Training in progress, step 2050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803c4a6d1224f4cccaa865d5f234c98fc604663a56f02aca7b212731cc155316
+oid sha256:d8c07c45cd740f6c38df8b73c4bc4f9f8c11bd6712886d745d8476e5ba112852
 size 29034840

trainer_log.jsonl

@@ -438,3 +438,14 @@
 {"current_steps": 1995, "total_steps": 3882, "loss": 0.2697, "lr": 5.185283416802539e-05, "epoch": 1.0272984805562708, "percentage": 51.39, "elapsed_time": "10:09:27", "remaining_time": "9:36:28", "throughput": 637.93, "total_tokens": 23327800}
 {"current_steps": 2000, "total_steps": 3882, "loss": 0.2272, "lr": 5.1639946088933444e-05, "epoch": 1.029873808910636, "percentage": 51.52, "elapsed_time": "10:10:55", "remaining_time": "9:34:53", "throughput": 637.99, "total_tokens": 23386232}
 {"current_steps": 2000, "total_steps": 3882, "eval_loss": 0.2834003269672394, "epoch": 1.029873808910636, "percentage": 51.52, "elapsed_time": "10:11:15", "remaining_time": "9:35:11", "throughput": 637.66, "total_tokens": 23386232}
+{"current_steps": 2005, "total_steps": 3882, "loss": 0.2455, "lr": 5.1427028243710174e-05, "epoch": 1.0324491372650013, "percentage": 51.65, "elapsed_time": "10:12:49", "remaining_time": "9:33:41", "throughput": 637.62, "total_tokens": 23444712}
+{"current_steps": 2010, "total_steps": 3882, "loss": 0.268, "lr": 5.121408449695856e-05, "epoch": 1.0350244656193666, "percentage": 51.78, "elapsed_time": "10:14:18", "remaining_time": "9:32:07", "throughput": 637.66, "total_tokens": 23503192}
+{"current_steps": 2015, "total_steps": 3882, "loss": 0.2721, "lr": 5.100111871375173e-05, "epoch": 1.0375997939737316, "percentage": 51.91, "elapsed_time": "10:15:46", "remaining_time": "9:30:32", "throughput": 637.72, "total_tokens": 23561688}
+{"current_steps": 2020, "total_steps": 3882, "loss": 0.3521, "lr": 5.078813475956276e-05, "epoch": 1.0401751223280968, "percentage": 52.04, "elapsed_time": "10:17:15", "remaining_time": "9:28:58", "throughput": 637.78, "total_tokens": 23620160}
+{"current_steps": 2025, "total_steps": 3882, "loss": 0.3624, "lr": 5.057513650019452e-05, "epoch": 1.042750450682462, "percentage": 52.16, "elapsed_time": "10:18:43", "remaining_time": "9:27:23", "throughput": 637.83, "total_tokens": 23678624}
+{"current_steps": 2030, "total_steps": 3882, "loss": 0.2742, "lr": 5.0362127801709614e-05, "epoch": 1.045325779036827, "percentage": 52.29, "elapsed_time": "10:20:12", "remaining_time": "9:25:49", "throughput": 637.88, "total_tokens": 23737064}
+{"current_steps": 2035, "total_steps": 3882, "loss": 0.3377, "lr": 5.014911253036004e-05, "epoch": 1.0479011073911924, "percentage": 52.42, "elapsed_time": "10:21:40", "remaining_time": "9:24:14", "throughput": 637.93, "total_tokens": 23795568}
+{"current_steps": 2040, "total_steps": 3882, "loss": 0.3059, "lr": 4.993609455251713e-05, "epoch": 1.0504764357455576, "percentage": 52.55, "elapsed_time": "10:23:09", "remaining_time": "9:22:40", "throughput": 637.99, "total_tokens": 23854040}
+{"current_steps": 2045, "total_steps": 3882, "loss": 0.2534, "lr": 4.972307773460133e-05, "epoch": 1.0530517640999228, "percentage": 52.68, "elapsed_time": "10:24:37", "remaining_time": "9:21:05", "throughput": 638.06, "total_tokens": 23912520}
+{"current_steps": 2050, "total_steps": 3882, "loss": 0.2924, "lr": 4.9510065943012076e-05, "epoch": 1.0556270924542879, "percentage": 52.81, "elapsed_time": "10:26:05", "remaining_time": "9:19:30", "throughput": 638.11, "total_tokens": 23971048}
+{"current_steps": 2050, "total_steps": 3882, "eval_loss": 0.2703675329685211, "epoch": 1.0556270924542879, "percentage": 52.81, "elapsed_time": "10:26:25", "remaining_time": "9:19:48", "throughput": 637.78, "total_tokens": 23971048}