Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-onof-neg_if-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
218d793
·
verified ·
1 Parent(s): 6edea20

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 sha256:16a98f9a5d5751f392e3f2ca3c1e35d7247f5e61970f40b07693cc4fc268c69e
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b9098a55898b982d679c6cba531027c7f3a59c8db4150d9bd7503f0058ef56
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2294, "accuracy": 0.9375, "learning_rate": 2.813333083910761e-06, "epoch": 0.5930382466695315, "percentage": 46.0, "elapsed_time": "1:32:18", "remaining_time": "1:48:21", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2469, "accuracy": 0.9375, "learning_rate": 2.761321158169134e-06, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:33:28", "remaining_time": "1:46:49", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.2584603726863861, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:33:53", "remaining_time": "1:47:18", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2294, "accuracy": 0.9375, "learning_rate": 2.813333083910761e-06, "epoch": 0.5930382466695315, "percentage": 46.0, "elapsed_time": "1:32:18", "remaining_time": "1:48:21", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2469, "accuracy": 0.9375, "learning_rate": 2.761321158169134e-06, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:33:28", "remaining_time": "1:46:49", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.2584603726863861, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:33:53", "remaining_time": "1:47:18", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.2732, "accuracy": 0.9375, "learning_rate": 2.70919460833079e-06, "epoch": 0.6102277610657499, "percentage": 47.33, "elapsed_time": "1:35:10", "remaining_time": "1:45:54", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 0.2583, "accuracy": 0.8999999761581421, "learning_rate": 2.6569762988232838e-06, "epoch": 0.618822518263859, "percentage": 48.0, "elapsed_time": "1:36:23", "remaining_time": "1:44:25", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.2889, "accuracy": 0.925000011920929, "learning_rate": 2.604689134322999e-06, "epoch": 0.6274172754619682, "percentage": 48.67, "elapsed_time": "1:37:40", "remaining_time": "1:43:01", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.1972, "accuracy": 0.9624999761581421, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6360120326600773, "percentage": 49.33, "elapsed_time": "1:38:56", "remaining_time": "1:41:36", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.2282, "accuracy": 0.949999988079071, "learning_rate": 2.5e-06, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:40:10", "remaining_time": "1:40:10", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2537557780742645, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:40:35", "remaining_time": "1:40:35", "throughput": "0.00", "total_tokens": 0}