Hugging Face's logo

prosecalign
/
clm7b0129-wds-0.8-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files
xet
Community
ziansu commited on
Commit
d51eb00
·
verified ·
1 Parent(s): 7c7907b

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 sha256:1b6c528d8c3d83041b9517e51c5c5af41bfae5086fd51e92acf4a42f54faba0c
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ec2cef8e530cd60c8c7b53869b4ce90e0f6158a1ea2814cde110870bb0c1fe0
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -10,3 +10,9 @@
10
  {"current_steps": 90, "total_steps": 1500, "loss": 7.4584, "accuracy": 0.512499988079071, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07386130488305294, "percentage": 6.0, "elapsed_time": "0:11:15", "remaining_time": "2:56:27", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 7.4116, "accuracy": 0.5375000238418579, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08206811653672548, "percentage": 6.67, "elapsed_time": "0:12:26", "remaining_time": "2:54:12", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9129964113235474, "epoch": 0.08206811653672548, "percentage": 6.67, "elapsed_time": "0:12:52", "remaining_time": "3:00:17", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
10
  {"current_steps": 90, "total_steps": 1500, "loss": 7.4584, "accuracy": 0.512499988079071, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07386130488305294, "percentage": 6.0, "elapsed_time": "0:11:15", "remaining_time": "2:56:27", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 7.4116, "accuracy": 0.5375000238418579, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08206811653672548, "percentage": 6.67, "elapsed_time": "0:12:26", "remaining_time": "2:54:12", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9129964113235474, "epoch": 0.08206811653672548, "percentage": 6.67, "elapsed_time": "0:12:52", "remaining_time": "3:00:17", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 110, "total_steps": 1500, "loss": 7.3604, "accuracy": 0.512499988079071, "learning_rate": 4.933947257182901e-06, "epoch": 0.09027492819039803, "percentage": 7.33, "elapsed_time": "0:14:16", "remaining_time": "3:00:19", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 120, "total_steps": 1500, "loss": 7.3624, "accuracy": 0.6000000238418579, "learning_rate": 4.921457902821578e-06, "epoch": 0.09848173984407058, "percentage": 8.0, "elapsed_time": "0:15:26", "remaining_time": "2:57:39", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 130, "total_steps": 1500, "loss": 7.3464, "accuracy": 0.675000011920929, "learning_rate": 4.907906416994146e-06, "epoch": 0.10668855149774313, "percentage": 8.67, "elapsed_time": "0:16:38", "remaining_time": "2:55:24", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 140, "total_steps": 1500, "loss": 7.3179, "accuracy": 0.574999988079071, "learning_rate": 4.893298743830168e-06, "epoch": 0.11489536315141567, "percentage": 9.33, "elapsed_time": "0:17:51", "remaining_time": "2:53:25", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 150, "total_steps": 1500, "loss": 7.2384, "accuracy": 0.574999988079071, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12310217480508823, "percentage": 10.0, "elapsed_time": "0:18:58", "remaining_time": "2:50:49", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8982937335968018, "epoch": 0.12310217480508823, "percentage": 10.0, "elapsed_time": "0:19:24", "remaining_time": "2:54:44", "throughput": "0.00", "total_tokens": 0}