Hugging Face's logo

tuantmdev
/
628afe34-ea8c-4443-b5f7-a6e1af539965

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
628afe34-ea8c-4443-b5f7-a6e1af539965
File size: 2,695 Bytes
2f63272
 
 
0c60bae
2f63272
0c60bae
2f63272
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b8dbcf6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3241d08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b807a8e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0c60bae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2f63272
 
 
 
 
 
 
 
 
 
 
 
 
 
0c60bae
2f63272
 
 
 
0c60bae
2f63272
 
 
 
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
116
117
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07370215118153761,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036851075590768807,
      "eval_loss": NaN,
      "eval_runtime": 99.3489,
      "eval_samples_per_second": 46.01,
      "eval_steps_per_second": 23.01,
      "step": 1
    },
    {
      "epoch": 0.014740430236307523,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.014740430236307523,
      "eval_loss": NaN,
      "eval_runtime": 97.8099,
      "eval_samples_per_second": 46.734,
      "eval_steps_per_second": 23.372,
      "step": 40
    },
    {
      "epoch": 0.029480860472615045,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.029480860472615045,
      "eval_loss": NaN,
      "eval_runtime": 98.4188,
      "eval_samples_per_second": 46.444,
      "eval_steps_per_second": 23.227,
      "step": 80
    },
    {
      "epoch": 0.04422129070892257,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.04422129070892257,
      "eval_loss": NaN,
      "eval_runtime": 99.877,
      "eval_samples_per_second": 45.766,
      "eval_steps_per_second": 22.888,
      "step": 120
    },
    {
      "epoch": 0.05896172094523009,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.05896172094523009,
      "eval_loss": NaN,
      "eval_runtime": 98.8283,
      "eval_samples_per_second": 46.252,
      "eval_steps_per_second": 23.131,
      "step": 160
    },
    {
      "epoch": 0.07370215118153761,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.07370215118153761,
      "eval_loss": NaN,
      "eval_runtime": 98.4516,
      "eval_samples_per_second": 46.429,
      "eval_steps_per_second": 23.22,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9533761389330432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}