Hugging Face's logo

tuanna08go
/
3914fcfc-706c-4a02-ab6b-4cd0cbe61b21

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3914fcfc-706c-4a02-ab6b-4cd0cbe61b21
File size: 2,783 Bytes 
a27831a
 
 
7c29cda
db1f041
7c29cda
a27831a
 
 
 
 
 
 
db1f041
 
 
a27831a
db1f041
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c07ed37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7c29cda
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a27831a
 
 
db1f041
a27831a
 
db1f041
a27831a
 
 
 
 
 
 
db1f041
a27831a
 
 
 
7c29cda
a27831a
 
 
 
 
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": 0.022168537729145944,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005684240443370755,
      "eval_loss": 1.7579647302627563,
      "eval_runtime": 55.1355,
      "eval_samples_per_second": 13.44,
      "eval_steps_per_second": 6.729,
      "step": 1
    },
    {
      "epoch": 0.002842120221685377,
      "grad_norm": 0.6500794887542725,
      "learning_rate": 5e-05,
      "loss": 1.7961,
      "step": 5
    },
    {
      "epoch": 0.005684240443370754,
      "grad_norm": 0.509131133556366,
      "learning_rate": 0.0001,
      "loss": 1.7088,
      "step": 10
    },
    {
      "epoch": 0.005684240443370754,
      "eval_loss": 1.7291897535324097,
      "eval_runtime": 54.7873,
      "eval_samples_per_second": 13.525,
      "eval_steps_per_second": 6.772,
      "step": 10
    },
    {
      "epoch": 0.008526360665056132,
      "grad_norm": 0.7104833722114563,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8415,
      "step": 15
    },
    {
      "epoch": 0.011368480886741509,
      "grad_norm": 0.6715155243873596,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3906,
      "step": 20
    },
    {
      "epoch": 0.011368480886741509,
      "eval_loss": 1.5854151248931885,
      "eval_runtime": 54.9652,
      "eval_samples_per_second": 13.481,
      "eval_steps_per_second": 6.75,
      "step": 20
    },
    {
      "epoch": 0.014210601108426887,
      "grad_norm": 0.6591376662254333,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7109,
      "step": 25
    },
    {
      "epoch": 0.017052721330112264,
      "grad_norm": 0.5782737731933594,
      "learning_rate": 5e-05,
      "loss": 1.629,
      "step": 30
    },
    {
      "epoch": 0.017052721330112264,
      "eval_loss": 1.5050691366195679,
      "eval_runtime": 55.0316,
      "eval_samples_per_second": 13.465,
      "eval_steps_per_second": 6.742,
      "step": 30
    },
    {
      "epoch": 0.019894841551797642,
      "grad_norm": 0.9463327527046204,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.3634,
      "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": 7785963312906240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}