Hugging Face's logo

adammandic87
/
af2782bb-b492-459a-9f7c-9a24a6c89674

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
af2782bb-b492-459a-9f7c-9a24a6c89674
File size: 2,963 Bytes 
ccce535
 
 
2e50e5d
ccce535
2e50e5d
ccce535
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2e50e5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ccce535
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2e50e5d
ccce535
 
 
 
 
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": 0.437636761487965,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00437636761487965,
      "eval_loss": 2.1039679050445557,
      "eval_runtime": 5.4829,
      "eval_samples_per_second": 17.692,
      "eval_steps_per_second": 8.937,
      "step": 1
    },
    {
      "epoch": 0.0437636761487965,
      "grad_norm": 1.9867570400238037,
      "learning_rate": 0.0002,
      "loss": 0.8878,
      "step": 10
    },
    {
      "epoch": 0.087527352297593,
      "grad_norm": 1.723362684249878,
      "learning_rate": 0.0002,
      "loss": 0.4308,
      "step": 20
    },
    {
      "epoch": 0.13129102844638948,
      "grad_norm": 1.2347863912582397,
      "learning_rate": 0.0002,
      "loss": 0.3851,
      "step": 30
    },
    {
      "epoch": 0.175054704595186,
      "grad_norm": 0.8125748038291931,
      "learning_rate": 0.0002,
      "loss": 0.324,
      "step": 40
    },
    {
      "epoch": 0.2188183807439825,
      "grad_norm": 1.0239754915237427,
      "learning_rate": 0.0002,
      "loss": 0.3551,
      "step": 50
    },
    {
      "epoch": 0.2188183807439825,
      "eval_loss": 0.35808104276657104,
      "eval_runtime": 3.9367,
      "eval_samples_per_second": 24.64,
      "eval_steps_per_second": 12.447,
      "step": 50
    },
    {
      "epoch": 0.26258205689277897,
      "grad_norm": 0.9813992381095886,
      "learning_rate": 0.0002,
      "loss": 0.3551,
      "step": 60
    },
    {
      "epoch": 0.3063457330415755,
      "grad_norm": 1.1051058769226074,
      "learning_rate": 0.0002,
      "loss": 0.3701,
      "step": 70
    },
    {
      "epoch": 0.350109409190372,
      "grad_norm": 0.8475605249404907,
      "learning_rate": 0.0002,
      "loss": 0.2976,
      "step": 80
    },
    {
      "epoch": 0.3938730853391685,
      "grad_norm": 1.0010513067245483,
      "learning_rate": 0.0002,
      "loss": 0.2987,
      "step": 90
    },
    {
      "epoch": 0.437636761487965,
      "grad_norm": 1.0572749376296997,
      "learning_rate": 0.0002,
      "loss": 0.3285,
      "step": 100
    },
    {
      "epoch": 0.437636761487965,
      "eval_loss": 0.31449094414711,
      "eval_runtime": 3.9469,
      "eval_samples_per_second": 24.576,
      "eval_steps_per_second": 12.415,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.122743621353472e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}