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
4b6be4a
·
verified ·
1 Parent(s): e96aeb0

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 sha256:1cd8c812b88b9716acc7634cc7562dbbaf736d39d8642b7f2313619a2e02824b
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26947209838a67812fe35b67388e1964ecb05c57d192af61e0770ffc0e8cf09
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -10,3 +10,9 @@
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}
 
 
 
 
 
 
 
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}
13
+ {"current_steps": 110, "total_steps": 1500, "loss": 0.9307, "accuracy": 0.5874999761581421, "learning_rate": 4.933947257182901e-06, "epoch": 0.09769094138543517, "percentage": 7.33, "elapsed_time": "0:15:33", "remaining_time": "3:16:39", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 120, "total_steps": 1500, "loss": 0.9046, "accuracy": 0.574999988079071, "learning_rate": 4.921457902821578e-06, "epoch": 0.10657193605683836, "percentage": 8.0, "elapsed_time": "0:16:52", "remaining_time": "3:14:09", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 130, "total_steps": 1500, "loss": 0.9151, "accuracy": 0.6000000238418579, "learning_rate": 4.907906416994146e-06, "epoch": 0.11545293072824156, "percentage": 8.67, "elapsed_time": "0:18:11", "remaining_time": "3:11:38", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 140, "total_steps": 1500, "loss": 0.9053, "accuracy": 0.6000000238418579, "learning_rate": 4.893298743830168e-06, "epoch": 0.12433392539964476, "percentage": 9.33, "elapsed_time": "0:19:26", "remaining_time": "3:08:53", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 150, "total_steps": 1500, "loss": 0.9097, "accuracy": 0.5375000238418579, "learning_rate": 4.8776412907378845e-06, "epoch": 0.13321492007104796, "percentage": 10.0, "elapsed_time": "0:20:41", "remaining_time": "3:06:15", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9194123148918152, "epoch": 0.13321492007104796, "percentage": 10.0, "elapsed_time": "0:21:08", "remaining_time": "3:10:17", "throughput": "0.00", "total_tokens": 0}