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
79d01de
·
verified ·
1 Parent(s): 3c0dc3c

Training in progress, step 300

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 sha256:0395a9a4a94869c7ef5b6377172ca90c291ec769effe4a91936239fd47c2a734
3
  size 25200088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234eb9a83fd6eaa3292cba1e1004a1ff7572f49fc1cae58cbb39e8c04c5ad859
3
  size 25200088
trainer_log.jsonl CHANGED
@@ -28,3 +28,9 @@
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7898, "accuracy": 0.612500011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.21314387211367672, "percentage": 16.0, "elapsed_time": "0:32:20", "remaining_time": "2:49:45", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7626, "accuracy": 0.6625000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:33:37", "remaining_time": "2:48:09", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7631083130836487, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:34:03", "remaining_time": "2:50:15", "throughput": "0.00", "total_tokens": 0}
 
 
 
 
 
 
 
28
  {"current_steps": 240, "total_steps": 1500, "loss": 0.7898, "accuracy": 0.612500011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.21314387211367672, "percentage": 16.0, "elapsed_time": "0:32:20", "remaining_time": "2:49:45", "throughput": "0.00", "total_tokens": 0}
29
  {"current_steps": 250, "total_steps": 1500, "loss": 0.7626, "accuracy": 0.6625000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:33:37", "remaining_time": "2:48:09", "throughput": "0.00", "total_tokens": 0}
30
  {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7631083130836487, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:34:03", "remaining_time": "2:50:15", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 260, "total_steps": 1500, "loss": 0.7026, "accuracy": 0.762499988079071, "learning_rate": 4.638410650401267e-06, "epoch": 0.23090586145648312, "percentage": 17.33, "elapsed_time": "0:35:25", "remaining_time": "2:48:55", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 270, "total_steps": 1500, "loss": 0.7317, "accuracy": 0.699999988079071, "learning_rate": 4.610819813755038e-06, "epoch": 0.23978685612788633, "percentage": 18.0, "elapsed_time": "0:36:38", "remaining_time": "2:46:55", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 280, "total_steps": 1500, "loss": 0.6887, "accuracy": 0.6499999761581421, "learning_rate": 4.582303101775249e-06, "epoch": 0.24866785079928952, "percentage": 18.67, "elapsed_time": "0:37:56", "remaining_time": "2:45:18", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 290, "total_steps": 1500, "loss": 0.5695, "accuracy": 0.6625000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.25754884547069273, "percentage": 19.33, "elapsed_time": "0:39:11", "remaining_time": "2:43:33", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 300, "total_steps": 1500, "loss": 0.5366, "accuracy": 0.762499988079071, "learning_rate": 4.522542485937369e-06, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:40:23", "remaining_time": "2:41:35", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.551510214805603, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:40:49", "remaining_time": "2:43:16", "throughput": "0.00", "total_tokens": 0}