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
d564dfe
·
verified ·
1 Parent(s): 296d27b

Training in progress, step 100

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:cc0c3f69507d62c3fb624a9c44fcfca14667d4d33382fef0ae0c6735f55f50d9
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf5a45ac83b946e5e265b71b5785a26c038ceec5d9cc55fa214072d5bbabf1a
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -4,3 +4,9 @@
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9184, "accuracy": 0.4124999940395355, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:48", "remaining_time": "2:55:43", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.5249999761581421, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:03", "remaining_time": "2:55:44", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9324354529380798, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:29", "remaining_time": "3:08:29", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9184, "accuracy": 0.4124999940395355, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:48", "remaining_time": "2:55:43", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.5249999761581421, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:03", "remaining_time": "2:55:44", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9324354529380798, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:29", "remaining_time": "3:08:29", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 60, "total_steps": 1500, "loss": 0.9323, "accuracy": 0.5, "learning_rate": 4.980286753286196e-06, "epoch": 0.05156854318865492, "percentage": 4.0, "elapsed_time": "0:07:47", "remaining_time": "3:07:04", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 70, "total_steps": 1500, "loss": 0.9172, "accuracy": 0.48750001192092896, "learning_rate": 4.973180832407471e-06, "epoch": 0.060163300386764075, "percentage": 4.67, "elapsed_time": "0:09:01", "remaining_time": "3:04:18", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 80, "total_steps": 1500, "loss": 0.9245, "accuracy": 0.48750001192092896, "learning_rate": 4.964990092676263e-06, "epoch": 0.06875805758487323, "percentage": 5.33, "elapsed_time": "0:10:16", "remaining_time": "3:02:22", "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}