Hugging Face's logo

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

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
54e46de
·
verified ·
1 Parent(s): 50b3977

Training in progress, step 150

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 sha256:9cf5a45ac83b946e5e265b71b5785a26c038ceec5d9cc55fa214072d5bbabf1a
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858615ba8711149ca3bffaabea9993faf32ee41829ca40d166ca47a485008823
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -10,3 +10,9 @@
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9359, "accuracy": 0.5, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:30", "remaining_time": "3:00:21", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.9066, "accuracy": 0.5874999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:42", "remaining_time": "2:57:53", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9236211180686951, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:08", "remaining_time": "3:03:54", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9359, "accuracy": 0.5, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:30", "remaining_time": "3:00:21", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.9066, "accuracy": 0.5874999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:42", "remaining_time": "2:57:53", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9236211180686951, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:08", "remaining_time": "3:03:54", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 110, "total_steps": 1500, "loss": 0.929, "accuracy": 0.44999998807907104, "learning_rate": 4.933947257182901e-06, "epoch": 0.09454232917920069, "percentage": 7.33, "elapsed_time": "0:14:26", "remaining_time": "3:02:28", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 120, "total_steps": 1500, "loss": 0.9299, "accuracy": 0.5874999761581421, "learning_rate": 4.921457902821578e-06, "epoch": 0.10313708637730984, "percentage": 8.0, "elapsed_time": "0:15:43", "remaining_time": "3:00:55", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 130, "total_steps": 1500, "loss": 0.9109, "accuracy": 0.5375000238418579, "learning_rate": 4.907906416994146e-06, "epoch": 0.11173184357541899, "percentage": 8.67, "elapsed_time": "0:16:56", "remaining_time": "2:58:35", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 140, "total_steps": 1500, "loss": 0.9138, "accuracy": 0.5625, "learning_rate": 4.893298743830168e-06, "epoch": 0.12032660077352815, "percentage": 9.33, "elapsed_time": "0:18:12", "remaining_time": "2:56:55", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 150, "total_steps": 1500, "loss": 0.9157, "accuracy": 0.574999988079071, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:26", "remaining_time": "2:54:58", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.909102737903595, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:52", "remaining_time": "2:58:50", "throughput": "0.00", "total_tokens": 0}