Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-onof-neg_if-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
cb8bb10
·
verified ·
1 Parent(s): 453dba4

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 sha256:093026d7831c2fbaa54005e9ef25ba2c7c76cdee79a093fe8bf90f161e381be4
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa0ddb1bbae1fd5e0e31590ab4c7768adaf38553dddbdbd055d7b10cdb0a06c7
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -10,3 +10,9 @@
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9273, "accuracy": 0.5249999761581421, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:38", "remaining_time": "3:02:27", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.9009, "accuracy": 0.574999988079071, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:53", "remaining_time": "3:00:35", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9138591885566711, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:19", "remaining_time": "3:06:31", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9273, "accuracy": 0.5249999761581421, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:38", "remaining_time": "3:02:27", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.9009, "accuracy": 0.574999988079071, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:53", "remaining_time": "3:00:35", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9138591885566711, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:19", "remaining_time": "3:06:31", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 110, "total_steps": 1500, "loss": 0.916, "accuracy": 0.4625000059604645, "learning_rate": 4.933947257182901e-06, "epoch": 0.09454232917920069, "percentage": 7.33, "elapsed_time": "0:14:42", "remaining_time": "3:05:53", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 120, "total_steps": 1500, "loss": 0.9167, "accuracy": 0.550000011920929, "learning_rate": 4.921457902821578e-06, "epoch": 0.10313708637730984, "percentage": 8.0, "elapsed_time": "0:15:55", "remaining_time": "3:03:02", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 130, "total_steps": 1500, "loss": 0.9087, "accuracy": 0.5249999761581421, "learning_rate": 4.907906416994146e-06, "epoch": 0.11173184357541899, "percentage": 8.67, "elapsed_time": "0:17:09", "remaining_time": "3:00:44", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 140, "total_steps": 1500, "loss": 0.9053, "accuracy": 0.612500011920929, "learning_rate": 4.893298743830168e-06, "epoch": 0.12032660077352815, "percentage": 9.33, "elapsed_time": "0:18:25", "remaining_time": "2:58:55", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 150, "total_steps": 1500, "loss": 0.8999, "accuracy": 0.625, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:38", "remaining_time": "2:56:45", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8956203460693359, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:20:03", "remaining_time": "3:00:34", "throughput": "0.00", "total_tokens": 0}