Hugging Face's logo

kooff11
/
956087b1-b534-49b6-baa5-54e847616a3e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
956087b1-b534-49b6-baa5-54e847616a3e
File size: 2,867 Bytes 
3b7e400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2620802620802621,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02620802620802621,
      "grad_norm": 0.688605546951294,
      "learning_rate": 5e-05,
      "loss": 1.9615,
      "step": 1
    },
    {
      "epoch": 0.02620802620802621,
      "eval_loss": 1.9379749298095703,
      "eval_runtime": 6.8873,
      "eval_samples_per_second": 37.315,
      "eval_steps_per_second": 9.438,
      "step": 1
    },
    {
      "epoch": 0.05241605241605242,
      "grad_norm": 0.7276808023452759,
      "learning_rate": 0.0001,
      "loss": 1.9459,
      "step": 2
    },
    {
      "epoch": 0.07862407862407862,
      "grad_norm": 0.7033953666687012,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.9077,
      "step": 3
    },
    {
      "epoch": 0.10483210483210484,
      "grad_norm": 0.719717264175415,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.9109,
      "step": 4
    },
    {
      "epoch": 0.13104013104013104,
      "grad_norm": 0.6515451669692993,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.8254,
      "step": 5
    },
    {
      "epoch": 0.15724815724815724,
      "grad_norm": 0.6293128728866577,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.7722,
      "step": 6
    },
    {
      "epoch": 0.18345618345618345,
      "grad_norm": 0.5616139769554138,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.7974,
      "step": 7
    },
    {
      "epoch": 0.20966420966420968,
      "grad_norm": 0.6011109948158264,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.7045,
      "step": 8
    },
    {
      "epoch": 0.23587223587223588,
      "grad_norm": 0.6134763956069946,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.7578,
      "step": 9
    },
    {
      "epoch": 0.2620802620802621,
      "grad_norm": 0.6061597466468811,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.7537,
      "step": 10
    },
    {
      "epoch": 0.2620802620802621,
      "eval_loss": 1.690554141998291,
      "eval_runtime": 6.9618,
      "eval_samples_per_second": 36.916,
      "eval_steps_per_second": 9.337,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.1209052633563136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}