Training in progress, step 1550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6289479e907da413d0601e67681f7846ac9804602b3a5c4cb53469f8420fd060
+oid sha256:364d970c0898c9aa3378ce697d8c156c845bc89c410b474424ed0f6f28d86575
 size 29034840

trainer_log.jsonl

@@ -329,3 +329,14 @@
 {"current_steps": 1495, "total_steps": 6770, "loss": 0.2615, "lr": 9.223706238134485e-05, "epoch": 0.44165435745937964, "percentage": 22.08, "elapsed_time": "2:29:49", "remaining_time": "8:48:38", "throughput": 1726.41, "total_tokens": 15519472}
 {"current_steps": 1500, "total_steps": 6770, "loss": 0.2928, "lr": 9.217157719029469e-05, "epoch": 0.4431314623338257, "percentage": 22.16, "elapsed_time": "2:31:16", "remaining_time": "8:51:27", "throughput": 1715.71, "total_tokens": 15572048}
 {"current_steps": 1500, "total_steps": 6770, "eval_loss": 0.40494996309280396, "epoch": 0.4431314623338257, "percentage": 22.16, "elapsed_time": "2:31:35", "remaining_time": "8:52:35", "throughput": 1712.08, "total_tokens": 15572048}
+{"current_steps": 1505, "total_steps": 6770, "loss": 0.3622, "lr": 9.210584040403793e-05, "epoch": 0.4446085672082718, "percentage": 22.23, "elapsed_time": "2:33:08", "remaining_time": "8:55:43", "throughput": 1700.37, "total_tokens": 15623400}
+{"current_steps": 1510, "total_steps": 6770, "loss": 0.3192, "lr": 9.20398524147596e-05, "epoch": 0.4460856720827179, "percentage": 22.3, "elapsed_time": "2:34:35", "remaining_time": "8:58:31", "throughput": 1690.08, "total_tokens": 15676712}
+{"current_steps": 1515, "total_steps": 6770, "loss": 0.3463, "lr": 9.197361361614339e-05, "epoch": 0.44756277695716395, "percentage": 22.38, "elapsed_time": "2:36:03", "remaining_time": "9:01:17", "throughput": 1679.92, "total_tokens": 15729304}
+{"current_steps": 1520, "total_steps": 6770, "loss": 0.3675, "lr": 9.190712440336928e-05, "epoch": 0.44903988183161003, "percentage": 22.45, "elapsed_time": "2:37:29", "remaining_time": "9:03:57", "throughput": 1669.98, "total_tokens": 15780144}
+{"current_steps": 1525, "total_steps": 6770, "loss": 0.3305, "lr": 9.184038517311126e-05, "epoch": 0.4505169867060561, "percentage": 22.53, "elapsed_time": "2:38:58", "remaining_time": "9:06:45", "throughput": 1659.85, "total_tokens": 15832032}
+{"current_steps": 1530, "total_steps": 6770, "loss": 0.3817, "lr": 9.177339632353492e-05, "epoch": 0.4519940915805022, "percentage": 22.6, "elapsed_time": "2:40:25", "remaining_time": "9:09:24", "throughput": 1650.3, "total_tokens": 15884152}
+{"current_steps": 1535, "total_steps": 6770, "loss": 0.3742, "lr": 9.170615825429502e-05, "epoch": 0.4534711964549483, "percentage": 22.67, "elapsed_time": "2:41:52", "remaining_time": "9:12:03", "throughput": 1640.73, "total_tokens": 15935688}
+{"current_steps": 1540, "total_steps": 6770, "loss": 0.34, "lr": 9.163867136653327e-05, "epoch": 0.4549483013293944, "percentage": 22.75, "elapsed_time": "2:43:20", "remaining_time": "9:14:42", "throughput": 1631.38, "total_tokens": 15987800}
+{"current_steps": 1545, "total_steps": 6770, "loss": 0.3389, "lr": 9.157093606287572e-05, "epoch": 0.4564254062038405, "percentage": 22.82, "elapsed_time": "2:44:46", "remaining_time": "9:17:15", "throughput": 1622.32, "total_tokens": 16039472}
+{"current_steps": 1550, "total_steps": 6770, "loss": 0.3588, "lr": 9.150295274743053e-05, "epoch": 0.45790251107828656, "percentage": 22.9, "elapsed_time": "2:46:13", "remaining_time": "9:19:49", "throughput": 1613.43, "total_tokens": 16091960}
+{"current_steps": 1550, "total_steps": 6770, "eval_loss": 0.28714123368263245, "epoch": 0.45790251107828656, "percentage": 22.9, "elapsed_time": "2:46:32", "remaining_time": "9:20:53", "throughput": 1610.35, "total_tokens": 16091960}