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
7b1ce47
·
verified ·
1 Parent(s): 41f194b

Training in progress, step 750

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 sha256:8020df4428a4bb0226fcdb433566eee61a8744cb0a01975a9edb530f8d10891f
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a572548387925cd8f685602286fec9b24c27a0f784762ddcad95945849d6a3b
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2356, "accuracy": 0.949999988079071, "learning_rate": 2.813333083910761e-06, "epoch": 0.557013118062563, "percentage": 46.0, "elapsed_time": "1:36:42", "remaining_time": "1:53:31", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.212, "accuracy": 0.949999988079071, "learning_rate": 2.761321158169134e-06, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:37:56", "remaining_time": "1:51:55", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.24302434921264648, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:38:26", "remaining_time": "1:52:29", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2356, "accuracy": 0.949999988079071, "learning_rate": 2.813333083910761e-06, "epoch": 0.557013118062563, "percentage": 46.0, "elapsed_time": "1:36:42", "remaining_time": "1:53:31", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.212, "accuracy": 0.949999988079071, "learning_rate": 2.761321158169134e-06, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:37:56", "remaining_time": "1:51:55", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.24302434921264648, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:38:26", "remaining_time": "1:52:29", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.192, "accuracy": 0.925000011920929, "learning_rate": 2.70919460833079e-06, "epoch": 0.5731584258324924, "percentage": 47.33, "elapsed_time": "1:39:46", "remaining_time": "1:51:01", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 0.2578, "accuracy": 0.8999999761581421, "learning_rate": 2.6569762988232838e-06, "epoch": 0.5812310797174571, "percentage": 48.0, "elapsed_time": "1:41:04", "remaining_time": "1:49:29", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.2569, "accuracy": 0.875, "learning_rate": 2.604689134322999e-06, "epoch": 0.5893037336024218, "percentage": 48.67, "elapsed_time": "1:42:17", "remaining_time": "1:47:54", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.205, "accuracy": 0.949999988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.5973763874873865, "percentage": 49.33, "elapsed_time": "1:43:36", "remaining_time": "1:46:24", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.2279, "accuracy": 0.9375, "learning_rate": 2.5e-06, "epoch": 0.6054490413723511, "percentage": 50.0, "elapsed_time": "1:44:54", "remaining_time": "1:44:54", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.23516784608364105, "epoch": 0.6054490413723511, "percentage": 50.0, "elapsed_time": "1:45:24", "remaining_time": "1:45:24", "throughput": "0.00", "total_tokens": 0}