Training in progress, step 2100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58273020b4ec80c27bd67a1dcf93114d440f82a76094d3bc50faf05938ff6dc
+oid sha256:1b39895ee437656d2822d9ef3e148e364db825b03d8467830b69e5610c256e5a
 size 18516456

trainer_log.jsonl

@@ -453,3 +453,14 @@
 {"current_steps": 2045, "total_steps": 3400, "loss": 0.3864, "lr": 3.749015493966817e-05, "epoch": 1.0530517640999228, "percentage": 60.15, "elapsed_time": "7:37:04", "remaining_time": "5:02:51", "throughput": 871.93, "total_tokens": 23912520}
 {"current_steps": 2050, "total_steps": 3400, "loss": 0.3602, "lr": 3.7254880096057073e-05, "epoch": 1.0556270924542879, "percentage": 60.29, "elapsed_time": "7:38:09", "remaining_time": "5:01:42", "throughput": 872.01, "total_tokens": 23971048}
 {"current_steps": 2050, "total_steps": 3400, "eval_loss": 0.7190810441970825, "epoch": 1.0556270924542879, "percentage": 60.29, "elapsed_time": "7:38:25", "remaining_time": "5:01:53", "throughput": 871.5, "total_tokens": 23971048}
+{"current_steps": 2055, "total_steps": 3400, "loss": 0.3203, "lr": 3.7019906676411446e-05, "epoch": 1.0582024208086531, "percentage": 60.44, "elapsed_time": "7:39:34", "remaining_time": "5:00:47", "throughput": 871.43, "total_tokens": 24029544}
+{"current_steps": 2060, "total_steps": 3400, "loss": 0.3906, "lr": 3.678524023788735e-05, "epoch": 1.0607777491630184, "percentage": 60.59, "elapsed_time": "7:40:39", "remaining_time": "4:59:38", "throughput": 871.52, "total_tokens": 24088008}
+{"current_steps": 2065, "total_steps": 3400, "loss": 0.3604, "lr": 3.6550886330380665e-05, "epoch": 1.0633530775173834, "percentage": 60.74, "elapsed_time": "7:41:42", "remaining_time": "4:58:29", "throughput": 871.63, "total_tokens": 24146480}
+{"current_steps": 2070, "total_steps": 3400, "loss": 0.3271, "lr": 3.631685049639586e-05, "epoch": 1.0659284058717486, "percentage": 60.88, "elapsed_time": "7:42:46", "remaining_time": "4:57:20", "throughput": 871.73, "total_tokens": 24204984}
+{"current_steps": 2075, "total_steps": 3400, "loss": 0.2996, "lr": 3.608313827091493e-05, "epoch": 1.0685037342261139, "percentage": 61.03, "elapsed_time": "7:43:51", "remaining_time": "4:56:11", "throughput": 871.8, "total_tokens": 24263456}
+{"current_steps": 2080, "total_steps": 3400, "loss": 0.3767, "lr": 3.5849755181266474e-05, "epoch": 1.071079062580479, "percentage": 61.18, "elapsed_time": "7:44:55", "remaining_time": "4:55:03", "throughput": 871.88, "total_tokens": 24321960}
+{"current_steps": 2085, "total_steps": 3400, "loss": 0.4208, "lr": 3.5616706746995026e-05, "epoch": 1.0736543909348442, "percentage": 61.32, "elapsed_time": "7:46:00", "remaining_time": "4:53:54", "throughput": 871.96, "total_tokens": 24380464}
+{"current_steps": 2090, "total_steps": 3400, "loss": 0.3479, "lr": 3.538399847973036e-05, "epoch": 1.0762297192892094, "percentage": 61.47, "elapsed_time": "7:47:04", "remaining_time": "4:52:45", "throughput": 872.05, "total_tokens": 24438976}
+{"current_steps": 2095, "total_steps": 3400, "loss": 0.3654, "lr": 3.515163588305735e-05, "epoch": 1.0788050476435747, "percentage": 61.62, "elapsed_time": "7:48:09", "remaining_time": "4:51:37", "throughput": 872.12, "total_tokens": 24497448}
+{"current_steps": 2100, "total_steps": 3400, "loss": 0.3351, "lr": 3.491962445238569e-05, "epoch": 1.0813803759979397, "percentage": 61.76, "elapsed_time": "7:49:14", "remaining_time": "4:50:28", "throughput": 872.19, "total_tokens": 24555904}
+{"current_steps": 2100, "total_steps": 3400, "eval_loss": 0.8075026869773865, "epoch": 1.0813803759979397, "percentage": 61.76, "elapsed_time": "7:49:30", "remaining_time": "4:50:38", "throughput": 871.69, "total_tokens": 24555904}