Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.8-kendall-on-neg_if-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
17b3a9a
·
verified ·
1 Parent(s): 364bcfa

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 sha256:91040a19cbc22ac5ff56faa301c87b6fc84bcbcdcbd02311da38e1949dd2cd49
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b45d7689da9a67f47ab49f9c47c8f48b663956dff274e8d8a256d52314d48147
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -160,3 +160,9 @@
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1863, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 1.151267726686721, "percentage": 89.33, "elapsed_time": "2:57:51", "remaining_time": "0:21:14", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1924, "accuracy": 0.949999988079071, "learning_rate": 1.223587092621162e-07, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:59:04", "remaining_time": "0:19:53", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.210895836353302, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:59:29", "remaining_time": "0:19:56", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
160
  {"current_steps": 1340, "total_steps": 1500, "loss": 0.1863, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 1.151267726686721, "percentage": 89.33, "elapsed_time": "2:57:51", "remaining_time": "0:21:14", "throughput": "0.00", "total_tokens": 0}
161
  {"current_steps": 1350, "total_steps": 1500, "loss": 0.1924, "accuracy": 0.949999988079071, "learning_rate": 1.223587092621162e-07, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:59:04", "remaining_time": "0:19:53", "throughput": "0.00", "total_tokens": 0}
162
  {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.210895836353302, "epoch": 1.1598624838848304, "percentage": 90.0, "elapsed_time": "2:59:29", "remaining_time": "0:19:56", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1360, "total_steps": 1500, "loss": 0.2042, "accuracy": 0.8999999761581421, "learning_rate": 1.067012561698319e-07, "epoch": 1.1684572410829395, "percentage": 90.67, "elapsed_time": "3:00:47", "remaining_time": "0:18:36", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1370, "total_steps": 1500, "loss": 0.189, "accuracy": 0.9375, "learning_rate": 9.209358300585474e-08, "epoch": 1.1770519982810486, "percentage": 91.33, "elapsed_time": "3:02:00", "remaining_time": "0:17:16", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1380, "total_steps": 1500, "loss": 0.1725, "accuracy": 0.9125000238418579, "learning_rate": 7.854209717842231e-08, "epoch": 1.1856467554791577, "percentage": 92.0, "elapsed_time": "3:03:14", "remaining_time": "0:15:56", "throughput": "0.00", "total_tokens": 0}
166
+ {"current_steps": 1390, "total_steps": 1500, "loss": 0.1906, "accuracy": 0.925000011920929, "learning_rate": 6.605274281709929e-08, "epoch": 1.1942415126772667, "percentage": 92.67, "elapsed_time": "3:04:31", "remaining_time": "0:14:36", "throughput": "0.00", "total_tokens": 0}
167
+ {"current_steps": 1400, "total_steps": 1500, "loss": 0.1958, "accuracy": 0.949999988079071, "learning_rate": 5.463099816548578e-08, "epoch": 1.202836269875376, "percentage": 93.33, "elapsed_time": "3:05:42", "remaining_time": "0:13:15", "throughput": "0.00", "total_tokens": 0}
168
+ {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.21151940524578094, "epoch": 1.202836269875376, "percentage": 93.33, "elapsed_time": "3:06:07", "remaining_time": "0:13:17", "throughput": "0.00", "total_tokens": 0}