Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78819c357843cb90faf95c4daadb8c5cd09aa28aa4e21b94365ed6519ef11c2d
+oid sha256:f70e5f70f7dbd269ccea4f3063c06bb9cd0d480430eb496da59b5090f53b2154
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7305823ef250eb705ac71b9f3730b78befb91e180628c0c3de8f1a040055360d
+oid sha256:64ca72c8b0fd3e392c1f79015f78f178472f42733c574093a340025f7bb57fc4
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ebd170137490598e8a54b11debd9abbdcafe734ac7bf2ba37d0b32a0c2f3d39
+oid sha256:5b63a37533dc4c78c94252742ba1cfced05a1bf87cd7763c5bbd37fb0774d05b
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83698f2d2338125e2754a01d2cd41c54d13fcd62e7ccbde176edccd579f1321
+oid sha256:e2a78744cbd3659e0732b0f24b7ef25c973e2b75c5229d85087c2bcab86305c5
 size 1089994880

trainer_log.jsonl

@@ -88,3 +88,46 @@
 {"current_steps": 870, "total_steps": 1314, "loss": 0.5961, "learning_rate": 4.795735609559657e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:50:58", "remaining_time": "6:33:27"}
 {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.618708610534668, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:04:24", "remaining_time": "6:30:51"}
 {"current_steps": 880, "total_steps": 1314, "loss": 0.6157, "learning_rate": 4.793531180296065e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:08:11", "remaining_time": "6:28:43"}
+{"current_steps": 890, "total_steps": 1314, "loss": 0.5553, "learning_rate": 4.7913297881339085e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:16:57", "remaining_time": "6:19:40"}
+{"current_steps": 900, "total_steps": 1314, "loss": 0.5704, "learning_rate": 4.789131426105757e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:25:42", "remaining_time": "6:10:37"}
+{"current_steps": 910, "total_steps": 1314, "loss": 0.5686, "learning_rate": 4.786936087266542e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:34:29", "remaining_time": "6:01:35"}
+{"current_steps": 920, "total_steps": 1314, "loss": 0.5717, "learning_rate": 4.784743764693455e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:43:15", "remaining_time": "5:52:34"}
+{"current_steps": 930, "total_steps": 1314, "loss": 0.5697, "learning_rate": 4.7825544514858655e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:52:03", "remaining_time": "5:43:33"}
+{"current_steps": 940, "total_steps": 1314, "loss": 0.5644, "learning_rate": 4.780368140765222e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "14:00:50", "remaining_time": "5:34:32"}
+{"current_steps": 950, "total_steps": 1314, "loss": 0.5653, "learning_rate": 4.778184825674966e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:09:35", "remaining_time": "5:25:31"}
+{"current_steps": 960, "total_steps": 1314, "loss": 0.5703, "learning_rate": 4.776004499380439e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:18:22", "remaining_time": "5:16:31"}
+{"current_steps": 970, "total_steps": 1314, "loss": 0.5698, "learning_rate": 4.773827155068793e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:27:09", "remaining_time": "5:07:31"}
+{"current_steps": 980, "total_steps": 1314, "loss": 0.5594, "learning_rate": 4.771652785948902e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:35:55", "remaining_time": "4:58:31"}
+{"current_steps": 990, "total_steps": 1314, "loss": 0.5684, "learning_rate": 4.769481385251275e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:44:41", "remaining_time": "4:49:32"}
+{"current_steps": 1000, "total_steps": 1314, "loss": 0.5687, "learning_rate": 4.767312946227961e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:53:27", "remaining_time": "4:40:32"}
+{"current_steps": 1010, "total_steps": 1314, "loss": 0.5662, "learning_rate": 4.765147462152471e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:02:12", "remaining_time": "4:31:33"}
+{"current_steps": 1020, "total_steps": 1314, "loss": 0.5693, "learning_rate": 4.762984926319677e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:10:59", "remaining_time": "4:22:34"}
+{"current_steps": 1030, "total_steps": 1314, "loss": 0.5706, "learning_rate": 4.760825332045738e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:19:46", "remaining_time": "4:13:36"}
+{"current_steps": 1040, "total_steps": 1314, "loss": 0.5685, "learning_rate": 4.758668672668006e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:28:32", "remaining_time": "4:04:38"}
+{"current_steps": 1050, "total_steps": 1314, "loss": 0.5679, "learning_rate": 4.756514941544941e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:37:19", "remaining_time": "3:55:40"}
+{"current_steps": 1060, "total_steps": 1314, "loss": 0.5762, "learning_rate": 4.754364132056025e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:46:06", "remaining_time": "3:46:42"}
+{"current_steps": 1070, "total_steps": 1314, "loss": 0.579, "learning_rate": 4.752216237601676e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:54:53", "remaining_time": "3:37:44"}
+{"current_steps": 1080, "total_steps": 1314, "loss": 0.5743, "learning_rate": 4.750071251603165e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:03:40", "remaining_time": "3:28:47"}
+{"current_steps": 1090, "total_steps": 1314, "loss": 0.5719, "learning_rate": 4.7479291675025314e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:12:26", "remaining_time": "3:19:50"}
+{"current_steps": 1100, "total_steps": 1314, "loss": 0.5784, "learning_rate": 4.745789978762496e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:21:12", "remaining_time": "3:10:53"}
+{"current_steps": 1110, "total_steps": 1314, "loss": 0.5718, "learning_rate": 4.7436536788663765e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:29:59", "remaining_time": "3:01:56"}
+{"current_steps": 1120, "total_steps": 1314, "loss": 0.57, "learning_rate": 4.74152026131801e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:38:44", "remaining_time": "2:52:59"}
+{"current_steps": 1130, "total_steps": 1314, "loss": 0.5694, "learning_rate": 4.739389719641665e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:47:29", "remaining_time": "2:44:03"}
+{"current_steps": 1140, "total_steps": 1314, "loss": 0.5691, "learning_rate": 4.7372620473819615e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:56:15", "remaining_time": "2:35:06"}
+{"current_steps": 1150, "total_steps": 1314, "loss": 0.5694, "learning_rate": 4.735137238103785e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:05:01", "remaining_time": "2:26:10"}
+{"current_steps": 1160, "total_steps": 1314, "loss": 0.5705, "learning_rate": 4.7330152853922064e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:13:48", "remaining_time": "2:17:14"}
+{"current_steps": 1170, "total_steps": 1314, "loss": 0.5733, "learning_rate": 4.730896182852409e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:22:35", "remaining_time": "2:08:19"}
+{"current_steps": 1180, "total_steps": 1314, "loss": 0.5684, "learning_rate": 4.72877992410959e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:31:19", "remaining_time": "1:59:23"}
+{"current_steps": 1190, "total_steps": 1314, "loss": 0.5695, "learning_rate": 4.7266665028088985e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:40:06", "remaining_time": "1:50:27"}
+{"current_steps": 1200, "total_steps": 1314, "loss": 0.5727, "learning_rate": 4.72455591261534e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:48:52", "remaining_time": "1:41:32"}
+{"current_steps": 1210, "total_steps": 1314, "loss": 0.5761, "learning_rate": 4.722448147213712e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:57:37", "remaining_time": "1:32:37"}
+{"current_steps": 1220, "total_steps": 1314, "loss": 0.5659, "learning_rate": 4.720343200308507e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:06:24", "remaining_time": "1:23:42"}
+{"current_steps": 1230, "total_steps": 1314, "loss": 0.5644, "learning_rate": 4.7182410656238484e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:15:10", "remaining_time": "1:14:47"}
+{"current_steps": 1240, "total_steps": 1314, "loss": 0.5792, "learning_rate": 4.716141736903407e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:23:54", "remaining_time": "1:05:52"}
+{"current_steps": 1250, "total_steps": 1314, "loss": 0.5759, "learning_rate": 4.714045207910318e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:32:41", "remaining_time": "0:56:58"}
+{"current_steps": 1260, "total_steps": 1314, "loss": 0.573, "learning_rate": 4.71195147242711e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:41:27", "remaining_time": "0:48:03"}
+{"current_steps": 1270, "total_steps": 1314, "loss": 0.574, "learning_rate": 4.709860524255622e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:50:13", "remaining_time": "0:39:09"}
+{"current_steps": 1280, "total_steps": 1314, "loss": 0.5642, "learning_rate": 4.707772357216934e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:58:59", "remaining_time": "0:30:15"}
+{"current_steps": 1290, "total_steps": 1314, "loss": 0.5644, "learning_rate": 4.705686965151282e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:07:45", "remaining_time": "0:21:21"}
+{"current_steps": 1300, "total_steps": 1314, "loss": 0.5655, "learning_rate": 4.703604341917987e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:16:31", "remaining_time": "0:12:27"}
+{"current_steps": 1310, "total_steps": 1314, "loss": 0.5753, "learning_rate": 4.701524481395374e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:25:18", "remaining_time": "0:03:33"}