Hugging Face's logo

Nexspear
/
fc1fccdf-3b76-4ae5-8c3a-1cd875b2e097

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
fc1fccdf-3b76-4ae5-8c3a-1cd875b2e097
File size: 3,386 Bytes 
6da9ef6
 
 
07797e9
6da9ef6
07797e9
6da9ef6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c005134
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf04ab9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fd84a66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
07797e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6da9ef6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
07797e9
6da9ef6
 
 
 
 
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
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011756407241946862,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047025628967787447,
      "eval_loss": 1.3333030939102173,
      "eval_runtime": 72.5334,
      "eval_samples_per_second": 49.384,
      "eval_steps_per_second": 6.176,
      "step": 1
    },
    {
      "epoch": 0.0014107688690336232,
      "grad_norm": 1.7957247495651245,
      "learning_rate": 3e-05,
      "loss": 1.3816,
      "step": 3
    },
    {
      "epoch": 0.0023512814483893723,
      "eval_loss": 1.252621054649353,
      "eval_runtime": 72.4361,
      "eval_samples_per_second": 49.451,
      "eval_steps_per_second": 6.185,
      "step": 5
    },
    {
      "epoch": 0.0028215377380672465,
      "grad_norm": 0.8181892037391663,
      "learning_rate": 6e-05,
      "loss": 1.2521,
      "step": 6
    },
    {
      "epoch": 0.00423230660710087,
      "grad_norm": 0.6588422060012817,
      "learning_rate": 9e-05,
      "loss": 1.2152,
      "step": 9
    },
    {
      "epoch": 0.0047025628967787446,
      "eval_loss": 1.1770787239074707,
      "eval_runtime": 72.7257,
      "eval_samples_per_second": 49.254,
      "eval_steps_per_second": 6.16,
      "step": 10
    },
    {
      "epoch": 0.005643075476134493,
      "grad_norm": 0.6331816911697388,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.1578,
      "step": 12
    },
    {
      "epoch": 0.007053844345168116,
      "grad_norm": 0.5597560405731201,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2228,
      "step": 15
    },
    {
      "epoch": 0.007053844345168116,
      "eval_loss": 1.157048225402832,
      "eval_runtime": 72.6624,
      "eval_samples_per_second": 49.296,
      "eval_steps_per_second": 6.166,
      "step": 15
    },
    {
      "epoch": 0.00846461321420174,
      "grad_norm": 0.6084182262420654,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2561,
      "step": 18
    },
    {
      "epoch": 0.009405125793557489,
      "eval_loss": 1.14651358127594,
      "eval_runtime": 72.6867,
      "eval_samples_per_second": 49.28,
      "eval_steps_per_second": 6.163,
      "step": 20
    },
    {
      "epoch": 0.009875382083235363,
      "grad_norm": 0.5509119033813477,
      "learning_rate": 8.247240241650918e-05,
      "loss": 1.1259,
      "step": 21
    },
    {
      "epoch": 0.011286150952268986,
      "grad_norm": 0.48853400349617004,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.1989,
      "step": 24
    },
    {
      "epoch": 0.011756407241946862,
      "eval_loss": 1.1405397653579712,
      "eval_runtime": 72.6738,
      "eval_samples_per_second": 49.289,
      "eval_steps_per_second": 6.165,
      "step": 25
    }
  ],
  "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": 5332869631180800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}