Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.75-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
908c1d2
·
verified ·
1 Parent(s): 1ebae91

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:b1c834e857d811c66077e5fa4e40ac729017cbc9cc68b5ae7e1b473afac18961
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69da499287abbf00e637f8f43a5e4a6cb8d37a7bf2fe43112f9d435671207efb
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -160,3 +160,9 @@
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.182, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 1.1900532859680284, "percentage": 89.33, "elapsed_time": "3:02:29", "remaining_time": "0:21:47", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.2274, "accuracy": 0.9375, "learning_rate": 1.223587092621162e-07, "epoch": 1.1989342806394316, "percentage": 90.0, "elapsed_time": "3:03:43", "remaining_time": "0:20:24", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.20770707726478577, "epoch": 1.1989342806394316, "percentage": 90.0, "elapsed_time": "3:04:08", "remaining_time": "0:20:27", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.182, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 1.1900532859680284, "percentage": 89.33, "elapsed_time": "3:02:29", "remaining_time": "0:21:47", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.2274, "accuracy": 0.9375, "learning_rate": 1.223587092621162e-07, "epoch": 1.1989342806394316, "percentage": 90.0, "elapsed_time": "3:03:43", "remaining_time": "0:20:24", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.20770707726478577, "epoch": 1.1989342806394316, "percentage": 90.0, "elapsed_time": "3:04:08", "remaining_time": "0:20:27", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1360, "total_steps": 1500, "loss": 0.1977, "accuracy": 0.9375, "learning_rate": 1.067012561698319e-07, "epoch": 1.2078152753108349, "percentage": 90.67, "elapsed_time": "3:05:31", "remaining_time": "0:19:05", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1370, "total_steps": 1500, "loss": 0.1655, "accuracy": 0.987500011920929, "learning_rate": 9.209358300585474e-08, "epoch": 1.2166962699822381, "percentage": 91.33, "elapsed_time": "3:06:54", "remaining_time": "0:17:44", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1380, "total_steps": 1500, "loss": 0.1918, "accuracy": 0.9624999761581421, "learning_rate": 7.854209717842231e-08, "epoch": 1.2255772646536411, "percentage": 92.0, "elapsed_time": "3:08:06", "remaining_time": "0:16:21", "throughput": "0.00", "total_tokens": 0}
166
+ {"current_steps": 1390, "total_steps": 1500, "loss": 0.219, "accuracy": 0.9750000238418579, "learning_rate": 6.605274281709929e-08, "epoch": 1.2344582593250444, "percentage": 92.67, "elapsed_time": "3:09:24", "remaining_time": "0:14:59", "throughput": "0.00", "total_tokens": 0}
167
+ {"current_steps": 1400, "total_steps": 1500, "loss": 0.1719, "accuracy": 0.9624999761581421, "learning_rate": 5.463099816548578e-08, "epoch": 1.2433392539964476, "percentage": 93.33, "elapsed_time": "3:10:42", "remaining_time": "0:13:37", "throughput": "0.00", "total_tokens": 0}
168
+ {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.20297038555145264, "epoch": 1.2433392539964476, "percentage": 93.33, "elapsed_time": "3:11:08", "remaining_time": "0:13:39", "throughput": "0.00", "total_tokens": 0}