Hugging Face's logo

ardaspear
/
a15cb6da-e674-42f9-8be4-692b0f7970da

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
a15cb6da-e674-42f9-8be4-692b0f7970da
File size: 3,125 Bytes 
9b377b7
 
 
a0d3308
9b377b7
a0d3308
9b377b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a2bc3fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a0d3308
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9b377b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a0d3308
9b377b7
 
 
 
 
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": 0.23893805309734514,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008849557522123894,
      "eval_loss": 7.850747108459473,
      "eval_runtime": 11.9245,
      "eval_samples_per_second": 7.967,
      "eval_steps_per_second": 2.013,
      "step": 1
    },
    {
      "epoch": 0.02654867256637168,
      "grad_norm": 23.30268096923828,
      "learning_rate": 3e-05,
      "loss": 32.3052,
      "step": 3
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": 24.82865333557129,
      "learning_rate": 6e-05,
      "loss": 26.7374,
      "step": 6
    },
    {
      "epoch": 0.07964601769911504,
      "grad_norm": 16.411090850830078,
      "learning_rate": 9e-05,
      "loss": 15.0507,
      "step": 9
    },
    {
      "epoch": 0.07964601769911504,
      "eval_loss": 1.889989972114563,
      "eval_runtime": 12.1586,
      "eval_samples_per_second": 7.813,
      "eval_steps_per_second": 1.974,
      "step": 9
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 16.30251693725586,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.4943,
      "step": 12
    },
    {
      "epoch": 0.13274336283185842,
      "grad_norm": 2.594444513320923,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.7033,
      "step": 15
    },
    {
      "epoch": 0.1592920353982301,
      "grad_norm": 0.005044514779001474,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0137,
      "step": 18
    },
    {
      "epoch": 0.1592920353982301,
      "eval_loss": 0.0003469553776085377,
      "eval_runtime": 12.2289,
      "eval_samples_per_second": 7.769,
      "eval_steps_per_second": 1.963,
      "step": 18
    },
    {
      "epoch": 0.18584070796460178,
      "grad_norm": 0.012934673577547073,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0003,
      "step": 21
    },
    {
      "epoch": 0.21238938053097345,
      "grad_norm": 0.00015438912669196725,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0002,
      "step": 24
    },
    {
      "epoch": 0.23893805309734514,
      "grad_norm": 0.0381203256547451,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0001,
      "step": 27
    },
    {
      "epoch": 0.23893805309734514,
      "eval_loss": 1.8848184026865056e-06,
      "eval_runtime": 12.2379,
      "eval_samples_per_second": 7.763,
      "eval_steps_per_second": 1.961,
      "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": 3.86407084326912e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}