Hugging Face's logo

justmalhar
/
mistral-ashoka-7b-finetune

PEFT
Safetensors
Model card Files Community
mistral-ashoka-7b-finetune
File size: 2,424 Bytes 
30eb33a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.048028817290374226,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.272727272727273e-05,
      "loss": 1.2333,
      "step": 50
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.9392214417457581,
      "eval_runtime": 4053.3544,
      "eval_samples_per_second": 12.328,
      "eval_steps_per_second": 1.541,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 0.9153,
      "step": 100
    },
    {
      "epoch": 0.02,
      "eval_loss": 0.8664643168449402,
      "eval_runtime": 4052.1353,
      "eval_samples_per_second": 12.332,
      "eval_steps_per_second": 1.542,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.7676767676767676e-05,
      "loss": 0.8489,
      "step": 150
    },
    {
      "epoch": 0.02,
      "eval_loss": 0.8392552733421326,
      "eval_runtime": 4051.5661,
      "eval_samples_per_second": 12.333,
      "eval_steps_per_second": 1.542,
      "step": 150
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.8405,
      "step": 200
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.8204770684242249,
      "eval_runtime": 4049.9004,
      "eval_samples_per_second": 12.338,
      "eval_steps_per_second": 1.543,
      "step": 200
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.826,
      "step": 250
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.8067930340766907,
      "eval_runtime": 4050.2988,
      "eval_samples_per_second": 12.337,
      "eval_steps_per_second": 1.542,
      "step": 250
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.0101010101010101e-05,
      "loss": 0.8077,
      "step": 300
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.7965855002403259,
      "eval_runtime": 4052.9604,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 1.541,
      "step": 300
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 5.25822226071552e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}