Hugging Face's logo

VERSIL91
/
ebfa63ec-b835-4714-bd4e-ef9e45a9563e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ebfa63ec-b835-4714-bd4e-ef9e45a9563e
File size: 2,970 Bytes 
e46a309
 
 
5b40bce
e46a309
5b40bce
e46a309
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5b40bce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e46a309
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5b40bce
e46a309
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01710681064898963,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017106810648989629,
      "grad_norm": 0.5461569428443909,
      "learning_rate": 1e-05,
      "loss": 3.6187,
      "step": 1
    },
    {
      "epoch": 0.0017106810648989629,
      "eval_loss": 3.4791719913482666,
      "eval_runtime": 44.1144,
      "eval_samples_per_second": 22.328,
      "eval_steps_per_second": 11.176,
      "step": 1
    },
    {
      "epoch": 0.0034213621297979257,
      "grad_norm": 0.5224133729934692,
      "learning_rate": 2e-05,
      "loss": 3.4447,
      "step": 2
    },
    {
      "epoch": 0.005132043194696889,
      "grad_norm": 0.600152313709259,
      "learning_rate": 3e-05,
      "loss": 3.4106,
      "step": 3
    },
    {
      "epoch": 0.0068427242595958514,
      "grad_norm": 0.5289663672447205,
      "learning_rate": 4e-05,
      "loss": 3.551,
      "step": 4
    },
    {
      "epoch": 0.008553405324494815,
      "grad_norm": 0.5006380081176758,
      "learning_rate": 5e-05,
      "loss": 3.3413,
      "step": 5
    },
    {
      "epoch": 0.008553405324494815,
      "eval_loss": 3.4636945724487305,
      "eval_runtime": 3.823,
      "eval_samples_per_second": 257.654,
      "eval_steps_per_second": 128.958,
      "step": 5
    },
    {
      "epoch": 0.010264086389393778,
      "grad_norm": 0.4884447753429413,
      "learning_rate": 6e-05,
      "loss": 3.3282,
      "step": 6
    },
    {
      "epoch": 0.01197476745429274,
      "grad_norm": 0.5128330588340759,
      "learning_rate": 7e-05,
      "loss": 3.3899,
      "step": 7
    },
    {
      "epoch": 0.013685448519191703,
      "grad_norm": 0.4853476583957672,
      "learning_rate": 8e-05,
      "loss": 3.4673,
      "step": 8
    },
    {
      "epoch": 0.015396129584090666,
      "grad_norm": 0.4155305325984955,
      "learning_rate": 9e-05,
      "loss": 3.1119,
      "step": 9
    },
    {
      "epoch": 0.01710681064898963,
      "grad_norm": 0.5410354733467102,
      "learning_rate": 0.0001,
      "loss": 3.4547,
      "step": 10
    },
    {
      "epoch": 0.01710681064898963,
      "eval_loss": 3.410022020339966,
      "eval_runtime": 3.9919,
      "eval_samples_per_second": 246.751,
      "eval_steps_per_second": 123.501,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 137170601902080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}