Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:505052fd447e82a4abc24247799308483adb5e768f191f23677c8d33b4d7cac4
+oid sha256:085286a0e6090c82fcc13eea53f92c3af07a3dd530dc3c67c22de5abfe705112
 size 29034840

trainer_log.jsonl

@@ -119,3 +119,14 @@
 {"current_steps": 545, "total_steps": 3400, "loss": 0.0431, "lr": 9.67108983539777e-05, "epoch": 0.2807107906258048, "percentage": 16.03, "elapsed_time": "2:42:22", "remaining_time": "14:10:33", "throughput": 558.54, "total_tokens": 5441280}
 {"current_steps": 550, "total_steps": 3400, "loss": 0.0339, "lr": 9.662361147021779e-05, "epoch": 0.28328611898017, "percentage": 16.18, "elapsed_time": "2:43:46", "remaining_time": "14:08:40", "throughput": 558.8, "total_tokens": 5491200}
 {"current_steps": 550, "total_steps": 3400, "eval_loss": 0.0033526704646646976, "epoch": 0.28328611898017, "percentage": 16.18, "elapsed_time": "2:44:05", "remaining_time": "14:10:18", "throughput": 557.73, "total_tokens": 5491200}
+{"current_steps": 555, "total_steps": 3400, "loss": 0.0341, "lr": 9.653522193117013e-05, "epoch": 0.28586144733453517, "percentage": 16.32, "elapsed_time": "2:45:37", "remaining_time": "14:09:00", "throughput": 557.6, "total_tokens": 5541120}
+{"current_steps": 560, "total_steps": 3400, "loss": 0.0341, "lr": 9.644573182726035e-05, "epoch": 0.28843677568890036, "percentage": 16.47, "elapsed_time": "2:47:02", "remaining_time": "14:07:07", "throughput": 557.86, "total_tokens": 5591040}
+{"current_steps": 565, "total_steps": 3400, "loss": 0.0453, "lr": 9.63551432749426e-05, "epoch": 0.2910121040432655, "percentage": 16.62, "elapsed_time": "2:48:27", "remaining_time": "14:05:18", "throughput": 558.08, "total_tokens": 5640960}
+{"current_steps": 570, "total_steps": 3400, "loss": 0.0227, "lr": 9.626345841664953e-05, "epoch": 0.2935874323976307, "percentage": 16.76, "elapsed_time": "2:49:53", "remaining_time": "14:03:28", "throughput": 558.3, "total_tokens": 5690880}
+{"current_steps": 575, "total_steps": 3400, "loss": 0.0135, "lr": 9.617067942074153e-05, "epoch": 0.2961627607519959, "percentage": 16.91, "elapsed_time": "2:51:18", "remaining_time": "14:01:39", "throughput": 558.51, "total_tokens": 5740800}
+{"current_steps": 580, "total_steps": 3400, "loss": 0.0439, "lr": 9.607680848145558e-05, "epoch": 0.29873808910636107, "percentage": 17.06, "elapsed_time": "2:52:44", "remaining_time": "13:59:53", "throughput": 558.7, "total_tokens": 5790720}
+{"current_steps": 585, "total_steps": 3400, "loss": 0.0344, "lr": 9.598184781885318e-05, "epoch": 0.30131341746072626, "percentage": 17.21, "elapsed_time": "2:54:09", "remaining_time": "13:58:03", "throughput": 558.93, "total_tokens": 5840640}
+{"current_steps": 590, "total_steps": 3400, "loss": 0.0244, "lr": 9.588579967876806e-05, "epoch": 0.3038887458150914, "percentage": 17.35, "elapsed_time": "2:55:35", "remaining_time": "13:56:19", "throughput": 559.09, "total_tokens": 5890560}
+{"current_steps": 595, "total_steps": 3400, "loss": 0.022, "lr": 9.578866633275288e-05, "epoch": 0.3064640741694566, "percentage": 17.5, "elapsed_time": "2:57:00", "remaining_time": "13:54:29", "throughput": 559.32, "total_tokens": 5940480}
+{"current_steps": 600, "total_steps": 3400, "loss": 0.0217, "lr": 9.569045007802559e-05, "epoch": 0.3090394025238218, "percentage": 17.65, "elapsed_time": "2:58:27", "remaining_time": "13:52:46", "throughput": 559.48, "total_tokens": 5990400}
+{"current_steps": 600, "total_steps": 3400, "eval_loss": 0.013290103524923325, "epoch": 0.3090394025238218, "percentage": 17.65, "elapsed_time": "2:58:45", "remaining_time": "13:54:14", "throughput": 558.49, "total_tokens": 5990400}