Hugging Face's logo

trenden
/
8529bb55-26cf-4635-887b-f35e49f70acc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
8529bb55-26cf-4635-887b-f35e49f70acc
File size: 3,026 Bytes 
5d9ae20
 
 
68a7ec5
5d9ae20
68a7ec5
5d9ae20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d10976d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68a7ec5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d9ae20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68a7ec5
5d9ae20
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03171806167400881,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003524229074889868,
      "grad_norm": 32.06682205200195,
      "learning_rate": 2e-05,
      "loss": 10.1682,
      "step": 1
    },
    {
      "epoch": 0.003524229074889868,
      "eval_loss": 10.107810020446777,
      "eval_runtime": 4.3614,
      "eval_samples_per_second": 27.514,
      "eval_steps_per_second": 13.757,
      "step": 1
    },
    {
      "epoch": 0.007048458149779736,
      "grad_norm": 28.340951919555664,
      "learning_rate": 4e-05,
      "loss": 10.2809,
      "step": 2
    },
    {
      "epoch": 0.010572687224669603,
      "grad_norm": 26.849491119384766,
      "learning_rate": 6e-05,
      "loss": 9.5855,
      "step": 3
    },
    {
      "epoch": 0.010572687224669603,
      "eval_loss": 9.586976051330566,
      "eval_runtime": 3.6708,
      "eval_samples_per_second": 32.691,
      "eval_steps_per_second": 16.345,
      "step": 3
    },
    {
      "epoch": 0.014096916299559472,
      "grad_norm": 29.646787643432617,
      "learning_rate": 8e-05,
      "loss": 10.0704,
      "step": 4
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 32.25894546508789,
      "learning_rate": 0.0001,
      "loss": 7.8373,
      "step": 5
    },
    {
      "epoch": 0.021145374449339206,
      "grad_norm": 26.04344367980957,
      "learning_rate": 0.00012,
      "loss": 5.4309,
      "step": 6
    },
    {
      "epoch": 0.021145374449339206,
      "eval_loss": 3.7627370357513428,
      "eval_runtime": 3.7381,
      "eval_samples_per_second": 32.102,
      "eval_steps_per_second": 16.051,
      "step": 6
    },
    {
      "epoch": 0.024669603524229075,
      "grad_norm": 20.36292839050293,
      "learning_rate": 0.00014,
      "loss": 3.3894,
      "step": 7
    },
    {
      "epoch": 0.028193832599118944,
      "grad_norm": 21.608123779296875,
      "learning_rate": 0.00016,
      "loss": 1.8491,
      "step": 8
    },
    {
      "epoch": 0.03171806167400881,
      "grad_norm": 10.76959228515625,
      "learning_rate": 0.00018,
      "loss": 0.8269,
      "step": 9
    },
    {
      "epoch": 0.03171806167400881,
      "eval_loss": 0.6693419814109802,
      "eval_runtime": 3.7065,
      "eval_samples_per_second": 32.376,
      "eval_steps_per_second": 16.188,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1664607823331328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}