Hugging Face's logo

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

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files
xet
Community
ziansu commited on
Commit
b3dad21
·
verified ·
1 Parent(s): 23762a4

Training in progress, step 750

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 sha256:379cce85da9fcbf98da16e2218d5147d990dcabef2293a3b6bb0f07b82736e43
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb873b27a0ddbd459a54abf7c399a01453a2e748ed4875561bd6cfe3333f2007
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -82,3 +82,9 @@
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2458, "accuracy": 0.949999988079071, "learning_rate": 2.813333083910761e-06, "epoch": 0.5930382466695315, "percentage": 46.0, "elapsed_time": "1:30:30", "remaining_time": "1:46:15", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2464, "accuracy": 0.925000011920929, "learning_rate": 2.761321158169134e-06, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:31:41", "remaining_time": "1:44:47", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26223084330558777, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:32:07", "remaining_time": "1:45:17", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
82
  {"current_steps": 690, "total_steps": 1500, "loss": 0.2458, "accuracy": 0.949999988079071, "learning_rate": 2.813333083910761e-06, "epoch": 0.5930382466695315, "percentage": 46.0, "elapsed_time": "1:30:30", "remaining_time": "1:46:15", "throughput": "0.00", "total_tokens": 0}
83
  {"current_steps": 700, "total_steps": 1500, "loss": 0.2464, "accuracy": 0.925000011920929, "learning_rate": 2.761321158169134e-06, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:31:41", "remaining_time": "1:44:47", "throughput": "0.00", "total_tokens": 0}
84
  {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26223084330558777, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:32:07", "remaining_time": "1:45:17", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.2785, "accuracy": 0.9624999761581421, "learning_rate": 2.70919460833079e-06, "epoch": 0.6102277610657499, "percentage": 47.33, "elapsed_time": "1:33:23", "remaining_time": "1:43:55", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 720, "total_steps": 1500, "loss": 0.2623, "accuracy": 0.925000011920929, "learning_rate": 2.6569762988232838e-06, "epoch": 0.618822518263859, "percentage": 48.0, "elapsed_time": "1:34:36", "remaining_time": "1:42:29", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.2702, "accuracy": 0.9125000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 0.6274172754619682, "percentage": 48.67, "elapsed_time": "1:35:48", "remaining_time": "1:41:03", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.2103, "accuracy": 0.949999988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6360120326600773, "percentage": 49.33, "elapsed_time": "1:37:00", "remaining_time": "1:39:37", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.2545, "accuracy": 0.949999988079071, "learning_rate": 2.5e-06, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:38:13", "remaining_time": "1:38:13", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2537091076374054, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:38:39", "remaining_time": "1:38:39", "throughput": "0.00", "total_tokens": 0}