Hugging Face's logo

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

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
55115a3a-053b-43e4-9a9d-d6f9717f600f
File size: 2,979 Bytes 
5b962a1
 
 
9185989
5b962a1
9185989
5b962a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74b023f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9185989
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5b962a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9185989
5b962a1
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004287756074321105,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004764173415912339,
      "grad_norm": 1.3637402057647705,
      "learning_rate": 2e-05,
      "loss": 2.8479,
      "step": 1
    },
    {
      "epoch": 0.0004764173415912339,
      "eval_loss": NaN,
      "eval_runtime": 49.5822,
      "eval_samples_per_second": 17.829,
      "eval_steps_per_second": 8.914,
      "step": 1
    },
    {
      "epoch": 0.0009528346831824678,
      "grad_norm": 0.9972659349441528,
      "learning_rate": 4e-05,
      "loss": 2.8832,
      "step": 2
    },
    {
      "epoch": 0.0014292520247737017,
      "grad_norm": 1.3149476051330566,
      "learning_rate": 6e-05,
      "loss": 3.3305,
      "step": 3
    },
    {
      "epoch": 0.0014292520247737017,
      "eval_loss": NaN,
      "eval_runtime": 48.3871,
      "eval_samples_per_second": 18.269,
      "eval_steps_per_second": 9.135,
      "step": 3
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 0.9289590716362,
      "learning_rate": 8e-05,
      "loss": 2.595,
      "step": 4
    },
    {
      "epoch": 0.0023820867079561697,
      "grad_norm": 0.8951483964920044,
      "learning_rate": 0.0001,
      "loss": 2.8625,
      "step": 5
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 1.0807698965072632,
      "learning_rate": 0.00012,
      "loss": 2.9945,
      "step": 6
    },
    {
      "epoch": 0.0028585040495474035,
      "eval_loss": NaN,
      "eval_runtime": 48.4269,
      "eval_samples_per_second": 18.254,
      "eval_steps_per_second": 9.127,
      "step": 6
    },
    {
      "epoch": 0.0033349213911386373,
      "grad_norm": 1.1401915550231934,
      "learning_rate": 0.00014,
      "loss": 2.9902,
      "step": 7
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 0.9969739317893982,
      "learning_rate": 0.00016,
      "loss": 2.6715,
      "step": 8
    },
    {
      "epoch": 0.004287756074321105,
      "grad_norm": 1.4261023998260498,
      "learning_rate": 0.00018,
      "loss": 2.9923,
      "step": 9
    },
    {
      "epoch": 0.004287756074321105,
      "eval_loss": NaN,
      "eval_runtime": 48.4412,
      "eval_samples_per_second": 18.249,
      "eval_steps_per_second": 9.124,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3329215646662656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}