Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.3-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
90991f0
·
verified ·
1 Parent(s): 20dc186

Training in progress, step 1450

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +6 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ffd470b9c3e75342af8cf004acb37a77b94337ae55d95fba0580e64615d5a07
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f405b7423578b04f8bdd6d5e9e96614b91c0aef424901e9ed53d97f45566b5fe
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -166,3 +166,9 @@
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.3194, "accuracy": 0.8999999761581421, "learning_rate": 6.605274281709929e-08, "epoch": 1.7644444444444445, "percentage": 92.67, "elapsed_time": "3:11:04", "remaining_time": "0:15:07", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.2854, "accuracy": 0.8999999761581421, "learning_rate": 5.463099816548578e-08, "epoch": 1.7771428571428571, "percentage": 93.33, "elapsed_time": "3:12:19", "remaining_time": "0:13:44", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.24849724769592285, "epoch": 1.7771428571428571, "percentage": 93.33, "elapsed_time": "3:12:37", "remaining_time": "0:13:45", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.3194, "accuracy": 0.8999999761581421, "learning_rate": 6.605274281709929e-08, "epoch": 1.7644444444444445, "percentage": 92.67, "elapsed_time": "3:11:04", "remaining_time": "0:15:07", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.2854, "accuracy": 0.8999999761581421, "learning_rate": 5.463099816548578e-08, "epoch": 1.7771428571428571, "percentage": 93.33, "elapsed_time": "3:12:19", "remaining_time": "0:13:44", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.24849724769592285, "epoch": 1.7771428571428571, "percentage": 93.33, "elapsed_time": "3:12:37", "remaining_time": "0:13:45", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1410, "total_steps": 1500, "loss": 0.2838, "accuracy": 0.887499988079071, "learning_rate": 4.428187317827848e-08, "epoch": 1.7898412698412698, "percentage": 94.0, "elapsed_time": "3:14:13", "remaining_time": "0:12:23", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1420, "total_steps": 1500, "loss": 0.2815, "accuracy": 0.925000011920929, "learning_rate": 3.5009907323737826e-08, "epoch": 1.8025396825396824, "percentage": 94.67, "elapsed_time": "3:15:29", "remaining_time": "0:11:00", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1430, "total_steps": 1500, "loss": 0.3363, "accuracy": 0.925000011920929, "learning_rate": 2.681916759252917e-08, "epoch": 1.815238095238095, "percentage": 95.33, "elapsed_time": "3:16:44", "remaining_time": "0:09:37", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1440, "total_steps": 1500, "loss": 0.2786, "accuracy": 0.949999988079071, "learning_rate": 1.9713246713805588e-08, "epoch": 1.827936507936508, "percentage": 96.0, "elapsed_time": "3:18:01", "remaining_time": "0:08:15", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1450, "total_steps": 1500, "loss": 0.2848, "accuracy": 0.925000011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.8406349206349206, "percentage": 96.67, "elapsed_time": "3:19:15", "remaining_time": "0:06:52", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.24686568975448608, "epoch": 1.8406349206349206, "percentage": 96.67, "elapsed_time": "3:19:34", "remaining_time": "0:06:52", "throughput": "0.00", "total_tokens": 0}