Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a64544e5741ccad546e9e3d5ccefa02074891b61be4b7d065c00f8388e3835a6
+oid sha256:de30e06016ca93c7d8a0f81360394990e8c8f38caa788e4ed8328ae15f8b73eb
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65dac55f38b2522db78712502a42f54d3bc0a242b7a8cf6c3e5d3ba7a09c5d32
+oid sha256:a4409d4ef6d1ee20b517560c9ec70648635f6a87566d36337db94b21048f7d44
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8f857b616b7b4710b092ed2f1df79b4192a141610436ca2fab82469f2cc551
+oid sha256:5a618832d2558b85992134c779ff16f8ae5242a07fe5b3621ed3a0a081ef55d5
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aebf14be8ddb8c0aa833d8c53127acc8a0b7c44fcbc9cf714003b49a006637f
+oid sha256:1ce9c9a73226be579d433a4ff3f9e4936753d9723b2580e5dc18cb8da3563029
 size 1168138808

trainer_log.jsonl

@@ -35,3 +35,21 @@
 {"current_steps": 340, "total_steps": 525, "loss": 0.7038, "learning_rate": 5e-06, "epoch": 1.940798858773181, "percentage": 64.76, "elapsed_time": "2:58:43", "remaining_time": "1:37:15"}
 {"current_steps": 350, "total_steps": 525, "loss": 0.6988, "learning_rate": 5e-06, "epoch": 1.9978601997146934, "percentage": 66.67, "elapsed_time": "3:03:52", "remaining_time": "1:31:56"}
 {"current_steps": 350, "total_steps": 525, "eval_loss": 0.752321720123291, "epoch": 1.9978601997146934, "percentage": 66.67, "elapsed_time": "3:05:58", "remaining_time": "1:32:59"}
+{"current_steps": 360, "total_steps": 525, "loss": 0.697, "learning_rate": 5e-06, "epoch": 2.055634807417974, "percentage": 68.57, "elapsed_time": "3:11:58", "remaining_time": "1:27:59"}
+{"current_steps": 370, "total_steps": 525, "loss": 0.6309, "learning_rate": 5e-06, "epoch": 2.1126961483594866, "percentage": 70.48, "elapsed_time": "3:17:07", "remaining_time": "1:22:34"}
+{"current_steps": 380, "total_steps": 525, "loss": 0.6301, "learning_rate": 5e-06, "epoch": 2.1697574893009985, "percentage": 72.38, "elapsed_time": "3:22:15", "remaining_time": "1:17:10"}
+{"current_steps": 390, "total_steps": 525, "loss": 0.6274, "learning_rate": 5e-06, "epoch": 2.226818830242511, "percentage": 74.29, "elapsed_time": "3:27:25", "remaining_time": "1:11:47"}
+{"current_steps": 400, "total_steps": 525, "loss": 0.631, "learning_rate": 5e-06, "epoch": 2.283880171184023, "percentage": 76.19, "elapsed_time": "3:32:34", "remaining_time": "1:06:25"}
+{"current_steps": 410, "total_steps": 525, "loss": 0.6321, "learning_rate": 5e-06, "epoch": 2.340941512125535, "percentage": 78.1, "elapsed_time": "3:37:44", "remaining_time": "1:01:04"}
+{"current_steps": 420, "total_steps": 525, "loss": 0.6352, "learning_rate": 5e-06, "epoch": 2.398002853067047, "percentage": 80.0, "elapsed_time": "3:42:53", "remaining_time": "0:55:43"}
+{"current_steps": 430, "total_steps": 525, "loss": 0.6356, "learning_rate": 5e-06, "epoch": 2.455064194008559, "percentage": 81.9, "elapsed_time": "3:48:02", "remaining_time": "0:50:22"}
+{"current_steps": 440, "total_steps": 525, "loss": 0.635, "learning_rate": 5e-06, "epoch": 2.512125534950071, "percentage": 83.81, "elapsed_time": "3:53:11", "remaining_time": "0:45:02"}
+{"current_steps": 450, "total_steps": 525, "loss": 0.6349, "learning_rate": 5e-06, "epoch": 2.5691868758915835, "percentage": 85.71, "elapsed_time": "3:58:19", "remaining_time": "0:39:43"}
+{"current_steps": 460, "total_steps": 525, "loss": 0.6355, "learning_rate": 5e-06, "epoch": 2.626248216833096, "percentage": 87.62, "elapsed_time": "4:03:28", "remaining_time": "0:34:24"}
+{"current_steps": 470, "total_steps": 525, "loss": 0.6377, "learning_rate": 5e-06, "epoch": 2.683309557774608, "percentage": 89.52, "elapsed_time": "4:08:36", "remaining_time": "0:29:05"}
+{"current_steps": 480, "total_steps": 525, "loss": 0.6367, "learning_rate": 5e-06, "epoch": 2.7403708987161197, "percentage": 91.43, "elapsed_time": "4:13:43", "remaining_time": "0:23:47"}
+{"current_steps": 490, "total_steps": 525, "loss": 0.6382, "learning_rate": 5e-06, "epoch": 2.797432239657632, "percentage": 93.33, "elapsed_time": "4:18:50", "remaining_time": "0:18:29"}
+{"current_steps": 500, "total_steps": 525, "loss": 0.6357, "learning_rate": 5e-06, "epoch": 2.854493580599144, "percentage": 95.24, "elapsed_time": "4:23:57", "remaining_time": "0:13:11"}
+{"current_steps": 510, "total_steps": 525, "loss": 0.6363, "learning_rate": 5e-06, "epoch": 2.911554921540656, "percentage": 97.14, "elapsed_time": "4:29:05", "remaining_time": "0:07:54"}
+{"current_steps": 520, "total_steps": 525, "loss": 0.644, "learning_rate": 5e-06, "epoch": 2.9686162624821684, "percentage": 99.05, "elapsed_time": "4:34:14", "remaining_time": "0:02:38"}
+{"current_steps": 525, "total_steps": 525, "eval_loss": 0.7613628506660461, "epoch": 2.9971469329529246, "percentage": 100.0, "elapsed_time": "4:39:50", "remaining_time": "0:00:00"}