Training in progress, step 2900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab786f741c7a478f92cbba3fdd1ddd3a418946d605848f775e0f6c469c96daf4
+oid sha256:f649bc97ca842140ab28c612e0e561ebbde8139ce799f23e401fad5ec0bf673a
 size 29034840

trainer_log.jsonl

@@ -637,3 +637,14 @@
 {"current_steps": 2845, "total_steps": 6770, "loss": 0.1715, "lr": 6.698491824460371e-05, "epoch": 0.8404726735598228, "percentage": 42.02, "elapsed_time": "5:57:53", "remaining_time": "8:13:44", "throughput": 1376.04, "total_tokens": 29548008}
 {"current_steps": 2850, "total_steps": 6770, "loss": 0.1928, "lr": 6.687000312800178e-05, "epoch": 0.8419497784342689, "percentage": 42.1, "elapsed_time": "5:59:21", "remaining_time": "8:14:17", "throughput": 1372.81, "total_tokens": 29600536}
 {"current_steps": 2850, "total_steps": 6770, "eval_loss": 0.28275948762893677, "epoch": 0.8419497784342689, "percentage": 42.1, "elapsed_time": "5:59:41", "remaining_time": "8:14:44", "throughput": 1371.57, "total_tokens": 29600536}
+{"current_steps": 2855, "total_steps": 6770, "loss": 0.2163, "lr": 6.675498736513036e-05, "epoch": 0.843426883308715, "percentage": 42.17, "elapsed_time": "6:01:13", "remaining_time": "8:15:20", "throughput": 1368.13, "total_tokens": 29652440}
+{"current_steps": 2860, "total_steps": 6770, "loss": 0.2589, "lr": 6.663987164217236e-05, "epoch": 0.844903988183161, "percentage": 42.25, "elapsed_time": "6:02:41", "remaining_time": "8:15:50", "throughput": 1365.0, "total_tokens": 29704376}
+{"current_steps": 2865, "total_steps": 6770, "loss": 0.2325, "lr": 6.652465664590703e-05, "epoch": 0.8463810930576071, "percentage": 42.32, "elapsed_time": "6:04:07", "remaining_time": "8:16:18", "throughput": 1362.0, "total_tokens": 29756504}
+{"current_steps": 2870, "total_steps": 6770, "loss": 0.242, "lr": 6.640934306370586e-05, "epoch": 0.8478581979320532, "percentage": 42.39, "elapsed_time": "6:05:35", "remaining_time": "8:16:47", "throughput": 1358.88, "total_tokens": 29807328}
+{"current_steps": 2875, "total_steps": 6770, "loss": 0.2169, "lr": 6.629393158352854e-05, "epoch": 0.8493353028064993, "percentage": 42.47, "elapsed_time": "6:07:01", "remaining_time": "8:17:14", "throughput": 1355.89, "total_tokens": 29859208}
+{"current_steps": 2880, "total_steps": 6770, "loss": 0.2335, "lr": 6.61784228939188e-05, "epoch": 0.8508124076809453, "percentage": 42.54, "elapsed_time": "6:08:28", "remaining_time": "8:17:41", "throughput": 1352.93, "total_tokens": 29911128}
+{"current_steps": 2885, "total_steps": 6770, "loss": 0.1913, "lr": 6.606281768400032e-05, "epoch": 0.8522895125553914, "percentage": 42.61, "elapsed_time": "6:09:55", "remaining_time": "8:18:08", "throughput": 1349.95, "total_tokens": 29962384}
+{"current_steps": 2890, "total_steps": 6770, "loss": 0.2425, "lr": 6.594711664347264e-05, "epoch": 0.8537666174298375, "percentage": 42.69, "elapsed_time": "6:11:22", "remaining_time": "8:18:35", "throughput": 1346.98, "total_tokens": 30013664}
+{"current_steps": 2895, "total_steps": 6770, "loss": 0.2312, "lr": 6.5831320462607e-05, "epoch": 0.8552437223042836, "percentage": 42.76, "elapsed_time": "6:12:49", "remaining_time": "8:19:01", "throughput": 1344.06, "total_tokens": 30066016}
+{"current_steps": 2900, "total_steps": 6770, "loss": 0.2029, "lr": 6.571542983224223e-05, "epoch": 0.8567208271787297, "percentage": 42.84, "elapsed_time": "6:14:15", "remaining_time": "8:19:26", "throughput": 1341.23, "total_tokens": 30118072}
+{"current_steps": 2900, "total_steps": 6770, "eval_loss": 0.39434579014778137, "epoch": 0.8567208271787297, "percentage": 42.84, "elapsed_time": "6:14:34", "remaining_time": "8:19:52", "throughput": 1340.09, "total_tokens": 30118072}