Hugging Face's logo

rak-r05
/
b5793bec-9c1a-4d53-a534-7656ddb75c50

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b5793bec-9c1a-4d53-a534-7656ddb75c50
File size: 3,218 Bytes 
ad231aa
 
 
ecc7145
ad231aa
ecc7145
ad231aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
245eeeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f65696b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ecc7145
 
 
 
 
 
 
ad231aa
 
 
 
 
 
 
 
 
 
 
 
 
 
ecc7145
ad231aa
 
 
 
ecc7145
ad231aa
 
 
 
 
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": 0.010526315789473684,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010526315789473684,
      "grad_norm": 0.022679297253489494,
      "learning_rate": 2e-05,
      "loss": 10.3788,
      "step": 1
    },
    {
      "epoch": 0.0010526315789473684,
      "eval_loss": 10.377253532409668,
      "eval_runtime": 2.6851,
      "eval_samples_per_second": 148.972,
      "eval_steps_per_second": 74.486,
      "step": 1
    },
    {
      "epoch": 0.002105263157894737,
      "grad_norm": 0.016693023964762688,
      "learning_rate": 4e-05,
      "loss": 10.3776,
      "step": 2
    },
    {
      "epoch": 0.003157894736842105,
      "grad_norm": 0.015842318534851074,
      "learning_rate": 6e-05,
      "loss": 10.3845,
      "step": 3
    },
    {
      "epoch": 0.003157894736842105,
      "eval_loss": 10.377248764038086,
      "eval_runtime": 2.672,
      "eval_samples_per_second": 149.702,
      "eval_steps_per_second": 74.851,
      "step": 3
    },
    {
      "epoch": 0.004210526315789474,
      "grad_norm": 0.01499270461499691,
      "learning_rate": 8e-05,
      "loss": 10.3793,
      "step": 4
    },
    {
      "epoch": 0.005263157894736842,
      "grad_norm": 0.017152471467852592,
      "learning_rate": 0.0001,
      "loss": 10.3772,
      "step": 5
    },
    {
      "epoch": 0.00631578947368421,
      "grad_norm": 0.014443840831518173,
      "learning_rate": 0.00012,
      "loss": 10.3754,
      "step": 6
    },
    {
      "epoch": 0.00631578947368421,
      "eval_loss": 10.377209663391113,
      "eval_runtime": 2.6482,
      "eval_samples_per_second": 151.046,
      "eval_steps_per_second": 75.523,
      "step": 6
    },
    {
      "epoch": 0.007368421052631579,
      "grad_norm": 0.01774691417813301,
      "learning_rate": 0.00014,
      "loss": 10.3827,
      "step": 7
    },
    {
      "epoch": 0.008421052631578947,
      "grad_norm": 0.014606388285756111,
      "learning_rate": 0.00016,
      "loss": 10.375,
      "step": 8
    },
    {
      "epoch": 0.009473684210526316,
      "grad_norm": 0.018191713839769363,
      "learning_rate": 0.00018,
      "loss": 10.3804,
      "step": 9
    },
    {
      "epoch": 0.009473684210526316,
      "eval_loss": 10.377147674560547,
      "eval_runtime": 2.5658,
      "eval_samples_per_second": 155.897,
      "eval_steps_per_second": 77.949,
      "step": 9
    },
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 0.017616568133234978,
      "learning_rate": 0.0002,
      "loss": 10.3752,
      "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": 232756346880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}