Hugging Face's logo

Nexspear
/
7e852ab3-311c-49ae-b796-8794108180b7

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
7e852ab3-311c-49ae-b796-8794108180b7
File size: 2,396 Bytes 
6bcace8
 
 
1c877ce
6bcace8
1c877ce
6bcace8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1c877ce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6bcace8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1c877ce
6bcace8
 
 
 
 
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": 0.024836150396688513,
  "eval_steps": 9,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013797861331493618,
      "eval_loss": 0.7372766733169556,
      "eval_runtime": 168.7844,
      "eval_samples_per_second": 7.234,
      "eval_steps_per_second": 0.906,
      "step": 1
    },
    {
      "epoch": 0.004139358399448086,
      "grad_norm": 33.24546432495117,
      "learning_rate": 1.5e-05,
      "loss": 3.0101,
      "step": 3
    },
    {
      "epoch": 0.008278716798896172,
      "grad_norm": 17.34926986694336,
      "learning_rate": 3e-05,
      "loss": 2.2218,
      "step": 6
    },
    {
      "epoch": 0.012418075198344257,
      "grad_norm": 5.28987979888916,
      "learning_rate": 4.5e-05,
      "loss": 1.4942,
      "step": 9
    },
    {
      "epoch": 0.012418075198344257,
      "eval_loss": 0.26399311423301697,
      "eval_runtime": 170.9677,
      "eval_samples_per_second": 7.142,
      "eval_steps_per_second": 0.895,
      "step": 9
    },
    {
      "epoch": 0.016557433597792343,
      "grad_norm": 4.505770683288574,
      "learning_rate": 4.993910125649561e-05,
      "loss": 1.0678,
      "step": 12
    },
    {
      "epoch": 0.020696791997240428,
      "grad_norm": 3.744687795639038,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.7375,
      "step": 15
    },
    {
      "epoch": 0.024836150396688513,
      "grad_norm": 3.299644708633423,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 0.9198,
      "step": 18
    },
    {
      "epoch": 0.024836150396688513,
      "eval_loss": 0.21940629184246063,
      "eval_runtime": 170.9547,
      "eval_samples_per_second": 7.142,
      "eval_steps_per_second": 0.895,
      "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": 5.062532390505677e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}