Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.85-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
33ce165
·
verified ·
1 Parent(s): 244b9eb

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 sha256:3292d9abed177700623ac68bf4e0346979ed6530ffc8d3defb295d7ba4665b14
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece6ad9df06b1e4b9925e01c290469ee0045dc95f4363363b890797dff5cce09
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -142,3 +142,9 @@
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.2178, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 0.990737849932355, "percentage": 79.33, "elapsed_time": "2:46:11", "remaining_time": "0:43:17", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.1799, "accuracy": 0.9375, "learning_rate": 4.774575140626317e-07, "epoch": 0.9990633780830471, "percentage": 80.0, "elapsed_time": "2:47:27", "remaining_time": "0:41:51", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.21951240301132202, "epoch": 0.9990633780830471, "percentage": 80.0, "elapsed_time": "2:47:56", "remaining_time": "0:41:59", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.2178, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 0.990737849932355, "percentage": 79.33, "elapsed_time": "2:46:11", "remaining_time": "0:43:17", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.1799, "accuracy": 0.9375, "learning_rate": 4.774575140626317e-07, "epoch": 0.9990633780830471, "percentage": 80.0, "elapsed_time": "2:47:27", "remaining_time": "0:41:51", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.21951240301132202, "epoch": 0.9990633780830471, "percentage": 80.0, "elapsed_time": "2:47:56", "remaining_time": "0:41:59", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1210, "total_steps": 1500, "loss": 0.1878, "accuracy": 0.9452054500579834, "learning_rate": 4.4712697716573994e-07, "epoch": 1.0066604225205535, "percentage": 80.67, "elapsed_time": "2:49:16", "remaining_time": "0:40:34", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1220, "total_steps": 1500, "loss": 0.1861, "accuracy": 0.9125000238418579, "learning_rate": 4.1769689822475147e-07, "epoch": 1.0149859506712458, "percentage": 81.33, "elapsed_time": "2:50:34", "remaining_time": "0:39:08", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1230, "total_steps": 1500, "loss": 0.2212, "accuracy": 0.987500011920929, "learning_rate": 3.891801862449629e-07, "epoch": 1.0233114788219377, "percentage": 82.0, "elapsed_time": "2:51:51", "remaining_time": "0:37:43", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1240, "total_steps": 1500, "loss": 0.1869, "accuracy": 0.9624999761581421, "learning_rate": 3.615893495987335e-07, "epoch": 1.0316370069726297, "percentage": 82.67, "elapsed_time": "2:53:05", "remaining_time": "0:36:17", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1250, "total_steps": 1500, "loss": 0.1817, "accuracy": 0.949999988079071, "learning_rate": 3.3493649053890325e-07, "epoch": 1.039962535123322, "percentage": 83.33, "elapsed_time": "2:54:22", "remaining_time": "0:34:52", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.21760709583759308, "epoch": 1.039962535123322, "percentage": 83.33, "elapsed_time": "2:54:51", "remaining_time": "0:34:58", "throughput": "0.00", "total_tokens": 0}