Hugging Face's logo

tuanna08go
/
2c1f0dce-c24d-43f8-86dc-589d6d262200

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
2c1f0dce-c24d-43f8-86dc-589d6d262200
File size: 2,589 Bytes 
483e4cc
 
 
a2e1ce4
0c2dd68
a2e1ce4
483e4cc
 
 
 
 
 
 
0c2dd68
 
 
483e4cc
0c2dd68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
beb0fa8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a2e1ce4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
483e4cc
 
 
0c2dd68
483e4cc
 
0c2dd68
483e4cc
 
 
 
 
 
 
0c2dd68
483e4cc
 
 
 
a2e1ce4
483e4cc
 
 
 
 
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": 0.14130434782608695,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036231884057971015,
      "eval_loss": NaN,
      "eval_runtime": 6.0138,
      "eval_samples_per_second": 19.455,
      "eval_steps_per_second": 9.811,
      "step": 1
    },
    {
      "epoch": 0.018115942028985508,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.036231884057971016,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.036231884057971016,
      "eval_loss": NaN,
      "eval_runtime": 5.0957,
      "eval_samples_per_second": 22.96,
      "eval_steps_per_second": 11.578,
      "step": 10
    },
    {
      "epoch": 0.05434782608695652,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.07246376811594203,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.07246376811594203,
      "eval_loss": NaN,
      "eval_runtime": 5.1159,
      "eval_samples_per_second": 22.87,
      "eval_steps_per_second": 11.533,
      "step": 20
    },
    {
      "epoch": 0.09057971014492754,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.10869565217391304,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.10869565217391304,
      "eval_loss": NaN,
      "eval_runtime": 5.1128,
      "eval_samples_per_second": 22.884,
      "eval_steps_per_second": 11.54,
      "step": 30
    },
    {
      "epoch": 0.12681159420289856,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "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": 2270087809597440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}