Hugging Face's logo

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

Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
Model card Files Community
ziansu commited on
Commit
d06882f
·
verified ·
1 Parent(s): d22316a

Training in progress, step 100

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 sha256:47de066386174e3625f9d22bfa6d60926cfe856f9d99ad1c9e72e64fc389cb26
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:093026d7831c2fbaa54005e9ef25ba2c7c76cdee79a093fe8bf90f161e381be4
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -4,3 +4,9 @@
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.922, "accuracy": 0.44999998807907104, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:46", "remaining_time": "2:54:23", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9201, "accuracy": 0.5375000238418579, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:01", "remaining_time": "2:54:47", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9226060509681702, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:27", "remaining_time": "3:07:19", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.922, "accuracy": 0.44999998807907104, "learning_rate": 4.9912321481237616e-06, "epoch": 0.034379028792436615, "percentage": 2.67, "elapsed_time": "0:04:46", "remaining_time": "2:54:23", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9201, "accuracy": 0.5375000238418579, "learning_rate": 4.986304738420684e-06, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:01", "remaining_time": "2:54:47", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9226060509681702, "epoch": 0.042973785990545764, "percentage": 3.33, "elapsed_time": "0:06:27", "remaining_time": "3:07:19", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 60, "total_steps": 1500, "loss": 0.9356, "accuracy": 0.512499988079071, "learning_rate": 4.980286753286196e-06, "epoch": 0.05156854318865492, "percentage": 4.0, "elapsed_time": "0:07:48", "remaining_time": "3:07:31", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 70, "total_steps": 1500, "loss": 0.9257, "accuracy": 0.550000011920929, "learning_rate": 4.973180832407471e-06, "epoch": 0.060163300386764075, "percentage": 4.67, "elapsed_time": "0:09:05", "remaining_time": "3:05:51", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 80, "total_steps": 1500, "loss": 0.9168, "accuracy": 0.5, "learning_rate": 4.964990092676263e-06, "epoch": 0.06875805758487323, "percentage": 5.33, "elapsed_time": "0:10:21", "remaining_time": "3:03:54", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 90, "total_steps": 1500, "loss": 0.9273, "accuracy": 0.5249999761581421, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07735281478298238, "percentage": 6.0, "elapsed_time": "0:11:38", "remaining_time": "3:02:27", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 100, "total_steps": 1500, "loss": 0.9009, "accuracy": 0.574999988079071, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:12:53", "remaining_time": "3:00:35", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9138591885566711, "epoch": 0.08594757198109153, "percentage": 6.67, "elapsed_time": "0:13:19", "remaining_time": "3:06:31", "throughput": "0.00", "total_tokens": 0}