Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.75-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
05833d5
·
verified ·
1 Parent(s): 6c3494f

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 sha256:2a4dc31dca542061b86d970aa8cead98221276343d97e4719d3bf92738e43a48
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6fee61b8a941bc2d7ee7ee6bf6505fcf83cab940a1d54702c7d2cab67c8091
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -40,3 +40,9 @@
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.5592, "accuracy": 0.637499988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3019538188277087, "percentage": 22.67, "elapsed_time": "0:45:56", "remaining_time": "2:36:42", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.4737, "accuracy": 0.6625000238418579, "learning_rate": 4.357862063693486e-06, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:47:09", "remaining_time": "2:34:58", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5021397471427917, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:47:35", "remaining_time": "2:36:21", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
40
  {"current_steps": 340, "total_steps": 1500, "loss": 0.5592, "accuracy": 0.637499988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3019538188277087, "percentage": 22.67, "elapsed_time": "0:45:56", "remaining_time": "2:36:42", "throughput": "0.00", "total_tokens": 0}
41
  {"current_steps": 350, "total_steps": 1500, "loss": 0.4737, "accuracy": 0.6625000238418579, "learning_rate": 4.357862063693486e-06, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:47:09", "remaining_time": "2:34:58", "throughput": "0.00", "total_tokens": 0}
42
  {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5021397471427917, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:47:35", "remaining_time": "2:36:21", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 360, "total_steps": 1500, "loss": 0.489, "accuracy": 0.7250000238418579, "learning_rate": 4.322421568553529e-06, "epoch": 0.3197158081705151, "percentage": 24.0, "elapsed_time": "0:48:55", "remaining_time": "2:34:56", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 370, "total_steps": 1500, "loss": 0.4812, "accuracy": 0.675000011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.3285968028419183, "percentage": 24.67, "elapsed_time": "0:50:10", "remaining_time": "2:33:12", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 380, "total_steps": 1500, "loss": 0.4651, "accuracy": 0.737500011920929, "learning_rate": 4.249158351283414e-06, "epoch": 0.33747779751332146, "percentage": 25.33, "elapsed_time": "0:51:24", "remaining_time": "2:31:29", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 390, "total_steps": 1500, "loss": 0.4292, "accuracy": 0.800000011920929, "learning_rate": 4.211367764821722e-06, "epoch": 0.3463587921847247, "percentage": 26.0, "elapsed_time": "0:52:38", "remaining_time": "2:29:49", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 400, "total_steps": 1500, "loss": 0.3902, "accuracy": 0.8500000238418579, "learning_rate": 4.172826515897146e-06, "epoch": 0.3552397868561279, "percentage": 26.67, "elapsed_time": "0:53:53", "remaining_time": "2:28:11", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.4054907560348511, "epoch": 0.3552397868561279, "percentage": 26.67, "elapsed_time": "0:54:18", "remaining_time": "2:29:21", "throughput": "0.00", "total_tokens": 0}