Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.3-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
7753e2b
·
verified ·
1 Parent(s): e20f6ea

Training in progress, step 1250

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 sha256:6d1e1e8b7692eec4cffc7d373c632a50d70aaeb9e2110c1175f4974e17a757ac
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43e012f1c21d754a50b38bef3b896c9bf9d6c4df42194652a2f5bd31711bcac
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -142,3 +142,9 @@
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.2863, "accuracy": 0.9375, "learning_rate": 5.086752049395094e-07, "epoch": 1.5104761904761905, "percentage": 79.33, "elapsed_time": "2:43:43", "remaining_time": "0:42:38", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.274, "accuracy": 0.9750000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.5231746031746032, "percentage": 80.0, "elapsed_time": "2:45:04", "remaining_time": "0:41:16", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.25126969814300537, "epoch": 1.5231746031746032, "percentage": 80.0, "elapsed_time": "2:45:22", "remaining_time": "0:41:20", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.2863, "accuracy": 0.9375, "learning_rate": 5.086752049395094e-07, "epoch": 1.5104761904761905, "percentage": 79.33, "elapsed_time": "2:43:43", "remaining_time": "0:42:38", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.274, "accuracy": 0.9750000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.5231746031746032, "percentage": 80.0, "elapsed_time": "2:45:04", "remaining_time": "0:41:16", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.25126969814300537, "epoch": 1.5231746031746032, "percentage": 80.0, "elapsed_time": "2:45:22", "remaining_time": "0:41:20", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1210, "total_steps": 1500, "loss": 0.2878, "accuracy": 0.9375, "learning_rate": 4.4712697716573994e-07, "epoch": 1.5358730158730158, "percentage": 80.67, "elapsed_time": "2:46:58", "remaining_time": "0:40:01", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1220, "total_steps": 1500, "loss": 0.2557, "accuracy": 0.8999999761581421, "learning_rate": 4.1769689822475147e-07, "epoch": 1.5485714285714285, "percentage": 81.33, "elapsed_time": "2:48:12", "remaining_time": "0:38:36", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1230, "total_steps": 1500, "loss": 0.2745, "accuracy": 0.925000011920929, "learning_rate": 3.891801862449629e-07, "epoch": 1.5612698412698411, "percentage": 82.0, "elapsed_time": "2:49:29", "remaining_time": "0:37:12", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1240, "total_steps": 1500, "loss": 0.3246, "accuracy": 0.8500000238418579, "learning_rate": 3.615893495987335e-07, "epoch": 1.573968253968254, "percentage": 82.67, "elapsed_time": "2:50:45", "remaining_time": "0:35:48", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1250, "total_steps": 1500, "loss": 0.2725, "accuracy": 0.925000011920929, "learning_rate": 3.3493649053890325e-07, "epoch": 1.5866666666666667, "percentage": 83.33, "elapsed_time": "2:52:01", "remaining_time": "0:34:24", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.24976640939712524, "epoch": 1.5866666666666667, "percentage": 83.33, "elapsed_time": "2:52:19", "remaining_time": "0:34:27", "throughput": "0.00", "total_tokens": 0}