Hugging Face's logo

Nexspear
/
04d6a5c5-6ec8-4a19-affc-264fd2f3ac4a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
04d6a5c5-6ec8-4a19-affc-264fd2f3ac4a
File size: 2,415 Bytes 
5d1d6db
 
 
58484e2
5d1d6db
58484e2
5d1d6db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54f8ba5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58484e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d1d6db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58484e2
5d1d6db
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1073345259391771,
  "eval_steps": 5,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007155635062611807,
      "eval_loss": 8.003866195678711,
      "eval_runtime": 21.074,
      "eval_samples_per_second": 11.199,
      "eval_steps_per_second": 1.424,
      "step": 1
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 36.30503845214844,
      "learning_rate": 3e-05,
      "loss": 29.32,
      "step": 3
    },
    {
      "epoch": 0.03577817531305903,
      "eval_loss": 6.45150899887085,
      "eval_runtime": 21.281,
      "eval_samples_per_second": 11.09,
      "eval_steps_per_second": 1.41,
      "step": 5
    },
    {
      "epoch": 0.04293381037567084,
      "grad_norm": 59.01460647583008,
      "learning_rate": 6e-05,
      "loss": 29.5122,
      "step": 6
    },
    {
      "epoch": 0.06440071556350627,
      "grad_norm": 31.912750244140625,
      "learning_rate": 9e-05,
      "loss": 15.7048,
      "step": 9
    },
    {
      "epoch": 0.07155635062611806,
      "eval_loss": 1.4119746685028076,
      "eval_runtime": 21.3324,
      "eval_samples_per_second": 11.063,
      "eval_steps_per_second": 1.406,
      "step": 10
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 12.302176475524902,
      "learning_rate": 9.938441702975689e-05,
      "loss": 5.5122,
      "step": 12
    },
    {
      "epoch": 0.1073345259391771,
      "grad_norm": 7.404484272003174,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.4541,
      "step": 15
    },
    {
      "epoch": 0.1073345259391771,
      "eval_loss": 0.1575503647327423,
      "eval_runtime": 21.3407,
      "eval_samples_per_second": 11.059,
      "eval_steps_per_second": 1.406,
      "step": 15
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.995762988744704e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}