Hugging Face's logo

duyphu
/
99ac8d3a-6195-42ce-bb9f-d715820c4f0f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
99ac8d3a-6195-42ce-bb9f-d715820c4f0f
File size: 2,797 Bytes 
d2e992f
 
 
b82b68d
f647151
b82b68d
d2e992f
 
 
 
 
 
 
f647151
 
 
d2e992f
f647151
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
501dbcd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b82b68d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2e992f
 
 
f647151
d2e992f
 
f647151
d2e992f
 
 
 
 
 
 
f647151
d2e992f
 
 
 
b82b68d
d2e992f
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005533484676503973,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014188422247446084,
      "eval_loss": 0.9373186230659485,
      "eval_runtime": 85.4442,
      "eval_samples_per_second": 34.736,
      "eval_steps_per_second": 17.368,
      "step": 1
    },
    {
      "epoch": 0.0007094211123723042,
      "grad_norm": 0.4906405508518219,
      "learning_rate": 5e-05,
      "loss": 0.9687,
      "step": 5
    },
    {
      "epoch": 0.0014188422247446084,
      "grad_norm": 0.6939789056777954,
      "learning_rate": 0.0001,
      "loss": 0.8927,
      "step": 10
    },
    {
      "epoch": 0.0014188422247446084,
      "eval_loss": 0.8500236868858337,
      "eval_runtime": 86.1579,
      "eval_samples_per_second": 34.448,
      "eval_steps_per_second": 17.224,
      "step": 10
    },
    {
      "epoch": 0.0021282633371169125,
      "grad_norm": 0.6280760765075684,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7719,
      "step": 15
    },
    {
      "epoch": 0.0028376844494892167,
      "grad_norm": 1.1123079061508179,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7106,
      "step": 20
    },
    {
      "epoch": 0.0028376844494892167,
      "eval_loss": 0.6546657085418701,
      "eval_runtime": 85.8004,
      "eval_samples_per_second": 34.592,
      "eval_steps_per_second": 17.296,
      "step": 20
    },
    {
      "epoch": 0.003547105561861521,
      "grad_norm": 0.8203548192977905,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6668,
      "step": 25
    },
    {
      "epoch": 0.004256526674233825,
      "grad_norm": 0.8009120225906372,
      "learning_rate": 5e-05,
      "loss": 0.6256,
      "step": 30
    },
    {
      "epoch": 0.004256526674233825,
      "eval_loss": 0.6064170002937317,
      "eval_runtime": 86.325,
      "eval_samples_per_second": 34.382,
      "eval_steps_per_second": 17.191,
      "step": 30
    },
    {
      "epoch": 0.004965947786606129,
      "grad_norm": 0.7089608311653137,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6629,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1028332078497792.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}