Hugging Face's logo

tuanna08go
/
d1b9408a-8b32-42be-94a7-434382605027

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
d1b9408a-8b32-42be-94a7-434382605027
File size: 2,767 Bytes 
4fa824e
 
 
9db2f60
d26659f
9db2f60
4fa824e
 
 
 
 
 
 
d26659f
 
 
4fa824e
d26659f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6949b43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9db2f60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4fa824e
 
 
d26659f
4fa824e
 
d26659f
4fa824e
 
 
 
 
 
 
d26659f
4fa824e
 
 
 
9db2f60
4fa824e
 
 
 
 
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": 0.08249603384452671,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021152829190904283,
      "eval_loss": 0.8276494741439819,
      "eval_runtime": 16.2246,
      "eval_samples_per_second": 12.265,
      "eval_steps_per_second": 6.163,
      "step": 1
    },
    {
      "epoch": 0.010576414595452142,
      "grad_norm": 63.81797790527344,
      "learning_rate": 5e-05,
      "loss": 4.1889,
      "step": 5
    },
    {
      "epoch": 0.021152829190904283,
      "grad_norm": 21.4931697845459,
      "learning_rate": 0.0001,
      "loss": 0.841,
      "step": 10
    },
    {
      "epoch": 0.021152829190904283,
      "eval_loss": 0.2516094148159027,
      "eval_runtime": 16.9953,
      "eval_samples_per_second": 11.709,
      "eval_steps_per_second": 5.884,
      "step": 10
    },
    {
      "epoch": 0.03172924378635643,
      "grad_norm": 6.5418853759765625,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0068,
      "step": 15
    },
    {
      "epoch": 0.04230565838180857,
      "grad_norm": 1.9580116271972656,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7493,
      "step": 20
    },
    {
      "epoch": 0.04230565838180857,
      "eval_loss": 0.2253044992685318,
      "eval_runtime": 17.4081,
      "eval_samples_per_second": 11.431,
      "eval_steps_per_second": 5.744,
      "step": 20
    },
    {
      "epoch": 0.05288207297726071,
      "grad_norm": 4.782344818115234,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.57,
      "step": 25
    },
    {
      "epoch": 0.06345848757271286,
      "grad_norm": 1.8820977210998535,
      "learning_rate": 5e-05,
      "loss": 1.2061,
      "step": 30
    },
    {
      "epoch": 0.06345848757271286,
      "eval_loss": 0.2232237458229065,
      "eval_runtime": 17.669,
      "eval_samples_per_second": 11.263,
      "eval_steps_per_second": 5.66,
      "step": 30
    },
    {
      "epoch": 0.074034902168165,
      "grad_norm": 1.589575171470642,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7223,
      "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": 7189115808251904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}