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
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
316dd43
·
verified ·
1 Parent(s): acfb53a

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:bb1ad4d8146d1c0ffaadf909c904bdea6ec9c72fd04281742417f71e91a03fe4
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caccd1d257c08975a4bdce849e481458c3fa7cb875e557131170383c57d0ae00
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -142,3 +142,9 @@
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.1689, "accuracy": 0.9624999761581421, "learning_rate": 5.086752049395094e-07, "epoch": 1.0223463687150838, "percentage": 79.33, "elapsed_time": "2:36:27", "remaining_time": "0:40:45", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.2052, "accuracy": 0.9125000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:37:43", "remaining_time": "0:39:25", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.2119421511888504, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:38:09", "remaining_time": "0:39:32", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
142
  {"current_steps": 1190, "total_steps": 1500, "loss": 0.1689, "accuracy": 0.9624999761581421, "learning_rate": 5.086752049395094e-07, "epoch": 1.0223463687150838, "percentage": 79.33, "elapsed_time": "2:36:27", "remaining_time": "0:40:45", "throughput": "0.00", "total_tokens": 0}
143
  {"current_steps": 1200, "total_steps": 1500, "loss": 0.2052, "accuracy": 0.9125000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:37:43", "remaining_time": "0:39:25", "throughput": "0.00", "total_tokens": 0}
144
  {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.2119421511888504, "epoch": 1.0309411259131929, "percentage": 80.0, "elapsed_time": "2:38:09", "remaining_time": "0:39:32", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1210, "total_steps": 1500, "loss": 0.2114, "accuracy": 0.925000011920929, "learning_rate": 4.4712697716573994e-07, "epoch": 1.0395358831113022, "percentage": 80.67, "elapsed_time": "2:39:25", "remaining_time": "0:38:12", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1220, "total_steps": 1500, "loss": 0.1962, "accuracy": 0.949999988079071, "learning_rate": 4.1769689822475147e-07, "epoch": 1.0481306403094113, "percentage": 81.33, "elapsed_time": "2:40:40", "remaining_time": "0:36:52", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1230, "total_steps": 1500, "loss": 0.1811, "accuracy": 1.0, "learning_rate": 3.891801862449629e-07, "epoch": 1.0567253975075204, "percentage": 82.0, "elapsed_time": "2:41:53", "remaining_time": "0:35:32", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1240, "total_steps": 1500, "loss": 0.1833, "accuracy": 0.9624999761581421, "learning_rate": 3.615893495987335e-07, "epoch": 1.0653201547056295, "percentage": 82.67, "elapsed_time": "2:43:05", "remaining_time": "0:34:11", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1250, "total_steps": 1500, "loss": 0.1952, "accuracy": 0.9750000238418579, "learning_rate": 3.3493649053890325e-07, "epoch": 1.0739149119037388, "percentage": 83.33, "elapsed_time": "2:44:19", "remaining_time": "0:32:51", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.21290886402130127, "epoch": 1.0739149119037388, "percentage": 83.33, "elapsed_time": "2:44:45", "remaining_time": "0:32:57", "throughput": "0.00", "total_tokens": 0}