Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.75-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
1b9db2c
·
verified ·
1 Parent(s): 0246c75

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:f7c51fe7edcf641e9593b0313333e7d09858938367b43b4a221c7fdfda538101
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd8c812b88b9716acc7634cc7562dbbaf736d39d8642b7f2313619a2e02824b
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -4,3 +4,9 @@
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.941, "accuracy": 0.5375000238418579, "learning_rate": 4.9912321481237616e-06, "epoch": 0.035523978685612786, "percentage": 2.67, "elapsed_time": "0:05:15", "remaining_time": "3:11:41", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.929, "accuracy": 0.44999998807907104, "learning_rate": 4.986304738420684e-06, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:06:32", "remaining_time": "3:09:51", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9458721876144409, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:07:00", "remaining_time": "3:23:16", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.941, "accuracy": 0.5375000238418579, "learning_rate": 4.9912321481237616e-06, "epoch": 0.035523978685612786, "percentage": 2.67, "elapsed_time": "0:05:15", "remaining_time": "3:11:41", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.929, "accuracy": 0.44999998807907104, "learning_rate": 4.986304738420684e-06, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:06:32", "remaining_time": "3:09:51", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9458721876144409, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:07:00", "remaining_time": "3:23:16", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 60, "total_steps": 1500, "loss": 0.9335, "accuracy": 0.5, "learning_rate": 4.980286753286196e-06, "epoch": 0.05328596802841918, "percentage": 4.0, "elapsed_time": "0:08:28", "remaining_time": "3:23:30", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 70, "total_steps": 1500, "loss": 0.9234, "accuracy": 0.6499999761581421, "learning_rate": 4.973180832407471e-06, "epoch": 0.06216696269982238, "percentage": 4.67, "elapsed_time": "0:09:46", "remaining_time": "3:19:45", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 80, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.550000011920929, "learning_rate": 4.964990092676263e-06, "epoch": 0.07104795737122557, "percentage": 5.33, "elapsed_time": "0:11:06", "remaining_time": "3:17:03", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 90, "total_steps": 1500, "loss": 0.9276, "accuracy": 0.5625, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07992895204262877, "percentage": 6.0, "elapsed_time": "0:12:23", "remaining_time": "3:14:11", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 100, "total_steps": 1500, "loss": 0.9448, "accuracy": 0.5249999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08880994671403197, "percentage": 6.67, "elapsed_time": "0:13:44", "remaining_time": "3:12:26", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9382757544517517, "epoch": 0.08880994671403197, "percentage": 6.67, "elapsed_time": "0:14:11", "remaining_time": "3:18:43", "throughput": "0.00", "total_tokens": 0}