Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.5-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
fbea4a9
·
verified ·
1 Parent(s): c767941

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 sha256:9693b12ca6a27446f74e7a1718f86827e00aa5501f1427e60d615b0169c7c561
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793347103f5d64dde939fd8d6a96a1efbbd6a6e390cc84febb1d8bcd9926159b
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -46,3 +46,9 @@
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4969, "accuracy": 0.8500000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.4157782515991471, "percentage": 26.0, "elapsed_time": "0:52:40", "remaining_time": "2:29:56", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.5135, "accuracy": 0.8374999761581421, "learning_rate": 4.172826515897146e-06, "epoch": 0.42643923240938164, "percentage": 26.67, "elapsed_time": "0:53:56", "remaining_time": "2:28:21", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47455134987831116, "epoch": 0.42643923240938164, "percentage": 26.67, "elapsed_time": "0:54:18", "remaining_time": "2:29:19", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
46
  {"current_steps": 390, "total_steps": 1500, "loss": 0.4969, "accuracy": 0.8500000238418579, "learning_rate": 4.211367764821722e-06, "epoch": 0.4157782515991471, "percentage": 26.0, "elapsed_time": "0:52:40", "remaining_time": "2:29:56", "throughput": "0.00", "total_tokens": 0}
47
  {"current_steps": 400, "total_steps": 1500, "loss": 0.5135, "accuracy": 0.8374999761581421, "learning_rate": 4.172826515897146e-06, "epoch": 0.42643923240938164, "percentage": 26.67, "elapsed_time": "0:53:56", "remaining_time": "2:28:21", "throughput": "0.00", "total_tokens": 0}
48
  {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.47455134987831116, "epoch": 0.42643923240938164, "percentage": 26.67, "elapsed_time": "0:54:18", "remaining_time": "2:29:19", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 410, "total_steps": 1500, "loss": 0.498, "accuracy": 0.8500000238418579, "learning_rate": 4.133551509975264e-06, "epoch": 0.43710021321961623, "percentage": 27.33, "elapsed_time": "0:55:41", "remaining_time": "2:28:02", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 420, "total_steps": 1500, "loss": 0.4494, "accuracy": 0.862500011920929, "learning_rate": 4.093559974371725e-06, "epoch": 0.44776119402985076, "percentage": 28.0, "elapsed_time": "0:56:57", "remaining_time": "2:26:28", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 430, "total_steps": 1500, "loss": 0.4796, "accuracy": 0.8500000238418579, "learning_rate": 4.052869450695776e-06, "epoch": 0.4584221748400853, "percentage": 28.67, "elapsed_time": "0:58:11", "remaining_time": "2:24:47", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 440, "total_steps": 1500, "loss": 0.4468, "accuracy": 0.862500011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.4690831556503198, "percentage": 29.33, "elapsed_time": "0:59:26", "remaining_time": "2:23:11", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 450, "total_steps": 1500, "loss": 0.4073, "accuracy": 0.887499988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.47974413646055436, "percentage": 30.0, "elapsed_time": "1:00:40", "remaining_time": "2:21:35", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.41499289870262146, "epoch": 0.47974413646055436, "percentage": 30.0, "elapsed_time": "1:01:02", "remaining_time": "2:22:25", "throughput": "0.00", "total_tokens": 0}