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
7411670
·
verified ·
1 Parent(s): e8c2069

Training in progress, step 1400

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 sha256:1a12d579687529127242685c92518ad316f0c79435b272c04f35b7ca43a314af
3
  size 40036488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6150263d38c3da0d07e4ed09b7511e4bc9075691427ce4e4c25bff6b94235a6d
3
  size 40036488
trainer_log.jsonl CHANGED
@@ -160,3 +160,9 @@
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 1.3939, "accuracy": 0.9750000238418579, "learning_rate": 1.3905907440629752e-07, "epoch": 0.9712784271088158, "percentage": 89.33, "elapsed_time": "3:05:22", "remaining_time": "0:22:08", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.7096, "accuracy": 1.0, "learning_rate": 1.223587092621162e-07, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:06:38", "remaining_time": "0:20:44", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.08608455955982208, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:07:08", "remaining_time": "0:20:47", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 1.3939, "accuracy": 0.9750000238418579, "learning_rate": 1.3905907440629752e-07, "epoch": 0.9712784271088158, "percentage": 89.33, "elapsed_time": "3:05:22", "remaining_time": "0:22:08", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.7096, "accuracy": 1.0, "learning_rate": 1.223587092621162e-07, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:06:38", "remaining_time": "0:20:44", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.08608455955982208, "epoch": 0.9785267735797771, "percentage": 90.0, "elapsed_time": "3:07:08", "remaining_time": "0:20:47", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1360, "total_steps": 1500, "loss": 0.6009, "accuracy": 0.9750000238418579, "learning_rate": 1.067012561698319e-07, "epoch": 0.9857751200507384, "percentage": 90.67, "elapsed_time": "3:08:36", "remaining_time": "0:19:24", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1370, "total_steps": 1500, "loss": 0.6913, "accuracy": 0.9750000238418579, "learning_rate": 9.209358300585474e-08, "epoch": 0.9930234665216997, "percentage": 91.33, "elapsed_time": "3:09:51", "remaining_time": "0:18:00", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1380, "total_steps": 1500, "loss": 0.3924, "accuracy": 1.0, "learning_rate": 7.854209717842231e-08, "epoch": 1.0, "percentage": 92.0, "elapsed_time": "3:11:02", "remaining_time": "0:16:36", "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}