Hugging Face's logo

ivangrapher
/
cb041de6-b977-4a4d-8a28-8d5c545e754b

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
cb041de6-b977-4a4d-8a28-8d5c545e754b
File size: 3,033 Bytes 
2c5187d
 
 
6b28bb7
2c5187d
6b28bb7
2c5187d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6b28bb7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2c5187d
 
 
 
 
 
 
 
 
 
 
 
 
 
6b28bb7
2c5187d
 
 
 
6b28bb7
2c5187d
 
 
 
 
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
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004796674305814635,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015988914352715452,
      "eval_loss": NaN,
      "eval_runtime": 64.2227,
      "eval_samples_per_second": 30.752,
      "eval_steps_per_second": 15.384,
      "step": 1
    },
    {
      "epoch": 0.0004796674305814635,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.000959334861162927,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0012791131482172361,
      "eval_loss": NaN,
      "eval_runtime": 63.0517,
      "eval_samples_per_second": 31.323,
      "eval_steps_per_second": 15.67,
      "step": 8
    },
    {
      "epoch": 0.0014390022917443906,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.001918669722325854,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0023983371529073174,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0025582262964344723,
      "eval_loss": NaN,
      "eval_runtime": 63.0749,
      "eval_samples_per_second": 31.312,
      "eval_steps_per_second": 15.664,
      "step": 16
    },
    {
      "epoch": 0.002878004583488781,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0033576720140702444,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.003837339444651708,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.003837339444651708,
      "eval_loss": NaN,
      "eval_runtime": 63.0203,
      "eval_samples_per_second": 31.339,
      "eval_steps_per_second": 15.678,
      "step": 24
    },
    {
      "epoch": 0.0043170068752331715,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.004796674305814635,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1469552441425920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}