Training in progress, step 1000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80df5e3a8d607d66820e6fd586076f2617165a54c1dd83c001587d2b85b8c1ef
+oid sha256:eec35e19707d55e085c42f2fc7f96384949ae1c2b6909dea425372d9568c8a7a
 size 29034840

trainer_log.jsonl

@@ -207,3 +207,14 @@
 {"current_steps": 945, "total_steps": 3882, "loss": 0.6968, "lr": 9.013299794022622e-05, "epoch": 0.4867370589750193, "percentage": 24.34, "elapsed_time": "4:50:55", "remaining_time": "15:04:10", "throughput": 633.21, "total_tokens": 11053016}
 {"current_steps": 950, "total_steps": 3882, "loss": 0.6825, "lr": 9.00055821768278e-05, "epoch": 0.4893123873293845, "percentage": 24.47, "elapsed_time": "4:52:24", "remaining_time": "15:02:28", "throughput": 633.32, "total_tokens": 11111520}
 {"current_steps": 950, "total_steps": 3882, "eval_loss": 0.6830747723579407, "epoch": 0.4893123873293845, "percentage": 24.47, "elapsed_time": "4:52:44", "remaining_time": "15:03:29", "throughput": 632.61, "total_tokens": 11111520}
+{"current_steps": 955, "total_steps": 3882, "loss": 0.6957, "lr": 8.987744028503981e-05, "epoch": 0.49188771568374967, "percentage": 24.6, "elapsed_time": "4:54:17", "remaining_time": "15:01:58", "throughput": 632.6, "total_tokens": 11170016}
+{"current_steps": 960, "total_steps": 3882, "loss": 0.6531, "lr": 8.974857459072435e-05, "epoch": 0.49446304403811486, "percentage": 24.73, "elapsed_time": "4:55:46", "remaining_time": "15:00:16", "throughput": 632.71, "total_tokens": 11228496}
+{"current_steps": 965, "total_steps": 3882, "loss": 0.6201, "lr": 8.961898743288094e-05, "epoch": 0.49703837239248005, "percentage": 24.86, "elapsed_time": "4:57:14", "remaining_time": "14:58:29", "throughput": 632.88, "total_tokens": 11286928}
+{"current_steps": 970, "total_steps": 3882, "loss": 0.5677, "lr": 8.948868116360421e-05, "epoch": 0.49961370074684525, "percentage": 24.99, "elapsed_time": "4:58:42", "remaining_time": "14:56:45", "throughput": 633.01, "total_tokens": 11345400}
+{"current_steps": 975, "total_steps": 3882, "loss": 0.5763, "lr": 8.935765814804112e-05, "epoch": 0.5021890291012104, "percentage": 25.12, "elapsed_time": "5:00:10", "remaining_time": "14:54:59", "throughput": 633.18, "total_tokens": 11403912}
+{"current_steps": 980, "total_steps": 3882, "loss": 0.6348, "lr": 8.922592076434804e-05, "epoch": 0.5047643574555756, "percentage": 25.24, "elapsed_time": "5:01:39", "remaining_time": "14:53:16", "throughput": 633.3, "total_tokens": 11462344}
+{"current_steps": 985, "total_steps": 3882, "loss": 0.6541, "lr": 8.90934714036477e-05, "epoch": 0.5073396858099408, "percentage": 25.37, "elapsed_time": "5:03:07", "remaining_time": "14:51:31", "throughput": 633.45, "total_tokens": 11520808}
+{"current_steps": 990, "total_steps": 3882, "loss": 0.7012, "lr": 8.896031246998558e-05, "epoch": 0.509915014164306, "percentage": 25.5, "elapsed_time": "5:04:35", "remaining_time": "14:49:45", "throughput": 633.61, "total_tokens": 11579248}
+{"current_steps": 995, "total_steps": 3882, "loss": 0.6508, "lr": 8.882644638028646e-05, "epoch": 0.5124903425186711, "percentage": 25.63, "elapsed_time": "5:06:03", "remaining_time": "14:48:01", "throughput": 633.74, "total_tokens": 11637712}
+{"current_steps": 1000, "total_steps": 3882, "loss": 0.5971, "lr": 8.869187556431046e-05, "epoch": 0.5150656708730363, "percentage": 25.76, "elapsed_time": "5:07:31", "remaining_time": "14:46:17", "throughput": 633.88, "total_tokens": 11696200}
+{"current_steps": 1000, "total_steps": 3882, "eval_loss": 0.7078786492347717, "epoch": 0.5150656708730363, "percentage": 25.76, "elapsed_time": "5:07:51", "remaining_time": "14:47:14", "throughput": 633.21, "total_tokens": 11696200}