Hugging Face's logo

Nexspear
/
55115a3a-053b-43e4-9a9d-d6f9717f600f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
55115a3a-053b-43e4-9a9d-d6f9717f600f
File size: 2,821 Bytes 
bda5268
 
 
58f8db7
bda5268
58f8db7
bda5268
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
762a9dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c294124
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58f8db7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bda5268
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58f8db7
bda5268
 
 
 
 
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": 0.038113387327298714,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019056693663649356,
      "eval_loss": 3.0111310482025146,
      "eval_runtime": 139.5262,
      "eval_samples_per_second": 6.336,
      "eval_steps_per_second": 0.796,
      "step": 1
    },
    {
      "epoch": 0.005717008099094807,
      "grad_norm": 1.745223045349121,
      "learning_rate": 3e-05,
      "loss": 2.8529,
      "step": 3
    },
    {
      "epoch": 0.009528346831824679,
      "eval_loss": 2.849209785461426,
      "eval_runtime": 140.6511,
      "eval_samples_per_second": 6.285,
      "eval_steps_per_second": 0.789,
      "step": 5
    },
    {
      "epoch": 0.011434016198189614,
      "grad_norm": 1.5631052255630493,
      "learning_rate": 6e-05,
      "loss": 2.8163,
      "step": 6
    },
    {
      "epoch": 0.01715102429728442,
      "grad_norm": 1.3446643352508545,
      "learning_rate": 9e-05,
      "loss": 2.5454,
      "step": 9
    },
    {
      "epoch": 0.019056693663649357,
      "eval_loss": 2.5639851093292236,
      "eval_runtime": 140.6263,
      "eval_samples_per_second": 6.286,
      "eval_steps_per_second": 0.789,
      "step": 10
    },
    {
      "epoch": 0.022868032396379228,
      "grad_norm": 1.6127707958221436,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.5243,
      "step": 12
    },
    {
      "epoch": 0.028585040495474036,
      "grad_norm": 1.2866557836532593,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3552,
      "step": 15
    },
    {
      "epoch": 0.028585040495474036,
      "eval_loss": 2.4209542274475098,
      "eval_runtime": 140.5703,
      "eval_samples_per_second": 6.289,
      "eval_steps_per_second": 0.79,
      "step": 15
    },
    {
      "epoch": 0.03430204859456884,
      "grad_norm": 1.7916969060897827,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.6218,
      "step": 18
    },
    {
      "epoch": 0.038113387327298714,
      "eval_loss": 2.3375890254974365,
      "eval_runtime": 140.5851,
      "eval_samples_per_second": 6.288,
      "eval_steps_per_second": 0.79,
      "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": 6.034054314983424e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}