Hugging Face's logo

lesso07
/
7c1ea36b-86eb-47aa-8ee3-c37f307aa141

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7c1ea36b-86eb-47aa-8ee3-c37f307aa141
File size: 2,896 Bytes 
7ac6426
 
 
0a4701c
7ac6426
0a4701c
7ac6426
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ee6422d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d845e40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a4701c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7ac6426
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a4701c
7ac6426
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00011492519088355923,
  "eval_steps": 2,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4365648860444904e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.4365648860444904e-05,
      "eval_loss": NaN,
      "eval_runtime": 3458.3695,
      "eval_samples_per_second": 8.475,
      "eval_steps_per_second": 4.238,
      "step": 1
    },
    {
      "epoch": 2.8731297720889808e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 2.8731297720889808e-05,
      "eval_loss": NaN,
      "eval_runtime": 3458.607,
      "eval_samples_per_second": 8.475,
      "eval_steps_per_second": 4.237,
      "step": 2
    },
    {
      "epoch": 4.3096946581334714e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 5.7462595441779616e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 5.7462595441779616e-05,
      "eval_loss": NaN,
      "eval_runtime": 3460.8748,
      "eval_samples_per_second": 8.469,
      "eval_steps_per_second": 4.234,
      "step": 4
    },
    {
      "epoch": 7.182824430222452e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 8.619389316266943e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 8.619389316266943e-05,
      "eval_loss": NaN,
      "eval_runtime": 3456.2528,
      "eval_samples_per_second": 8.48,
      "eval_steps_per_second": 4.24,
      "step": 6
    },
    {
      "epoch": 0.00010055954202311432,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00011492519088355923,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00011492519088355923,
      "eval_loss": NaN,
      "eval_runtime": 3457.476,
      "eval_samples_per_second": 8.477,
      "eval_steps_per_second": 4.239,
      "step": 8
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2967549134241792.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}