Hugging Face's logo

prosecalign
/
phi3m0128-wds-0.7-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
a39bc8b
·
verified ·
1 Parent(s): 772181b

Training in progress, step 350

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 sha256:3723d7a38a8c8710653f37f912461e0112b9c9676394cbf49f046e933d47ce4d
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23cd58c65dac831d811daf44f1c8f0947baec6f46f0d5f9b1288f2e131bafaba
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -34,3 +34,9 @@
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5988, "accuracy": 0.7250000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.2664522797748938, "percentage": 19.33, "elapsed_time": "0:39:52", "remaining_time": "2:46:21", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5927, "accuracy": 0.6625000238418579, "learning_rate": 4.522542485937369e-06, "epoch": 0.2756402894223039, "percentage": 20.0, "elapsed_time": "0:41:07", "remaining_time": "2:44:29", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5978505611419678, "epoch": 0.2756402894223039, "percentage": 20.0, "elapsed_time": "0:41:31", "remaining_time": "2:46:07", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5988, "accuracy": 0.7250000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.2664522797748938, "percentage": 19.33, "elapsed_time": "0:39:52", "remaining_time": "2:46:21", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5927, "accuracy": 0.6625000238418579, "learning_rate": 4.522542485937369e-06, "epoch": 0.2756402894223039, "percentage": 20.0, "elapsed_time": "0:41:07", "remaining_time": "2:44:29", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5978505611419678, "epoch": 0.2756402894223039, "percentage": 20.0, "elapsed_time": "0:41:31", "remaining_time": "2:46:07", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 310, "total_steps": 1500, "loss": 0.5792, "accuracy": 0.625, "learning_rate": 4.491324795060491e-06, "epoch": 0.284828299069714, "percentage": 20.67, "elapsed_time": "0:42:55", "remaining_time": "2:44:44", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 320, "total_steps": 1500, "loss": 0.5384, "accuracy": 0.762499988079071, "learning_rate": 4.4592336433146e-06, "epoch": 0.29401630871712414, "percentage": 21.33, "elapsed_time": "0:44:13", "remaining_time": "2:43:04", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 330, "total_steps": 1500, "loss": 0.5671, "accuracy": 0.75, "learning_rate": 4.426283106939474e-06, "epoch": 0.30320431836453426, "percentage": 22.0, "elapsed_time": "0:45:28", "remaining_time": "2:41:13", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 340, "total_steps": 1500, "loss": 0.5124, "accuracy": 0.7250000238418579, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3123923280119444, "percentage": 22.67, "elapsed_time": "0:46:44", "remaining_time": "2:39:28", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 350, "total_steps": 1500, "loss": 0.516, "accuracy": 0.7250000238418579, "learning_rate": 4.357862063693486e-06, "epoch": 0.32158033765935456, "percentage": 23.33, "elapsed_time": "0:48:01", "remaining_time": "2:37:47", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5133901238441467, "epoch": 0.32158033765935456, "percentage": 23.33, "elapsed_time": "0:48:25", "remaining_time": "2:39:08", "throughput": "0.00", "total_tokens": 0}