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
4c9892b
·
verified ·
1 Parent(s): eb46e2f

Training in progress, step 400

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 sha256:23cd58c65dac831d811daf44f1c8f0947baec6f46f0d5f9b1288f2e131bafaba
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99374767f519854618ef8ab382afb028eb65463205a88bc282551170250ec3ba
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -40,3 +40,9 @@
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.5124, "accuracy": 0.7250000238418579, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3123923280119444, "percentage": 22.67, "elapsed_time": "0:46:44", "remaining_time": "2:39:28", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.516, "accuracy": 0.7250000238418579, "learning_rate": 4.357862063693486e-06, "epoch": 0.32158033765935456, "percentage": 23.33, "elapsed_time": "0:48:01", "remaining_time": "2:37:47", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5133901238441467, "epoch": 0.32158033765935456, "percentage": 23.33, "elapsed_time": "0:48:25", "remaining_time": "2:39:08", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.5124, "accuracy": 0.7250000238418579, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3123923280119444, "percentage": 22.67, "elapsed_time": "0:46:44", "remaining_time": "2:39:28", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.516, "accuracy": 0.7250000238418579, "learning_rate": 4.357862063693486e-06, "epoch": 0.32158033765935456, "percentage": 23.33, "elapsed_time": "0:48:01", "remaining_time": "2:37:47", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5133901238441467, "epoch": 0.32158033765935456, "percentage": 23.33, "elapsed_time": "0:48:25", "remaining_time": "2:39:08", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 360, "total_steps": 1500, "loss": 0.4811, "accuracy": 0.800000011920929, "learning_rate": 4.322421568553529e-06, "epoch": 0.3307683473067647, "percentage": 24.0, "elapsed_time": "0:49:50", "remaining_time": "2:37:49", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 370, "total_steps": 1500, "loss": 0.4326, "accuracy": 0.824999988079071, "learning_rate": 4.286181699082008e-06, "epoch": 0.3399563569541748, "percentage": 24.67, "elapsed_time": "0:51:05", "remaining_time": "2:36:02", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 380, "total_steps": 1500, "loss": 0.4027, "accuracy": 0.875, "learning_rate": 4.249158351283414e-06, "epoch": 0.34914436660158493, "percentage": 25.33, "elapsed_time": "0:52:25", "remaining_time": "2:34:30", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 390, "total_steps": 1500, "loss": 0.4118, "accuracy": 0.8125, "learning_rate": 4.211367764821722e-06, "epoch": 0.35833237624899505, "percentage": 26.0, "elapsed_time": "0:53:42", "remaining_time": "2:32:52", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 400, "total_steps": 1500, "loss": 0.3557, "accuracy": 0.8500000238418579, "learning_rate": 4.172826515897146e-06, "epoch": 0.3675203858964052, "percentage": 26.67, "elapsed_time": "0:54:59", "remaining_time": "2:31:13", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.4082850515842438, "epoch": 0.3675203858964052, "percentage": 26.67, "elapsed_time": "0:55:23", "remaining_time": "2:32:20", "throughput": "0.00", "total_tokens": 0}