Hugging Face's logo

quannh197
/
c4ff25be-7ef1-40cb-a8cb-e0bc2a097844

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c4ff25be-7ef1-40cb-a8cb-e0bc2a097844
File size: 3,200 Bytes 
42b1ba6
 
 
ed78ef2
42b1ba6
ed78ef2
42b1ba6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c880832
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b5f50b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed78ef2
 
 
 
 
 
 
42b1ba6
 
 
 
 
 
 
 
 
 
 
 
 
 
ed78ef2
42b1ba6
 
 
 
ed78ef2
42b1ba6
 
 
 
 
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": 0.004253056884635832,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "grad_norm": 0.6765125393867493,
      "learning_rate": 2e-05,
      "loss": 1.7296,
      "step": 1
    },
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 1.7417739629745483,
      "eval_runtime": 13.6849,
      "eval_samples_per_second": 72.343,
      "eval_steps_per_second": 36.171,
      "step": 1
    },
    {
      "epoch": 0.0008506113769271664,
      "grad_norm": 0.6839314103126526,
      "learning_rate": 4e-05,
      "loss": 1.8076,
      "step": 2
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 0.6799637079238892,
      "learning_rate": 6e-05,
      "loss": 1.7601,
      "step": 3
    },
    {
      "epoch": 0.0012759170653907496,
      "eval_loss": 1.738396167755127,
      "eval_runtime": 13.1982,
      "eval_samples_per_second": 75.01,
      "eval_steps_per_second": 37.505,
      "step": 3
    },
    {
      "epoch": 0.0017012227538543328,
      "grad_norm": 0.7580278515815735,
      "learning_rate": 8e-05,
      "loss": 1.7209,
      "step": 4
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 0.8269679546356201,
      "learning_rate": 0.0001,
      "loss": 1.7431,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 0.6974154710769653,
      "learning_rate": 0.00012,
      "loss": 1.7149,
      "step": 6
    },
    {
      "epoch": 0.002551834130781499,
      "eval_loss": 1.6992298364639282,
      "eval_runtime": 13.3487,
      "eval_samples_per_second": 74.165,
      "eval_steps_per_second": 37.082,
      "step": 6
    },
    {
      "epoch": 0.0029771398192450825,
      "grad_norm": 0.8422204852104187,
      "learning_rate": 0.00014,
      "loss": 1.8683,
      "step": 7
    },
    {
      "epoch": 0.0034024455077086655,
      "grad_norm": 0.7477498650550842,
      "learning_rate": 0.00016,
      "loss": 1.5238,
      "step": 8
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.7416492104530334,
      "learning_rate": 0.00018,
      "loss": 1.6067,
      "step": 9
    },
    {
      "epoch": 0.003827751196172249,
      "eval_loss": 1.580859661102295,
      "eval_runtime": 13.3094,
      "eval_samples_per_second": 74.384,
      "eval_steps_per_second": 37.192,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 0.8465039134025574,
      "learning_rate": 0.0002,
      "loss": 1.6505,
      "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": 255791978250240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}