Hugging Face's logo

phungkhaccuong
/
5a17e82d-6f5f-9fd6-a584-cc2d17416988

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
5a17e82d-6f5f-9fd6-a584-cc2d17416988
File size: 2,776 Bytes 
44b39d0
 
 
4579c55
210992a
4579c55
44b39d0
 
 
 
 
 
 
210992a
 
 
44b39d0
210992a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1372c50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4579c55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44b39d0
 
 
210992a
44b39d0
 
210992a
44b39d0
 
 
 
 
 
 
210992a
44b39d0
 
 
 
4579c55
44b39d0
 
 
 
 
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": 0.01845062093435837,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004730928444707274,
      "eval_loss": 3.7715675830841064,
      "eval_runtime": 60.1303,
      "eval_samples_per_second": 14.801,
      "eval_steps_per_second": 7.401,
      "step": 1
    },
    {
      "epoch": 0.002365464222353637,
      "grad_norm": 4.726196765899658,
      "learning_rate": 5e-05,
      "loss": 3.9595,
      "step": 5
    },
    {
      "epoch": 0.004730928444707274,
      "grad_norm": 5.4399495124816895,
      "learning_rate": 0.0001,
      "loss": 3.7568,
      "step": 10
    },
    {
      "epoch": 0.004730928444707274,
      "eval_loss": 3.23077654838562,
      "eval_runtime": 60.5455,
      "eval_samples_per_second": 14.7,
      "eval_steps_per_second": 7.35,
      "step": 10
    },
    {
      "epoch": 0.007096392667060911,
      "grad_norm": 3.918861150741577,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.9987,
      "step": 15
    },
    {
      "epoch": 0.009461856889414548,
      "grad_norm": 3.6118011474609375,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8883,
      "step": 20
    },
    {
      "epoch": 0.009461856889414548,
      "eval_loss": 1.7703381776809692,
      "eval_runtime": 60.7528,
      "eval_samples_per_second": 14.65,
      "eval_steps_per_second": 7.325,
      "step": 20
    },
    {
      "epoch": 0.011827321111768185,
      "grad_norm": 2.6210219860076904,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6853,
      "step": 25
    },
    {
      "epoch": 0.014192785334121822,
      "grad_norm": 2.8847033977508545,
      "learning_rate": 5e-05,
      "loss": 1.545,
      "step": 30
    },
    {
      "epoch": 0.014192785334121822,
      "eval_loss": 1.4944615364074707,
      "eval_runtime": 60.8895,
      "eval_samples_per_second": 14.617,
      "eval_steps_per_second": 7.308,
      "step": 30
    },
    {
      "epoch": 0.01655824955647546,
      "grad_norm": 3.2016212940216064,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4231,
      "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": 7259539673972736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}