Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef4b030ed090e9115c15077bc0fb766b2b60c332109cee689109997adb01abb
+oid sha256:c1823e75c770ddbc8d6531e7f85826da065b7a2754ed8b899a4980ed80a2911e
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a6f8516e3db90cab0f9250bc6ecbc4d361788bf4efaf4d93ff0ecddc171197c
+oid sha256:54891491e101f86890a7036a8f1b1b3da261c097c19c9ea4c9c35dada3e016b4
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87466d1e2c405c6315dde04eaf2a98c9794c62f0beaf48766a2f18d7b1d582e0
+oid sha256:44d541365a9b6324d6d80b8930df6a81b7fed073a078bc5ed08dc81fc9435ed1
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea70f98bb50ab881e4430b308e177a87f2c3b6b8bb6a075505ad67dc6551c3f
+oid sha256:940df23d748dbba6a17e56807e4f1244d30b18b929c73f00fb968e0cfee8c6ff
 size 1089994880

trainer_log.jsonl

@@ -44,3 +44,24 @@
 {"current_steps": 430, "total_steps": 657, "loss": 0.6083, "learning_rate": 5e-06, "epoch": 1.96011396011396, "percentage": 65.45, "elapsed_time": "6:24:56", "remaining_time": "3:23:12"}
 {"current_steps": 438, "total_steps": 657, "eval_loss": 0.6215006709098816, "epoch": 1.9965811965811966, "percentage": 66.67, "elapsed_time": "6:36:21", "remaining_time": "3:18:10"}
 {"current_steps": 440, "total_steps": 657, "loss": 0.6421, "learning_rate": 5e-06, "epoch": 2.005698005698006, "percentage": 66.97, "elapsed_time": "6:38:26", "remaining_time": "3:16:30"}
+{"current_steps": 450, "total_steps": 657, "loss": 0.5803, "learning_rate": 5e-06, "epoch": 2.051282051282051, "percentage": 68.49, "elapsed_time": "6:47:18", "remaining_time": "3:07:21"}
+{"current_steps": 460, "total_steps": 657, "loss": 0.5869, "learning_rate": 5e-06, "epoch": 2.096866096866097, "percentage": 70.02, "elapsed_time": "6:56:09", "remaining_time": "2:58:13"}
+{"current_steps": 470, "total_steps": 657, "loss": 0.5845, "learning_rate": 5e-06, "epoch": 2.1424501424501425, "percentage": 71.54, "elapsed_time": "7:05:00", "remaining_time": "2:49:05"}
+{"current_steps": 480, "total_steps": 657, "loss": 0.5837, "learning_rate": 5e-06, "epoch": 2.1880341880341883, "percentage": 73.06, "elapsed_time": "7:13:50", "remaining_time": "2:39:58"}
+{"current_steps": 490, "total_steps": 657, "loss": 0.5828, "learning_rate": 5e-06, "epoch": 2.2336182336182335, "percentage": 74.58, "elapsed_time": "7:22:42", "remaining_time": "2:30:52"}
+{"current_steps": 500, "total_steps": 657, "loss": 0.5831, "learning_rate": 5e-06, "epoch": 2.2792022792022792, "percentage": 76.1, "elapsed_time": "7:31:33", "remaining_time": "2:21:47"}
+{"current_steps": 510, "total_steps": 657, "loss": 0.5838, "learning_rate": 5e-06, "epoch": 2.324786324786325, "percentage": 77.63, "elapsed_time": "7:40:25", "remaining_time": "2:12:42"}
+{"current_steps": 520, "total_steps": 657, "loss": 0.586, "learning_rate": 5e-06, "epoch": 2.3703703703703702, "percentage": 79.15, "elapsed_time": "7:49:16", "remaining_time": "2:03:38"}
+{"current_steps": 530, "total_steps": 657, "loss": 0.5883, "learning_rate": 5e-06, "epoch": 2.415954415954416, "percentage": 80.67, "elapsed_time": "7:58:07", "remaining_time": "1:54:34"}
+{"current_steps": 540, "total_steps": 657, "loss": 0.5927, "learning_rate": 5e-06, "epoch": 2.4615384615384617, "percentage": 82.19, "elapsed_time": "8:06:58", "remaining_time": "1:45:30"}
+{"current_steps": 550, "total_steps": 657, "loss": 0.5914, "learning_rate": 5e-06, "epoch": 2.5071225071225074, "percentage": 83.71, "elapsed_time": "8:15:49", "remaining_time": "1:36:27"}
+{"current_steps": 560, "total_steps": 657, "loss": 0.5859, "learning_rate": 5e-06, "epoch": 2.5527065527065527, "percentage": 85.24, "elapsed_time": "8:24:39", "remaining_time": "1:27:24"}
+{"current_steps": 570, "total_steps": 657, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 2.5982905982905984, "percentage": 86.76, "elapsed_time": "8:33:30", "remaining_time": "1:18:22"}
+{"current_steps": 580, "total_steps": 657, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 2.6438746438746437, "percentage": 88.28, "elapsed_time": "8:42:20", "remaining_time": "1:09:20"}
+{"current_steps": 590, "total_steps": 657, "loss": 0.5865, "learning_rate": 5e-06, "epoch": 2.6894586894586894, "percentage": 89.8, "elapsed_time": "8:51:11", "remaining_time": "1:00:19"}
+{"current_steps": 600, "total_steps": 657, "loss": 0.5862, "learning_rate": 5e-06, "epoch": 2.735042735042735, "percentage": 91.32, "elapsed_time": "9:00:03", "remaining_time": "0:51:18"}
+{"current_steps": 610, "total_steps": 657, "loss": 0.5856, "learning_rate": 5e-06, "epoch": 2.780626780626781, "percentage": 92.85, "elapsed_time": "9:08:55", "remaining_time": "0:42:17"}
+{"current_steps": 620, "total_steps": 657, "loss": 0.5874, "learning_rate": 5e-06, "epoch": 2.826210826210826, "percentage": 94.37, "elapsed_time": "9:17:47", "remaining_time": "0:33:17"}
+{"current_steps": 630, "total_steps": 657, "loss": 0.5889, "learning_rate": 5e-06, "epoch": 2.871794871794872, "percentage": 95.89, "elapsed_time": "9:26:38", "remaining_time": "0:24:17"}
+{"current_steps": 640, "total_steps": 657, "loss": 0.585, "learning_rate": 5e-06, "epoch": 2.9173789173789175, "percentage": 97.41, "elapsed_time": "9:35:29", "remaining_time": "0:15:17"}
+{"current_steps": 650, "total_steps": 657, "loss": 0.58, "learning_rate": 5e-06, "epoch": 2.962962962962963, "percentage": 98.93, "elapsed_time": "9:44:20", "remaining_time": "0:06:17"}