Hugging Face's logo

havinash-ai
/
99be823e-10bb-4b57-83f6-be3de629d1eb

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
99be823e-10bb-4b57-83f6-be3de629d1eb
File size: 3,200 Bytes 
b3fd2ad
 
 
457b78d
b3fd2ad
457b78d
b3fd2ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ef4b8c4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
04f8b2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
457b78d
 
 
 
 
 
 
b3fd2ad
 
 
 
 
 
 
 
 
 
 
 
 
 
457b78d
b3fd2ad
 
 
 
457b78d
b3fd2ad
 
 
 
 
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": 0.000827934510380229,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.27934510380229e-05,
      "grad_norm": 1.477283000946045,
      "learning_rate": 2e-05,
      "loss": 2.8657,
      "step": 1
    },
    {
      "epoch": 8.27934510380229e-05,
      "eval_loss": 0.6027017831802368,
      "eval_runtime": 763.0731,
      "eval_samples_per_second": 6.665,
      "eval_steps_per_second": 3.333,
      "step": 1
    },
    {
      "epoch": 0.0001655869020760458,
      "grad_norm": 0.8949412107467651,
      "learning_rate": 4e-05,
      "loss": 2.1009,
      "step": 2
    },
    {
      "epoch": 0.00024838035311406867,
      "grad_norm": 1.8197911977767944,
      "learning_rate": 6e-05,
      "loss": 2.5783,
      "step": 3
    },
    {
      "epoch": 0.00024838035311406867,
      "eval_loss": 0.5999210476875305,
      "eval_runtime": 653.8233,
      "eval_samples_per_second": 7.779,
      "eval_steps_per_second": 3.889,
      "step": 3
    },
    {
      "epoch": 0.0003311738041520916,
      "grad_norm": 1.435214638710022,
      "learning_rate": 8e-05,
      "loss": 2.3543,
      "step": 4
    },
    {
      "epoch": 0.0004139672551901145,
      "grad_norm": 1.3697088956832886,
      "learning_rate": 0.0001,
      "loss": 2.2362,
      "step": 5
    },
    {
      "epoch": 0.0004967607062281373,
      "grad_norm": 1.8139108419418335,
      "learning_rate": 0.00012,
      "loss": 3.0984,
      "step": 6
    },
    {
      "epoch": 0.0004967607062281373,
      "eval_loss": 0.541894257068634,
      "eval_runtime": 422.6787,
      "eval_samples_per_second": 12.033,
      "eval_steps_per_second": 6.016,
      "step": 6
    },
    {
      "epoch": 0.0005795541572661603,
      "grad_norm": 2.073357343673706,
      "learning_rate": 0.00014,
      "loss": 1.9979,
      "step": 7
    },
    {
      "epoch": 0.0006623476083041832,
      "grad_norm": 2.176180124282837,
      "learning_rate": 0.00016,
      "loss": 1.9623,
      "step": 8
    },
    {
      "epoch": 0.000745141059342206,
      "grad_norm": 2.046623706817627,
      "learning_rate": 0.00018,
      "loss": 1.6899,
      "step": 9
    },
    {
      "epoch": 0.000745141059342206,
      "eval_loss": 0.30938443541526794,
      "eval_runtime": 422.8667,
      "eval_samples_per_second": 12.027,
      "eval_steps_per_second": 6.014,
      "step": 9
    },
    {
      "epoch": 0.000827934510380229,
      "grad_norm": 1.7581552267074585,
      "learning_rate": 0.0002,
      "loss": 1.0762,
      "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": 4670180850401280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}