Hugging Face's logo

prosecalign
/
clm7b0129-kendall-onof-ofif-corr-max-2-simpo-max1500-decay-sft-beta1.5-gamma0.5-lr5e-6

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
f230b8a
·
verified ·
1 Parent(s): 563ce7e

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 sha256:6150263d38c3da0d07e4ed09b7511e4bc9075691427ce4e4c25bff6b94235a6d
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c94f42fb65ec9a3f4f54d72d46a9b2cb25cac5db3e943f29977b3bfca1b658b
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -166,3 +166,9 @@
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 1.4012, "accuracy": 0.9125000238418579, "learning_rate": 6.605274281709929e-08, "epoch": 1.0072483464709614, "percentage": 92.67, "elapsed_time": "3:12:14", "remaining_time": "0:15:12", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.6699, "accuracy": 0.9375, "learning_rate": 5.463099816548578e-08, "epoch": 1.0144966929419226, "percentage": 93.33, "elapsed_time": "3:13:28", "remaining_time": "0:13:49", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.08683376014232635, "epoch": 1.0144966929419226, "percentage": 93.33, "elapsed_time": "3:13:58", "remaining_time": "0:13:51", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 1.4012, "accuracy": 0.9125000238418579, "learning_rate": 6.605274281709929e-08, "epoch": 1.0072483464709614, "percentage": 92.67, "elapsed_time": "3:12:14", "remaining_time": "0:15:12", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.6699, "accuracy": 0.9375, "learning_rate": 5.463099816548578e-08, "epoch": 1.0144966929419226, "percentage": 93.33, "elapsed_time": "3:13:28", "remaining_time": "0:13:49", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.08683376014232635, "epoch": 1.0144966929419226, "percentage": 93.33, "elapsed_time": "3:13:58", "remaining_time": "0:13:51", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1410, "total_steps": 1500, "loss": 0.7684, "accuracy": 1.0, "learning_rate": 4.428187317827848e-08, "epoch": 1.021745039412884, "percentage": 94.0, "elapsed_time": "3:15:22", "remaining_time": "0:12:28", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1420, "total_steps": 1500, "loss": 0.6473, "accuracy": 1.0, "learning_rate": 3.5009907323737826e-08, "epoch": 1.0289933858838451, "percentage": 94.67, "elapsed_time": "3:16:37", "remaining_time": "0:11:04", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1430, "total_steps": 1500, "loss": 0.5875, "accuracy": 0.987500011920929, "learning_rate": 2.681916759252917e-08, "epoch": 1.0362417323548065, "percentage": 95.33, "elapsed_time": "3:17:52", "remaining_time": "0:09:41", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1440, "total_steps": 1500, "loss": 0.7658, "accuracy": 0.987500011920929, "learning_rate": 1.9713246713805588e-08, "epoch": 1.043490078825768, "percentage": 96.0, "elapsed_time": "3:19:11", "remaining_time": "0:08:17", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1450, "total_steps": 1500, "loss": 0.6331, "accuracy": 0.987500011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.0507384252967291, "percentage": 96.67, "elapsed_time": "3:20:24", "remaining_time": "0:06:54", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.08744800090789795, "epoch": 1.0507384252967291, "percentage": 96.67, "elapsed_time": "3:20:55", "remaining_time": "0:06:55", "throughput": "0.00", "total_tokens": 0}