Hugging Face's logo

Weni
/
Test-tensorboard-metrics-Mistral-7b-Multilanguage-3.0.3

PEFT
PyTorch
TensorBoard
Safetensors
mistral
Model card Files Metrics Community
Test-tensorboard-metrics-Mistral-7b-Multilanguage-3.0.3
File size: 2,557 Bytes 
e8aca2f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.0401246547698975,
  "best_model_checkpoint": "./Mistral/04-12-23-mistralai-Mistral-7B-v0.1_teste-multilang-dataset-3.0.3-portuguese-2_epochs-10_batch_2/checkpoints/checkpoint-67",
  "epoch": 9.777777777777779,
  "eval_steps": 500,
  "global_step": 220,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.98,
      "eval_loss": 1.666649580001831,
      "eval_runtime": 0.5837,
      "eval_samples_per_second": 17.132,
      "eval_steps_per_second": 3.426,
      "step": 22
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.125360131263733,
      "eval_runtime": 0.5844,
      "eval_samples_per_second": 17.112,
      "eval_steps_per_second": 3.422,
      "step": 45
    },
    {
      "epoch": 2.98,
      "eval_loss": 1.0401246547698975,
      "eval_runtime": 0.5839,
      "eval_samples_per_second": 17.127,
      "eval_steps_per_second": 3.425,
      "step": 67
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.064213514328003,
      "eval_runtime": 0.5866,
      "eval_samples_per_second": 17.049,
      "eval_steps_per_second": 3.41,
      "step": 90
    },
    {
      "epoch": 4.98,
      "eval_loss": 1.0575947761535645,
      "eval_runtime": 0.5832,
      "eval_samples_per_second": 17.146,
      "eval_steps_per_second": 3.429,
      "step": 112
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.145155906677246,
      "eval_runtime": 0.5836,
      "eval_samples_per_second": 17.136,
      "eval_steps_per_second": 3.427,
      "step": 135
    },
    {
      "epoch": 6.98,
      "eval_loss": 1.1963560581207275,
      "eval_runtime": 0.5826,
      "eval_samples_per_second": 17.165,
      "eval_steps_per_second": 3.433,
      "step": 157
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.2468668222427368,
      "eval_runtime": 0.5861,
      "eval_samples_per_second": 17.061,
      "eval_steps_per_second": 3.412,
      "step": 180
    },
    {
      "epoch": 8.98,
      "eval_loss": 1.319059133529663,
      "eval_runtime": 0.5831,
      "eval_samples_per_second": 17.15,
      "eval_steps_per_second": 3.43,
      "step": 202
    },
    {
      "epoch": 9.78,
      "eval_loss": 1.31288743019104,
      "eval_runtime": 0.5859,
      "eval_samples_per_second": 17.069,
      "eval_steps_per_second": 3.414,
      "step": 220
    }
  ],
  "logging_steps": 500,
  "max_steps": 220,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.2265876796522496e+16,
  "trial_name": null,
  "trial_params": null
}