Hugging Face's logo

VERSIL91
/
b579a441-a51c-4ef7-8196-0b2dd3b7a5f0

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b579a441-a51c-4ef7-8196-0b2dd3b7a5f0
File size: 2,784 Bytes 
511c75f
 
 
9293bd8
511c75f
9293bd8
511c75f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9293bd8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
511c75f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9293bd8
511c75f
 
 
 
 
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": 0.1423487544483986,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014234875444839857,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 3346.0093,
      "step": 1
    },
    {
      "epoch": 0.014234875444839857,
      "eval_loss": NaN,
      "eval_runtime": 69.0908,
      "eval_samples_per_second": 6.861,
      "eval_steps_per_second": 0.868,
      "step": 1
    },
    {
      "epoch": 0.028469750889679714,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 5441.3306,
      "step": 2
    },
    {
      "epoch": 0.042704626334519574,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 850.3894,
      "step": 3
    },
    {
      "epoch": 0.05693950177935943,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 1138.0363,
      "step": 4
    },
    {
      "epoch": 0.0711743772241993,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 3671.7151,
      "step": 5
    },
    {
      "epoch": 0.0711743772241993,
      "eval_loss": NaN,
      "eval_runtime": 12.5954,
      "eval_samples_per_second": 37.633,
      "eval_steps_per_second": 4.764,
      "step": 5
    },
    {
      "epoch": 0.08540925266903915,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 2033.0361,
      "step": 6
    },
    {
      "epoch": 0.099644128113879,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 366.2248,
      "step": 7
    },
    {
      "epoch": 0.11387900355871886,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 588.2904,
      "step": 8
    },
    {
      "epoch": 0.12811387900355872,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 2884.811,
      "step": 9
    },
    {
      "epoch": 0.1423487544483986,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 441.9196,
      "step": 10
    },
    {
      "epoch": 0.1423487544483986,
      "eval_loss": NaN,
      "eval_runtime": 12.6367,
      "eval_samples_per_second": 37.51,
      "eval_steps_per_second": 4.748,
      "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": 5.123764987625472e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}