Hugging Face's logo

lesso02
/
38fe8890-38d3-462e-b178-9c4267f40f15

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
38fe8890-38d3-462e-b178-9c4267f40f15
File size: 2,962 Bytes 
15b7b41
 
 
3b5a506
15b7b41
3b5a506
15b7b41
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
584c7d6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4cc56fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b5a506
 
 
 
 
 
 
15b7b41
 
 
 
 
 
 
 
 
 
 
 
 
 
3b5a506
15b7b41
 
 
 
3b5a506
15b7b41
 
 
 
 
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": 0.0054473648372599754,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005447364837259975,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0005447364837259975,
      "eval_loss": NaN,
      "eval_runtime": 67.6324,
      "eval_samples_per_second": 11.429,
      "eval_steps_per_second": 5.722,
      "step": 1
    },
    {
      "epoch": 0.001089472967451995,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0016342094511779927,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0016342094511779927,
      "eval_loss": NaN,
      "eval_runtime": 65.3125,
      "eval_samples_per_second": 11.835,
      "eval_steps_per_second": 5.925,
      "step": 3
    },
    {
      "epoch": 0.00217894593490399,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0027236824186299877,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0032684189023559854,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0032684189023559854,
      "eval_loss": NaN,
      "eval_runtime": 65.3406,
      "eval_samples_per_second": 11.83,
      "eval_steps_per_second": 5.923,
      "step": 6
    },
    {
      "epoch": 0.0038131553860819827,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 6.1537,
      "step": 7
    },
    {
      "epoch": 0.00435789186980798,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.004902628353533978,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.004902628353533978,
      "eval_loss": NaN,
      "eval_runtime": 65.3309,
      "eval_samples_per_second": 11.832,
      "eval_steps_per_second": 5.924,
      "step": 9
    },
    {
      "epoch": 0.0054473648372599754,
      "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": 2496911734996992.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}