Training in progress, step 1050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad45929d086065d20a0650a45b6e51c5f6dbe2a33201f46beb88ae470ba1fc7
+oid sha256:da53d237a43e76b6b6ecf9bc93363994b337aa5f251d99299031ee1f2c39842a
 size 25200088

trainer_log.jsonl

@@ -118,3 +118,9 @@
 {"current_steps": 990, "total_steps": 1500, "loss": 0.216, "accuracy": 0.8999999761581421, "learning_rate": 1.2956158147457116e-06, "epoch": 0.9096129550936028, "percentage": 66.0, "elapsed_time": "2:17:00", "remaining_time": "1:10:34", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1000, "total_steps": 1500, "loss": 0.1812, "accuracy": 0.949999988079071, "learning_rate": 1.2500000000000007e-06, "epoch": 0.918800964741013, "percentage": 66.67, "elapsed_time": "2:18:19", "remaining_time": "1:09:09", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.21498693525791168, "epoch": 0.918800964741013, "percentage": 66.67, "elapsed_time": "2:18:44", "remaining_time": "1:09:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1010, "total_steps": 1500, "loss": 0.2113, "accuracy": 0.9125000238418579, "learning_rate": 1.204932476567175e-06, "epoch": 0.9279889743884231, "percentage": 67.33, "elapsed_time": "2:20:05", "remaining_time": "1:07:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1020, "total_steps": 1500, "loss": 0.2414, "accuracy": 0.949999988079071, "learning_rate": 1.160433012552508e-06, "epoch": 0.9371769840358333, "percentage": 68.0, "elapsed_time": "2:21:23", "remaining_time": "1:06:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1030, "total_steps": 1500, "loss": 0.1763, "accuracy": 0.949999988079071, "learning_rate": 1.11652112689164e-06, "epoch": 0.9463649936832433, "percentage": 68.67, "elapsed_time": "2:22:42", "remaining_time": "1:05:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1040, "total_steps": 1500, "loss": 0.2158, "accuracy": 0.9375, "learning_rate": 1.073216080788921e-06, "epoch": 0.9555530033306535, "percentage": 69.33, "elapsed_time": "2:23:57", "remaining_time": "1:03:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 1500, "loss": 0.1967, "accuracy": 0.9125000238418579, "learning_rate": 1.0305368692688175e-06, "epoch": 0.9647410129780636, "percentage": 70.0, "elapsed_time": "2:25:13", "remaining_time": "1:02:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.20923514664173126, "epoch": 0.9647410129780636, "percentage": 70.0, "elapsed_time": "2:25:37", "remaining_time": "1:02:24", "throughput": "0.00", "total_tokens": 0}