Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-on-neg_if-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
8028dc4
·
verified ·
1 Parent(s): 676b1d0

Training in progress, step 1000

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 sha256:4b8efbac71665abd10ce94a37cb1f7cc15dda9ee73479e57f21c8feb9643d4e7
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3f359fa43cb12d319b4228bb3a4dd508d3506ef46eb349fed079989d0a86dd
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -112,3 +112,9 @@
112
  {"current_steps": 940, "total_steps": 1500, "loss": 0.2211, "accuracy": 0.8999999761581421, "learning_rate": 1.5312110338697427e-06, "epoch": 0.8079071766222604, "percentage": 62.67, "elapsed_time": "2:04:37", "remaining_time": "1:14:14", "throughput": "0.00", "total_tokens": 0}
113
  {"current_steps": 950, "total_steps": 1500, "loss": 0.2359, "accuracy": 0.9624999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:05:49", "remaining_time": "1:12:51", "throughput": "0.00", "total_tokens": 0}
114
  {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.2290637195110321, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:06:15", "remaining_time": "1:13:05", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
112
  {"current_steps": 940, "total_steps": 1500, "loss": 0.2211, "accuracy": 0.8999999761581421, "learning_rate": 1.5312110338697427e-06, "epoch": 0.8079071766222604, "percentage": 62.67, "elapsed_time": "2:04:37", "remaining_time": "1:14:14", "throughput": "0.00", "total_tokens": 0}
113
  {"current_steps": 950, "total_steps": 1500, "loss": 0.2359, "accuracy": 0.9624999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:05:49", "remaining_time": "1:12:51", "throughput": "0.00", "total_tokens": 0}
114
  {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.2290637195110321, "epoch": 0.8165019338203696, "percentage": 63.33, "elapsed_time": "2:06:15", "remaining_time": "1:13:05", "throughput": "0.00", "total_tokens": 0}
115
+ {"current_steps": 960, "total_steps": 1500, "loss": 0.2369, "accuracy": 0.925000011920929, "learning_rate": 1.4355517710873184e-06, "epoch": 0.8250966910184787, "percentage": 64.0, "elapsed_time": "2:07:36", "remaining_time": "1:11:46", "throughput": "0.00", "total_tokens": 0}
116
+ {"current_steps": 970, "total_steps": 1500, "loss": 0.2339, "accuracy": 0.9750000238418579, "learning_rate": 1.388412052037682e-06, "epoch": 0.8336914482165879, "percentage": 64.67, "elapsed_time": "2:08:48", "remaining_time": "1:10:22", "throughput": "0.00", "total_tokens": 0}
117
+ {"current_steps": 980, "total_steps": 1500, "loss": 0.1535, "accuracy": 0.9750000238418579, "learning_rate": 1.3417599122003464e-06, "epoch": 0.842286205414697, "percentage": 65.33, "elapsed_time": "2:10:04", "remaining_time": "1:09:01", "throughput": "0.00", "total_tokens": 0}
118
+ {"current_steps": 990, "total_steps": 1500, "loss": 0.2337, "accuracy": 0.9375, "learning_rate": 1.2956158147457116e-06, "epoch": 0.8508809626128062, "percentage": 66.0, "elapsed_time": "2:11:13", "remaining_time": "1:07:36", "throughput": "0.00", "total_tokens": 0}
119
+ {"current_steps": 1000, "total_steps": 1500, "loss": 0.2062, "accuracy": 0.9125000238418579, "learning_rate": 1.2500000000000007e-06, "epoch": 0.8594757198109153, "percentage": 66.67, "elapsed_time": "2:12:30", "remaining_time": "1:06:15", "throughput": "0.00", "total_tokens": 0}
120
+ {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.2193986475467682, "epoch": 0.8594757198109153, "percentage": 66.67, "elapsed_time": "2:12:56", "remaining_time": "1:06:28", "throughput": "0.00", "total_tokens": 0}