Training in progress, step 1300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49efabf09713516088de3465883ff1d8943c4d5b7de6e932ffa50531df3a26bb
+oid sha256:b44254d9a1623586ea1f5a75bfc6d736cfd5e37677b54824320d6e82460a2035
 size 29034840

trainer_log.jsonl

@@ -274,3 +274,14 @@
 {"current_steps": 1245, "total_steps": 6770, "loss": 0.3431, "lr": 9.518231677207192e-05, "epoch": 0.36779911373707536, "percentage": 18.39, "elapsed_time": "1:14:52", "remaining_time": "5:32:16", "throughput": 2875.92, "total_tokens": 12920168}
 {"current_steps": 1250, "total_steps": 6770, "loss": 0.335, "lr": 9.512987759739003e-05, "epoch": 0.36927621861152143, "percentage": 18.46, "elapsed_time": "1:16:20", "remaining_time": "5:37:06", "throughput": 2832.29, "total_tokens": 12972696}
 {"current_steps": 1250, "total_steps": 6770, "eval_loss": 0.31846168637275696, "epoch": 0.36927621861152143, "percentage": 18.46, "elapsed_time": "1:16:39", "remaining_time": "5:38:30", "throughput": 2820.63, "total_tokens": 12972696}
+{"current_steps": 1255, "total_steps": 6770, "loss": 0.3242, "lr": 9.507716917831099e-05, "epoch": 0.3707533234859675, "percentage": 18.54, "elapsed_time": "1:18:10", "remaining_time": "5:43:33", "throughput": 2776.73, "total_tokens": 13025280}
+{"current_steps": 1260, "total_steps": 6770, "loss": 0.4083, "lr": 9.50241918292927e-05, "epoch": 0.3722304283604136, "percentage": 18.61, "elapsed_time": "1:19:37", "remaining_time": "5:48:14", "throughput": 2736.74, "total_tokens": 13075992}
+{"current_steps": 1265, "total_steps": 6770, "loss": 0.4043, "lr": 9.49709458663975e-05, "epoch": 0.37370753323485967, "percentage": 18.69, "elapsed_time": "1:21:04", "remaining_time": "5:52:48", "throughput": 2699.0, "total_tokens": 13128592}
+{"current_steps": 1270, "total_steps": 6770, "loss": 0.3481, "lr": 9.491743160729026e-05, "epoch": 0.37518463810930575, "percentage": 18.76, "elapsed_time": "1:22:31", "remaining_time": "5:57:23", "throughput": 2662.2, "total_tokens": 13181824}
+{"current_steps": 1275, "total_steps": 6770, "loss": 0.4121, "lr": 9.486364937123651e-05, "epoch": 0.3766617429837518, "percentage": 18.83, "elapsed_time": "1:23:58", "remaining_time": "6:01:54", "throughput": 2626.51, "total_tokens": 13233624}
+{"current_steps": 1280, "total_steps": 6770, "loss": 0.487, "lr": 9.480959947910055e-05, "epoch": 0.37813884785819796, "percentage": 18.91, "elapsed_time": "1:25:26", "remaining_time": "6:06:25", "throughput": 2591.83, "total_tokens": 13285808}
+{"current_steps": 1285, "total_steps": 6770, "loss": 0.3798, "lr": 9.47552822533435e-05, "epoch": 0.37961595273264404, "percentage": 18.98, "elapsed_time": "1:26:54", "remaining_time": "6:10:57", "throughput": 2557.91, "total_tokens": 13337864}
+{"current_steps": 1290, "total_steps": 6770, "loss": 0.348, "lr": 9.470069801802135e-05, "epoch": 0.3810930576070901, "percentage": 19.05, "elapsed_time": "1:28:21", "remaining_time": "6:15:22", "throughput": 2525.65, "total_tokens": 13390544}
+{"current_steps": 1295, "total_steps": 6770, "loss": 0.41, "lr": 9.464584709878313e-05, "epoch": 0.3825701624815362, "percentage": 19.13, "elapsed_time": "1:29:50", "remaining_time": "6:19:48", "throughput": 2493.77, "total_tokens": 13441664}
+{"current_steps": 1300, "total_steps": 6770, "loss": 0.3594, "lr": 9.459072982286886e-05, "epoch": 0.38404726735598227, "percentage": 19.2, "elapsed_time": "1:31:16", "remaining_time": "6:24:03", "throughput": 2463.8, "total_tokens": 13493264}
+{"current_steps": 1300, "total_steps": 6770, "eval_loss": 0.4715976417064667, "epoch": 0.38404726735598227, "percentage": 19.2, "elapsed_time": "1:31:35", "remaining_time": "6:25:24", "throughput": 2455.24, "total_tokens": 13493264}