Hugging Face's logo

g0001
/
f33db66b-e13b-4580-a89c-4c90efeda0ea

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
f33db66b-e13b-4580-a89c-4c90efeda0ea
File size: 2,964 Bytes 
9f5faad
 
 
b75c3c4
9f5faad
b75c3c4
9f5faad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f9f5fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b4b945c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b75c3c4
 
 
 
 
 
 
9f5faad
 
 
 
 
 
 
 
 
 
 
 
 
 
b75c3c4
9f5faad
 
 
 
b75c3c4
9f5faad
 
 
 
 
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": 0.004507042253521127,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004507042253521127,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0004507042253521127,
      "eval_loss": NaN,
      "eval_runtime": 28.5809,
      "eval_samples_per_second": 32.714,
      "eval_steps_per_second": 16.375,
      "step": 1
    },
    {
      "epoch": 0.0009014084507042254,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.001352112676056338,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.001352112676056338,
      "eval_loss": NaN,
      "eval_runtime": 26.5013,
      "eval_samples_per_second": 35.281,
      "eval_steps_per_second": 17.66,
      "step": 3
    },
    {
      "epoch": 0.0018028169014084508,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0022535211267605635,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.002704225352112676,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002704225352112676,
      "eval_loss": NaN,
      "eval_runtime": 26.6093,
      "eval_samples_per_second": 35.138,
      "eval_steps_per_second": 17.588,
      "step": 6
    },
    {
      "epoch": 0.0031549295774647886,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0036056338028169015,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0040563380281690145,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0040563380281690145,
      "eval_loss": NaN,
      "eval_runtime": 26.5429,
      "eval_samples_per_second": 35.226,
      "eval_steps_per_second": 17.632,
      "step": 9
    },
    {
      "epoch": 0.004507042253521127,
      "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": 1916899650699264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}