Training in progress, epoch 2

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e081c4c477e73ac66effa621c12bae0f676518353bd73524075ee46f3a272dff
+oid sha256:e9ec2a1a3100f1f7a3c7ab1c7b2b73ea1ec94e4e3fd156d0189604815d33eccf
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fa53459b2d69772df9e8f4d70ebde85990f3e43930743f0874b1ed07b74354
+oid sha256:acfd1251b6007f843d78e2aad12b3d348798112952c10ccc3f6c09c7ab04c692
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e8c9709c7349377da0b05a36754b6d0e3cb76918d3d23ce9e5cc2da05522cb
+oid sha256:8d3af8a8acffebab3cf4d4e7677e8d79cb6f04bcd0b9b07b2acd886d5cf5a440
 size 4540516344

trainer_log.jsonl

@@ -49,3 +49,27 @@
 {"current_steps": 480, "total_steps": 738, "loss": 0.4871, "learning_rate": 5e-06, "epoch": 1.9452887537993921, "percentage": 65.04, "elapsed_time": "13:33:11", "remaining_time": "7:17:05"}
 {"current_steps": 490, "total_steps": 738, "loss": 0.4893, "learning_rate": 5e-06, "epoch": 1.9858156028368794, "percentage": 66.4, "elapsed_time": "13:50:02", "remaining_time": "7:00:06"}
 {"current_steps": 493, "total_steps": 738, "eval_loss": 0.5415348410606384, "epoch": 1.9979736575481257, "percentage": 66.8, "elapsed_time": "14:03:57", "remaining_time": "6:59:24"}
+{"current_steps": 500, "total_steps": 738, "loss": 0.4478, "learning_rate": 5e-06, "epoch": 2.026342451874367, "percentage": 67.75, "elapsed_time": "14:19:34", "remaining_time": "6:49:09"}
+{"current_steps": 510, "total_steps": 738, "loss": 0.4216, "learning_rate": 5e-06, "epoch": 2.066869300911854, "percentage": 69.11, "elapsed_time": "14:36:18", "remaining_time": "6:31:45"}
+{"current_steps": 520, "total_steps": 738, "loss": 0.4209, "learning_rate": 5e-06, "epoch": 2.1073961499493414, "percentage": 70.46, "elapsed_time": "14:53:00", "remaining_time": "6:14:22"}
+{"current_steps": 530, "total_steps": 738, "loss": 0.4216, "learning_rate": 5e-06, "epoch": 2.1479229989868287, "percentage": 71.82, "elapsed_time": "15:09:44", "remaining_time": "5:57:01"}
+{"current_steps": 540, "total_steps": 738, "loss": 0.4285, "learning_rate": 5e-06, "epoch": 2.188449848024316, "percentage": 73.17, "elapsed_time": "15:26:25", "remaining_time": "5:39:41"}
+{"current_steps": 550, "total_steps": 738, "loss": 0.4275, "learning_rate": 5e-06, "epoch": 2.2289766970618032, "percentage": 74.53, "elapsed_time": "15:43:07", "remaining_time": "5:22:22"}
+{"current_steps": 560, "total_steps": 738, "loss": 0.4315, "learning_rate": 5e-06, "epoch": 2.269503546099291, "percentage": 75.88, "elapsed_time": "15:59:50", "remaining_time": "5:05:05"}
+{"current_steps": 570, "total_steps": 738, "loss": 0.4317, "learning_rate": 5e-06, "epoch": 2.310030395136778, "percentage": 77.24, "elapsed_time": "16:16:33", "remaining_time": "4:47:49"}
+{"current_steps": 580, "total_steps": 738, "loss": 0.4312, "learning_rate": 5e-06, "epoch": 2.3505572441742655, "percentage": 78.59, "elapsed_time": "16:33:15", "remaining_time": "4:30:34"}
+{"current_steps": 590, "total_steps": 738, "loss": 0.4329, "learning_rate": 5e-06, "epoch": 2.3910840932117527, "percentage": 79.95, "elapsed_time": "16:49:59", "remaining_time": "4:13:21"}
+{"current_steps": 600, "total_steps": 738, "loss": 0.4317, "learning_rate": 5e-06, "epoch": 2.43161094224924, "percentage": 81.3, "elapsed_time": "17:06:41", "remaining_time": "3:56:08"}
+{"current_steps": 610, "total_steps": 738, "loss": 0.4332, "learning_rate": 5e-06, "epoch": 2.4721377912867273, "percentage": 82.66, "elapsed_time": "17:23:23", "remaining_time": "3:38:56"}
+{"current_steps": 620, "total_steps": 738, "loss": 0.4277, "learning_rate": 5e-06, "epoch": 2.512664640324215, "percentage": 84.01, "elapsed_time": "17:40:04", "remaining_time": "3:21:45"}
+{"current_steps": 630, "total_steps": 738, "loss": 0.4283, "learning_rate": 5e-06, "epoch": 2.5531914893617023, "percentage": 85.37, "elapsed_time": "17:56:46", "remaining_time": "3:04:35"}
+{"current_steps": 640, "total_steps": 738, "loss": 0.4336, "learning_rate": 5e-06, "epoch": 2.5937183383991895, "percentage": 86.72, "elapsed_time": "18:13:29", "remaining_time": "2:47:26"}
+{"current_steps": 650, "total_steps": 738, "loss": 0.4292, "learning_rate": 5e-06, "epoch": 2.634245187436677, "percentage": 88.08, "elapsed_time": "18:30:13", "remaining_time": "2:30:18"}
+{"current_steps": 660, "total_steps": 738, "loss": 0.4343, "learning_rate": 5e-06, "epoch": 2.674772036474164, "percentage": 89.43, "elapsed_time": "18:46:56", "remaining_time": "2:13:11"}
+{"current_steps": 670, "total_steps": 738, "loss": 0.4313, "learning_rate": 5e-06, "epoch": 2.7152988855116513, "percentage": 90.79, "elapsed_time": "19:03:39", "remaining_time": "1:56:04"}
+{"current_steps": 680, "total_steps": 738, "loss": 0.4332, "learning_rate": 5e-06, "epoch": 2.7558257345491386, "percentage": 92.14, "elapsed_time": "19:20:22", "remaining_time": "1:38:58"}
+{"current_steps": 690, "total_steps": 738, "loss": 0.432, "learning_rate": 5e-06, "epoch": 2.7963525835866263, "percentage": 93.5, "elapsed_time": "19:37:06", "remaining_time": "1:21:53"}
+{"current_steps": 700, "total_steps": 738, "loss": 0.436, "learning_rate": 5e-06, "epoch": 2.8368794326241136, "percentage": 94.85, "elapsed_time": "19:53:49", "remaining_time": "1:04:48"}
+{"current_steps": 710, "total_steps": 738, "loss": 0.4349, "learning_rate": 5e-06, "epoch": 2.877406281661601, "percentage": 96.21, "elapsed_time": "20:10:34", "remaining_time": "0:47:44"}
+{"current_steps": 720, "total_steps": 738, "loss": 0.4365, "learning_rate": 5e-06, "epoch": 2.917933130699088, "percentage": 97.56, "elapsed_time": "20:27:19", "remaining_time": "0:30:40"}
+{"current_steps": 730, "total_steps": 738, "loss": 0.4355, "learning_rate": 5e-06, "epoch": 2.9584599797365754, "percentage": 98.92, "elapsed_time": "20:44:01", "remaining_time": "0:13:37"}