Training in progress, step 300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a03e9eee1ec95bdd483369ad9faaa09779f119406744d2cbea8db7e18f4878e
+oid sha256:ebc02da19989435043b7b50280b5e9e82d323b3ede799685ab53edfcf8cfad6a
 size 29034840

trainer_log.jsonl

@@ -53,3 +53,14 @@
 {"current_steps": 245, "total_steps": 3882, "loss": 0.9084, "lr": 9.995463010262206e-05, "epoch": 0.1261910893638939, "percentage": 6.31, "elapsed_time": "1:16:21", "remaining_time": "18:53:29", "throughput": 625.48, "total_tokens": 2865520}
 {"current_steps": 250, "total_steps": 3882, "loss": 0.9106, "lr": 9.994510416795519e-05, "epoch": 0.12876641771825909, "percentage": 6.44, "elapsed_time": "1:17:50", "remaining_time": "18:50:56", "throughput": 626.03, "total_tokens": 2924016}
 {"current_steps": 250, "total_steps": 3882, "eval_loss": 0.8958488702774048, "epoch": 0.12876641771825909, "percentage": 6.44, "elapsed_time": "1:18:10", "remaining_time": "18:55:39", "throughput": 623.43, "total_tokens": 2924016}
+{"current_steps": 255, "total_steps": 3882, "loss": 0.9012, "lr": 9.993467169584824e-05, "epoch": 0.13134174607262425, "percentage": 6.57, "elapsed_time": "1:19:44", "remaining_time": "18:54:06", "throughput": 623.43, "total_tokens": 2982520}
+{"current_steps": 260, "total_steps": 3882, "loss": 0.9069, "lr": 9.992333287565765e-05, "epoch": 0.13391707442698944, "percentage": 6.7, "elapsed_time": "1:21:14", "remaining_time": "18:51:41", "throughput": 623.9, "total_tokens": 3041008}
+{"current_steps": 265, "total_steps": 3882, "loss": 0.8918, "lr": 9.991108791319066e-05, "epoch": 0.13649240278135463, "percentage": 6.83, "elapsed_time": "1:22:42", "remaining_time": "18:48:57", "throughput": 624.54, "total_tokens": 3099464}
+{"current_steps": 270, "total_steps": 3882, "loss": 0.8996, "lr": 9.989793703070163e-05, "epoch": 0.1390677311357198, "percentage": 6.96, "elapsed_time": "1:24:13", "remaining_time": "18:46:38", "throughput": 624.96, "total_tokens": 3157944}
+{"current_steps": 275, "total_steps": 3882, "loss": 0.9009, "lr": 9.988388046688799e-05, "epoch": 0.141643059490085, "percentage": 7.08, "elapsed_time": "1:25:41", "remaining_time": "18:44:03", "throughput": 625.53, "total_tokens": 3216448}
+{"current_steps": 280, "total_steps": 3882, "loss": 0.9059, "lr": 9.986891847688587e-05, "epoch": 0.14421838784445018, "percentage": 7.21, "elapsed_time": "1:27:11", "remaining_time": "18:41:42", "throughput": 625.97, "total_tokens": 3274928}
+{"current_steps": 285, "total_steps": 3882, "loss": 0.8939, "lr": 9.985305133226553e-05, "epoch": 0.14679371619881534, "percentage": 7.34, "elapsed_time": "1:28:41", "remaining_time": "18:39:25", "throughput": 626.38, "total_tokens": 3333408}
+{"current_steps": 290, "total_steps": 3882, "loss": 0.8899, "lr": 9.983627932102638e-05, "epoch": 0.14936904455318054, "percentage": 7.47, "elapsed_time": "1:30:10", "remaining_time": "18:37:01", "throughput": 626.86, "total_tokens": 3391896}
+{"current_steps": 295, "total_steps": 3882, "loss": 0.9092, "lr": 9.981860274759173e-05, "epoch": 0.1519443729075457, "percentage": 7.6, "elapsed_time": "1:31:41", "remaining_time": "18:34:51", "throughput": 627.2, "total_tokens": 3450392}
+{"current_steps": 300, "total_steps": 3882, "loss": 0.8901, "lr": 9.980002193280342e-05, "epoch": 0.1545197012619109, "percentage": 7.73, "elapsed_time": "1:33:10", "remaining_time": "18:32:25", "throughput": 627.7, "total_tokens": 3508888}
+{"current_steps": 300, "total_steps": 3882, "eval_loss": 0.8932263255119324, "epoch": 0.1545197012619109, "percentage": 7.73, "elapsed_time": "1:33:29", "remaining_time": "18:36:21", "throughput": 625.48, "total_tokens": 3508888}