Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.75-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
377f386
·
verified ·
1 Parent(s): eb02bd2

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 sha256:234eb9a83fd6eaa3292cba1e1004a1ff7572f49fc1cae58cbb39e8c04c5ad859
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a4dc31dca542061b86d970aa8cead98221276343d97e4719d3bf92738e43a48
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -34,3 +34,9 @@
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5695, "accuracy": 0.6625000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.25754884547069273, "percentage": 19.33, "elapsed_time": "0:39:11", "remaining_time": "2:43:33", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5366, "accuracy": 0.762499988079071, "learning_rate": 4.522542485937369e-06, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:40:23", "remaining_time": "2:41:35", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.551510214805603, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:40:49", "remaining_time": "2:43:16", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
34
  {"current_steps": 290, "total_steps": 1500, "loss": 0.5695, "accuracy": 0.6625000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.25754884547069273, "percentage": 19.33, "elapsed_time": "0:39:11", "remaining_time": "2:43:33", "throughput": "0.00", "total_tokens": 0}
35
  {"current_steps": 300, "total_steps": 1500, "loss": 0.5366, "accuracy": 0.762499988079071, "learning_rate": 4.522542485937369e-06, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:40:23", "remaining_time": "2:41:35", "throughput": "0.00", "total_tokens": 0}
36
  {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.551510214805603, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:40:49", "remaining_time": "2:43:16", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 310, "total_steps": 1500, "loss": 0.5524, "accuracy": 0.675000011920929, "learning_rate": 4.491324795060491e-06, "epoch": 0.2753108348134991, "percentage": 20.67, "elapsed_time": "0:42:13", "remaining_time": "2:42:06", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 320, "total_steps": 1500, "loss": 0.5233, "accuracy": 0.6625000238418579, "learning_rate": 4.4592336433146e-06, "epoch": 0.2841918294849023, "percentage": 21.33, "elapsed_time": "0:43:28", "remaining_time": "2:40:19", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 330, "total_steps": 1500, "loss": 0.556, "accuracy": 0.6875, "learning_rate": 4.426283106939474e-06, "epoch": 0.29307282415630553, "percentage": 22.0, "elapsed_time": "0:44:43", "remaining_time": "2:38:35", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 340, "total_steps": 1500, "loss": 0.5592, "accuracy": 0.637499988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3019538188277087, "percentage": 22.67, "elapsed_time": "0:45:56", "remaining_time": "2:36:42", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 350, "total_steps": 1500, "loss": 0.4737, "accuracy": 0.6625000238418579, "learning_rate": 4.357862063693486e-06, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:47:09", "remaining_time": "2:34:58", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.5021397471427917, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:47:35", "remaining_time": "2:36:21", "throughput": "0.00", "total_tokens": 0}