Hugging Face's logo

black279
/
Qwen_LeetCoder

Text Generation
PEFT
Safetensors
Transformers
qwen2
lora
sft
trl
unsloth
conversational
text-generation-inference
4-bit precision
bitsandbytes
Model card Files
xet
Community
Qwen_LeetCoder
File size: 1,901 Bytes
d11b910
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 3.0624091625213623,
      "learning_rate": 9e-05,
      "loss": 0.8071,
      "step": 10
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.9347422122955322,
      "learning_rate": 0.00019,
      "loss": 0.5748,
      "step": 20
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.6845844984054565,
      "learning_rate": 0.00016785714285714288,
      "loss": 0.5403,
      "step": 30
    },
    {
      "epoch": 1.0533333333333332,
      "grad_norm": 1.5554804801940918,
      "learning_rate": 0.00013214285714285715,
      "loss": 0.4359,
      "step": 40
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.5799919366836548,
      "learning_rate": 9.642857142857143e-05,
      "loss": 0.3043,
      "step": 50
    },
    {
      "epoch": 1.5866666666666667,
      "grad_norm": 1.6146897077560425,
      "learning_rate": 6.0714285714285715e-05,
      "loss": 0.2456,
      "step": 60
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 1.3090317249298096,
      "learning_rate": 2.5e-05,
      "loss": 0.2944,
      "step": 70
    }
  ],
  "logging_steps": 10,
  "max_steps": 76,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 430849687716864.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}