Hugging Face's logo

prosecalign
/
clm7b0129-cds-0.8-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
8fae0bc
·
verified ·
1 Parent(s): 5bf2ce4

Training in progress, step 1450

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:c94c46af0f07287cafdcd1d60059dd32cb0036fea5475562acc8f4e681d6c8fb
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e596c26d2df35b77cc480d957016d295b5f3cce78d8ca6896a2874423ecc836
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -166,3 +166,9 @@
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.5117, "accuracy": 0.987500011920929, "learning_rate": 6.605274281709929e-08, "epoch": 1.1403364792778006, "percentage": 92.67, "elapsed_time": "3:04:27", "remaining_time": "0:14:35", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.7015, "accuracy": 0.987500011920929, "learning_rate": 5.463099816548578e-08, "epoch": 1.1485432909314732, "percentage": 93.33, "elapsed_time": "3:05:38", "remaining_time": "0:13:15", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.0803111121058464, "epoch": 1.1485432909314732, "percentage": 93.33, "elapsed_time": "3:06:04", "remaining_time": "0:13:17", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.5117, "accuracy": 0.987500011920929, "learning_rate": 6.605274281709929e-08, "epoch": 1.1403364792778006, "percentage": 92.67, "elapsed_time": "3:04:27", "remaining_time": "0:14:35", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.7015, "accuracy": 0.987500011920929, "learning_rate": 5.463099816548578e-08, "epoch": 1.1485432909314732, "percentage": 93.33, "elapsed_time": "3:05:38", "remaining_time": "0:13:15", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.0803111121058464, "epoch": 1.1485432909314732, "percentage": 93.33, "elapsed_time": "3:06:04", "remaining_time": "0:13:17", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1410, "total_steps": 1500, "loss": 0.6589, "accuracy": 0.987500011920929, "learning_rate": 4.428187317827848e-08, "epoch": 1.1567501025851457, "percentage": 94.0, "elapsed_time": "3:07:28", "remaining_time": "0:11:58", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1420, "total_steps": 1500, "loss": 0.682, "accuracy": 0.987500011920929, "learning_rate": 3.5009907323737826e-08, "epoch": 1.1649569142388183, "percentage": 94.67, "elapsed_time": "3:08:42", "remaining_time": "0:10:37", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1430, "total_steps": 1500, "loss": 0.8484, "accuracy": 0.9750000238418579, "learning_rate": 2.681916759252917e-08, "epoch": 1.1731637258924907, "percentage": 95.33, "elapsed_time": "3:09:51", "remaining_time": "0:09:17", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1440, "total_steps": 1500, "loss": 0.5759, "accuracy": 0.987500011920929, "learning_rate": 1.9713246713805588e-08, "epoch": 1.1813705375461634, "percentage": 96.0, "elapsed_time": "3:10:58", "remaining_time": "0:07:57", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1450, "total_steps": 1500, "loss": 0.7314, "accuracy": 0.987500011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.1895773491998358, "percentage": 96.67, "elapsed_time": "3:12:08", "remaining_time": "0:06:37", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.07983284443616867, "epoch": 1.1895773491998358, "percentage": 96.67, "elapsed_time": "3:12:34", "remaining_time": "0:06:38", "throughput": "0.00", "total_tokens": 0}