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
Model card Files Community
ziansu commited on
Commit
c0486d7
·
verified ·
1 Parent(s): f333d09

Training in progress, step 1400

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 sha256:70820fbc26ccf27443d6c53330482120e4bc434be5198734599ee0212dfd9ad5
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b11bbacdd0723ea6d0d583a468624f5b665d65b8e1bee78638b08df2d0597f
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -160,3 +160,9 @@
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1779, "accuracy": 0.9624999761581421, "learning_rate": 1.3905907440629752e-07, "epoch": 1.2306190421499943, "percentage": 89.33, "elapsed_time": "3:05:50", "remaining_time": "0:22:11", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1736, "accuracy": 0.987500011920929, "learning_rate": 1.223587092621162e-07, "epoch": 1.2398070517974045, "percentage": 90.0, "elapsed_time": "3:07:07", "remaining_time": "0:20:47", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.19999442994594574, "epoch": 1.2398070517974045, "percentage": 90.0, "elapsed_time": "3:07:31", "remaining_time": "0:20:50", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1779, "accuracy": 0.9624999761581421, "learning_rate": 1.3905907440629752e-07, "epoch": 1.2306190421499943, "percentage": 89.33, "elapsed_time": "3:05:50", "remaining_time": "0:22:11", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1736, "accuracy": 0.987500011920929, "learning_rate": 1.223587092621162e-07, "epoch": 1.2398070517974045, "percentage": 90.0, "elapsed_time": "3:07:07", "remaining_time": "0:20:47", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.19999442994594574, "epoch": 1.2398070517974045, "percentage": 90.0, "elapsed_time": "3:07:31", "remaining_time": "0:20:50", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1360, "total_steps": 1500, "loss": 0.2027, "accuracy": 0.8999999761581421, "learning_rate": 1.067012561698319e-07, "epoch": 1.2489950614448144, "percentage": 90.67, "elapsed_time": "3:08:52", "remaining_time": "0:19:26", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1370, "total_steps": 1500, "loss": 0.1962, "accuracy": 0.9750000238418579, "learning_rate": 9.209358300585474e-08, "epoch": 1.2581830710922246, "percentage": 91.33, "elapsed_time": "3:10:06", "remaining_time": "0:18:02", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1380, "total_steps": 1500, "loss": 0.2435, "accuracy": 0.9375, "learning_rate": 7.854209717842231e-08, "epoch": 1.2673710807396348, "percentage": 92.0, "elapsed_time": "3:11:23", "remaining_time": "0:16:38", "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}