Hugging Face's logo

kk-aivio
/
dc969dc6-2bd4-4afc-a8b3-8e7bfb66d102

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
dc969dc6-2bd4-4afc-a8b3-8e7bfb66d102
File size: 3,063 Bytes 
39f1701
 
 
dd559ec
39f1701
dd559ec
39f1701
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c438367
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21c0409
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd559ec
 
 
 
 
 
 
39f1701
 
 
 
 
 
 
 
 
 
 
 
 
 
dd559ec
39f1701
 
 
 
dd559ec
39f1701
 
 
 
 
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": 0.0008437928488556059,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437928488556059e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 1.9361,
      "step": 1
    },
    {
      "epoch": 8.437928488556059e-05,
      "eval_loss": NaN,
      "eval_runtime": 259.0715,
      "eval_samples_per_second": 19.261,
      "eval_steps_per_second": 9.631,
      "step": 1
    },
    {
      "epoch": 0.00016875856977112118,
      "grad_norm": 0.1505316197872162,
      "learning_rate": 4e-05,
      "loss": 1.4514,
      "step": 2
    },
    {
      "epoch": 0.0002531378546566818,
      "grad_norm": 0.10612518340349197,
      "learning_rate": 6e-05,
      "loss": 1.3608,
      "step": 3
    },
    {
      "epoch": 0.0002531378546566818,
      "eval_loss": NaN,
      "eval_runtime": 258.2564,
      "eval_samples_per_second": 19.322,
      "eval_steps_per_second": 9.661,
      "step": 3
    },
    {
      "epoch": 0.00033751713954224236,
      "grad_norm": 0.11388365179300308,
      "learning_rate": 8e-05,
      "loss": 1.4392,
      "step": 4
    },
    {
      "epoch": 0.00042189642442780296,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 2.0835,
      "step": 5
    },
    {
      "epoch": 0.0005062757093133636,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 1.9221,
      "step": 6
    },
    {
      "epoch": 0.0005062757093133636,
      "eval_loss": NaN,
      "eval_runtime": 256.9107,
      "eval_samples_per_second": 19.423,
      "eval_steps_per_second": 9.712,
      "step": 6
    },
    {
      "epoch": 0.0005906549941989242,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 2.1004,
      "step": 7
    },
    {
      "epoch": 0.0006750342790844847,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 1.2015,
      "step": 8
    },
    {
      "epoch": 0.0007594135639700454,
      "grad_norm": 0.1415807455778122,
      "learning_rate": 0.00018,
      "loss": 1.229,
      "step": 9
    },
    {
      "epoch": 0.0007594135639700454,
      "eval_loss": NaN,
      "eval_runtime": 256.814,
      "eval_samples_per_second": 19.43,
      "eval_steps_per_second": 9.715,
      "step": 9
    },
    {
      "epoch": 0.0008437928488556059,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 2.6117,
      "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": 3257466271825920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}