Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba83473ace8f2ecdbc048dafa2d00257b4fa3a981f66b8f547625be4d8d6a90
+oid sha256:ad0a41144b9d8eea3b3f1de8e9e5e7c14c303c31098798928859d47cbd861a53
 size 18516456

trainer_log.jsonl

@@ -112,3 +112,14 @@
 {"current_steps": 495, "total_steps": 3400, "loss": 0.9132, "lr": 9.752267996462434e-05, "epoch": 0.254957507082153, "percentage": 14.56, "elapsed_time": "1:56:35", "remaining_time": "11:24:12", "throughput": 827.64, "total_tokens": 5789544}
 {"current_steps": 500, "total_steps": 3400, "loss": 0.8962, "lr": 9.744652884632406e-05, "epoch": 0.25753283543651817, "percentage": 14.71, "elapsed_time": "1:57:43", "remaining_time": "11:22:47", "throughput": 827.95, "total_tokens": 5848048}
 {"current_steps": 500, "total_steps": 3400, "eval_loss": 0.8987945914268494, "epoch": 0.25753283543651817, "percentage": 14.71, "elapsed_time": "1:58:00", "remaining_time": "11:24:26", "throughput": 825.94, "total_tokens": 5848048}
+{"current_steps": 505, "total_steps": 3400, "loss": 0.8954, "lr": 9.736925561061871e-05, "epoch": 0.26010816379088336, "percentage": 14.85, "elapsed_time": "1:59:12", "remaining_time": "11:23:24", "throughput": 825.76, "total_tokens": 5906512}
+{"current_steps": 510, "total_steps": 3400, "loss": 0.8927, "lr": 9.729086208503174e-05, "epoch": 0.2626834921452485, "percentage": 15.0, "elapsed_time": "2:00:20", "remaining_time": "11:21:55", "throughput": 826.14, "total_tokens": 5965024}
+{"current_steps": 515, "total_steps": 3400, "loss": 0.898, "lr": 9.721135012358156e-05, "epoch": 0.2652588204996137, "percentage": 15.15, "elapsed_time": "2:01:28", "remaining_time": "11:20:27", "throughput": 826.48, "total_tokens": 6023496}
+{"current_steps": 520, "total_steps": 3400, "loss": 0.9016, "lr": 9.713072160673777e-05, "epoch": 0.2678341488539789, "percentage": 15.29, "elapsed_time": "2:02:35", "remaining_time": "11:19:00", "throughput": 826.81, "total_tokens": 6082000}
+{"current_steps": 525, "total_steps": 3400, "loss": 0.8842, "lr": 9.704897844137673e-05, "epoch": 0.2704094772083441, "percentage": 15.44, "elapsed_time": "2:03:43", "remaining_time": "11:17:34", "throughput": 827.13, "total_tokens": 6140480}
+{"current_steps": 530, "total_steps": 3400, "loss": 0.8921, "lr": 9.696612256073633e-05, "epoch": 0.27298480556270927, "percentage": 15.59, "elapsed_time": "2:04:51", "remaining_time": "11:16:05", "throughput": 827.5, "total_tokens": 6198968}
+{"current_steps": 535, "total_steps": 3400, "loss": 0.8979, "lr": 9.688215592437039e-05, "epoch": 0.2755601339170744, "percentage": 15.74, "elapsed_time": "2:05:58", "remaining_time": "11:14:37", "throughput": 827.85, "total_tokens": 6257464}
+{"current_steps": 540, "total_steps": 3400, "loss": 0.8951, "lr": 9.679708051810221e-05, "epoch": 0.2781354622714396, "percentage": 15.88, "elapsed_time": "2:07:06", "remaining_time": "11:13:12", "throughput": 828.16, "total_tokens": 6315944}
+{"current_steps": 545, "total_steps": 3400, "loss": 0.9149, "lr": 9.67108983539777e-05, "epoch": 0.2807107906258048, "percentage": 16.03, "elapsed_time": "2:08:15", "remaining_time": "11:11:51", "throughput": 828.37, "total_tokens": 6374408}
+{"current_steps": 550, "total_steps": 3400, "loss": 0.9013, "lr": 9.662361147021779e-05, "epoch": 0.28328611898017, "percentage": 16.18, "elapsed_time": "2:09:23", "remaining_time": "11:10:29", "throughput": 828.6, "total_tokens": 6432936}
+{"current_steps": 550, "total_steps": 3400, "eval_loss": 0.9001271724700928, "epoch": 0.28328611898017, "percentage": 16.18, "elapsed_time": "2:09:40", "remaining_time": "11:11:57", "throughput": 826.79, "total_tokens": 6432936}