Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a9264918d1a32f7f7380b47ea3913df05c696c6270b8036bd4a6e252f3bfba
+oid sha256:16ebb238066311e1d044b75ba68510f141fa7dcb784eb182857a664e1c5d33e5
 size 25200088

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 0.9185, "accuracy": 0.512499988079071, "learning_rate": 4.893298743830168e-06, "epoch": 0.12863213506374183, "percentage": 9.33, "elapsed_time": "0:19:01", "remaining_time": "3:04:48", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 0.9106, "accuracy": 0.5874999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.13782014471115195, "percentage": 10.0, "elapsed_time": "0:20:16", "remaining_time": "3:02:28", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9164085388183594, "epoch": 0.13782014471115195, "percentage": 10.0, "elapsed_time": "0:20:40", "remaining_time": "3:06:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 0.9094, "accuracy": 0.625, "learning_rate": 4.860940925593703e-06, "epoch": 0.14700815435856207, "percentage": 10.67, "elapsed_time": "0:22:06", "remaining_time": "3:05:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 0.9057, "accuracy": 0.5375000238418579, "learning_rate": 4.84320497372973e-06, "epoch": 0.1561961640059722, "percentage": 11.33, "elapsed_time": "0:23:27", "remaining_time": "3:03:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 0.8954, "accuracy": 0.5249999761581421, "learning_rate": 4.824441214720629e-06, "epoch": 0.16538417365338234, "percentage": 12.0, "elapsed_time": "0:24:46", "remaining_time": "3:01:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 0.8875, "accuracy": 0.625, "learning_rate": 4.804657878971252e-06, "epoch": 0.17457218330079247, "percentage": 12.67, "elapsed_time": "0:26:04", "remaining_time": "2:59:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 0.8647, "accuracy": 0.6000000238418579, "learning_rate": 4.783863644106502e-06, "epoch": 0.1837601929482026, "percentage": 13.33, "elapsed_time": "0:27:19", "remaining_time": "2:57:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8702690005302429, "epoch": 0.1837601929482026, "percentage": 13.33, "elapsed_time": "0:27:44", "remaining_time": "3:00:16", "throughput": "0.00", "total_tokens": 0}