Hugging Face's logo

chauhoang
/
a79f36e0-cd5a-587d-166c-c790adbbe046

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
a79f36e0-cd5a-587d-166c-c790adbbe046
File size: 2,244 Bytes 
c42af3b
 
 
f7f8066
881cd10
f7f8066
c42af3b
 
 
 
 
 
 
881cd10
 
 
c42af3b
881cd10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7f8066
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c42af3b
 
 
881cd10
c42af3b
 
881cd10
c42af3b
 
 
 
 
 
 
881cd10
c42af3b
 
 
 
f7f8066
c42af3b
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015945784333266893,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.13299397433342e-05,
      "eval_loss": 2.1146581172943115,
      "eval_runtime": 271.7079,
      "eval_samples_per_second": 25.27,
      "eval_steps_per_second": 12.635,
      "step": 1
    },
    {
      "epoch": 0.000306649698716671,
      "grad_norm": 0.4814217686653137,
      "learning_rate": 5e-05,
      "loss": 2.122,
      "step": 5
    },
    {
      "epoch": 0.000613299397433342,
      "grad_norm": 0.4163660407066345,
      "learning_rate": 0.0001,
      "loss": 2.1498,
      "step": 10
    },
    {
      "epoch": 0.000613299397433342,
      "eval_loss": 2.0929524898529053,
      "eval_runtime": 270.9012,
      "eval_samples_per_second": 25.345,
      "eval_steps_per_second": 12.673,
      "step": 10
    },
    {
      "epoch": 0.0009199490961500131,
      "grad_norm": 0.5417680740356445,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0991,
      "step": 15
    },
    {
      "epoch": 0.001226598794866684,
      "grad_norm": 0.5770021080970764,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.999,
      "step": 20
    },
    {
      "epoch": 0.001226598794866684,
      "eval_loss": 2.0414137840270996,
      "eval_runtime": 271.3537,
      "eval_samples_per_second": 25.303,
      "eval_steps_per_second": 12.651,
      "step": 20
    },
    {
      "epoch": 0.001533248493583355,
      "grad_norm": 0.49637794494628906,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0475,
      "step": 25
    }
  ],
  "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": 1005324601393152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}