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
Model card Files Community
ziansu commited on
Commit
5d3b473
·
verified ·
1 Parent(s): 3e230c9

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:daa2979877c388e7bf9b1c7efb205fe7a7e0ec3430ea741721706000acd8d08c
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a9264918d1a32f7f7380b47ea3913df05c696c6270b8036bd4a6e252f3bfba
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -10,3 +10,9 @@
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}
 
 
 
 
 
 
 
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}
13
+ {"current_steps": 110, "total_steps": 1500, "loss": 0.934, "accuracy": 0.574999988079071, "learning_rate": 4.933947257182901e-06, "epoch": 0.10106810612151143, "percentage": 7.33, "elapsed_time": "0:15:15", "remaining_time": "3:12:44", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 120, "total_steps": 1500, "loss": 0.9202, "accuracy": 0.4749999940395355, "learning_rate": 4.921457902821578e-06, "epoch": 0.11025611576892155, "percentage": 8.0, "elapsed_time": "0:16:32", "remaining_time": "3:10:18", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 130, "total_steps": 1500, "loss": 0.9266, "accuracy": 0.625, "learning_rate": 4.907906416994146e-06, "epoch": 0.11944412541633169, "percentage": 8.67, "elapsed_time": "0:17:47", "remaining_time": "3:07:29", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 140, "total_steps": 1500, "loss": 0.9185, "accuracy": 0.512499988079071, "learning_rate": 4.893298743830168e-06, "epoch": 0.12863213506374183, "percentage": 9.33, "elapsed_time": "0:19:01", "remaining_time": "3:04:48", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 150, "total_steps": 1500, "loss": 0.9106, "accuracy": 0.5874999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.13782014471115195, "percentage": 10.0, "elapsed_time": "0:20:16", "remaining_time": "3:02:28", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9164085388183594, "epoch": 0.13782014471115195, "percentage": 10.0, "elapsed_time": "0:20:40", "remaining_time": "3:06:08", "throughput": "0.00", "total_tokens": 0}