Training in progress, step 1700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98d193ab7c674712e3c18a30e49e6fde0bcc59efee6c60450baf3a08afe8f78
+oid sha256:6956268c1ac0ce3f63b81eb8b75c0c4b5ea990b8cf8dfa819dbcd8de1270e39d
 size 29034840

trainer_log.jsonl

@@ -361,3 +361,14 @@
 {"current_steps": 1645, "total_steps": 3882, "loss": 0.3644, "lr": 6.645218350024456e-05, "epoch": 0.8472830285861447, "percentage": 42.38, "elapsed_time": "8:23:14", "remaining_time": "11:24:20", "throughput": 637.21, "total_tokens": 19240352}
 {"current_steps": 1650, "total_steps": 3882, "loss": 0.475, "lr": 6.625087856544416e-05, "epoch": 0.8498583569405099, "percentage": 42.5, "elapsed_time": "8:24:42", "remaining_time": "11:22:43", "throughput": 637.3, "total_tokens": 19298848}
 {"current_steps": 1650, "total_steps": 3882, "eval_loss": 0.35129043459892273, "epoch": 0.8498583569405099, "percentage": 42.5, "elapsed_time": "8:25:01", "remaining_time": "11:23:09", "throughput": 636.9, "total_tokens": 19298848}
+{"current_steps": 1655, "total_steps": 3882, "loss": 0.3414, "lr": 6.604927866620031e-05, "epoch": 0.8524336852948751, "percentage": 42.63, "elapsed_time": "8:26:34", "remaining_time": "11:21:39", "throughput": 636.87, "total_tokens": 19357304}
+{"current_steps": 1660, "total_steps": 3882, "loss": 0.4728, "lr": 6.584738746168762e-05, "epoch": 0.8550090136492403, "percentage": 42.76, "elapsed_time": "8:28:02", "remaining_time": "11:20:02", "throughput": 636.95, "total_tokens": 19415800}
+{"current_steps": 1665, "total_steps": 3882, "loss": 0.4264, "lr": 6.564520861636808e-05, "epoch": 0.8575843420036054, "percentage": 42.89, "elapsed_time": "8:29:31", "remaining_time": "11:18:26", "throughput": 637.01, "total_tokens": 19474256}
+{"current_steps": 1670, "total_steps": 3882, "loss": 0.4038, "lr": 6.544274579992453e-05, "epoch": 0.8601596703579707, "percentage": 43.02, "elapsed_time": "8:31:00", "remaining_time": "11:16:51", "throughput": 637.07, "total_tokens": 19532736}
+{"current_steps": 1675, "total_steps": 3882, "loss": 0.3241, "lr": 6.524000268719411e-05, "epoch": 0.8627349987123358, "percentage": 43.15, "elapsed_time": "8:32:29", "remaining_time": "11:15:15", "throughput": 637.13, "total_tokens": 19591184}
+{"current_steps": 1680, "total_steps": 3882, "loss": 0.3248, "lr": 6.503698295810154e-05, "epoch": 0.865310327066701, "percentage": 43.28, "elapsed_time": "8:33:58", "remaining_time": "11:13:39", "throughput": 637.19, "total_tokens": 19649656}
+{"current_steps": 1685, "total_steps": 3882, "loss": 0.4295, "lr": 6.483369029759229e-05, "epoch": 0.8678856554210662, "percentage": 43.41, "elapsed_time": "8:35:26", "remaining_time": "11:12:03", "throughput": 637.26, "total_tokens": 19708144}
+{"current_steps": 1690, "total_steps": 3882, "loss": 0.3785, "lr": 6.463012839556569e-05, "epoch": 0.8704609837754314, "percentage": 43.53, "elapsed_time": "8:36:55", "remaining_time": "11:10:28", "throughput": 637.3, "total_tokens": 19766592}
+{"current_steps": 1695, "total_steps": 3882, "loss": 0.3376, "lr": 6.442630094680805e-05, "epoch": 0.8730363121297966, "percentage": 43.66, "elapsed_time": "8:38:24", "remaining_time": "11:08:52", "throughput": 637.37, "total_tokens": 19825064}
+{"current_steps": 1700, "total_steps": 3882, "loss": 0.3752, "lr": 6.42222116509255e-05, "epoch": 0.8756116404841617, "percentage": 43.79, "elapsed_time": "8:39:53", "remaining_time": "11:07:17", "throughput": 637.42, "total_tokens": 19883504}
+{"current_steps": 1700, "total_steps": 3882, "eval_loss": 0.34382957220077515, "epoch": 0.8756116404841617, "percentage": 43.79, "elapsed_time": "8:40:12", "remaining_time": "11:07:42", "throughput": 637.03, "total_tokens": 19883504}