Hugging Face's logo

prosecalign
/
phi3m0128-kendall-onof-neg_if-corr-max-2-simpo-max1500-decay-sft0.2-beta1.5-gamma0.5-lr5e-6

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
0bb92d6
·
verified ·
1 Parent(s): 21e0e2c

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:c4f90f07cd1e4284f06578821b6fc9420cb526fb508f6fe9bafa16cf9fc92528
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6592e9c006f8b90ef954ffd3f3dd2c13e92948feb80f52fbaa3fa09dc8ff00b7
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -166,3 +166,9 @@
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.2012, "accuracy": 0.949999988079071, "learning_rate": 6.605274281709929e-08, "epoch": 1.0578386605783865, "percentage": 92.67, "elapsed_time": "3:12:29", "remaining_time": "0:15:13", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.1754, "accuracy": 0.9624999761581421, "learning_rate": 5.463099816548578e-08, "epoch": 1.06544901065449, "percentage": 93.33, "elapsed_time": "3:13:44", "remaining_time": "0:13:50", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.198856920003891, "epoch": 1.06544901065449, "percentage": 93.33, "elapsed_time": "3:14:15", "remaining_time": "0:13:52", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
166
  {"current_steps": 1390, "total_steps": 1500, "loss": 0.2012, "accuracy": 0.949999988079071, "learning_rate": 6.605274281709929e-08, "epoch": 1.0578386605783865, "percentage": 92.67, "elapsed_time": "3:12:29", "remaining_time": "0:15:13", "throughput": "0.00", "total_tokens": 0}
167
  {"current_steps": 1400, "total_steps": 1500, "loss": 0.1754, "accuracy": 0.9624999761581421, "learning_rate": 5.463099816548578e-08, "epoch": 1.06544901065449, "percentage": 93.33, "elapsed_time": "3:13:44", "remaining_time": "0:13:50", "throughput": "0.00", "total_tokens": 0}
168
  {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.198856920003891, "epoch": 1.06544901065449, "percentage": 93.33, "elapsed_time": "3:14:15", "remaining_time": "0:13:52", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1410, "total_steps": 1500, "loss": 0.1886, "accuracy": 0.9624999761581421, "learning_rate": 4.428187317827848e-08, "epoch": 1.0730593607305936, "percentage": 94.0, "elapsed_time": "3:15:37", "remaining_time": "0:12:29", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1420, "total_steps": 1500, "loss": 0.1632, "accuracy": 0.9375, "learning_rate": 3.5009907323737826e-08, "epoch": 1.0806697108066972, "percentage": 94.67, "elapsed_time": "3:16:57", "remaining_time": "0:11:05", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1430, "total_steps": 1500, "loss": 0.1752, "accuracy": 0.9375, "learning_rate": 2.681916759252917e-08, "epoch": 1.0882800608828007, "percentage": 95.33, "elapsed_time": "3:18:12", "remaining_time": "0:09:42", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1440, "total_steps": 1500, "loss": 0.2086, "accuracy": 0.9750000238418579, "learning_rate": 1.9713246713805588e-08, "epoch": 1.095890410958904, "percentage": 96.0, "elapsed_time": "3:19:26", "remaining_time": "0:08:18", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1450, "total_steps": 1500, "loss": 0.2, "accuracy": 0.925000011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.1035007610350076, "percentage": 96.67, "elapsed_time": "3:20:39", "remaining_time": "0:06:55", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.1981535106897354, "epoch": 1.1035007610350076, "percentage": 96.67, "elapsed_time": "3:21:10", "remaining_time": "0:06:56", "throughput": "0.00", "total_tokens": 0}