Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:560b63175837f5897493176da7d8843328baa2888c8e3db434e3672e05ac8a35
+oid sha256:97d519403421af1f66fefdc27809f73eb1363a8801f6eadb3317f39ca0732c34
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb29252f3527c504896a973ddff87090474d9eaed0972caab501f72e27aed60e
+oid sha256:98ad3fe8d4951738eec1dcd052a7abde56a2bb49592faceba0543499916e949c
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ff5fcd33cd47238da9d85ade20c13a3549b61771a099e56ea98495d49f12c9
+oid sha256:3fea98f5ad28cd40e8a4427946849a7ff176794f9519691f8118676d3a019649
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb021a34da2589dc5441ae5331fca668cbe041c6ca97fdb59b79e52020d34b4
+oid sha256:8a0a3716776c48d768b3742688d0b069334428102b4bdff4f39e484530b89e54
 size 1168138808

trainer_log.jsonl

@@ -108,3 +108,56 @@
 {"current_steps": 1070, "total_steps": 1617, "loss": 0.519, "lr": 5e-06, "epoch": 1.9846974263853467, "percentage": 66.17, "elapsed_time": "17:13:16", "remaining_time": "8:48:13"}
 {"current_steps": 1078, "total_steps": 1617, "eval_loss": 0.5572099685668945, "epoch": 1.9995362856480408, "percentage": 66.67, "elapsed_time": "17:30:39", "remaining_time": "8:45:19"}
 {"current_steps": 1080, "total_steps": 1617, "loss": 0.5612, "lr": 5e-06, "epoch": 2.0032460004637143, "percentage": 66.79, "elapsed_time": "17:33:34", "remaining_time": "8:43:51"}
+{"current_steps": 1090, "total_steps": 1617, "loss": 0.4796, "lr": 5e-06, "epoch": 2.0217945745420822, "percentage": 67.41, "elapsed_time": "17:43:09", "remaining_time": "8:34:01"}
+{"current_steps": 1100, "total_steps": 1617, "loss": 0.4717, "lr": 5e-06, "epoch": 2.0403431486204497, "percentage": 68.03, "elapsed_time": "17:52:43", "remaining_time": "8:24:10"}
+{"current_steps": 1110, "total_steps": 1617, "loss": 0.4705, "lr": 5e-06, "epoch": 2.0588917226988177, "percentage": 68.65, "elapsed_time": "18:02:17", "remaining_time": "8:14:20"}
+{"current_steps": 1120, "total_steps": 1617, "loss": 0.4661, "lr": 5e-06, "epoch": 2.0774402967771852, "percentage": 69.26, "elapsed_time": "18:11:51", "remaining_time": "8:04:30"}
+{"current_steps": 1130, "total_steps": 1617, "loss": 0.4674, "lr": 5e-06, "epoch": 2.095988870855553, "percentage": 69.88, "elapsed_time": "18:21:25", "remaining_time": "7:54:41"}
+{"current_steps": 1140, "total_steps": 1617, "loss": 0.4645, "lr": 5e-06, "epoch": 2.1145374449339207, "percentage": 70.5, "elapsed_time": "18:30:59", "remaining_time": "7:44:51"}
+{"current_steps": 1150, "total_steps": 1617, "loss": 0.4676, "lr": 5e-06, "epoch": 2.1330860190122882, "percentage": 71.12, "elapsed_time": "18:40:33", "remaining_time": "7:35:02"}
+{"current_steps": 1160, "total_steps": 1617, "loss": 0.4657, "lr": 5e-06, "epoch": 2.151634593090656, "percentage": 71.74, "elapsed_time": "18:50:07", "remaining_time": "7:25:13"}
+{"current_steps": 1170, "total_steps": 1617, "loss": 0.4656, "lr": 5e-06, "epoch": 2.1701831671690237, "percentage": 72.36, "elapsed_time": "18:59:40", "remaining_time": "7:15:24"}
+{"current_steps": 1180, "total_steps": 1617, "loss": 0.4583, "lr": 5e-06, "epoch": 2.1887317412473917, "percentage": 72.97, "elapsed_time": "19:09:14", "remaining_time": "7:05:36"}
+{"current_steps": 1190, "total_steps": 1617, "loss": 0.469, "lr": 5e-06, "epoch": 2.207280315325759, "percentage": 73.59, "elapsed_time": "19:18:47", "remaining_time": "6:55:48"}
+{"current_steps": 1200, "total_steps": 1617, "loss": 0.4715, "lr": 5e-06, "epoch": 2.225828889404127, "percentage": 74.21, "elapsed_time": "19:28:21", "remaining_time": "6:46:00"}
+{"current_steps": 1210, "total_steps": 1617, "loss": 0.4584, "lr": 5e-06, "epoch": 2.2443774634824947, "percentage": 74.83, "elapsed_time": "19:37:54", "remaining_time": "6:36:12"}
+{"current_steps": 1220, "total_steps": 1617, "loss": 0.4772, "lr": 5e-06, "epoch": 2.2629260375608626, "percentage": 75.45, "elapsed_time": "19:47:28", "remaining_time": "6:26:24"}
+{"current_steps": 1230, "total_steps": 1617, "loss": 0.4701, "lr": 5e-06, "epoch": 2.28147461163923, "percentage": 76.07, "elapsed_time": "19:57:01", "remaining_time": "6:16:37"}
+{"current_steps": 1240, "total_steps": 1617, "loss": 0.4619, "lr": 5e-06, "epoch": 2.300023185717598, "percentage": 76.69, "elapsed_time": "20:06:35", "remaining_time": "6:06:50"}
+{"current_steps": 1250, "total_steps": 1617, "loss": 0.4734, "lr": 5e-06, "epoch": 2.3185717597959656, "percentage": 77.3, "elapsed_time": "20:16:08", "remaining_time": "5:57:03"}
+{"current_steps": 1260, "total_steps": 1617, "loss": 0.4746, "lr": 5e-06, "epoch": 2.3371203338743336, "percentage": 77.92, "elapsed_time": "20:25:43", "remaining_time": "5:47:17"}
+{"current_steps": 1270, "total_steps": 1617, "loss": 0.4647, "lr": 5e-06, "epoch": 2.355668907952701, "percentage": 78.54, "elapsed_time": "20:35:16", "remaining_time": "5:37:30"}
+{"current_steps": 1280, "total_steps": 1617, "loss": 0.459, "lr": 5e-06, "epoch": 2.374217482031069, "percentage": 79.16, "elapsed_time": "20:44:50", "remaining_time": "5:27:44"}
+{"current_steps": 1290, "total_steps": 1617, "loss": 0.4687, "lr": 5e-06, "epoch": 2.3927660561094366, "percentage": 79.78, "elapsed_time": "20:54:24", "remaining_time": "5:17:58"}
+{"current_steps": 1300, "total_steps": 1617, "loss": 0.4636, "lr": 5e-06, "epoch": 2.411314630187804, "percentage": 80.4, "elapsed_time": "21:03:58", "remaining_time": "5:08:12"}
+{"current_steps": 1310, "total_steps": 1617, "loss": 0.4798, "lr": 5e-06, "epoch": 2.429863204266172, "percentage": 81.01, "elapsed_time": "21:13:32", "remaining_time": "4:58:27"}
+{"current_steps": 1320, "total_steps": 1617, "loss": 0.4743, "lr": 5e-06, "epoch": 2.4484117783445396, "percentage": 81.63, "elapsed_time": "21:23:06", "remaining_time": "4:48:42"}
+{"current_steps": 1330, "total_steps": 1617, "loss": 0.479, "lr": 5e-06, "epoch": 2.4669603524229076, "percentage": 82.25, "elapsed_time": "21:32:40", "remaining_time": "4:38:56"}
+{"current_steps": 1340, "total_steps": 1617, "loss": 0.4667, "lr": 5e-06, "epoch": 2.485508926501275, "percentage": 82.87, "elapsed_time": "21:42:14", "remaining_time": "4:29:11"}
+{"current_steps": 1350, "total_steps": 1617, "loss": 0.4756, "lr": 5e-06, "epoch": 2.504057500579643, "percentage": 83.49, "elapsed_time": "21:51:48", "remaining_time": "4:19:26"}
+{"current_steps": 1360, "total_steps": 1617, "loss": 0.4656, "lr": 5e-06, "epoch": 2.5226060746580106, "percentage": 84.11, "elapsed_time": "22:01:22", "remaining_time": "4:09:42"}
+{"current_steps": 1370, "total_steps": 1617, "loss": 0.4769, "lr": 5e-06, "epoch": 2.5411546487363785, "percentage": 84.72, "elapsed_time": "22:10:57", "remaining_time": "3:59:57"}
+{"current_steps": 1380, "total_steps": 1617, "loss": 0.4715, "lr": 5e-06, "epoch": 2.559703222814746, "percentage": 85.34, "elapsed_time": "22:20:30", "remaining_time": "3:50:13"}
+{"current_steps": 1390, "total_steps": 1617, "loss": 0.466, "lr": 5e-06, "epoch": 2.578251796893114, "percentage": 85.96, "elapsed_time": "22:30:05", "remaining_time": "3:40:28"}
+{"current_steps": 1400, "total_steps": 1617, "loss": 0.4719, "lr": 5e-06, "epoch": 2.5968003709714815, "percentage": 86.58, "elapsed_time": "22:39:38", "remaining_time": "3:30:44"}
+{"current_steps": 1410, "total_steps": 1617, "loss": 0.4657, "lr": 5e-06, "epoch": 2.615348945049849, "percentage": 87.2, "elapsed_time": "22:49:11", "remaining_time": "3:21:00"}
+{"current_steps": 1420, "total_steps": 1617, "loss": 0.4649, "lr": 5e-06, "epoch": 2.633897519128217, "percentage": 87.82, "elapsed_time": "22:58:45", "remaining_time": "3:11:16"}
+{"current_steps": 1430, "total_steps": 1617, "loss": 0.4734, "lr": 5e-06, "epoch": 2.652446093206585, "percentage": 88.44, "elapsed_time": "23:08:19", "remaining_time": "3:01:32"}
+{"current_steps": 1440, "total_steps": 1617, "loss": 0.4696, "lr": 5e-06, "epoch": 2.6709946672849525, "percentage": 89.05, "elapsed_time": "23:17:52", "remaining_time": "2:51:49"}
+{"current_steps": 1450, "total_steps": 1617, "loss": 0.4626, "lr": 5e-06, "epoch": 2.68954324136332, "percentage": 89.67, "elapsed_time": "23:27:26", "remaining_time": "2:42:05"}
+{"current_steps": 1460, "total_steps": 1617, "loss": 0.4683, "lr": 5e-06, "epoch": 2.708091815441688, "percentage": 90.29, "elapsed_time": "23:36:59", "remaining_time": "2:32:22"}
+{"current_steps": 1470, "total_steps": 1617, "loss": 0.4724, "lr": 5e-06, "epoch": 2.7266403895200555, "percentage": 90.91, "elapsed_time": "23:46:31", "remaining_time": "2:22:39"}
+{"current_steps": 1480, "total_steps": 1617, "loss": 0.4756, "lr": 5e-06, "epoch": 2.7451889635984235, "percentage": 91.53, "elapsed_time": "23:56:05", "remaining_time": "2:12:56"}
+{"current_steps": 1490, "total_steps": 1617, "loss": 0.4765, "lr": 5e-06, "epoch": 2.763737537676791, "percentage": 92.15, "elapsed_time": "1 day, 0:05:38", "remaining_time": "2:03:13"}
+{"current_steps": 1500, "total_steps": 1617, "loss": 0.4798, "lr": 5e-06, "epoch": 2.782286111755159, "percentage": 92.76, "elapsed_time": "1 day, 0:15:11", "remaining_time": "1:53:30"}
+{"current_steps": 1510, "total_steps": 1617, "loss": 0.4694, "lr": 5e-06, "epoch": 2.8008346858335265, "percentage": 93.38, "elapsed_time": "1 day, 0:24:45", "remaining_time": "1:43:47"}
+{"current_steps": 1520, "total_steps": 1617, "loss": 0.4672, "lr": 5e-06, "epoch": 2.8193832599118944, "percentage": 94.0, "elapsed_time": "1 day, 0:34:18", "remaining_time": "1:34:05"}
+{"current_steps": 1530, "total_steps": 1617, "loss": 0.4704, "lr": 5e-06, "epoch": 2.837931833990262, "percentage": 94.62, "elapsed_time": "1 day, 0:43:52", "remaining_time": "1:24:22"}
+{"current_steps": 1540, "total_steps": 1617, "loss": 0.4795, "lr": 5e-06, "epoch": 2.85648040806863, "percentage": 95.24, "elapsed_time": "1 day, 0:53:25", "remaining_time": "1:14:40"}
+{"current_steps": 1550, "total_steps": 1617, "loss": 0.4626, "lr": 5e-06, "epoch": 2.8750289821469974, "percentage": 95.86, "elapsed_time": "1 day, 1:02:59", "remaining_time": "1:04:58"}
+{"current_steps": 1560, "total_steps": 1617, "loss": 0.4767, "lr": 5e-06, "epoch": 2.893577556225365, "percentage": 96.47, "elapsed_time": "1 day, 1:12:32", "remaining_time": "0:55:15"}
+{"current_steps": 1570, "total_steps": 1617, "loss": 0.4681, "lr": 5e-06, "epoch": 2.912126130303733, "percentage": 97.09, "elapsed_time": "1 day, 1:22:05", "remaining_time": "0:45:33"}
+{"current_steps": 1580, "total_steps": 1617, "loss": 0.4732, "lr": 5e-06, "epoch": 2.930674704382101, "percentage": 97.71, "elapsed_time": "1 day, 1:31:39", "remaining_time": "0:35:52"}
+{"current_steps": 1590, "total_steps": 1617, "loss": 0.4732, "lr": 5e-06, "epoch": 2.9492232784604684, "percentage": 98.33, "elapsed_time": "1 day, 1:41:12", "remaining_time": "0:26:10"}
+{"current_steps": 1600, "total_steps": 1617, "loss": 0.4713, "lr": 5e-06, "epoch": 2.967771852538836, "percentage": 98.95, "elapsed_time": "1 day, 1:50:45", "remaining_time": "0:16:28"}
+{"current_steps": 1610, "total_steps": 1617, "loss": 0.469, "lr": 5e-06, "epoch": 2.986320426617204, "percentage": 99.57, "elapsed_time": "1 day, 2:00:19", "remaining_time": "0:06:47"}