Hugging Face's logo

prosecalign
/
phi3m0128-cds-0.75-kendall-onof-ofif-corr-max-2-simpo-max1500-default

Transformers
Safetensors
Generated from Trainer
llama-factory
Model card Files Community
ziansu commited on
Commit
b2d5a7f
·
verified ·
1 Parent(s): 49ff98f

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 sha256:40273f779afefaa0a76d224433074837a741f5c2872aeae44c99943e51af1785
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694d5f4c79a2275b8de2f85c85e9115209dacb3b1e9dea08da365c2bbf19ac31
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -4,3 +4,9 @@
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9386, "accuracy": 0.5, "learning_rate": 4.9912321481237616e-06, "epoch": 0.035523978685612786, "percentage": 2.67, "elapsed_time": "0:05:06", "remaining_time": "3:06:40", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.44999998807907104, "learning_rate": 4.986304738420684e-06, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:06:23", "remaining_time": "3:05:17", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9381324052810669, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:06:48", "remaining_time": "3:17:30", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
4
  {"current_steps": 40, "total_steps": 1500, "loss": 0.9386, "accuracy": 0.5, "learning_rate": 4.9912321481237616e-06, "epoch": 0.035523978685612786, "percentage": 2.67, "elapsed_time": "0:05:06", "remaining_time": "3:06:40", "throughput": "0.00", "total_tokens": 0}
5
  {"current_steps": 50, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.44999998807907104, "learning_rate": 4.986304738420684e-06, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:06:23", "remaining_time": "3:05:17", "throughput": "0.00", "total_tokens": 0}
6
  {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9381324052810669, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:06:48", "remaining_time": "3:17:30", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 60, "total_steps": 1500, "loss": 0.9319, "accuracy": 0.512499988079071, "learning_rate": 4.980286753286196e-06, "epoch": 0.05328596802841918, "percentage": 4.0, "elapsed_time": "0:08:11", "remaining_time": "3:16:47", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 70, "total_steps": 1500, "loss": 0.9185, "accuracy": 0.625, "learning_rate": 4.973180832407471e-06, "epoch": 0.06216696269982238, "percentage": 4.67, "elapsed_time": "0:09:27", "remaining_time": "3:13:09", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 80, "total_steps": 1500, "loss": 0.9388, "accuracy": 0.5375000238418579, "learning_rate": 4.964990092676263e-06, "epoch": 0.07104795737122557, "percentage": 5.33, "elapsed_time": "0:10:43", "remaining_time": "3:10:28", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 90, "total_steps": 1500, "loss": 0.9256, "accuracy": 0.5375000238418579, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07992895204262877, "percentage": 6.0, "elapsed_time": "0:11:57", "remaining_time": "3:07:28", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 100, "total_steps": 1500, "loss": 0.9374, "accuracy": 0.5375000238418579, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08880994671403197, "percentage": 6.67, "elapsed_time": "0:13:17", "remaining_time": "3:06:10", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9302808046340942, "epoch": 0.08880994671403197, "percentage": 6.67, "elapsed_time": "0:13:43", "remaining_time": "3:12:04", "throughput": "0.00", "total_tokens": 0}