Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.9-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
5c6012f
·
verified ·
1 Parent(s): c555df8

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:b593941f34d1b2a8e6b529cd2ffa7fdffdb5210951b4bd66051c21793f2fc75f
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb03d041c462ba3691a98bff499160687ca7817f78743c4634e942912e965b40
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -160,3 +160,9 @@
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1918, "accuracy": 0.9624999761581421, "learning_rate": 1.3905907440629752e-07, "epoch": 1.0823410696266398, "percentage": 89.33, "elapsed_time": "3:08:34", "remaining_time": "0:22:30", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1845, "accuracy": 0.949999988079071, "learning_rate": 1.223587092621162e-07, "epoch": 1.0904137235116045, "percentage": 90.0, "elapsed_time": "3:09:50", "remaining_time": "0:21:05", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.20255495607852936, "epoch": 1.0904137235116045, "percentage": 90.0, "elapsed_time": "3:10:20", "remaining_time": "0:21:08", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1918, "accuracy": 0.9624999761581421, "learning_rate": 1.3905907440629752e-07, "epoch": 1.0823410696266398, "percentage": 89.33, "elapsed_time": "3:08:34", "remaining_time": "0:22:30", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1845, "accuracy": 0.949999988079071, "learning_rate": 1.223587092621162e-07, "epoch": 1.0904137235116045, "percentage": 90.0, "elapsed_time": "3:09:50", "remaining_time": "0:21:05", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.20255495607852936, "epoch": 1.0904137235116045, "percentage": 90.0, "elapsed_time": "3:10:20", "remaining_time": "0:21:08", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1360, "total_steps": 1500, "loss": 0.1814, "accuracy": 0.9624999761581421, "learning_rate": 1.067012561698319e-07, "epoch": 1.0984863773965692, "percentage": 90.67, "elapsed_time": "3:11:47", "remaining_time": "0:19:44", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1370, "total_steps": 1500, "loss": 0.1561, "accuracy": 0.9375, "learning_rate": 9.209358300585474e-08, "epoch": 1.1065590312815339, "percentage": 91.33, "elapsed_time": "3:13:05", "remaining_time": "0:18:19", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1380, "total_steps": 1500, "loss": 0.1629, "accuracy": 0.9125000238418579, "learning_rate": 7.854209717842231e-08, "epoch": 1.1146316851664986, "percentage": 92.0, "elapsed_time": "3:14:23", "remaining_time": "0:16:54", "throughput": "0.00", "total_tokens": 0}
166
+ {"current_steps": 1390, "total_steps": 1500, "loss": 0.1615, "accuracy": 0.9624999761581421, "learning_rate": 6.605274281709929e-08, "epoch": 1.122704339051463, "percentage": 92.67, "elapsed_time": "3:15:35", "remaining_time": "0:15:28", "throughput": "0.00", "total_tokens": 0}
167
+ {"current_steps": 1400, "total_steps": 1500, "loss": 0.1679, "accuracy": 0.949999988079071, "learning_rate": 5.463099816548578e-08, "epoch": 1.1307769929364277, "percentage": 93.33, "elapsed_time": "3:16:56", "remaining_time": "0:14:04", "throughput": "0.00", "total_tokens": 0}
168
+ {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.20230723917484283, "epoch": 1.1307769929364277, "percentage": 93.33, "elapsed_time": "3:17:26", "remaining_time": "0:14:06", "throughput": "0.00", "total_tokens": 0}