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
dac78b4
·
verified ·
1 Parent(s): 0d71a93

Training in progress, step 150

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:f77f9bbea8fbcb0fc5d1127019dc21144f565fca30ef5e75742e25c4b625a357
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71776c82ae88f3abbd710a70cb54099833ae9c45e08362298f0538b3e8c50ef8
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -10,3 +10,9 @@
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9092, "accuracy": 0.5249999761581421, "learning_rate": 4.9557181268217225e-06, "epoch": 0.0684931506849315, "percentage": 6.0, "elapsed_time": "0:11:48", "remaining_time": "3:04:53", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.8932, "accuracy": 0.5625, "learning_rate": 4.9453690018345144e-06, "epoch": 0.076103500761035, "percentage": 6.67, "elapsed_time": "0:13:00", "remaining_time": "3:02:05", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.8984279036521912, "epoch": 0.076103500761035, "percentage": 6.67, "elapsed_time": "0:13:31", "remaining_time": "3:09:16", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
10
  {"current_steps": 90, "total_steps": 1500, "loss": 0.9092, "accuracy": 0.5249999761581421, "learning_rate": 4.9557181268217225e-06, "epoch": 0.0684931506849315, "percentage": 6.0, "elapsed_time": "0:11:48", "remaining_time": "3:04:53", "throughput": "0.00", "total_tokens": 0}
11
  {"current_steps": 100, "total_steps": 1500, "loss": 0.8932, "accuracy": 0.5625, "learning_rate": 4.9453690018345144e-06, "epoch": 0.076103500761035, "percentage": 6.67, "elapsed_time": "0:13:00", "remaining_time": "3:02:05", "throughput": "0.00", "total_tokens": 0}
12
  {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.8984279036521912, "epoch": 0.076103500761035, "percentage": 6.67, "elapsed_time": "0:13:31", "remaining_time": "3:09:16", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 110, "total_steps": 1500, "loss": 0.8995, "accuracy": 0.6000000238418579, "learning_rate": 4.933947257182901e-06, "epoch": 0.0837138508371385, "percentage": 7.33, "elapsed_time": "0:14:55", "remaining_time": "3:08:39", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 120, "total_steps": 1500, "loss": 0.8795, "accuracy": 0.574999988079071, "learning_rate": 4.921457902821578e-06, "epoch": 0.091324200913242, "percentage": 8.0, "elapsed_time": "0:16:08", "remaining_time": "3:05:40", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 130, "total_steps": 1500, "loss": 0.8912, "accuracy": 0.6000000238418579, "learning_rate": 4.907906416994146e-06, "epoch": 0.0989345509893455, "percentage": 8.67, "elapsed_time": "0:17:27", "remaining_time": "3:03:54", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 140, "total_steps": 1500, "loss": 0.8908, "accuracy": 0.6625000238418579, "learning_rate": 4.893298743830168e-06, "epoch": 0.106544901065449, "percentage": 9.33, "elapsed_time": "0:18:44", "remaining_time": "3:02:07", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 150, "total_steps": 1500, "loss": 0.8867, "accuracy": 0.5375000238418579, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1141552511415525, "percentage": 10.0, "elapsed_time": "0:20:01", "remaining_time": "3:00:16", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8765817284584045, "epoch": 0.1141552511415525, "percentage": 10.0, "elapsed_time": "0:20:32", "remaining_time": "3:04:53", "throughput": "0.00", "total_tokens": 0}