Training in progress, step 49

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4389bc853785f6f0b7a549fab1b3063262a707c18b546f54d132629472ce6fa5
+oid sha256:db7ee799c4d3c27ed7d566c982e345b115a5583eb3f85e50039a867d62084083
 size 2819582528

trainer_log.jsonl

@@ -12,3 +12,13 @@
 {"current_steps": 35, "total_steps": 125, "eval_loss": 0.36931881308555603, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:00:48", "remaining_time": "0:02:05", "throughput": 282.37, "total_tokens": 13824}
 {"current_steps": 40, "total_steps": 125, "loss": 0.3809, "lr": 4.364105412207914e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:00:58", "remaining_time": "0:02:05", "throughput": 268.48, "total_tokens": 15840}
 {"current_steps": 42, "total_steps": 125, "eval_loss": 0.3872639238834381, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:01:00", "remaining_time": "0:01:58", "throughput": 277.51, "total_tokens": 16672}
+{"current_steps": 45, "total_steps": 125, "loss": 0.3844, "lr": 4.1129299588552193e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:01:09", "remaining_time": "0:02:03", "throughput": 257.82, "total_tokens": 17920}
+{"current_steps": 49, "total_steps": 125, "eval_loss": 0.3777945637702942, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:01:10", "remaining_time": "0:01:50", "throughput": 272.03, "total_tokens": 19296}
+{"current_steps": 50, "total_steps": 125, "loss": 0.2817, "lr": 3.830080191288342e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:01:26", "remaining_time": "0:02:09", "throughput": 227.54, "total_tokens": 19712}
+{"current_steps": 55, "total_steps": 125, "loss": 0.3831, "lr": 3.521110642339991e-05, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:01:27", "remaining_time": "0:01:51", "throughput": 250.88, "total_tokens": 21952}
+{"current_steps": 56, "total_steps": 125, "eval_loss": 0.4436803460121155, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:01:28", "remaining_time": "0:01:48", "throughput": 253.75, "total_tokens": 22432}
+{"current_steps": 60, "total_steps": 125, "loss": 0.5576, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:01:37", "remaining_time": "0:01:46", "throughput": 246.65, "total_tokens": 24160}
+{"current_steps": 63, "total_steps": 125, "eval_loss": 0.35032057762145996, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:01:39", "remaining_time": "0:01:37", "throughput": 257.13, "total_tokens": 25504}
+{"current_steps": 65, "total_steps": 125, "loss": 0.4013, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:01:48", "remaining_time": "0:01:40", "throughput": 240.47, "total_tokens": 26112}
+{"current_steps": 70, "total_steps": 125, "loss": 0.3242, "lr": 2.5e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:49", "remaining_time": "0:01:25", "throughput": 256.58, "total_tokens": 28064}
+{"current_steps": 70, "total_steps": 125, "eval_loss": 0.37164703011512756, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:50", "remaining_time": "0:01:26", "throughput": 254.81, "total_tokens": 28064}