Hugging Face's logo

kooff11
/
04cd9d58-77d2-4065-abb8-8b161a76432d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
04cd9d58-77d2-4065-abb8-8b161a76432d
File size: 3,208 Bytes 
0874ba7
 
 
ca4ffaa
0874ba7
ca4ffaa
0874ba7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f86ba03
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
525eec1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ca4ffaa
 
 
 
 
 
 
0874ba7
 
 
 
 
 
 
 
 
 
 
 
 
 
ca4ffaa
0874ba7
 
 
 
ca4ffaa
0874ba7
 
 
 
 
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": 0.0026138665621120044,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002613866562112004,
      "grad_norm": 0.9460879564285278,
      "learning_rate": 2e-05,
      "loss": 0.2677,
      "step": 1
    },
    {
      "epoch": 0.0002613866562112004,
      "eval_loss": 0.34498801827430725,
      "eval_runtime": 100.97,
      "eval_samples_per_second": 63.811,
      "eval_steps_per_second": 7.983,
      "step": 1
    },
    {
      "epoch": 0.0005227733124224008,
      "grad_norm": 0.8985543847084045,
      "learning_rate": 4e-05,
      "loss": 0.2517,
      "step": 2
    },
    {
      "epoch": 0.0007841599686336013,
      "grad_norm": 1.076340913772583,
      "learning_rate": 6e-05,
      "loss": 0.3185,
      "step": 3
    },
    {
      "epoch": 0.0007841599686336013,
      "eval_loss": 0.32654470205307007,
      "eval_runtime": 100.8824,
      "eval_samples_per_second": 63.866,
      "eval_steps_per_second": 7.99,
      "step": 3
    },
    {
      "epoch": 0.0010455466248448016,
      "grad_norm": 1.1910107135772705,
      "learning_rate": 8e-05,
      "loss": 0.3072,
      "step": 4
    },
    {
      "epoch": 0.0013069332810560022,
      "grad_norm": 0.855275571346283,
      "learning_rate": 0.0001,
      "loss": 0.2373,
      "step": 5
    },
    {
      "epoch": 0.0015683199372672025,
      "grad_norm": 0.7225483059883118,
      "learning_rate": 0.00012,
      "loss": 0.1783,
      "step": 6
    },
    {
      "epoch": 0.0015683199372672025,
      "eval_loss": 0.17279158532619476,
      "eval_runtime": 100.8564,
      "eval_samples_per_second": 63.883,
      "eval_steps_per_second": 7.992,
      "step": 6
    },
    {
      "epoch": 0.0018297065934784029,
      "grad_norm": 0.7925214767456055,
      "learning_rate": 0.00014,
      "loss": 0.1235,
      "step": 7
    },
    {
      "epoch": 0.0020910932496896032,
      "grad_norm": 0.8158267736434937,
      "learning_rate": 0.00016,
      "loss": 0.1062,
      "step": 8
    },
    {
      "epoch": 0.002352479905900804,
      "grad_norm": 0.49643707275390625,
      "learning_rate": 0.00018,
      "loss": 0.0751,
      "step": 9
    },
    {
      "epoch": 0.002352479905900804,
      "eval_loss": 0.05340096727013588,
      "eval_runtime": 100.947,
      "eval_samples_per_second": 63.826,
      "eval_steps_per_second": 7.984,
      "step": 9
    },
    {
      "epoch": 0.0026138665621120044,
      "grad_norm": 0.6194673776626587,
      "learning_rate": 0.0002,
      "loss": 0.0491,
      "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": 7790166718545920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}