Hugging Face's logo

great0001
/
21ace498-004f-4e8d-8c62-fa91718a79e8

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
21ace498-004f-4e8d-8c62-fa91718a79e8
File size: 2,936 Bytes 
3766c01
 
 
f17f011
3766c01
f17f011
3766c01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1d47138
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73453bc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f17f011
 
 
 
 
 
 
3766c01
 
 
 
 
 
 
 
 
 
 
 
 
 
f17f011
3766c01
 
 
 
f17f011
3766c01
 
 
 
 
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": 0.26490066225165565,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026490066225165563,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.026490066225165563,
      "eval_loss": NaN,
      "eval_runtime": 1.0935,
      "eval_samples_per_second": 14.632,
      "eval_steps_per_second": 7.316,
      "step": 1
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.07947019867549669,
      "eval_loss": NaN,
      "eval_runtime": 0.4185,
      "eval_samples_per_second": 38.236,
      "eval_steps_per_second": 19.118,
      "step": 3
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.15894039735099338,
      "eval_loss": NaN,
      "eval_runtime": 0.4212,
      "eval_samples_per_second": 37.987,
      "eval_steps_per_second": 18.993,
      "step": 6
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.23841059602649006,
      "eval_loss": NaN,
      "eval_runtime": 0.4155,
      "eval_samples_per_second": 38.51,
      "eval_steps_per_second": 19.255,
      "step": 9
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 356728084365312.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}