Training in progress, step 2100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c07c45cd740f6c38df8b73c4bc4f9f8c11bd6712886d745d8476e5ba112852
+oid sha256:a111e8798c83c643eeba02e2a149e66e3437bb97bb843d76a35308962c3f1d78
 size 29034840

trainer_log.jsonl

@@ -449,3 +449,14 @@
 {"current_steps": 2045, "total_steps": 3882, "loss": 0.2534, "lr": 4.972307773460133e-05, "epoch": 1.0530517640999228, "percentage": 52.68, "elapsed_time": "10:24:37", "remaining_time": "9:21:05", "throughput": 638.06, "total_tokens": 23912520}
 {"current_steps": 2050, "total_steps": 3882, "loss": 0.2924, "lr": 4.9510065943012076e-05, "epoch": 1.0556270924542879, "percentage": 52.81, "elapsed_time": "10:26:05", "remaining_time": "9:19:30", "throughput": 638.11, "total_tokens": 23971048}
 {"current_steps": 2050, "total_steps": 3882, "eval_loss": 0.2703675329685211, "epoch": 1.0556270924542879, "percentage": 52.81, "elapsed_time": "10:26:25", "remaining_time": "9:19:48", "throughput": 637.78, "total_tokens": 23971048}
+{"current_steps": 2055, "total_steps": 3882, "loss": 0.217, "lr": 4.929706304405748e-05, "epoch": 1.0582024208086531, "percentage": 52.94, "elapsed_time": "10:27:58", "remaining_time": "9:18:18", "throughput": 637.75, "total_tokens": 24029544}
+{"current_steps": 2060, "total_steps": 3882, "loss": 0.2132, "lr": 4.9084072903884345e-05, "epoch": 1.0607777491630184, "percentage": 53.07, "elapsed_time": "10:29:27", "remaining_time": "9:16:44", "throughput": 637.8, "total_tokens": 24088008}
+{"current_steps": 2065, "total_steps": 3882, "loss": 0.2438, "lr": 4.887109938840783e-05, "epoch": 1.0633530775173834, "percentage": 53.19, "elapsed_time": "10:30:55", "remaining_time": "9:15:08", "throughput": 637.86, "total_tokens": 24146480}
+{"current_steps": 2070, "total_steps": 3882, "loss": 0.2623, "lr": 4.8658146363241406e-05, "epoch": 1.0659284058717486, "percentage": 53.32, "elapsed_time": "10:32:23", "remaining_time": "9:13:34", "throughput": 637.92, "total_tokens": 24204984}
+{"current_steps": 2075, "total_steps": 3882, "loss": 0.2041, "lr": 4.844521769362654e-05, "epoch": 1.0685037342261139, "percentage": 53.45, "elapsed_time": "10:33:51", "remaining_time": "9:11:59", "throughput": 637.99, "total_tokens": 24263456}
+{"current_steps": 2080, "total_steps": 3882, "loss": 0.246, "lr": 4.823231724436271e-05, "epoch": 1.071079062580479, "percentage": 53.58, "elapsed_time": "10:35:19", "remaining_time": "9:10:25", "throughput": 638.04, "total_tokens": 24321960}
+{"current_steps": 2085, "total_steps": 3882, "loss": 0.2857, "lr": 4.801944887973714e-05, "epoch": 1.0736543909348442, "percentage": 53.71, "elapsed_time": "10:36:47", "remaining_time": "9:08:50", "throughput": 638.1, "total_tokens": 24380464}
+{"current_steps": 2090, "total_steps": 3882, "loss": 0.2577, "lr": 4.7806616463454715e-05, "epoch": 1.0762297192892094, "percentage": 53.84, "elapsed_time": "10:38:16", "remaining_time": "9:07:15", "throughput": 638.16, "total_tokens": 24438976}
+{"current_steps": 2095, "total_steps": 3882, "loss": 0.2523, "lr": 4.759382385856779e-05, "epoch": 1.0788050476435747, "percentage": 53.97, "elapsed_time": "10:39:45", "remaining_time": "9:05:41", "throughput": 638.2, "total_tokens": 24497448}
+{"current_steps": 2100, "total_steps": 3882, "loss": 0.2805, "lr": 4.738107492740619e-05, "epoch": 1.0813803759979397, "percentage": 54.1, "elapsed_time": "10:41:13", "remaining_time": "9:04:07", "throughput": 638.26, "total_tokens": 24555904}
+{"current_steps": 2100, "total_steps": 3882, "eval_loss": 0.3205481469631195, "epoch": 1.0813803759979397, "percentage": 54.1, "elapsed_time": "10:41:32", "remaining_time": "9:04:23", "throughput": 637.94, "total_tokens": 24555904}