Hugging Face's logo

Nexspear
/
c7ad37b1-e5c1-4c70-b5de-ad2745e33277

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c7ad37b1-e5c1-4c70-b5de-ad2745e33277
File size: 2,813 Bytes 
fa71283
 
 
33eeb86
fa71283
33eeb86
fa71283
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67b8ed0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8851976
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33eeb86
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa71283
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33eeb86
fa71283
 
 
 
 
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
107
108
109
110
111
112
113
114
115
116
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.050156739811912224,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025078369905956114,
      "eval_loss": 2.34328031539917,
      "eval_runtime": 49.0034,
      "eval_samples_per_second": 13.713,
      "eval_steps_per_second": 1.714,
      "step": 1
    },
    {
      "epoch": 0.007523510971786834,
      "grad_norm": 1.412799596786499,
      "learning_rate": 3e-05,
      "loss": 2.3531,
      "step": 3
    },
    {
      "epoch": 0.012539184952978056,
      "eval_loss": 2.1037039756774902,
      "eval_runtime": 49.6313,
      "eval_samples_per_second": 13.54,
      "eval_steps_per_second": 1.692,
      "step": 5
    },
    {
      "epoch": 0.015047021943573668,
      "grad_norm": 1.2794967889785767,
      "learning_rate": 6e-05,
      "loss": 2.2497,
      "step": 6
    },
    {
      "epoch": 0.0225705329153605,
      "grad_norm": 0.7042816281318665,
      "learning_rate": 9e-05,
      "loss": 1.9238,
      "step": 9
    },
    {
      "epoch": 0.025078369905956112,
      "eval_loss": 1.7871791124343872,
      "eval_runtime": 49.7536,
      "eval_samples_per_second": 13.507,
      "eval_steps_per_second": 1.688,
      "step": 10
    },
    {
      "epoch": 0.030094043887147336,
      "grad_norm": 0.6223757266998291,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.7599,
      "step": 12
    },
    {
      "epoch": 0.03761755485893417,
      "grad_norm": 0.5316658020019531,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7352,
      "step": 15
    },
    {
      "epoch": 0.03761755485893417,
      "eval_loss": 1.6541856527328491,
      "eval_runtime": 49.8208,
      "eval_samples_per_second": 13.488,
      "eval_steps_per_second": 1.686,
      "step": 15
    },
    {
      "epoch": 0.045141065830721,
      "grad_norm": 0.4628920555114746,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.663,
      "step": 18
    },
    {
      "epoch": 0.050156739811912224,
      "eval_loss": 1.6090316772460938,
      "eval_runtime": 49.8182,
      "eval_samples_per_second": 13.489,
      "eval_steps_per_second": 1.686,
      "step": 20
    }
  ],
  "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": 2.7251793985536e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}