Hugging Face's logo

duyphu
/
767404e7-6d28-2259-3f28-6c282c503e99

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
767404e7-6d28-2259-3f28-6c282c503e99
File size: 2,799 Bytes 
e9bf9b7
 
 
1303d84
8dce0c2
1303d84
e9bf9b7
 
 
 
 
 
 
8dce0c2
 
 
e9bf9b7
8dce0c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2764077
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1303d84
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e9bf9b7
 
 
8dce0c2
e9bf9b7
 
8dce0c2
e9bf9b7
 
 
 
 
 
 
8dce0c2
e9bf9b7
 
 
 
1303d84
e9bf9b7
 
 
 
 
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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0019855664592004275,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0911960492318656e-05,
      "eval_loss": 3.2041211128234863,
      "eval_runtime": 273.0403,
      "eval_samples_per_second": 30.292,
      "eval_steps_per_second": 15.148,
      "step": 1
    },
    {
      "epoch": 0.0002545598024615933,
      "grad_norm": 3.1962180137634277,
      "learning_rate": 5e-05,
      "loss": 2.8082,
      "step": 5
    },
    {
      "epoch": 0.0005091196049231866,
      "grad_norm": 2.8137855529785156,
      "learning_rate": 0.0001,
      "loss": 3.1394,
      "step": 10
    },
    {
      "epoch": 0.0005091196049231866,
      "eval_loss": 2.8642525672912598,
      "eval_runtime": 273.8633,
      "eval_samples_per_second": 30.201,
      "eval_steps_per_second": 15.102,
      "step": 10
    },
    {
      "epoch": 0.0007636794073847798,
      "grad_norm": 2.929637908935547,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3929,
      "step": 15
    },
    {
      "epoch": 0.0010182392098463731,
      "grad_norm": 2.667923927307129,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.5685,
      "step": 20
    },
    {
      "epoch": 0.0010182392098463731,
      "eval_loss": 2.4445629119873047,
      "eval_runtime": 275.6971,
      "eval_samples_per_second": 30.0,
      "eval_steps_per_second": 15.002,
      "step": 20
    },
    {
      "epoch": 0.0012727990123079665,
      "grad_norm": 2.50893235206604,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.3904,
      "step": 25
    },
    {
      "epoch": 0.0015273588147695597,
      "grad_norm": 2.2464773654937744,
      "learning_rate": 5e-05,
      "loss": 2.2897,
      "step": 30
    },
    {
      "epoch": 0.0015273588147695597,
      "eval_loss": 2.3795933723449707,
      "eval_runtime": 274.5051,
      "eval_samples_per_second": 30.131,
      "eval_steps_per_second": 15.067,
      "step": 30
    },
    {
      "epoch": 0.001781918617231153,
      "grad_norm": 2.3766283988952637,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.1278,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 347248838836224.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}