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
81d5dd8
·
verified ·
1 Parent(s): 3b1cc0f

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 sha256:7489e9bc7d19b0729a77850ca332bf5be718cd0a777d40cb43e8348a3330cc7e
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24a7a47f45120cb86768cf6d416ae531f4243bc100226f511003c46a6d16e7b
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7992, "accuracy": 0.637499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:33", "remaining_time": "2:45:39", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7848, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:32:47", "remaining_time": "2:43:55", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7728626728057861, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:12", "remaining_time": "2:46:04", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7992, "accuracy": 0.637499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:33", "remaining_time": "2:45:39", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7848, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:32:47", "remaining_time": "2:43:55", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7728626728057861, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:12", "remaining_time": "2:46:04", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 0.7273, "accuracy": 0.7124999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.22346368715083798, "percentage": 17.33, "elapsed_time": "0:34:29", "remaining_time": "2:44:28", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 0.7483, "accuracy": 0.6875, "learning_rate": 4.610819813755038e-06, "epoch": 0.23205844434894715, "percentage": 18.0, "elapsed_time": "0:35:46", "remaining_time": "2:43:00", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 0.7165, "accuracy": 0.612500011920929, "learning_rate": 4.582303101775249e-06, "epoch": 0.2406532015470563, "percentage": 18.67, "elapsed_time": "0:36:58", "remaining_time": "2:41:04", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 0.6685, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.24924795874516545, "percentage": 19.33, "elapsed_time": "0:38:10", "remaining_time": "2:39:16", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 0.6009, "accuracy": 0.625, "learning_rate": 4.522542485937369e-06, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:25", "remaining_time": "2:37:41", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5855891704559326, "epoch": 0.2578427159432746, "percentage": 20.0, "elapsed_time": "0:39:51", "remaining_time": "2:39:24", "throughput": "0.00", "total_tokens": 0}