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
96c2693
·
verified ·
1 Parent(s): 8b674e9

Training in progress, step 450

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 sha256:99374767f519854618ef8ab382afb028eb65463205a88bc282551170250ec3ba
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5c49e5dbbbb952b0231024ed83dc94f00125f5a9d53a6fbb1962b4bd4aa1c2
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -46,3 +46,9 @@
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4118, "accuracy": 0.8125, "learning_rate": 4.211367764821722e-06, "epoch": 0.35833237624899505, "percentage": 26.0, "elapsed_time": "0:53:42", "remaining_time": "2:32:52", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.3557, "accuracy": 0.8500000238418579, "learning_rate": 4.172826515897146e-06, "epoch": 0.3675203858964052, "percentage": 26.67, "elapsed_time": "0:54:59", "remaining_time": "2:31:13", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.4082850515842438, "epoch": 0.3675203858964052, "percentage": 26.67, "elapsed_time": "0:55:23", "remaining_time": "2:32:20", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4118, "accuracy": 0.8125, "learning_rate": 4.211367764821722e-06, "epoch": 0.35833237624899505, "percentage": 26.0, "elapsed_time": "0:53:42", "remaining_time": "2:32:52", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.3557, "accuracy": 0.8500000238418579, "learning_rate": 4.172826515897146e-06, "epoch": 0.3675203858964052, "percentage": 26.67, "elapsed_time": "0:54:59", "remaining_time": "2:31:13", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.4082850515842438, "epoch": 0.3675203858964052, "percentage": 26.67, "elapsed_time": "0:55:23", "remaining_time": "2:32:20", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 410, "total_steps": 1500, "loss": 0.4184, "accuracy": 0.887499988079071, "learning_rate": 4.133551509975264e-06, "epoch": 0.3767083955438153, "percentage": 27.33, "elapsed_time": "0:56:48", "remaining_time": "2:31:01", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 420, "total_steps": 1500, "loss": 0.4096, "accuracy": 0.875, "learning_rate": 4.093559974371725e-06, "epoch": 0.3858964051912255, "percentage": 28.0, "elapsed_time": "0:58:03", "remaining_time": "2:29:17", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 430, "total_steps": 1500, "loss": 0.4083, "accuracy": 0.862500011920929, "learning_rate": 4.052869450695776e-06, "epoch": 0.3950844148386356, "percentage": 28.67, "elapsed_time": "0:59:18", "remaining_time": "2:27:33", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 440, "total_steps": 1500, "loss": 0.3783, "accuracy": 0.8374999761581421, "learning_rate": 4.011497787155938e-06, "epoch": 0.4042724244860457, "percentage": 29.33, "elapsed_time": "1:00:33", "remaining_time": "2:25:52", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 450, "total_steps": 1500, "loss": 0.347, "accuracy": 0.9375, "learning_rate": 3.969463130731183e-06, "epoch": 0.41346043413345585, "percentage": 30.0, "elapsed_time": "1:01:53", "remaining_time": "2:24:25", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.36501914262771606, "epoch": 0.41346043413345585, "percentage": 30.0, "elapsed_time": "1:02:18", "remaining_time": "2:25:22", "throughput": "0.00", "total_tokens": 0}