Hugging Face's logo

prosecalign
/
phi3m0128-kendall-onof-neg_if-corr-max-2-simpo-max1500-decay-sft0.2-beta1.5-gamma0.5-lr5e-6

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
66742a7
·
verified ·
1 Parent(s): 0c278bf

Training in progress, step 300

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 sha256:9fd57ddb7541d2dbf9ceb9ce37b1ecefe1b46caab2d1c9aeaa031a441c513d53
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb0b420c3ec2105799842438e00647c82387eaba56ababbee9f5c3a8ed7cfd5
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7474, "accuracy": 0.6875, "learning_rate": 4.690766700109659e-06, "epoch": 0.182648401826484, "percentage": 16.0, "elapsed_time": "0:32:36", "remaining_time": "2:51:11", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7017, "accuracy": 0.6875, "learning_rate": 4.665063509461098e-06, "epoch": 0.1902587519025875, "percentage": 16.67, "elapsed_time": "0:33:51", "remaining_time": "2:49:17", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.6914573907852173, "epoch": 0.1902587519025875, "percentage": 16.67, "elapsed_time": "0:34:22", "remaining_time": "2:51:50", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7474, "accuracy": 0.6875, "learning_rate": 4.690766700109659e-06, "epoch": 0.182648401826484, "percentage": 16.0, "elapsed_time": "0:32:36", "remaining_time": "2:51:11", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7017, "accuracy": 0.6875, "learning_rate": 4.665063509461098e-06, "epoch": 0.1902587519025875, "percentage": 16.67, "elapsed_time": "0:33:51", "remaining_time": "2:49:17", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.6914573907852173, "epoch": 0.1902587519025875, "percentage": 16.67, "elapsed_time": "0:34:22", "remaining_time": "2:51:50", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 0.6908, "accuracy": 0.637499988079071, "learning_rate": 4.638410650401267e-06, "epoch": 0.197869101978691, "percentage": 17.33, "elapsed_time": "0:35:43", "remaining_time": "2:50:25", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 0.6868, "accuracy": 0.637499988079071, "learning_rate": 4.610819813755038e-06, "epoch": 0.2054794520547945, "percentage": 18.0, "elapsed_time": "0:36:55", "remaining_time": "2:48:14", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 0.632, "accuracy": 0.6499999761581421, "learning_rate": 4.582303101775249e-06, "epoch": 0.213089802130898, "percentage": 18.67, "elapsed_time": "0:38:13", "remaining_time": "2:46:33", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 0.6447, "accuracy": 0.7250000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.2207001522070015, "percentage": 19.33, "elapsed_time": "0:39:24", "remaining_time": "2:44:24", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 0.5702, "accuracy": 0.637499988079071, "learning_rate": 4.522542485937369e-06, "epoch": 0.228310502283105, "percentage": 20.0, "elapsed_time": "0:40:37", "remaining_time": "2:42:29", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5786539912223816, "epoch": 0.228310502283105, "percentage": 20.0, "elapsed_time": "0:41:08", "remaining_time": "2:44:32", "throughput": "0.00", "total_tokens": 0}