Hugging Face's logo

brixeus
/
48ed755e-3ac9-4185-a25e-64b81c53b5a4

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
48ed755e-3ac9-4185-a25e-64b81c53b5a4
File size: 2,405 Bytes 
8458be1
 
 
64dc773
8458be1
64dc773
8458be1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64dc773
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8458be1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64dc773
8458be1
 
 
 
 
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": 0.0054869684499314125,
  "eval_steps": 9,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030483158055174517,
      "eval_loss": 1.6358747482299805,
      "eval_runtime": 393.362,
      "eval_samples_per_second": 14.046,
      "eval_steps_per_second": 1.757,
      "step": 1
    },
    {
      "epoch": 0.0009144947416552355,
      "grad_norm": 17.194887161254883,
      "learning_rate": 1.5e-05,
      "loss": 6.7621,
      "step": 3
    },
    {
      "epoch": 0.001828989483310471,
      "grad_norm": 10.281621932983398,
      "learning_rate": 3e-05,
      "loss": 5.8586,
      "step": 6
    },
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 6.017336845397949,
      "learning_rate": 4.5e-05,
      "loss": 6.2144,
      "step": 9
    },
    {
      "epoch": 0.0027434842249657062,
      "eval_loss": 1.4405845403671265,
      "eval_runtime": 397.296,
      "eval_samples_per_second": 13.907,
      "eval_steps_per_second": 1.739,
      "step": 9
    },
    {
      "epoch": 0.003657978966620942,
      "grad_norm": 5.029771327972412,
      "learning_rate": 4.993910125649561e-05,
      "loss": 5.5157,
      "step": 12
    },
    {
      "epoch": 0.004572473708276178,
      "grad_norm": 4.417510032653809,
      "learning_rate": 4.962019382530521e-05,
      "loss": 5.1545,
      "step": 15
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 4.255384922027588,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 5.7058,
      "step": 18
    },
    {
      "epoch": 0.0054869684499314125,
      "eval_loss": 1.3602502346038818,
      "eval_runtime": 397.5904,
      "eval_samples_per_second": 13.896,
      "eval_steps_per_second": 1.738,
      "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": 2.531269094355763e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}