Training in progress, step 1800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92217ee5caa46679cd4b9124f86c58f0a232d2a96f8a163a5ef9962c6bf71225
+oid sha256:04603741b11167d68167aad242ef57b5ecfe1c04a91ccd70126632f62049787d
 size 58745928

trainer_log.jsonl

@@ -369,3 +369,13 @@
 {"current_steps": 1750, "total_steps": 1800, "loss": 0.0, "lr": 1.22170413724923e-07, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "0:06:03", "remaining_time": "0:00:10", "throughput": 1503.08, "total_tokens": 546912}
 {"current_steps": 1755, "total_steps": 1800, "loss": 0.0, "lr": 9.940480466855417e-08, "epoch": 19.5, "percentage": 97.5, "elapsed_time": "0:06:04", "remaining_time": "0:00:09", "throughput": 1503.64, "total_tokens": 548512}
 {"current_steps": 1760, "total_steps": 1800, "loss": 0.0, "lr": 7.898027451078982e-08, "epoch": 19.555555555555557, "percentage": 97.78, "elapsed_time": "0:06:05", "remaining_time": "0:00:08", "throughput": 1504.21, "total_tokens": 550112}
+{"current_steps": 1765, "total_steps": 1800, "loss": 0.0, "lr": 6.089874350439506e-08, "epoch": 19.61111111111111, "percentage": 98.06, "elapsed_time": "0:06:06", "remaining_time": "0:00:07", "throughput": 1504.67, "total_tokens": 551680}
+{"current_steps": 1770, "total_steps": 1800, "loss": 0.0, "lr": 4.516191162040051e-08, "epoch": 19.666666666666668, "percentage": 98.33, "elapsed_time": "0:06:07", "remaining_time": "0:00:06", "throughput": 1505.25, "total_tokens": 553280}
+{"current_steps": 1775, "total_steps": 1800, "loss": 0.0, "lr": 3.177125838830786e-08, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "0:06:08", "remaining_time": "0:00:05", "throughput": 1505.73, "total_tokens": 554848}
+{"current_steps": 1780, "total_steps": 1800, "loss": 0.0, "lr": 2.0728042756967824e-08, "epoch": 19.77777777777778, "percentage": 98.89, "elapsed_time": "0:06:09", "remaining_time": "0:00:04", "throughput": 1506.47, "total_tokens": 556512}
+{"current_steps": 1785, "total_steps": 1800, "loss": 0.0, "lr": 1.2033302976222071e-08, "epoch": 19.833333333333332, "percentage": 99.17, "elapsed_time": "0:06:10", "remaining_time": "0:00:03", "throughput": 1507.04, "total_tokens": 558112}
+{"current_steps": 1790, "total_steps": 1800, "loss": 0.0, "lr": 5.687856499297928e-09, "epoch": 19.88888888888889, "percentage": 99.44, "elapsed_time": "0:06:11", "remaining_time": "0:00:02", "throughput": 1507.6, "total_tokens": 559712}
+{"current_steps": 1795, "total_steps": 1800, "loss": 0.0, "lr": 1.692299905944883e-09, "epoch": 19.944444444444443, "percentage": 99.72, "elapsed_time": "0:06:12", "remaining_time": "0:00:01", "throughput": 1508.07, "total_tokens": 561280}
+{"current_steps": 1800, "total_steps": 1800, "loss": 0.0, "lr": 4.700884634611935e-11, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:06:13", "remaining_time": "0:00:00", "throughput": 1508.38, "total_tokens": 562848}
+{"current_steps": 1800, "total_steps": 1800, "eval_loss": 0.02443142607808113, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:06:13", "remaining_time": "0:00:00", "throughput": 1506.08, "total_tokens": 562848}
+{"current_steps": 1800, "total_steps": 1800, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:06:16", "remaining_time": "0:00:00", "throughput": 1496.24, "total_tokens": 562848}