Hugging Face's logo

tuanna08go
/
7250e8f6-e6de-40f0-abf5-2d0a8225e9af

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7250e8f6-e6de-40f0-abf5-2d0a8225e9af
File size: 2,793 Bytes 
8a2efbc
 
 
a00237a
4519d12
a00237a
8a2efbc
 
 
 
 
 
 
4519d12
 
 
8a2efbc
4519d12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b7d9342
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a00237a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a2efbc
 
 
4519d12
8a2efbc
 
4519d12
8a2efbc
 
 
 
 
 
 
4519d12
8a2efbc
 
 
 
a00237a
8a2efbc
 
 
 
 
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": 0.006972690296339338,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017878693067536764,
      "eval_loss": 2.933220624923706,
      "eval_runtime": 233.474,
      "eval_samples_per_second": 10.091,
      "eval_steps_per_second": 5.046,
      "step": 1
    },
    {
      "epoch": 0.0008939346533768382,
      "grad_norm": 0.2832305431365967,
      "learning_rate": 5e-05,
      "loss": 2.8622,
      "step": 5
    },
    {
      "epoch": 0.0017878693067536764,
      "grad_norm": 0.40609437227249146,
      "learning_rate": 0.0001,
      "loss": 2.7993,
      "step": 10
    },
    {
      "epoch": 0.0017878693067536764,
      "eval_loss": 2.906853437423706,
      "eval_runtime": 242.4442,
      "eval_samples_per_second": 9.718,
      "eval_steps_per_second": 4.859,
      "step": 10
    },
    {
      "epoch": 0.0026818039601305146,
      "grad_norm": 0.3924393951892853,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.764,
      "step": 15
    },
    {
      "epoch": 0.0035757386135073527,
      "grad_norm": 0.4617941379547119,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7949,
      "step": 20
    },
    {
      "epoch": 0.0035757386135073527,
      "eval_loss": 2.8182547092437744,
      "eval_runtime": 241.8579,
      "eval_samples_per_second": 9.741,
      "eval_steps_per_second": 4.871,
      "step": 20
    },
    {
      "epoch": 0.0044696732668841905,
      "grad_norm": 0.5247169137001038,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.6913,
      "step": 25
    },
    {
      "epoch": 0.005363607920261029,
      "grad_norm": 0.5109822750091553,
      "learning_rate": 5e-05,
      "loss": 2.7626,
      "step": 30
    },
    {
      "epoch": 0.005363607920261029,
      "eval_loss": 2.7879366874694824,
      "eval_runtime": 241.7636,
      "eval_samples_per_second": 9.745,
      "eval_steps_per_second": 4.873,
      "step": 30
    },
    {
      "epoch": 0.006257542573637867,
      "grad_norm": 0.4426691234111786,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.8036,
      "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": 8503374869692416.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}