Hugging Face's logo

dimasik1987
/
eafea6e5-1d87-4eb2-a92d-8f29e493ec54

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
eafea6e5-1d87-4eb2-a92d-8f29e493ec54
File size: 2,244 Bytes 
79f635b
 
 
f17974a
79f635b
f17974a
79f635b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f17974a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79f635b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f17974a
79f635b
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015854141894569955,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007927070947284979,
      "eval_loss": NaN,
      "eval_runtime": 61.2857,
      "eval_samples_per_second": 8.681,
      "eval_steps_per_second": 4.34,
      "step": 1
    },
    {
      "epoch": 0.0023781212841854932,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0047562425683709865,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.006341656757827983,
      "eval_loss": NaN,
      "eval_runtime": 60.8856,
      "eval_samples_per_second": 8.738,
      "eval_steps_per_second": 4.369,
      "step": 8
    },
    {
      "epoch": 0.007134363852556481,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.009512485136741973,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.011890606420927468,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.012683313515655966,
      "eval_loss": NaN,
      "eval_runtime": 61.086,
      "eval_samples_per_second": 8.709,
      "eval_steps_per_second": 4.355,
      "step": 16
    },
    {
      "epoch": 0.014268727705112961,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7207077361483776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}