Hugging Face's logo

JacksonBrune
/
7d9de563-e053-4f0e-97a9-13bcd61edb60

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7d9de563-e053-4f0e-97a9-13bcd61edb60
File size: 3,226 Bytes 
919fa83
 
 
369255e
919fa83
369255e
919fa83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f215ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d05599
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
369255e
 
 
 
 
 
 
919fa83
 
 
 
 
 
 
 
 
 
 
 
 
 
369255e
919fa83
 
 
 
369255e
919fa83
 
 
 
 
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": 0.00020155702804162154,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0155702804162153e-05,
      "grad_norm": 1.1627131700515747,
      "learning_rate": 2e-05,
      "loss": 1.8235,
      "step": 1
    },
    {
      "epoch": 2.0155702804162153e-05,
      "eval_loss": 1.8384151458740234,
      "eval_runtime": 858.5305,
      "eval_samples_per_second": 24.332,
      "eval_steps_per_second": 12.166,
      "step": 1
    },
    {
      "epoch": 4.0311405608324306e-05,
      "grad_norm": 2.0875329971313477,
      "learning_rate": 4e-05,
      "loss": 1.9389,
      "step": 2
    },
    {
      "epoch": 6.0467108412486456e-05,
      "grad_norm": 3.7231967449188232,
      "learning_rate": 6e-05,
      "loss": 1.5567,
      "step": 3
    },
    {
      "epoch": 6.0467108412486456e-05,
      "eval_loss": 1.817110300064087,
      "eval_runtime": 857.1198,
      "eval_samples_per_second": 24.372,
      "eval_steps_per_second": 12.186,
      "step": 3
    },
    {
      "epoch": 8.062281121664861e-05,
      "grad_norm": 3.0493383407592773,
      "learning_rate": 8e-05,
      "loss": 1.6595,
      "step": 4
    },
    {
      "epoch": 0.00010077851402081077,
      "grad_norm": 1.6077319383621216,
      "learning_rate": 0.0001,
      "loss": 2.2053,
      "step": 5
    },
    {
      "epoch": 0.00012093421682497291,
      "grad_norm": 1.1640726327896118,
      "learning_rate": 0.00012,
      "loss": 2.1634,
      "step": 6
    },
    {
      "epoch": 0.00012093421682497291,
      "eval_loss": 1.5944300889968872,
      "eval_runtime": 857.3585,
      "eval_samples_per_second": 24.366,
      "eval_steps_per_second": 12.183,
      "step": 6
    },
    {
      "epoch": 0.00014108991962913508,
      "grad_norm": 2.123807191848755,
      "learning_rate": 0.00014,
      "loss": 1.7407,
      "step": 7
    },
    {
      "epoch": 0.00016124562243329722,
      "grad_norm": 1.0386054515838623,
      "learning_rate": 0.00016,
      "loss": 1.1746,
      "step": 8
    },
    {
      "epoch": 0.00018140132523745937,
      "grad_norm": 2.409040689468384,
      "learning_rate": 0.00018,
      "loss": 1.4244,
      "step": 9
    },
    {
      "epoch": 0.00018140132523745937,
      "eval_loss": 1.3097835779190063,
      "eval_runtime": 857.3178,
      "eval_samples_per_second": 24.367,
      "eval_steps_per_second": 12.183,
      "step": 9
    },
    {
      "epoch": 0.00020155702804162154,
      "grad_norm": 1.3552900552749634,
      "learning_rate": 0.0002,
      "loss": 1.1348,
      "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": 2728107266015232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}