Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.7-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
af96662
·
verified ·
1 Parent(s): 9ad0613

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 sha256:44b11bbacdd0723ea6d0d583a468624f5b665d65b8e1bee78638b08df2d0597f
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed64d1015a9c17473c46d78a917025768c7e9a1cf22dd8bc180b758f9fede4de
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -166,3 +166,9 @@
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.2051, "accuracy": 0.9624999761581421, "learning_rate": 6.605274281709929e-08, "epoch": 1.276559090387045, "percentage": 92.67, "elapsed_time": "3:12:40", "remaining_time": "0:15:14", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.2139, "accuracy": 0.925000011920929, "learning_rate": 5.463099816548578e-08, "epoch": 1.2857471000344551, "percentage": 93.33, "elapsed_time": "3:13:57", "remaining_time": "0:13:51", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.2001064419746399, "epoch": 1.2857471000344551, "percentage": 93.33, "elapsed_time": "3:14:21", "remaining_time": "0:13:52", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.2051, "accuracy": 0.9624999761581421, "learning_rate": 6.605274281709929e-08, "epoch": 1.276559090387045, "percentage": 92.67, "elapsed_time": "3:12:40", "remaining_time": "0:15:14", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.2139, "accuracy": 0.925000011920929, "learning_rate": 5.463099816548578e-08, "epoch": 1.2857471000344551, "percentage": 93.33, "elapsed_time": "3:13:57", "remaining_time": "0:13:51", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.2001064419746399, "epoch": 1.2857471000344551, "percentage": 93.33, "elapsed_time": "3:14:21", "remaining_time": "0:13:52", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1410, "total_steps": 1500, "loss": 0.1929, "accuracy": 0.949999988079071, "learning_rate": 4.428187317827848e-08, "epoch": 1.294935109681865, "percentage": 94.0, "elapsed_time": "3:15:45", "remaining_time": "0:12:29", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1420, "total_steps": 1500, "loss": 0.186, "accuracy": 0.9375, "learning_rate": 3.5009907323737826e-08, "epoch": 1.3041231193292753, "percentage": 94.67, "elapsed_time": "3:17:02", "remaining_time": "0:11:06", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1430, "total_steps": 1500, "loss": 0.2139, "accuracy": 0.9375, "learning_rate": 2.681916759252917e-08, "epoch": 1.3133111289766854, "percentage": 95.33, "elapsed_time": "3:18:20", "remaining_time": "0:09:42", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1440, "total_steps": 1500, "loss": 0.199, "accuracy": 0.949999988079071, "learning_rate": 1.9713246713805588e-08, "epoch": 1.3224991386240956, "percentage": 96.0, "elapsed_time": "3:19:36", "remaining_time": "0:08:19", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1450, "total_steps": 1500, "loss": 0.2255, "accuracy": 0.9624999761581421, "learning_rate": 1.3695261579316776e-08, "epoch": 1.3316871482715058, "percentage": 96.67, "elapsed_time": "3:20:58", "remaining_time": "0:06:55", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.19852806627750397, "epoch": 1.3316871482715058, "percentage": 96.67, "elapsed_time": "3:21:22", "remaining_time": "0:06:56", "throughput": "0.00", "total_tokens": 0}