Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0a41144b9d8eea3b3f1de8e9e5e7c14c303c31098798928859d47cbd861a53
+oid sha256:d1513791e52117a6d639f05fdddf98b812e9b7c86a4830e79581dc7ae45e41a8
 size 18516456

trainer_log.jsonl

@@ -123,3 +123,14 @@
 {"current_steps": 545, "total_steps": 3400, "loss": 0.9149, "lr": 9.67108983539777e-05, "epoch": 0.2807107906258048, "percentage": 16.03, "elapsed_time": "2:08:15", "remaining_time": "11:11:51", "throughput": 828.37, "total_tokens": 6374408}
 {"current_steps": 550, "total_steps": 3400, "loss": 0.9013, "lr": 9.662361147021779e-05, "epoch": 0.28328611898017, "percentage": 16.18, "elapsed_time": "2:09:23", "remaining_time": "11:10:29", "throughput": 828.6, "total_tokens": 6432936}
 {"current_steps": 550, "total_steps": 3400, "eval_loss": 0.9001271724700928, "epoch": 0.28328611898017, "percentage": 16.18, "elapsed_time": "2:09:40", "remaining_time": "11:11:57", "throughput": 826.79, "total_tokens": 6432936}
+{"current_steps": 555, "total_steps": 3400, "loss": 0.8981, "lr": 9.653522193117013e-05, "epoch": 0.28586144733453517, "percentage": 16.32, "elapsed_time": "2:10:53", "remaining_time": "11:10:57", "throughput": 826.56, "total_tokens": 6491400}
+{"current_steps": 560, "total_steps": 3400, "loss": 0.9041, "lr": 9.644573182726035e-05, "epoch": 0.28843677568890036, "percentage": 16.47, "elapsed_time": "2:12:01", "remaining_time": "11:09:31", "throughput": 826.89, "total_tokens": 6549872}
+{"current_steps": 565, "total_steps": 3400, "loss": 0.9024, "lr": 9.63551432749426e-05, "epoch": 0.2910121040432655, "percentage": 16.62, "elapsed_time": "2:13:08", "remaining_time": "11:08:04", "throughput": 827.21, "total_tokens": 6608296}
+{"current_steps": 570, "total_steps": 3400, "loss": 0.9002, "lr": 9.626345841664953e-05, "epoch": 0.2935874323976307, "percentage": 16.76, "elapsed_time": "2:14:16", "remaining_time": "11:06:41", "throughput": 827.46, "total_tokens": 6666768}
+{"current_steps": 575, "total_steps": 3400, "loss": 0.9035, "lr": 9.617067942074153e-05, "epoch": 0.2961627607519959, "percentage": 16.91, "elapsed_time": "2:15:24", "remaining_time": "11:05:16", "throughput": 827.76, "total_tokens": 6725248}
+{"current_steps": 580, "total_steps": 3400, "loss": 0.9019, "lr": 9.607680848145558e-05, "epoch": 0.29873808910636107, "percentage": 17.06, "elapsed_time": "2:16:32", "remaining_time": "11:03:54", "throughput": 827.99, "total_tokens": 6783680}
+{"current_steps": 585, "total_steps": 3400, "loss": 0.9001, "lr": 9.598184781885318e-05, "epoch": 0.30131341746072626, "percentage": 17.21, "elapsed_time": "2:17:40", "remaining_time": "11:02:30", "throughput": 828.27, "total_tokens": 6842144}
+{"current_steps": 590, "total_steps": 3400, "loss": 0.8961, "lr": 9.588579967876806e-05, "epoch": 0.3038887458150914, "percentage": 17.35, "elapsed_time": "2:18:48", "remaining_time": "11:01:05", "throughput": 828.58, "total_tokens": 6900656}
+{"current_steps": 595, "total_steps": 3400, "loss": 0.9, "lr": 9.578866633275288e-05, "epoch": 0.3064640741694566, "percentage": 17.5, "elapsed_time": "2:19:56", "remaining_time": "10:59:41", "throughput": 828.86, "total_tokens": 6959128}
+{"current_steps": 600, "total_steps": 3400, "loss": 0.9046, "lr": 9.569045007802559e-05, "epoch": 0.3090394025238218, "percentage": 17.65, "elapsed_time": "2:21:03", "remaining_time": "10:58:14", "throughput": 829.2, "total_tokens": 7017576}
+{"current_steps": 600, "total_steps": 3400, "eval_loss": 0.9053278565406799, "epoch": 0.3090394025238218, "percentage": 17.65, "elapsed_time": "2:21:20", "remaining_time": "10:59:34", "throughput": 827.52, "total_tokens": 7017576}