Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c376e64fb5f34160ee951d397ea4a38ad3dd5c06122aadc3446a3b2148c3c6d
+oid sha256:469a98fbc6896c783d21345cf47acbe97a753d3fb3ddbcd50e7ebfbce6f0f52d
 size 4903351912

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae28ba6a3e5800497381a302934f8026e9d634555cfa60da6fddefeb27beac9
+oid sha256:50fd02c3d56456a8fcb35def311d083e600956628065f7dbc7e6f06e8703b9ee
 size 4947570872

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ae89cc41315d0c8fe8ddddfbe3f03f77042e7c64247e20da81a7d7088ed5c0
+oid sha256:38284cd6ec70205e8fbbdf52927470e82a119fab94c91e85fbdb0fa0fbb0c45c
 size 4962221464

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d261735f2da7cbfdfea5f65236c90287e425e92e0ee71f3133fea13be73a292e
+oid sha256:dc002edd557284ed00d2e010b52ca0029d2bc118d0c5aa5a8009b558a19b40c4
 size 3670322200

trainer_log.jsonl

@@ -44,3 +44,25 @@
 {"current_steps": 430, "total_steps": 663, "loss": 0.5486, "learning_rate": 5e-06, "epoch": 1.9418899858956276, "percentage": 64.86, "elapsed_time": "10:55:58", "remaining_time": "5:55:26"}
 {"current_steps": 440, "total_steps": 663, "loss": 0.5591, "learning_rate": 5e-06, "epoch": 1.987023977433004, "percentage": 66.37, "elapsed_time": "11:11:04", "remaining_time": "5:40:06"}
 {"current_steps": 442, "total_steps": 663, "eval_loss": 0.5866958498954773, "epoch": 1.9960507757404795, "percentage": 66.67, "elapsed_time": "11:20:56", "remaining_time": "5:40:28"}
+{"current_steps": 450, "total_steps": 663, "loss": 0.5574, "learning_rate": 5e-06, "epoch": 2.0332863187588153, "percentage": 67.87, "elapsed_time": "11:33:17", "remaining_time": "5:28:09"}
+{"current_steps": 460, "total_steps": 663, "loss": 0.5064, "learning_rate": 5e-06, "epoch": 2.078420310296192, "percentage": 69.38, "elapsed_time": "11:48:25", "remaining_time": "5:12:37"}
+{"current_steps": 470, "total_steps": 663, "loss": 0.5109, "learning_rate": 5e-06, "epoch": 2.1235543018335683, "percentage": 70.89, "elapsed_time": "12:03:32", "remaining_time": "4:57:06"}
+{"current_steps": 480, "total_steps": 663, "loss": 0.5119, "learning_rate": 5e-06, "epoch": 2.168688293370945, "percentage": 72.4, "elapsed_time": "12:18:40", "remaining_time": "4:41:37"}
+{"current_steps": 490, "total_steps": 663, "loss": 0.5045, "learning_rate": 5e-06, "epoch": 2.213822284908322, "percentage": 73.91, "elapsed_time": "12:33:48", "remaining_time": "4:26:08"}
+{"current_steps": 500, "total_steps": 663, "loss": 0.5058, "learning_rate": 5e-06, "epoch": 2.2589562764456983, "percentage": 75.41, "elapsed_time": "12:48:56", "remaining_time": "4:10:40"}
+{"current_steps": 510, "total_steps": 663, "loss": 0.5134, "learning_rate": 5e-06, "epoch": 2.304090267983075, "percentage": 76.92, "elapsed_time": "13:04:03", "remaining_time": "3:55:13"}
+{"current_steps": 520, "total_steps": 663, "loss": 0.5135, "learning_rate": 5e-06, "epoch": 2.3492242595204513, "percentage": 78.43, "elapsed_time": "13:19:11", "remaining_time": "3:39:46"}
+{"current_steps": 530, "total_steps": 663, "loss": 0.5115, "learning_rate": 5e-06, "epoch": 2.394358251057828, "percentage": 79.94, "elapsed_time": "13:34:19", "remaining_time": "3:24:21"}
+{"current_steps": 540, "total_steps": 663, "loss": 0.5102, "learning_rate": 5e-06, "epoch": 2.4394922425952044, "percentage": 81.45, "elapsed_time": "13:49:27", "remaining_time": "3:08:55"}
+{"current_steps": 550, "total_steps": 663, "loss": 0.5163, "learning_rate": 5e-06, "epoch": 2.4846262341325813, "percentage": 82.96, "elapsed_time": "14:04:35", "remaining_time": "2:53:31"}
+{"current_steps": 560, "total_steps": 663, "loss": 0.5115, "learning_rate": 5e-06, "epoch": 2.529760225669958, "percentage": 84.46, "elapsed_time": "14:19:42", "remaining_time": "2:38:07"}
+{"current_steps": 570, "total_steps": 663, "loss": 0.5129, "learning_rate": 5e-06, "epoch": 2.5748942172073344, "percentage": 85.97, "elapsed_time": "14:34:49", "remaining_time": "2:22:44"}
+{"current_steps": 580, "total_steps": 663, "loss": 0.5121, "learning_rate": 5e-06, "epoch": 2.620028208744711, "percentage": 87.48, "elapsed_time": "14:49:56", "remaining_time": "2:07:21"}
+{"current_steps": 590, "total_steps": 663, "loss": 0.5117, "learning_rate": 5e-06, "epoch": 2.6651622002820874, "percentage": 88.99, "elapsed_time": "15:05:02", "remaining_time": "1:51:58"}
+{"current_steps": 600, "total_steps": 663, "loss": 0.5162, "learning_rate": 5e-06, "epoch": 2.710296191819464, "percentage": 90.5, "elapsed_time": "15:20:08", "remaining_time": "1:36:36"}
+{"current_steps": 610, "total_steps": 663, "loss": 0.5132, "learning_rate": 5e-06, "epoch": 2.7554301833568404, "percentage": 92.01, "elapsed_time": "15:35:16", "remaining_time": "1:21:15"}
+{"current_steps": 620, "total_steps": 663, "loss": 0.518, "learning_rate": 5e-06, "epoch": 2.800564174894217, "percentage": 93.51, "elapsed_time": "15:50:22", "remaining_time": "1:05:54"}
+{"current_steps": 630, "total_steps": 663, "loss": 0.5195, "learning_rate": 5e-06, "epoch": 2.845698166431594, "percentage": 95.02, "elapsed_time": "16:05:28", "remaining_time": "0:50:34"}
+{"current_steps": 640, "total_steps": 663, "loss": 0.5135, "learning_rate": 5e-06, "epoch": 2.8908321579689704, "percentage": 96.53, "elapsed_time": "16:20:36", "remaining_time": "0:35:14"}
+{"current_steps": 650, "total_steps": 663, "loss": 0.5154, "learning_rate": 5e-06, "epoch": 2.935966149506347, "percentage": 98.04, "elapsed_time": "16:35:40", "remaining_time": "0:19:54"}
+{"current_steps": 660, "total_steps": 663, "loss": 0.5153, "learning_rate": 5e-06, "epoch": 2.9811001410437235, "percentage": 99.55, "elapsed_time": "16:50:45", "remaining_time": "0:04:35"}