Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.7-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
97049c0
·
verified ·
1 Parent(s): 906f152

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:adfb653713a92770b256f3670aff9e8d632bf514b6f45f6e431f6c42c98e22fd
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa2979877c388e7bf9b1c7efb205fe7a7e0ec3430ea741721706000acd8d08c
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -4,3 +4,9 @@
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9215, "accuracy": 0.5249999761581421, "learning_rate": 4.9912321481237616e-06, "epoch": 0.03675203858964052, "percentage": 2.67, "elapsed_time": "0:05:15", "remaining_time": "3:12:10", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9464, "accuracy": 0.4749999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.04594004823705065, "percentage": 3.33, "elapsed_time": "0:06:32", "remaining_time": "3:09:31", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9397181868553162, "epoch": 0.04594004823705065, "percentage": 3.33, "elapsed_time": "0:06:57", "remaining_time": "3:21:35", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9215, "accuracy": 0.5249999761581421, "learning_rate": 4.9912321481237616e-06, "epoch": 0.03675203858964052, "percentage": 2.67, "elapsed_time": "0:05:15", "remaining_time": "3:12:10", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9464, "accuracy": 0.4749999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.04594004823705065, "percentage": 3.33, "elapsed_time": "0:06:32", "remaining_time": "3:09:31", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9397181868553162, "epoch": 0.04594004823705065, "percentage": 3.33, "elapsed_time": "0:06:57", "remaining_time": "3:21:35", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 60, "total_steps": 1500, "loss": 0.9318, "accuracy": 0.5625, "learning_rate": 4.980286753286196e-06, "epoch": 0.05512805788446078, "percentage": 4.0, "elapsed_time": "0:08:21", "remaining_time": "3:20:36", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 70, "total_steps": 1500, "loss": 0.9158, "accuracy": 0.75, "learning_rate": 4.973180832407471e-06, "epoch": 0.06431606753187091, "percentage": 4.67, "elapsed_time": "0:09:38", "remaining_time": "3:17:07", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 80, "total_steps": 1500, "loss": 0.9372, "accuracy": 0.5249999761581421, "learning_rate": 4.964990092676263e-06, "epoch": 0.07350407717928104, "percentage": 5.33, "elapsed_time": "0:10:56", "remaining_time": "3:14:08", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 90, "total_steps": 1500, "loss": 0.9324, "accuracy": 0.5625, "learning_rate": 4.9557181268217225e-06, "epoch": 0.08269208682669117, "percentage": 6.0, "elapsed_time": "0:12:15", "remaining_time": "3:11:55", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 100, "total_steps": 1500, "loss": 0.9353, "accuracy": 0.637499988079071, "learning_rate": 4.9453690018345144e-06, "epoch": 0.0918800964741013, "percentage": 6.67, "elapsed_time": "0:13:28", "remaining_time": "3:08:44", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9324077367782593, "epoch": 0.0918800964741013, "percentage": 6.67, "elapsed_time": "0:13:53", "remaining_time": "3:14:26", "throughput": "0.00", "total_tokens": 0}