Hugging Face's logo

tuanna08go
/
1aed0141-ee20-4046-8b50-c028c83bb455

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
1aed0141-ee20-4046-8b50-c028c83bb455
File size: 2,789 Bytes 
e88191a
 
 
b14c170
1aec78a
b14c170
e88191a
 
 
 
 
 
 
1aec78a
 
 
e88191a
1aec78a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2e5e975
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b14c170
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e88191a
 
 
1aec78a
e88191a
 
1aec78a
e88191a
 
 
 
 
 
 
1aec78a
e88191a
 
 
 
b14c170
e88191a
 
 
 
 
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": 0.0016437490121700648,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.21474105684632e-05,
      "eval_loss": 0.8874483108520508,
      "eval_runtime": 1530.7819,
      "eval_samples_per_second": 6.526,
      "eval_steps_per_second": 3.263,
      "step": 1
    },
    {
      "epoch": 0.000210737052842316,
      "grad_norm": 4.626171112060547,
      "learning_rate": 5e-05,
      "loss": 3.5018,
      "step": 5
    },
    {
      "epoch": 0.000421474105684632,
      "grad_norm": 3.7195966243743896,
      "learning_rate": 0.0001,
      "loss": 3.3865,
      "step": 10
    },
    {
      "epoch": 0.000421474105684632,
      "eval_loss": 0.7994943261146545,
      "eval_runtime": 1558.7542,
      "eval_samples_per_second": 6.409,
      "eval_steps_per_second": 3.204,
      "step": 10
    },
    {
      "epoch": 0.000632211158526948,
      "grad_norm": 5.0703887939453125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.0742,
      "step": 15
    },
    {
      "epoch": 0.000842948211369264,
      "grad_norm": 3.5031182765960693,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.9059,
      "step": 20
    },
    {
      "epoch": 0.000842948211369264,
      "eval_loss": 0.7205164432525635,
      "eval_runtime": 1556.9817,
      "eval_samples_per_second": 6.416,
      "eval_steps_per_second": 3.208,
      "step": 20
    },
    {
      "epoch": 0.00105368526421158,
      "grad_norm": 4.231757640838623,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.7684,
      "step": 25
    },
    {
      "epoch": 0.001264422317053896,
      "grad_norm": 3.9624576568603516,
      "learning_rate": 5e-05,
      "loss": 2.8031,
      "step": 30
    },
    {
      "epoch": 0.001264422317053896,
      "eval_loss": 0.6921516060829163,
      "eval_runtime": 1561.0748,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 3.2,
      "step": 30
    },
    {
      "epoch": 0.001475159369896212,
      "grad_norm": 4.666100978851318,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.7865,
      "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": 1.2137252209557504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}