Hugging Face's logo

brixeus
/
1a3afaaa-f8be-49a8-b91a-3b3899767c15

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
1a3afaaa-f8be-49a8-b91a-3b3899767c15
File size: 2,380 Bytes 
5550f93
 
 
47dcf4e
5550f93
47dcf4e
5550f93
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47dcf4e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5550f93
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47dcf4e
5550f93
 
 
 
 
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": null,
  "best_model_checkpoint": null,
  "epoch": 0.0207732256203116,
  "eval_steps": 9,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001154068090017311,
      "eval_loss": 2.0465598106384277,
      "eval_runtime": 103.0211,
      "eval_samples_per_second": 14.172,
      "eval_steps_per_second": 1.776,
      "step": 1
    },
    {
      "epoch": 0.003462204270051933,
      "grad_norm": 8.097893714904785,
      "learning_rate": 3e-05,
      "loss": 8.0719,
      "step": 3
    },
    {
      "epoch": 0.006924408540103866,
      "grad_norm": 5.514200210571289,
      "learning_rate": 6e-05,
      "loss": 8.0211,
      "step": 6
    },
    {
      "epoch": 0.0103866128101558,
      "grad_norm": 5.214906692504883,
      "learning_rate": 9e-05,
      "loss": 8.0571,
      "step": 9
    },
    {
      "epoch": 0.0103866128101558,
      "eval_loss": 1.9573053121566772,
      "eval_runtime": 104.5011,
      "eval_samples_per_second": 13.971,
      "eval_steps_per_second": 1.751,
      "step": 9
    },
    {
      "epoch": 0.013848817080207732,
      "grad_norm": 4.61670446395874,
      "learning_rate": 9.987820251299122e-05,
      "loss": 7.7237,
      "step": 12
    },
    {
      "epoch": 0.017311021350259664,
      "grad_norm": 4.776439666748047,
      "learning_rate": 9.924038765061042e-05,
      "loss": 7.5723,
      "step": 15
    },
    {
      "epoch": 0.0207732256203116,
      "grad_norm": 3.863844394683838,
      "learning_rate": 9.806308479691595e-05,
      "loss": 7.8625,
      "step": 18
    },
    {
      "epoch": 0.0207732256203116,
      "eval_loss": 1.938367247581482,
      "eval_runtime": 104.6138,
      "eval_samples_per_second": 13.956,
      "eval_steps_per_second": 1.749,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.523847390868275e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}