Hugging Face's logo

trenden
/
cf851d40-256d-4233-b70c-8d5e93b45f3c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cf851d40-256d-4233-b70c-8d5e93b45f3c
File size: 2,980 Bytes 
7f402f6
 
 
9566257
7f402f6
9566257
7f402f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a456aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c9e1d9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9566257
 
 
 
 
 
 
7f402f6
 
 
 
 
 
 
 
 
 
 
 
 
 
9566257
7f402f6
 
 
 
9566257
7f402f6
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006747638326585695,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.747638326585695e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 6.747638326585695e-05,
      "eval_loss": NaN,
      "eval_runtime": 254.5032,
      "eval_samples_per_second": 24.518,
      "eval_steps_per_second": 12.259,
      "step": 1
    },
    {
      "epoch": 0.0001349527665317139,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 1.4803,
      "step": 2
    },
    {
      "epoch": 0.00020242914979757084,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00020242914979757084,
      "eval_loss": NaN,
      "eval_runtime": 253.2462,
      "eval_samples_per_second": 24.64,
      "eval_steps_per_second": 12.32,
      "step": 3
    },
    {
      "epoch": 0.0002699055330634278,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00033738191632928474,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0004048582995951417,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0004048582995951417,
      "eval_loss": NaN,
      "eval_runtime": 253.2964,
      "eval_samples_per_second": 24.635,
      "eval_steps_per_second": 12.318,
      "step": 6
    },
    {
      "epoch": 0.00047233468286099863,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0005398110661268556,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0006072874493927126,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0006072874493927126,
      "eval_loss": NaN,
      "eval_runtime": 253.6018,
      "eval_samples_per_second": 24.606,
      "eval_steps_per_second": 12.303,
      "step": 9
    },
    {
      "epoch": 0.0006747638326585695,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2320944718675968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}