Training in progress, step 3100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb314047f6c123f2abaf4b7b141070b2299dee4fc65b9c0ec7277494419776e
+oid sha256:fae7873da4e864e2fb488bd3cadfc022d2333da4131c0ae5cf85dc328c20163a
 size 18516456

trainer_log.jsonl

@@ -673,3 +673,14 @@
 {"current_steps": 3045, "total_steps": 3400, "loss": 0.2485, "lr": 2.951021558623274e-06, "epoch": 1.568117434972959, "percentage": 89.56, "elapsed_time": "11:16:21", "remaining_time": "1:18:51", "throughput": 877.45, "total_tokens": 35608488}
 {"current_steps": 3050, "total_steps": 3400, "loss": 0.2851, "lr": 2.869278393262226e-06, "epoch": 1.5706927633273242, "percentage": 89.71, "elapsed_time": "11:17:25", "remaining_time": "1:17:44", "throughput": 877.5, "total_tokens": 35666976}
 {"current_steps": 3050, "total_steps": 3400, "eval_loss": 0.8473746180534363, "epoch": 1.5706927633273242, "percentage": 89.71, "elapsed_time": "11:17:41", "remaining_time": "1:17:46", "throughput": 877.16, "total_tokens": 35666976}
+{"current_steps": 3055, "total_steps": 3400, "loss": 0.2514, "lr": 2.7886498764184588e-06, "epoch": 1.5732680916816895, "percentage": 89.85, "elapsed_time": "11:18:51", "remaining_time": "1:16:39", "throughput": 877.1, "total_tokens": 35725456}
+{"current_steps": 3060, "total_steps": 3400, "loss": 0.3091, "lr": 2.7091379149682685e-06, "epoch": 1.5758434200360547, "percentage": 90.0, "elapsed_time": "11:19:55", "remaining_time": "1:15:32", "throughput": 877.15, "total_tokens": 35783912}
+{"current_steps": 3065, "total_steps": 3400, "loss": 0.2629, "lr": 2.6307443893812843e-06, "epoch": 1.5784187483904197, "percentage": 90.15, "elapsed_time": "11:20:59", "remaining_time": "1:14:25", "throughput": 877.21, "total_tokens": 35842376}
+{"current_steps": 3070, "total_steps": 3400, "loss": 0.3065, "lr": 2.5534711536759404e-06, "epoch": 1.580994076744785, "percentage": 90.29, "elapsed_time": "11:22:04", "remaining_time": "1:13:19", "throughput": 877.25, "total_tokens": 35900824}
+{"current_steps": 3075, "total_steps": 3400, "loss": 0.2577, "lr": 2.4773200353756798e-06, "epoch": 1.58356940509915, "percentage": 90.44, "elapsed_time": "11:23:08", "remaining_time": "1:12:12", "throughput": 877.3, "total_tokens": 35959264}
+{"current_steps": 3080, "total_steps": 3400, "loss": 0.2359, "lr": 2.4022928354656473e-06, "epoch": 1.5861447334535153, "percentage": 90.59, "elapsed_time": "11:24:12", "remaining_time": "1:11:05", "throughput": 877.35, "total_tokens": 36017760}
+{"current_steps": 3085, "total_steps": 3400, "loss": 0.1897, "lr": 2.3283913283502044e-06, "epoch": 1.5887200618078805, "percentage": 90.74, "elapsed_time": "11:25:17", "remaining_time": "1:09:58", "throughput": 877.4, "total_tokens": 36076280}
+{"current_steps": 3090, "total_steps": 3400, "loss": 0.286, "lr": 2.2556172618108997e-06, "epoch": 1.5912953901622457, "percentage": 90.88, "elapsed_time": "11:26:21", "remaining_time": "1:08:51", "throughput": 877.44, "total_tokens": 36134784}
+{"current_steps": 3095, "total_steps": 3400, "loss": 0.2733, "lr": 2.183972356965125e-06, "epoch": 1.593870718516611, "percentage": 91.03, "elapsed_time": "11:27:26", "remaining_time": "1:07:44", "throughput": 877.49, "total_tokens": 36193288}
+{"current_steps": 3100, "total_steps": 3400, "loss": 0.2351, "lr": 2.113458308225458e-06, "epoch": 1.596446046870976, "percentage": 91.18, "elapsed_time": "11:28:30", "remaining_time": "1:06:37", "throughput": 877.54, "total_tokens": 36251744}
+{"current_steps": 3100, "total_steps": 3400, "eval_loss": 0.8650907874107361, "epoch": 1.596446046870976, "percentage": 91.18, "elapsed_time": "11:28:46", "remaining_time": "1:06:39", "throughput": 877.2, "total_tokens": 36251744}