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
103f3b9
·
verified ·
1 Parent(s): 1fc06b0

Training in progress, step 450

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:eb6fee61b8a941bc2d7ee7ee6bf6505fcf83cab940a1d54702c7d2cab67c8091
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3838f6fa412378b6f36b3f773cede659c9f0fc77d473841346746580eb5780f5
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -46,3 +46,9 @@
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}
 
 
 
 
 
 
 
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}
49
+ {"current_steps": 410, "total_steps": 1500, "loss": 0.3977, "accuracy": 0.862500011920929, "learning_rate": 4.133551509975264e-06, "epoch": 0.3641207815275311, "percentage": 27.33, "elapsed_time": "0:55:43", "remaining_time": "2:28:09", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 420, "total_steps": 1500, "loss": 0.3527, "accuracy": 0.875, "learning_rate": 4.093559974371725e-06, "epoch": 0.37300177619893427, "percentage": 28.0, "elapsed_time": "0:57:00", "remaining_time": "2:26:34", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 430, "total_steps": 1500, "loss": 0.387, "accuracy": 0.887499988079071, "learning_rate": 4.052869450695776e-06, "epoch": 0.38188277087033745, "percentage": 28.67, "elapsed_time": "0:58:17", "remaining_time": "2:25:03", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 440, "total_steps": 1500, "loss": 0.3611, "accuracy": 0.925000011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.3907637655417407, "percentage": 29.33, "elapsed_time": "0:59:33", "remaining_time": "2:23:28", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 450, "total_steps": 1500, "loss": 0.354, "accuracy": 0.8500000238418579, "learning_rate": 3.969463130731183e-06, "epoch": 0.3996447602131439, "percentage": 30.0, "elapsed_time": "1:00:48", "remaining_time": "2:21:53", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.36211252212524414, "epoch": 0.3996447602131439, "percentage": 30.0, "elapsed_time": "1:01:14", "remaining_time": "2:22:52", "throughput": "0.00", "total_tokens": 0}