Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-onof-decrease-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
e430a8e
·
verified ·
1 Parent(s): 953b031

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 sha256:42e5c6f577a5db1527d5fde86c1e8af7d9c8b94e21324e7861916ef3352adc90
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d57704881e7fcbb9e56f84efbea3c6cc8423f70250963dbc46dd1392f117ca
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -160,3 +160,9 @@
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1844, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 1.151267726686721, "percentage": 89.33, "elapsed_time": "2:56:34", "remaining_time": "0:21:04", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1844, "accuracy": 0.949999988079071, "learning_rate": 1.223587092621162e-07, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:57:46", "remaining_time": "0:19:45", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.21017144620418549, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:58:12", "remaining_time": "0:19:48", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1844, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 1.151267726686721, "percentage": 89.33, "elapsed_time": "2:56:34", "remaining_time": "0:21:04", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1844, "accuracy": 0.949999988079071, "learning_rate": 1.223587092621162e-07, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:57:46", "remaining_time": "0:19:45", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.21017144620418549, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:58:12", "remaining_time": "0:19:48", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1360, "total_steps": 1500, "loss": 0.2093, "accuracy": 0.887499988079071, "learning_rate": 1.067012561698319e-07, "epoch": 1.1684572410829395, "percentage": 90.67, "elapsed_time": "2:59:32", "remaining_time": "0:18:28", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1370, "total_steps": 1500, "loss": 0.1869, "accuracy": 0.9624999761581421, "learning_rate": 9.209358300585474e-08, "epoch": 1.1770519982810486, "percentage": 91.33, "elapsed_time": "3:00:45", "remaining_time": "0:17:09", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1380, "total_steps": 1500, "loss": 0.1987, "accuracy": 0.949999988079071, "learning_rate": 7.854209717842231e-08, "epoch": 1.1856467554791577, "percentage": 92.0, "elapsed_time": "3:01:56", "remaining_time": "0:15:49", "throughput": "0.00", "total_tokens": 0}
166
+ {"current_steps": 1390, "total_steps": 1500, "loss": 0.2021, "accuracy": 0.9125000238418579, "learning_rate": 6.605274281709929e-08, "epoch": 1.1942415126772667, "percentage": 92.67, "elapsed_time": "3:03:15", "remaining_time": "0:14:30", "throughput": "0.00", "total_tokens": 0}
167
+ {"current_steps": 1400, "total_steps": 1500, "loss": 0.1899, "accuracy": 0.9375, "learning_rate": 5.463099816548578e-08, "epoch": 1.202836269875376, "percentage": 93.33, "elapsed_time": "3:04:25", "remaining_time": "0:13:10", "throughput": "0.00", "total_tokens": 0}
168
+ {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.21005278825759888, "epoch": 1.202836269875376, "percentage": 93.33, "elapsed_time": "3:04:51", "remaining_time": "0:13:12", "throughput": "0.00", "total_tokens": 0}