Hugging Face's logo

bbytxt
/
6799bb9d-5883-4250-b4bd-d699d70348da

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
custom_code
Model card Files Community
6799bb9d-5883-4250-b4bd-d699d70348da
File size: 2,726 Bytes 
8b25f5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
116
117
118
119
120
121
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.076923076923077,
  "eval_steps": 50,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 145.8916473388672,
      "learning_rate": 1e-05,
      "loss": 6.3039,
      "step": 1
    },
    {
      "epoch": 0.3076923076923077,
      "eval_loss": 1.207192063331604,
      "eval_runtime": 0.5709,
      "eval_samples_per_second": 10.509,
      "eval_steps_per_second": 3.503,
      "step": 1
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 152.0794677734375,
      "learning_rate": 2e-05,
      "loss": 7.072,
      "step": 2
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 105.73599243164062,
      "learning_rate": 3e-05,
      "loss": 3.4334,
      "step": 3
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 49.147640228271484,
      "learning_rate": 4e-05,
      "loss": 1.4872,
      "step": 4
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 32.453651428222656,
      "learning_rate": 5e-05,
      "loss": 0.9264,
      "step": 5
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 19.655824661254883,
      "learning_rate": 6e-05,
      "loss": 0.8667,
      "step": 6
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 15.027318000793457,
      "learning_rate": 7e-05,
      "loss": 0.5885,
      "step": 7
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 9.182798385620117,
      "learning_rate": 8e-05,
      "loss": 0.4349,
      "step": 8
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 10.852940559387207,
      "learning_rate": 9e-05,
      "loss": 0.3853,
      "step": 9
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 12.851784706115723,
      "learning_rate": 0.0001,
      "loss": 0.346,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3907511899848704e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}