Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af0bf2bfaaae9e35ecb5ca2c54adf01a17f257c619c283e3eac894177fc726db
+oid sha256:cf562e0725b165446bb7ecc8f792860b14b7cf9fe7fa98020e93ae0e56c7e3f5
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.3822, "accuracy": 0.9125000238418579, "learning_rate": 3.795067523432826e-06, "epoch": 0.7690798508926819, "percentage": 32.67, "elapsed_time": "1:05:25", "remaining_time": "2:14:50", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.352, "accuracy": 0.887499988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.7847753580537571, "percentage": 33.33, "elapsed_time": "1:06:40", "remaining_time": "2:13:21", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3888731002807617, "epoch": 0.7847753580537571, "percentage": 33.33, "elapsed_time": "1:06:55", "remaining_time": "2:13:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.4009, "accuracy": 0.8500000238418579, "learning_rate": 3.7043841852542884e-06, "epoch": 0.8004708652148322, "percentage": 34.0, "elapsed_time": "1:08:19", "remaining_time": "2:12:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.3327, "accuracy": 0.9125000238418579, "learning_rate": 3.658240087799655e-06, "epoch": 0.8161663723759074, "percentage": 34.67, "elapsed_time": "1:09:33", "remaining_time": "2:11:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.3255, "accuracy": 0.8999999761581421, "learning_rate": 3.611587947962319e-06, "epoch": 0.8318618795369825, "percentage": 35.33, "elapsed_time": "1:10:50", "remaining_time": "2:09:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.2941, "accuracy": 0.925000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.8475573866980577, "percentage": 36.0, "elapsed_time": "1:12:05", "remaining_time": "2:08:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.3906, "accuracy": 0.8999999761581421, "learning_rate": 3.516841607689501e-06, "epoch": 0.8632528938591328, "percentage": 36.67, "elapsed_time": "1:13:20", "remaining_time": "2:06:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.3577499985694885, "epoch": 0.8632528938591328, "percentage": 36.67, "elapsed_time": "1:13:34", "remaining_time": "2:07:05", "throughput": "0.00", "total_tokens": 0}