Training in progress, epoch 1

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf0d5572d85b4f64e962a854d358b0766b24b8cbaed3919fbbc70a637267ca36
+oid sha256:b2aa3fcbd12f65c079990d9aa2c1c85aab2f0d26a0fc7113c42eff559bbd4197
 size 4938985352

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436742ff8334aa42b44e395c9793f7e43b3ab1f0a616855c2c683cf96b20ccbd
+oid sha256:353663238168d7534151fca4a4729dd66a4bea43b24e73a628300525f97ddd4f
 size 4947390880

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c02fe1efa43646b2c21a19615c2b0cc0975b4519becbfafe62a8f40446069af
+oid sha256:6baa42776b699eb59ad8a63347f64c79b30978dd4fe51cd859e80ba7f362458f
 size 3590488816

trainer_log.jsonl

@@ -7,3 +7,12 @@
 {"current_steps": 70, "total_steps": 237, "loss": 0.5358, "lr": 5e-06, "epoch": 0.8763693270735524, "percentage": 29.54, "elapsed_time": "1:03:28", "remaining_time": "2:31:25"}
 {"current_steps": 79, "total_steps": 237, "eval_loss": 0.526888906955719, "epoch": 0.9890453834115805, "percentage": 33.33, "elapsed_time": "1:13:47", "remaining_time": "2:27:35"}
 {"current_steps": 80, "total_steps": 237, "loss": 0.5358, "lr": 5e-06, "epoch": 1.001564945226917, "percentage": 33.76, "elapsed_time": "1:14:58", "remaining_time": "2:27:09"}
+{"current_steps": 90, "total_steps": 237, "loss": 0.5137, "lr": 5e-06, "epoch": 1.1267605633802817, "percentage": 37.97, "elapsed_time": "1:24:03", "remaining_time": "2:17:18"}
+{"current_steps": 100, "total_steps": 237, "loss": 0.497, "lr": 5e-06, "epoch": 1.2519561815336462, "percentage": 42.19, "elapsed_time": "1:33:10", "remaining_time": "2:07:38"}
+{"current_steps": 110, "total_steps": 237, "loss": 0.4959, "lr": 5e-06, "epoch": 1.3771517996870108, "percentage": 46.41, "elapsed_time": "1:42:16", "remaining_time": "1:58:04"}
+{"current_steps": 120, "total_steps": 237, "loss": 0.495, "lr": 5e-06, "epoch": 1.5023474178403755, "percentage": 50.63, "elapsed_time": "1:51:22", "remaining_time": "1:48:35"}
+{"current_steps": 130, "total_steps": 237, "loss": 0.4827, "lr": 5e-06, "epoch": 1.6275430359937402, "percentage": 54.85, "elapsed_time": "2:00:27", "remaining_time": "1:39:08"}
+{"current_steps": 140, "total_steps": 237, "loss": 0.4899, "lr": 5e-06, "epoch": 1.7527386541471048, "percentage": 59.07, "elapsed_time": "2:09:32", "remaining_time": "1:29:45"}
+{"current_steps": 150, "total_steps": 237, "loss": 0.4852, "lr": 5e-06, "epoch": 1.8779342723004695, "percentage": 63.29, "elapsed_time": "2:18:38", "remaining_time": "1:20:24"}
+{"current_steps": 159, "total_steps": 237, "eval_loss": 0.49927353858947754, "epoch": 1.9906103286384975, "percentage": 67.09, "elapsed_time": "2:28:46", "remaining_time": "1:12:59"}
+{"current_steps": 160, "total_steps": 237, "loss": 0.4861, "lr": 5e-06, "epoch": 2.003129890453834, "percentage": 67.51, "elapsed_time": "2:30:08", "remaining_time": "1:12:15"}