Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d705dd99814267821cd8d09503bcdb39775b52c9a5778b863885f85c749a48a4
+oid sha256:87c5c5bb13b2f9891961a1af048bd7469b196705458eff48651ae470ca78403c
 size 29034840

trainer_log.jsonl

@@ -97,3 +97,14 @@
 {"current_steps": 445, "total_steps": 3400, "loss": 0.6258, "lr": 9.822209166377635e-05, "epoch": 0.11460211176925057, "percentage": 13.09, "elapsed_time": "2:18:17", "remaining_time": "15:18:17", "throughput": 562.81, "total_tokens": 4669784}
 {"current_steps": 450, "total_steps": 3400, "loss": 0.6732, "lr": 9.815725637431662e-05, "epoch": 0.11588977594643317, "percentage": 13.24, "elapsed_time": "2:19:48", "remaining_time": "15:16:28", "throughput": 563.01, "total_tokens": 4722528}
 {"current_steps": 450, "total_steps": 3400, "eval_loss": 0.6526497006416321, "epoch": 0.11588977594643317, "percentage": 13.24, "elapsed_time": "2:20:27", "remaining_time": "15:20:44", "throughput": 560.4, "total_tokens": 4722528}
+{"current_steps": 455, "total_steps": 3400, "loss": 0.6544, "lr": 9.809128215864097e-05, "epoch": 0.11717744012361576, "percentage": 13.38, "elapsed_time": "2:22:00", "remaining_time": "15:19:06", "throughput": 560.37, "total_tokens": 4774400}
+{"current_steps": 460, "total_steps": 3400, "loss": 0.652, "lr": 9.802417057704931e-05, "epoch": 0.11846510430079835, "percentage": 13.53, "elapsed_time": "2:23:28", "remaining_time": "15:17:02", "throughput": 560.67, "total_tokens": 4826704}
+{"current_steps": 465, "total_steps": 3400, "loss": 0.6582, "lr": 9.795592321674045e-05, "epoch": 0.11975276847798094, "percentage": 13.68, "elapsed_time": "2:24:56", "remaining_time": "15:14:49", "throughput": 561.17, "total_tokens": 4880072}
+{"current_steps": 470, "total_steps": 3400, "loss": 0.6506, "lr": 9.788654169177453e-05, "epoch": 0.12104043265516354, "percentage": 13.82, "elapsed_time": "2:26:24", "remaining_time": "15:12:43", "throughput": 561.43, "total_tokens": 4931968}
+{"current_steps": 475, "total_steps": 3400, "loss": 0.6551, "lr": 9.781602764303487e-05, "epoch": 0.12232809683234612, "percentage": 13.97, "elapsed_time": "2:27:52", "remaining_time": "15:10:36", "throughput": 561.69, "total_tokens": 4983656}
+{"current_steps": 480, "total_steps": 3400, "loss": 0.6978, "lr": 9.774438273818911e-05, "epoch": 0.12361576100952872, "percentage": 14.12, "elapsed_time": "2:29:20", "remaining_time": "15:08:32", "throughput": 562.05, "total_tokens": 5036528}
+{"current_steps": 485, "total_steps": 3400, "loss": 0.6407, "lr": 9.767160867164979e-05, "epoch": 0.12490342518671131, "percentage": 14.26, "elapsed_time": "2:30:49", "remaining_time": "15:06:32", "throughput": 562.3, "total_tokens": 5088768}
+{"current_steps": 490, "total_steps": 3400, "loss": 0.6641, "lr": 9.759770716453436e-05, "epoch": 0.1261910893638939, "percentage": 14.41, "elapsed_time": "2:32:17", "remaining_time": "15:04:26", "throughput": 562.73, "total_tokens": 5142080}
+{"current_steps": 495, "total_steps": 3400, "loss": 0.6588, "lr": 9.752267996462434e-05, "epoch": 0.1274787535410765, "percentage": 14.56, "elapsed_time": "2:33:47", "remaining_time": "15:02:30", "throughput": 562.95, "total_tokens": 5194432}
+{"current_steps": 500, "total_steps": 3400, "loss": 0.6304, "lr": 9.744652884632406e-05, "epoch": 0.12876641771825909, "percentage": 14.71, "elapsed_time": "2:35:15", "remaining_time": "15:00:27", "throughput": 563.24, "total_tokens": 5246640}
+{"current_steps": 500, "total_steps": 3400, "eval_loss": 0.6272165775299072, "epoch": 0.12876641771825909, "percentage": 14.71, "elapsed_time": "2:35:54", "remaining_time": "15:04:16", "throughput": 560.87, "total_tokens": 5246640}