,3 +98,54 @@
|
|
| 98 |
{"current_steps": 980, "total_steps": 1500, "loss": 0.0274, "accuracy": 0.9609375, "lr": 1.6176735882153284e-06, "epoch": 6.4916943521594686, "percentage": 65.33, "elapsed_time": "4:30:22", "remaining_time": "2:23:27"}
|
| 99 |
{"current_steps": 990, "total_steps": 1500, "loss": 0.0326, "accuracy": 0.953125, "lr": 1.56348351646022e-06, "epoch": 6.558139534883721, "percentage": 66.0, "elapsed_time": "4:33:10", "remaining_time": "2:20:43"}
|
| 100 |
{"current_steps": 1000, "total_steps": 1500, "loss": 0.025, "accuracy": 0.9640624523162842, "lr": 1.509800584902108e-06, "epoch": 6.6245847176079735, "percentage": 66.67, "elapsed_time": "4:35:56", "remaining_time": "2:17:58"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
{"current_steps": 980, "total_steps": 1500, "loss": 0.0274, "accuracy": 0.9609375, "lr": 1.6176735882153284e-06, "epoch": 6.4916943521594686, "percentage": 65.33, "elapsed_time": "4:30:22", "remaining_time": "2:23:27"}
|
| 99 |
{"current_steps": 990, "total_steps": 1500, "loss": 0.0326, "accuracy": 0.953125, "lr": 1.56348351646022e-06, "epoch": 6.558139534883721, "percentage": 66.0, "elapsed_time": "4:33:10", "remaining_time": "2:20:43"}
|
| 100 |
{"current_steps": 1000, "total_steps": 1500, "loss": 0.025, "accuracy": 0.9640624523162842, "lr": 1.509800584902108e-06, "epoch": 6.6245847176079735, "percentage": 66.67, "elapsed_time": "4:35:56", "remaining_time": "2:17:58"}
|
| 101 |
+
{"current_steps": 1010, "total_steps": 1500, "loss": 0.0229, "accuracy": 0.9671874642372131, "lr": 1.4566538637954556e-06, "epoch": 6.691029900332226, "percentage": 67.33, "elapsed_time": "4:38:41", "remaining_time": "2:15:12"}
|
| 102 |
+
{"current_steps": 1020, "total_steps": 1500, "loss": 0.0434, "accuracy": 0.9375, "lr": 1.4040721330273063e-06, "epoch": 6.7574750830564785, "percentage": 68.0, "elapsed_time": "4:41:24", "remaining_time": "2:12:25"}
|
| 103 |
+
{"current_steps": 1030, "total_steps": 1500, "loss": 0.0295, "accuracy": 0.957812488079071, "lr": 1.3520838665324704e-06, "epoch": 6.823920265780731, "percentage": 68.67, "elapsed_time": "4:44:10", "remaining_time": "2:09:40"}
|
| 104 |
+
{"current_steps": 1040, "total_steps": 1500, "loss": 0.0273, "accuracy": 0.9609375, "lr": 1.3007172168743854e-06, "epoch": 6.8903654485049834, "percentage": 69.33, "elapsed_time": "4:46:57", "remaining_time": "2:06:55"}
|
| 105 |
+
{"current_steps": 1050, "total_steps": 1500, "loss": 0.024, "accuracy": 0.965624988079071, "lr": 1.2500000000000007e-06, "epoch": 6.956810631229236, "percentage": 70.0, "elapsed_time": "4:49:42", "remaining_time": "2:04:09"}
|
| 106 |
+
{"current_steps": 1060, "total_steps": 1500, "loss": 0.0337, "accuracy": 0.9490132331848145, "lr": 1.1999596801769617e-06, "epoch": 7.019933554817276, "percentage": 70.67, "elapsed_time": "4:52:21", "remaining_time": "2:01:21"}
|
| 107 |
+
{"current_steps": 1070, "total_steps": 1500, "loss": 0.024, "accuracy": 0.965624988079071, "lr": 1.1506233551212186e-06, "epoch": 7.086378737541528, "percentage": 71.33, "elapsed_time": "4:55:04", "remaining_time": "1:58:35"}
|
| 108 |
+
{"current_steps": 1080, "total_steps": 1500, "loss": 0.0304, "accuracy": 0.956250011920929, "lr": 1.1020177413231334e-06, "epoch": 7.152823920265781, "percentage": 72.0, "elapsed_time": "4:57:47", "remaining_time": "1:55:48"}
|
| 109 |
+
{"current_steps": 1090, "total_steps": 1500, "loss": 0.0348, "accuracy": 0.949999988079071, "lr": 1.0541691595800338e-06, "epoch": 7.219269102990033, "percentage": 72.67, "elapsed_time": "5:00:35", "remaining_time": "1:53:03"}
|
| 110 |
+
{"current_steps": 1100, "total_steps": 1500, "loss": 0.0262, "accuracy": 0.9624999761581421, "lr": 1.0071035207430352e-06, "epoch": 7.285714285714286, "percentage": 73.33, "elapsed_time": "5:03:21", "remaining_time": "1:50:18"}
|
| 111 |
+
{"current_steps": 1110, "total_steps": 1500, "loss": 0.0217, "accuracy": 0.96875, "lr": 9.608463116858544e-07, "epoch": 7.352159468438538, "percentage": 74.0, "elapsed_time": "5:06:07", "remaining_time": "1:47:33"}
|
| 112 |
+
{"current_steps": 1120, "total_steps": 1500, "loss": 0.0284, "accuracy": 0.9593749642372131, "lr": 9.154225815032242e-07, "epoch": 7.4186046511627906, "percentage": 74.67, "elapsed_time": "5:08:47", "remaining_time": "1:44:46"}
|
| 113 |
+
{"current_steps": 1130, "total_steps": 1500, "loss": 0.0273, "accuracy": 0.9609375, "lr": 8.708569279463622e-07, "epoch": 7.485049833887043, "percentage": 75.33, "elapsed_time": "5:11:36", "remaining_time": "1:42:01"}
|
| 114 |
+
{"current_steps": 1140, "total_steps": 1500, "loss": 0.0305, "accuracy": 0.9578125476837158, "lr": 8.271734841028553e-07, "epoch": 7.5514950166112955, "percentage": 76.0, "elapsed_time": "5:14:21", "remaining_time": "1:39:16"}
|
| 115 |
+
{"current_steps": 1150, "total_steps": 1500, "loss": 0.024, "accuracy": 0.965624988079071, "lr": 7.843959053281663e-07, "epoch": 7.617940199335548, "percentage": 76.67, "elapsed_time": "5:17:09", "remaining_time": "1:36:31"}
|
| 116 |
+
{"current_steps": 1160, "total_steps": 1500, "loss": 0.0348, "accuracy": 0.9499999284744263, "lr": 7.425473564358457e-07, "epoch": 7.6843853820598005, "percentage": 77.33, "elapsed_time": "5:19:56", "remaining_time": "1:33:46"}
|
| 117 |
+
{"current_steps": 1170, "total_steps": 1500, "loss": 0.0273, "accuracy": 0.9609375, "lr": 7.016504991533727e-07, "epoch": 7.750830564784053, "percentage": 78.0, "elapsed_time": "5:22:41", "remaining_time": "1:31:00"}
|
| 118 |
+
{"current_steps": 1180, "total_steps": 1500, "loss": 0.038, "accuracy": 0.9468749761581421, "lr": 6.617274798504286e-07, "epoch": 7.8172757475083055, "percentage": 78.67, "elapsed_time": "5:25:28", "remaining_time": "1:28:15"}
|
| 119 |
+
{"current_steps": 1190, "total_steps": 1500, "loss": 0.03, "accuracy": 0.957812488079071, "lr": 6.227999175462521e-07, "epoch": 7.883720930232558, "percentage": 79.33, "elapsed_time": "5:28:12", "remaining_time": "1:25:29"}
|
| 120 |
+
{"current_steps": 1200, "total_steps": 1500, "loss": 0.0282, "accuracy": 0.9593750238418579, "lr": 5.848888922025553e-07, "epoch": 7.95016611295681, "percentage": 80.0, "elapsed_time": "5:30:59", "remaining_time": "1:22:44"}
|
| 121 |
+
{"current_steps": 1210, "total_steps": 1500, "loss": 0.0337, "accuracy": 0.9490132331848145, "lr": 5.48014933308352e-07, "epoch": 8.013289036544851, "percentage": 80.67, "elapsed_time": "5:33:32", "remaining_time": "1:19:56"}
|
| 122 |
+
{"current_steps": 1220, "total_steps": 1500, "loss": 0.0304, "accuracy": 0.9562499523162842, "lr": 5.121980087628802e-07, "epoch": 8.079734219269103, "percentage": 81.33, "elapsed_time": "5:36:17", "remaining_time": "1:17:10"}
|
| 123 |
+
{"current_steps": 1230, "total_steps": 1500, "loss": 0.0229, "accuracy": 0.9671875238418579, "lr": 4.774575140626317e-07, "epoch": 8.146179401993356, "percentage": 82.0, "elapsed_time": "5:39:02", "remaining_time": "1:14:25"}
|
| 124 |
+
{"current_steps": 1240, "total_steps": 1500, "loss": 0.0283, "accuracy": 0.9593749642372131, "lr": 4.438122617983442e-07, "epoch": 8.212624584717608, "percentage": 82.67, "elapsed_time": "5:41:47", "remaining_time": "1:11:40"}
|
| 125 |
+
{"current_steps": 1250, "total_steps": 1500, "loss": 0.0263, "accuracy": 0.9624999761581421, "lr": 4.1128047146765936e-07, "epoch": 8.279069767441861, "percentage": 83.33, "elapsed_time": "5:44:35", "remaining_time": "1:08:55"}
|
| 126 |
+
{"current_steps": 1260, "total_steps": 1500, "loss": 0.0294, "accuracy": 0.957812488079071, "lr": 3.798797596089351e-07, "epoch": 8.345514950166113, "percentage": 84.0, "elapsed_time": "5:47:19", "remaining_time": "1:06:09"}
|
| 127 |
+
{"current_steps": 1270, "total_steps": 1500, "loss": 0.0305, "accuracy": 0.956250011920929, "lr": 3.4962713026158697e-07, "epoch": 8.411960132890366, "percentage": 84.67, "elapsed_time": "5:50:06", "remaining_time": "1:03:24"}
|
| 128 |
+
{"current_steps": 1280, "total_steps": 1500, "loss": 0.0336, "accuracy": 0.9515625238418579, "lr": 3.2053896575809426e-07, "epoch": 8.478405315614618, "percentage": 85.33, "elapsed_time": "5:52:51", "remaining_time": "1:00:38"}
|
| 129 |
+
{"current_steps": 1290, "total_steps": 1500, "loss": 0.0317, "accuracy": 0.9546875357627869, "lr": 2.9263101785268253e-07, "epoch": 8.544850498338871, "percentage": 86.0, "elapsed_time": "5:55:40", "remaining_time": "0:57:53"}
|
| 130 |
+
{"current_steps": 1300, "total_steps": 1500, "loss": 0.0337, "accuracy": 0.9515624642372131, "lr": 2.6591839919146963e-07, "epoch": 8.611295681063122, "percentage": 86.67, "elapsed_time": "5:58:28", "remaining_time": "0:55:08"}
|
| 131 |
+
{"current_steps": 1310, "total_steps": 1500, "loss": 0.0217, "accuracy": 0.9687501192092896, "lr": 2.404155751286988e-07, "epoch": 8.677740863787376, "percentage": 87.33, "elapsed_time": "6:01:15", "remaining_time": "0:52:23"}
|
| 132 |
+
{"current_steps": 1320, "total_steps": 1500, "loss": 0.0255, "accuracy": 0.964062511920929, "lr": 2.1613635589349756e-07, "epoch": 8.744186046511627, "percentage": 88.0, "elapsed_time": "6:03:59", "remaining_time": "0:49:38"}
|
| 133 |
+
{"current_steps": 1330, "total_steps": 1500, "loss": 0.038, "accuracy": 0.9453125596046448, "lr": 1.9309388911139427e-07, "epoch": 8.81063122923588, "percentage": 88.67, "elapsed_time": "6:06:43", "remaining_time": "0:46:52"}
|
| 134 |
+
{"current_steps": 1340, "total_steps": 1500, "loss": 0.0197, "accuracy": 0.9718750715255737, "lr": 1.713006526846439e-07, "epoch": 8.877076411960132, "percentage": 89.33, "elapsed_time": "6:09:30", "remaining_time": "0:44:07"}
|
| 135 |
+
{"current_steps": 1350, "total_steps": 1500, "loss": 0.037, "accuracy": 0.948437511920929, "lr": 1.507684480352292e-07, "epoch": 8.943521594684386, "percentage": 90.0, "elapsed_time": "6:12:18", "remaining_time": "0:41:22"}
|
| 136 |
+
{"current_steps": 1360, "total_steps": 1500, "loss": 0.0293, "accuracy": 0.955592155456543, "lr": 1.31508393714177e-07, "epoch": 9.006644518272426, "percentage": 90.67, "elapsed_time": "6:14:56", "remaining_time": "0:38:35"}
|
| 137 |
+
{"current_steps": 1370, "total_steps": 1500, "loss": 0.0402, "accuracy": 0.942187488079071, "lr": 1.1353091938067024e-07, "epoch": 9.073089700996677, "percentage": 91.33, "elapsed_time": "6:17:37", "remaining_time": "0:35:50"}
|
| 138 |
+
{"current_steps": 1380, "total_steps": 1500, "loss": 0.0272, "accuracy": 0.9609375596046448, "lr": 9.684576015420277e-08, "epoch": 9.13953488372093, "percentage": 92.0, "elapsed_time": "6:20:25", "remaining_time": "0:33:04"}
|
| 139 |
+
{"current_steps": 1390, "total_steps": 1500, "loss": 0.0261, "accuracy": 0.9625000953674316, "lr": 8.146195134284052e-08, "epoch": 9.205980066445182, "percentage": 92.67, "elapsed_time": "6:23:09", "remaining_time": "0:30:19"}
|
| 140 |
+
{"current_steps": 1400, "total_steps": 1500, "loss": 0.0316, "accuracy": 0.9546874761581421, "lr": 6.738782355044048e-08, "epoch": 9.272425249169435, "percentage": 93.33, "elapsed_time": "6:25:51", "remaining_time": "0:27:33"}
|
| 141 |
+
{"current_steps": 1410, "total_steps": 1500, "loss": 0.0186, "accuracy": 0.973437488079071, "lr": 5.463099816548578e-08, "epoch": 9.338870431893687, "percentage": 94.0, "elapsed_time": "6:28:36", "remaining_time": "0:24:48"}
|
| 142 |
+
{"current_steps": 1420, "total_steps": 1500, "loss": 0.0295, "accuracy": 0.957812488079071, "lr": 4.319838323396691e-08, "epoch": 9.40531561461794, "percentage": 94.67, "elapsed_time": "6:31:21", "remaining_time": "0:22:02"}
|
| 143 |
+
{"current_steps": 1430, "total_steps": 1500, "loss": 0.0293, "accuracy": 0.9593750238418579, "lr": 3.309616971855195e-08, "epoch": 9.471760797342192, "percentage": 95.33, "elapsed_time": "6:34:05", "remaining_time": "0:19:17"}
|
| 144 |
+
{"current_steps": 1440, "total_steps": 1500, "loss": 0.0349, "accuracy": 0.949999988079071, "lr": 2.4329828146074096e-08, "epoch": 9.538205980066445, "percentage": 96.0, "elapsed_time": "6:36:51", "remaining_time": "0:16:32"}
|
| 145 |
+
{"current_steps": 1450, "total_steps": 1500, "loss": 0.0298, "accuracy": 0.957812488079071, "lr": 1.6904105645142443e-08, "epoch": 9.604651162790697, "percentage": 96.67, "elapsed_time": "6:39:37", "remaining_time": "0:13:46"}
|
| 146 |
+
{"current_steps": 1460, "total_steps": 1500, "loss": 0.0207, "accuracy": 0.9703124761581421, "lr": 1.0823023375489128e-08, "epoch": 9.67109634551495, "percentage": 97.33, "elapsed_time": "6:42:20", "remaining_time": "0:11:01"}
|
| 147 |
+
{"current_steps": 1470, "total_steps": 1500, "loss": 0.0338, "accuracy": 0.9515625238418579, "lr": 6.089874350439507e-09, "epoch": 9.737541528239202, "percentage": 98.0, "elapsed_time": "6:45:07", "remaining_time": "0:08:16"}
|
| 148 |
+
{"current_steps": 1480, "total_steps": 1500, "loss": 0.0359, "accuracy": 0.9484375715255737, "lr": 2.7072216536885855e-09, "epoch": 9.803986710963455, "percentage": 98.67, "elapsed_time": "6:47:52", "remaining_time": "0:05:30"}
|
| 149 |
+
{"current_steps": 1490, "total_steps": 1500, "loss": 0.0197, "accuracy": 0.971875011920929, "lr": 6.768970513457151e-10, "epoch": 9.870431893687707, "percentage": 99.33, "elapsed_time": "6:50:42", "remaining_time": "0:02:45"}
|
| 150 |
+
{"current_steps": 1500, "total_steps": 1500, "loss": 0.0272, "accuracy": 0.9609375, "lr": 0.0, "epoch": 9.93687707641196, "percentage": 100.0, "elapsed_time": "6:53:26", "remaining_time": "0:00:00"}
|
| 151 |
+
{"current_steps": 1500, "total_steps": 1500, "epoch": 9.93687707641196, "percentage": 100.0, "elapsed_time": "6:53:26", "remaining_time": "0:00:00"}
|