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
7398c78
·
verified ·
1 Parent(s): 8081bf8

Training in progress, step 450

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 sha256:16c89cc9c6eeee8ca994b86c0bb1e7cd5f01a58b6ff9b44219e32e3d455b5776
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ba3c34a6bda432b4b808645d40278644ecab1b8c2d0af4ef4a00234847ed01
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -46,3 +46,9 @@
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4585, "accuracy": 0.5874999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.33519553072625696, "percentage": 26.0, "elapsed_time": "0:51:21", "remaining_time": "2:26:11", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.4771, "accuracy": 0.675000011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:33", "remaining_time": "2:24:30", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47841358184814453, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:58", "remaining_time": "2:25:41", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4585, "accuracy": 0.5874999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.33519553072625696, "percentage": 26.0, "elapsed_time": "0:51:21", "remaining_time": "2:26:11", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.4771, "accuracy": 0.675000011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:33", "remaining_time": "2:24:30", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47841358184814453, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:52:58", "remaining_time": "2:25:41", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 410, "total_steps": 1500, "loss": 0.4449, "accuracy": 0.637499988079071, "learning_rate": 4.133551509975264e-06, "epoch": 0.3523850451224753, "percentage": 27.33, "elapsed_time": "0:54:22", "remaining_time": "2:24:32", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 420, "total_steps": 1500, "loss": 0.4598, "accuracy": 0.699999988079071, "learning_rate": 4.093559974371725e-06, "epoch": 0.36097980232058446, "percentage": 28.0, "elapsed_time": "0:55:35", "remaining_time": "2:22:57", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 430, "total_steps": 1500, "loss": 0.4275, "accuracy": 0.75, "learning_rate": 4.052869450695776e-06, "epoch": 0.3695745595186936, "percentage": 28.67, "elapsed_time": "0:56:48", "remaining_time": "2:21:21", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 440, "total_steps": 1500, "loss": 0.4132, "accuracy": 0.75, "learning_rate": 4.011497787155938e-06, "epoch": 0.37816931671680276, "percentage": 29.33, "elapsed_time": "0:57:57", "remaining_time": "2:19:37", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 450, "total_steps": 1500, "loss": 0.4266, "accuracy": 0.7749999761581421, "learning_rate": 3.969463130731183e-06, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "0:59:09", "remaining_time": "2:18:02", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.4397798478603363, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "0:59:35", "remaining_time": "2:19:03", "throughput": "0.00", "total_tokens": 0}