Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.3-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
a53719a
·
verified ·
1 Parent(s): dc95f53

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 sha256:9e5befebf1017039d1a13a3c3c99e065d865220f99076a124e5bb5e00ad0954c
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a4143c6f4548c15edb04225ada7d8afd2956948cce3d5785062760017743191
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.3531, "accuracy": 0.9375, "learning_rate": 2.813333083910761e-06, "epoch": 0.8761904761904762, "percentage": 46.0, "elapsed_time": "1:34:32", "remaining_time": "1:50:58", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.4327, "accuracy": 0.8374999761581421, "learning_rate": 2.761321158169134e-06, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:35:48", "remaining_time": "1:49:30", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.40030673146247864, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:36:07", "remaining_time": "1:49:51", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.3531, "accuracy": 0.9375, "learning_rate": 2.813333083910761e-06, "epoch": 0.8761904761904762, "percentage": 46.0, "elapsed_time": "1:34:32", "remaining_time": "1:50:58", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.4327, "accuracy": 0.8374999761581421, "learning_rate": 2.761321158169134e-06, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:35:48", "remaining_time": "1:49:30", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.40030673146247864, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:36:07", "remaining_time": "1:49:51", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.3878, "accuracy": 0.9125000238418579, "learning_rate": 2.70919460833079e-06, "epoch": 0.9015873015873016, "percentage": 47.33, "elapsed_time": "1:37:31", "remaining_time": "1:48:30", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 0.3841, "accuracy": 0.9375, "learning_rate": 2.6569762988232838e-06, "epoch": 0.9142857142857143, "percentage": 48.0, "elapsed_time": "1:38:44", "remaining_time": "1:46:58", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.4237, "accuracy": 0.8125, "learning_rate": 2.604689134322999e-06, "epoch": 0.926984126984127, "percentage": 48.67, "elapsed_time": "1:40:00", "remaining_time": "1:45:29", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.3566, "accuracy": 0.9375, "learning_rate": 2.5523560497083927e-06, "epoch": 0.9396825396825397, "percentage": 49.33, "elapsed_time": "1:41:16", "remaining_time": "1:44:00", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.3494, "accuracy": 0.9125000238418579, "learning_rate": 2.5e-06, "epoch": 0.9523809523809523, "percentage": 50.0, "elapsed_time": "1:42:35", "remaining_time": "1:42:35", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.37998583912849426, "epoch": 0.9523809523809523, "percentage": 50.0, "elapsed_time": "1:42:54", "remaining_time": "1:42:54", "throughput": "0.00", "total_tokens": 0}