Hugging Face's logo

tuanna08go
/
e1af209e-9139-4d0e-a422-fbcdda67f259

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e1af209e-9139-4d0e-a422-fbcdda67f259
File size: 2,848 Bytes 
5cfd6c9
 
 
6773928
a9ffc4b
6773928
5cfd6c9
 
 
 
 
 
 
a9ffc4b
 
 
5cfd6c9
a9ffc4b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43b1ca4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cc50589
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6773928
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5cfd6c9
 
 
a9ffc4b
5cfd6c9
 
a9ffc4b
5cfd6c9
 
 
 
 
 
 
6773928
5cfd6c9
 
 
 
6773928
5cfd6c9
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8333333333333334,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016666666666666666,
      "eval_loss": 6.828747272491455,
      "eval_runtime": 3.1635,
      "eval_samples_per_second": 128.022,
      "eval_steps_per_second": 16.121,
      "step": 1
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 2.298238754272461,
      "learning_rate": 9.330127018922194e-05,
      "loss": 6.479,
      "step": 10
    },
    {
      "epoch": 0.16666666666666666,
      "eval_loss": 6.025122165679932,
      "eval_runtime": 3.1802,
      "eval_samples_per_second": 127.352,
      "eval_steps_per_second": 16.037,
      "step": 10
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.1337666511535645,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.4595,
      "step": 20
    },
    {
      "epoch": 0.3333333333333333,
      "eval_loss": 5.005618572235107,
      "eval_runtime": 3.1314,
      "eval_samples_per_second": 129.334,
      "eval_steps_per_second": 16.287,
      "step": 20
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.1608963012695312,
      "learning_rate": 3.705904774487396e-05,
      "loss": 4.5889,
      "step": 30
    },
    {
      "epoch": 0.5,
      "eval_loss": 4.342362403869629,
      "eval_runtime": 3.2423,
      "eval_samples_per_second": 124.91,
      "eval_steps_per_second": 15.729,
      "step": 30
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.272810935974121,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 4.0775,
      "step": 40
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 4.024642467498779,
      "eval_runtime": 3.2316,
      "eval_samples_per_second": 125.327,
      "eval_steps_per_second": 15.782,
      "step": 40
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.1972110271453857,
      "learning_rate": 0.0,
      "loss": 3.8715,
      "step": 50
    },
    {
      "epoch": 0.8333333333333334,
      "eval_loss": 3.9678239822387695,
      "eval_runtime": 3.2072,
      "eval_samples_per_second": 126.279,
      "eval_steps_per_second": 15.902,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5486824076083200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}