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
Model card Files Community
ziansu commited on
Commit
9a34636
·
verified ·
1 Parent(s): fc6e29c

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 sha256:69da499287abbf00e637f8f43a5e4a6cb8d37a7bf2fe43112f9d435671207efb
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de926c2cc167701d3efd5b0b11e9cbf20e19baf4dad563da40697bc77c34ee41
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -166,3 +166,9 @@
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}
 
 
 
 
 
 
 
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}
169
+ {"current_steps": 1410, "total_steps": 1500, "loss": 0.199, "accuracy": 0.949999988079071, "learning_rate": 4.428187317827848e-08, "epoch": 1.2522202486678509, "percentage": 94.0, "elapsed_time": "3:12:30", "remaining_time": "0:12:17", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1420, "total_steps": 1500, "loss": 0.2149, "accuracy": 0.9375, "learning_rate": 3.5009907323737826e-08, "epoch": 1.261101243339254, "percentage": 94.67, "elapsed_time": "3:13:42", "remaining_time": "0:10:54", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1430, "total_steps": 1500, "loss": 0.1547, "accuracy": 0.949999988079071, "learning_rate": 2.681916759252917e-08, "epoch": 1.2699822380106571, "percentage": 95.33, "elapsed_time": "3:15:02", "remaining_time": "0:09:32", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1440, "total_steps": 1500, "loss": 0.2032, "accuracy": 0.9624999761581421, "learning_rate": 1.9713246713805588e-08, "epoch": 1.2788632326820604, "percentage": 96.0, "elapsed_time": "3:16:16", "remaining_time": "0:08:10", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1450, "total_steps": 1500, "loss": 0.1819, "accuracy": 0.9750000238418579, "learning_rate": 1.3695261579316776e-08, "epoch": 1.2877442273534636, "percentage": 96.67, "elapsed_time": "3:17:33", "remaining_time": "0:06:48", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.20565223693847656, "epoch": 1.2877442273534636, "percentage": 96.67, "elapsed_time": "3:17:58", "remaining_time": "0:06:49", "throughput": "0.00", "total_tokens": 0}