Hugging Face's logo

auxyus
/
0d8f1810-af0c-4b52-973f-9fe030a29e08

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0d8f1810-af0c-4b52-973f-9fe030a29e08
File size: 3,116 Bytes 
7b997f4
 
 
4c693a1
7b997f4
4c693a1
7b997f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6b250ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4c693a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b997f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4c693a1
7b997f4
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06279069767441861,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002325581395348837,
      "eval_loss": 5.767578601837158,
      "eval_runtime": 10.4189,
      "eval_samples_per_second": 69.489,
      "eval_steps_per_second": 8.734,
      "step": 1
    },
    {
      "epoch": 0.0069767441860465115,
      "grad_norm": 0.7177151441574097,
      "learning_rate": 3e-05,
      "loss": 5.7725,
      "step": 3
    },
    {
      "epoch": 0.013953488372093023,
      "grad_norm": 0.6705913543701172,
      "learning_rate": 6e-05,
      "loss": 5.6508,
      "step": 6
    },
    {
      "epoch": 0.020930232558139535,
      "grad_norm": 0.9152357578277588,
      "learning_rate": 9e-05,
      "loss": 5.7661,
      "step": 9
    },
    {
      "epoch": 0.020930232558139535,
      "eval_loss": 5.740058898925781,
      "eval_runtime": 10.4015,
      "eval_samples_per_second": 69.605,
      "eval_steps_per_second": 8.749,
      "step": 9
    },
    {
      "epoch": 0.027906976744186046,
      "grad_norm": 0.8683664798736572,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.7731,
      "step": 12
    },
    {
      "epoch": 0.03488372093023256,
      "grad_norm": 1.1061254739761353,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.4242,
      "step": 15
    },
    {
      "epoch": 0.04186046511627907,
      "grad_norm": 0.99778813123703,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.2717,
      "step": 18
    },
    {
      "epoch": 0.04186046511627907,
      "eval_loss": 5.513608932495117,
      "eval_runtime": 10.4282,
      "eval_samples_per_second": 69.427,
      "eval_steps_per_second": 8.726,
      "step": 18
    },
    {
      "epoch": 0.04883720930232558,
      "grad_norm": 1.3651623725891113,
      "learning_rate": 9.635919272833938e-05,
      "loss": 5.5186,
      "step": 21
    },
    {
      "epoch": 0.05581395348837209,
      "grad_norm": 1.554046630859375,
      "learning_rate": 9.414737964294636e-05,
      "loss": 5.3002,
      "step": 24
    },
    {
      "epoch": 0.06279069767441861,
      "grad_norm": 1.4339934587478638,
      "learning_rate": 9.145187862775209e-05,
      "loss": 5.1694,
      "step": 27
    },
    {
      "epoch": 0.06279069767441861,
      "eval_loss": 5.061354637145996,
      "eval_runtime": 10.4152,
      "eval_samples_per_second": 69.514,
      "eval_steps_per_second": 8.737,
      "step": 27
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1693262398095360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}