Training in progress, step 2300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:637d017e8d4d94ab07a703145f2af78722084a2aaf476d5f6576729ec37c71f4
+oid sha256:ee4d20084c020812db6dbd79fbf4828c8db14c421e8619ec1b2d21ffca81b370
 size 29034840

trainer_log.jsonl

@@ -505,3 +505,14 @@
 {"current_steps": 2245, "total_steps": 6770, "loss": 0.2496, "lr": 7.98477697267485e-05, "epoch": 0.6632200886262924, "percentage": 33.16, "elapsed_time": "2:59:11", "remaining_time": "6:01:10", "throughput": 2168.49, "total_tokens": 23314568}
 {"current_steps": 2250, "total_steps": 6770, "loss": 0.2332, "lr": 7.974970149098174e-05, "epoch": 0.6646971935007385, "percentage": 33.23, "elapsed_time": "3:00:38", "remaining_time": "6:02:53", "throughput": 2155.9, "total_tokens": 23366784}
 {"current_steps": 2250, "total_steps": 6770, "eval_loss": 0.4966147541999817, "epoch": 0.6646971935007385, "percentage": 33.23, "elapsed_time": "3:00:57", "remaining_time": "6:03:31", "throughput": 2152.09, "total_tokens": 23366784}
+{"current_steps": 2255, "total_steps": 6770, "loss": 0.3135, "lr": 7.965145576879423e-05, "epoch": 0.6661742983751846, "percentage": 33.31, "elapsed_time": "3:02:29", "remaining_time": "6:05:23", "throughput": 2138.79, "total_tokens": 23418504}
+{"current_steps": 2260, "total_steps": 6770, "loss": 0.3268, "lr": 7.955303314631898e-05, "epoch": 0.6676514032496307, "percentage": 33.38, "elapsed_time": "3:03:56", "remaining_time": "6:07:04", "throughput": 2126.5, "total_tokens": 23469840}
+{"current_steps": 2265, "total_steps": 6770, "loss": 0.2706, "lr": 7.945443421074436e-05, "epoch": 0.6691285081240768, "percentage": 33.46, "elapsed_time": "3:05:23", "remaining_time": "6:08:43", "throughput": 2114.63, "total_tokens": 23521416}
+{"current_steps": 2270, "total_steps": 6770, "loss": 0.2044, "lr": 7.935565955031064e-05, "epoch": 0.670605612998523, "percentage": 33.53, "elapsed_time": "3:06:50", "remaining_time": "6:10:22", "throughput": 2102.83, "total_tokens": 23573176}
+{"current_steps": 2275, "total_steps": 6770, "loss": 0.2724, "lr": 7.925670975430644e-05, "epoch": 0.672082717872969, "percentage": 33.6, "elapsed_time": "3:08:16", "remaining_time": "6:11:59", "throughput": 2091.44, "total_tokens": 23625080}
+{"current_steps": 2280, "total_steps": 6770, "loss": 0.2543, "lr": 7.915758541306523e-05, "epoch": 0.6735598227474151, "percentage": 33.68, "elapsed_time": "3:09:42", "remaining_time": "6:13:35", "throughput": 2080.16, "total_tokens": 23677096}
+{"current_steps": 2285, "total_steps": 6770, "loss": 0.2372, "lr": 7.90582871179619e-05, "epoch": 0.6750369276218612, "percentage": 33.75, "elapsed_time": "3:11:08", "remaining_time": "6:15:09", "throughput": 2069.13, "total_tokens": 23729168}
+{"current_steps": 2290, "total_steps": 6770, "loss": 0.2695, "lr": 7.895881546140902e-05, "epoch": 0.6765140324963073, "percentage": 33.83, "elapsed_time": "3:12:35", "remaining_time": "6:16:46", "throughput": 2057.97, "total_tokens": 23780568}
+{"current_steps": 2295, "total_steps": 6770, "loss": 0.3282, "lr": 7.885917103685353e-05, "epoch": 0.6779911373707533, "percentage": 33.9, "elapsed_time": "3:14:01", "remaining_time": "6:18:20", "throughput": 2047.05, "total_tokens": 23831360}
+{"current_steps": 2300, "total_steps": 6770, "loss": 0.2481, "lr": 7.875935443877305e-05, "epoch": 0.6794682422451994, "percentage": 33.97, "elapsed_time": "3:15:29", "remaining_time": "6:19:55", "throughput": 2036.18, "total_tokens": 23883032}
+{"current_steps": 2300, "total_steps": 6770, "eval_loss": 0.24180778861045837, "epoch": 0.6794682422451994, "percentage": 33.97, "elapsed_time": "3:15:48", "remaining_time": "6:20:32", "throughput": 2032.89, "total_tokens": 23883032}