Training in progress, step 3250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb7a1dd58ebc0c93ef82d01cefb2df34681f15debd4b2701f60fafd33e16761
+oid sha256:642c404d73293fddcd261352a6740967f2766dca25c2923d3502bb6f1bfc7e20
 size 29034840

trainer_log.jsonl

@@ -705,3 +705,14 @@
 {"current_steps": 3195, "total_steps": 3400, "loss": 0.3231, "lr": 9.906109807887032e-07, "epoch": 0.8228174092196755, "percentage": 93.97, "elapsed_time": "3:15:55", "remaining_time": "0:12:34", "throughput": 2854.25, "total_tokens": 33552400}
 {"current_steps": 3200, "total_steps": 3400, "loss": 0.3322, "lr": 9.430284218824026e-07, "epoch": 0.8241050733968581, "percentage": 94.12, "elapsed_time": "3:17:21", "remaining_time": "0:12:20", "throughput": 2837.93, "total_tokens": 33604328}
 {"current_steps": 3200, "total_steps": 3400, "eval_loss": 0.47025421261787415, "epoch": 0.8241050733968581, "percentage": 94.12, "elapsed_time": "3:17:58", "remaining_time": "0:12:22", "throughput": 2828.96, "total_tokens": 33604328}
+{"current_steps": 3205, "total_steps": 3400, "loss": 0.2841, "lr": 8.966060675892951e-07, "epoch": 0.8253927375740406, "percentage": 94.26, "elapsed_time": "3:19:28", "remaining_time": "0:12:08", "throughput": 2812.01, "total_tokens": 33656768}
+{"current_steps": 3210, "total_steps": 3400, "loss": 0.3064, "lr": 8.513450158049108e-07, "epoch": 0.8266804017512233, "percentage": 94.41, "elapsed_time": "3:20:54", "remaining_time": "0:11:53", "throughput": 2796.49, "total_tokens": 33709960}
+{"current_steps": 3215, "total_steps": 3400, "loss": 0.3126, "lr": 8.072463369597993e-07, "epoch": 0.8279680659284059, "percentage": 94.56, "elapsed_time": "3:22:19", "remaining_time": "0:11:38", "throughput": 2781.09, "total_tokens": 33762336}
+{"current_steps": 3220, "total_steps": 3400, "loss": 0.2758, "lr": 7.643110739942172e-07, "epoch": 0.8292557301055885, "percentage": 94.71, "elapsed_time": "3:23:45", "remaining_time": "0:11:23", "throughput": 2765.89, "total_tokens": 33814544}
+{"current_steps": 3225, "total_steps": 3400, "loss": 0.3154, "lr": 7.225402423334693e-07, "epoch": 0.830543394282771, "percentage": 94.85, "elapsed_time": "3:25:11", "remaining_time": "0:11:08", "throughput": 2750.96, "total_tokens": 33867184}
+{"current_steps": 3230, "total_steps": 3400, "loss": 0.2894, "lr": 6.819348298638839e-07, "epoch": 0.8318310584599536, "percentage": 95.0, "elapsed_time": "3:26:36", "remaining_time": "0:10:52", "throughput": 2736.37, "total_tokens": 33920120}
+{"current_steps": 3235, "total_steps": 3400, "loss": 0.2521, "lr": 6.424957969094536e-07, "epoch": 0.8331187226371363, "percentage": 95.15, "elapsed_time": "3:28:02", "remaining_time": "0:10:36", "throughput": 2721.63, "total_tokens": 33971928}
+{"current_steps": 3240, "total_steps": 3400, "loss": 0.3532, "lr": 6.0422407620912e-07, "epoch": 0.8344063868143188, "percentage": 95.29, "elapsed_time": "3:29:27", "remaining_time": "0:10:20", "throughput": 2707.38, "total_tokens": 34024272}
+{"current_steps": 3245, "total_steps": 3400, "loss": 0.2519, "lr": 5.671205728947305e-07, "epoch": 0.8356940509915014, "percentage": 95.44, "elapsed_time": "3:30:53", "remaining_time": "0:10:04", "throughput": 2693.25, "total_tokens": 34077920}
+{"current_steps": 3250, "total_steps": 3400, "loss": 0.2836, "lr": 5.311861644696048e-07, "epoch": 0.836981715168684, "percentage": 95.59, "elapsed_time": "3:32:17", "remaining_time": "0:09:47", "throughput": 2679.43, "total_tokens": 34129832}
+{"current_steps": 3250, "total_steps": 3400, "eval_loss": 0.46573224663734436, "epoch": 0.836981715168684, "percentage": 95.59, "elapsed_time": "3:32:55", "remaining_time": "0:09:49", "throughput": 2671.58, "total_tokens": 34129832}