Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.9-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
d62ccb9
·
verified ·
1 Parent(s): a451f9c

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:b0f3f4151fb62a22cf1c3d486b7cdb39752cf37cfb2b6840bab9e081788ba6b1
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f816513921eead20be38083633ae03c13535bc9218320e2ce541a573d481a335
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -10,3 +10,9 @@
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9055, "accuracy": 0.6000000238418579, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07265388496468214, "percentage": 6.0, "elapsed_time": "0:12:00", "remaining_time": "3:08:14", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.911, "accuracy": 0.48750001192092896, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:10", "remaining_time": "3:04:30", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.8986235857009888, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:39", "remaining_time": "3:11:17", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9055, "accuracy": 0.6000000238418579, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07265388496468214, "percentage": 6.0, "elapsed_time": "0:12:00", "remaining_time": "3:08:14", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.911, "accuracy": 0.48750001192092896, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:10", "remaining_time": "3:04:30", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.8986235857009888, "epoch": 0.08072653884964683, "percentage": 6.67, "elapsed_time": "0:13:39", "remaining_time": "3:11:17", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 110, "total_steps": 1500, "loss": 0.8993, "accuracy": 0.6875, "learning_rate": 4.933947257182901e-06, "epoch": 0.08879919273461151, "percentage": 7.33, "elapsed_time": "0:15:15", "remaining_time": "3:12:54", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 120, "total_steps": 1500, "loss": 0.8942, "accuracy": 0.6000000238418579, "learning_rate": 4.921457902821578e-06, "epoch": 0.09687184661957618, "percentage": 8.0, "elapsed_time": "0:16:30", "remaining_time": "3:09:45", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 130, "total_steps": 1500, "loss": 0.8922, "accuracy": 0.550000011920929, "learning_rate": 4.907906416994146e-06, "epoch": 0.10494450050454086, "percentage": 8.67, "elapsed_time": "0:17:46", "remaining_time": "3:07:18", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 140, "total_steps": 1500, "loss": 0.8957, "accuracy": 0.612500011920929, "learning_rate": 4.893298743830168e-06, "epoch": 0.11301715438950555, "percentage": 9.33, "elapsed_time": "0:19:03", "remaining_time": "3:05:11", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 150, "total_steps": 1500, "loss": 0.892, "accuracy": 0.4375, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:21", "remaining_time": "3:03:17", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8789658546447754, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:51", "remaining_time": "3:07:39", "throughput": "0.00", "total_tokens": 0}