Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:085286a0e6090c82fcc13eea53f92c3af07a3dd530dc3c67c22de5abfe705112
+oid sha256:f082218d4450a6fd5cba15403298e1e103fd66cae7d3efcef2dce424d9043bc9
 size 29034840

trainer_log.jsonl

@@ -130,3 +130,14 @@
 {"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}
+{"current_steps": 605, "total_steps": 3400, "loss": 0.0207, "lr": 9.55911532374151e-05, "epoch": 0.311614730878187, "percentage": 17.79, "elapsed_time": "3:00:16", "remaining_time": "13:52:50", "throughput": 558.44, "total_tokens": 6040320}
+{"current_steps": 610, "total_steps": 3400, "loss": 0.023, "lr": 9.549077815930636e-05, "epoch": 0.31419005923255217, "percentage": 17.94, "elapsed_time": "3:01:42", "remaining_time": "13:51:07", "throughput": 558.59, "total_tokens": 6090240}
+{"current_steps": 615, "total_steps": 3400, "loss": 0.017, "lr": 9.538932721758474e-05, "epoch": 0.31676538758691736, "percentage": 18.09, "elapsed_time": "3:03:08", "remaining_time": "13:49:20", "throughput": 558.78, "total_tokens": 6140160}
+{"current_steps": 620, "total_steps": 3400, "loss": 0.009, "lr": 9.528680281157999e-05, "epoch": 0.3193407159412825, "percentage": 18.24, "elapsed_time": "3:04:35", "remaining_time": "13:47:41", "throughput": 558.9, "total_tokens": 6190080}
+{"current_steps": 625, "total_steps": 3400, "loss": 0.0421, "lr": 9.518320736600943e-05, "epoch": 0.3219160442956477, "percentage": 18.38, "elapsed_time": "3:06:01", "remaining_time": "13:45:59", "throughput": 559.04, "total_tokens": 6240000}
+{"current_steps": 630, "total_steps": 3400, "loss": 0.0324, "lr": 9.507854333092063e-05, "epoch": 0.3244913726500129, "percentage": 18.53, "elapsed_time": "3:07:28", "remaining_time": "13:44:17", "throughput": 559.18, "total_tokens": 6289920}
+{"current_steps": 635, "total_steps": 3400, "loss": 0.0139, "lr": 9.497281318163346e-05, "epoch": 0.32706670100437807, "percentage": 18.68, "elapsed_time": "3:08:54", "remaining_time": "13:42:33", "throughput": 559.35, "total_tokens": 6339840}
+{"current_steps": 640, "total_steps": 3400, "loss": 0.0375, "lr": 9.486601941868154e-05, "epoch": 0.32964202935874326, "percentage": 18.82, "elapsed_time": "3:10:21", "remaining_time": "13:40:54", "throughput": 559.46, "total_tokens": 6389760}
+{"current_steps": 645, "total_steps": 3400, "loss": 0.0618, "lr": 9.475816456775313e-05, "epoch": 0.3322173577131084, "percentage": 18.97, "elapsed_time": "3:11:47", "remaining_time": "13:39:13", "throughput": 559.59, "total_tokens": 6439680}
+{"current_steps": 650, "total_steps": 3400, "loss": 0.0327, "lr": 9.464925117963133e-05, "epoch": 0.3347926860674736, "percentage": 19.12, "elapsed_time": "3:13:14", "remaining_time": "13:37:33", "throughput": 559.72, "total_tokens": 6489600}
+{"current_steps": 650, "total_steps": 3400, "eval_loss": 0.02095886506140232, "epoch": 0.3347926860674736, "percentage": 19.12, "elapsed_time": "3:13:33", "remaining_time": "13:38:54", "throughput": 558.79, "total_tokens": 6489600}