Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282863b7aca4687bff1a01122ab94c4d23e54a9274d81c191452cd2da4d6c93b
+oid sha256:66b0967890dc270cb6fbc278fee55118751ceb2fa742f1c0418512775167d016
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a908783c91cbc9db27fd59d4444bb32b8cd58e1a6dd48eaa98d0fc0a0f5bb49e
+oid sha256:a06de23937a3f35124d6a557a3845ea7a4531ccb772dbd6292be870750cbea70
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e10f7302d44b0ad8c0fde13e349bccbe1b9b3cdbbae35183fcad3fe874e07f
+oid sha256:649fb2dbdede408f84699fb433ddca6fc7e2f95f13127cddb6ceacaa3efde139
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6c2be9a17165decdd93382b6edbe0f4c0fa4df04593cbd0621e53b355429c2
+oid sha256:f2e0e4ed3164135b0e4b9c2c073c0bd5174f4a68860b90c04ddf080378734365
 size 1168138808

trainer_log.jsonl

@@ -45,3 +45,25 @@
 {"current_steps": 440, "total_steps": 678, "loss": 0.7657, "lr": 5e-06, "epoch": 1.9458264234383638, "percentage": 64.9, "elapsed_time": "7:07:32", "remaining_time": "3:51:15"}
 {"current_steps": 450, "total_steps": 678, "loss": 0.773, "lr": 5e-06, "epoch": 1.9900497512437811, "percentage": 66.37, "elapsed_time": "7:17:08", "remaining_time": "3:41:29"}
 {"current_steps": 452, "total_steps": 678, "eval_loss": 0.8043199181556702, "epoch": 1.9988944168048646, "percentage": 66.67, "elapsed_time": "7:23:17", "remaining_time": "3:41:38"}
+{"current_steps": 460, "total_steps": 678, "loss": 0.8044, "lr": 5e-06, "epoch": 2.0342730790491985, "percentage": 67.85, "elapsed_time": "7:31:59", "remaining_time": "3:34:12"}
+{"current_steps": 470, "total_steps": 678, "loss": 0.7156, "lr": 5e-06, "epoch": 2.0784964068546157, "percentage": 69.32, "elapsed_time": "7:41:35", "remaining_time": "3:24:16"}
+{"current_steps": 480, "total_steps": 678, "loss": 0.7241, "lr": 5e-06, "epoch": 2.1227197346600333, "percentage": 70.8, "elapsed_time": "7:51:13", "remaining_time": "3:14:22"}
+{"current_steps": 490, "total_steps": 678, "loss": 0.7254, "lr": 5e-06, "epoch": 2.1669430624654504, "percentage": 72.27, "elapsed_time": "8:00:50", "remaining_time": "3:04:29"}
+{"current_steps": 500, "total_steps": 678, "loss": 0.7226, "lr": 5e-06, "epoch": 2.211166390270868, "percentage": 73.75, "elapsed_time": "8:10:27", "remaining_time": "2:54:36"}
+{"current_steps": 510, "total_steps": 678, "loss": 0.7249, "lr": 5e-06, "epoch": 2.255389718076285, "percentage": 75.22, "elapsed_time": "8:20:04", "remaining_time": "2:44:43"}
+{"current_steps": 520, "total_steps": 678, "loss": 0.7238, "lr": 5e-06, "epoch": 2.299613045881703, "percentage": 76.7, "elapsed_time": "8:29:42", "remaining_time": "2:34:52"}
+{"current_steps": 530, "total_steps": 678, "loss": 0.7293, "lr": 5e-06, "epoch": 2.34383637368712, "percentage": 78.17, "elapsed_time": "8:39:19", "remaining_time": "2:25:01"}
+{"current_steps": 540, "total_steps": 678, "loss": 0.7265, "lr": 5e-06, "epoch": 2.388059701492537, "percentage": 79.65, "elapsed_time": "8:48:57", "remaining_time": "2:15:10"}
+{"current_steps": 550, "total_steps": 678, "loss": 0.728, "lr": 5e-06, "epoch": 2.4322830292979547, "percentage": 81.12, "elapsed_time": "8:58:35", "remaining_time": "2:05:20"}
+{"current_steps": 560, "total_steps": 678, "loss": 0.7212, "lr": 5e-06, "epoch": 2.476506357103372, "percentage": 82.6, "elapsed_time": "9:08:12", "remaining_time": "1:55:30"}
+{"current_steps": 570, "total_steps": 678, "loss": 0.7272, "lr": 5e-06, "epoch": 2.5207296849087895, "percentage": 84.07, "elapsed_time": "9:17:50", "remaining_time": "1:45:41"}
+{"current_steps": 580, "total_steps": 678, "loss": 0.7264, "lr": 5e-06, "epoch": 2.5649530127142066, "percentage": 85.55, "elapsed_time": "9:27:27", "remaining_time": "1:35:52"}
+{"current_steps": 590, "total_steps": 678, "loss": 0.7281, "lr": 5e-06, "epoch": 2.609176340519624, "percentage": 87.02, "elapsed_time": "9:37:04", "remaining_time": "1:26:04"}
+{"current_steps": 600, "total_steps": 678, "loss": 0.7267, "lr": 5e-06, "epoch": 2.6533996683250414, "percentage": 88.5, "elapsed_time": "9:46:41", "remaining_time": "1:16:16"}
+{"current_steps": 610, "total_steps": 678, "loss": 0.7288, "lr": 5e-06, "epoch": 2.697622996130459, "percentage": 89.97, "elapsed_time": "9:56:18", "remaining_time": "1:06:28"}
+{"current_steps": 620, "total_steps": 678, "loss": 0.7281, "lr": 5e-06, "epoch": 2.741846323935876, "percentage": 91.45, "elapsed_time": "10:05:55", "remaining_time": "0:56:40"}
+{"current_steps": 630, "total_steps": 678, "loss": 0.7259, "lr": 5e-06, "epoch": 2.7860696517412933, "percentage": 92.92, "elapsed_time": "10:15:31", "remaining_time": "0:46:53"}
+{"current_steps": 640, "total_steps": 678, "loss": 0.7244, "lr": 5e-06, "epoch": 2.830292979546711, "percentage": 94.4, "elapsed_time": "10:25:08", "remaining_time": "0:37:07"}
+{"current_steps": 650, "total_steps": 678, "loss": 0.7239, "lr": 5e-06, "epoch": 2.8745163073521285, "percentage": 95.87, "elapsed_time": "10:34:45", "remaining_time": "0:27:20"}
+{"current_steps": 660, "total_steps": 678, "loss": 0.72, "lr": 5e-06, "epoch": 2.9187396351575456, "percentage": 97.35, "elapsed_time": "10:44:22", "remaining_time": "0:17:34"}
+{"current_steps": 670, "total_steps": 678, "loss": 0.7266, "lr": 5e-06, "epoch": 2.962962962962963, "percentage": 98.82, "elapsed_time": "10:53:59", "remaining_time": "0:07:48"}