Hugging Face's logo

trenden
/
48ff2542-bbde-4abb-a93d-3a1baac74407

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
48ff2542-bbde-4abb-a93d-3a1baac74407
File size: 2,977 Bytes 
70bf1f6
 
 
2c23e49
70bf1f6
2c23e49
70bf1f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8671aab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
904c1ce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2c23e49
 
 
 
 
 
 
70bf1f6
 
 
 
 
 
 
 
 
 
 
 
 
 
2c23e49
70bf1f6
 
 
 
2c23e49
70bf1f6
 
 
 
 
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": 0.0021158423697434543,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002115842369743454,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0002115842369743454,
      "eval_loss": NaN,
      "eval_runtime": 99.2963,
      "eval_samples_per_second": 20.041,
      "eval_steps_per_second": 10.021,
      "step": 1
    },
    {
      "epoch": 0.0004231684739486908,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 1.2756,
      "step": 2
    },
    {
      "epoch": 0.0006347527109230362,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0006347527109230362,
      "eval_loss": NaN,
      "eval_runtime": 97.9516,
      "eval_samples_per_second": 20.316,
      "eval_steps_per_second": 10.158,
      "step": 3
    },
    {
      "epoch": 0.0008463369478973816,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 1.6354,
      "step": 4
    },
    {
      "epoch": 0.0010579211848717272,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0012695054218460724,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0012695054218460724,
      "eval_loss": NaN,
      "eval_runtime": 98.0287,
      "eval_samples_per_second": 20.3,
      "eval_steps_per_second": 10.15,
      "step": 6
    },
    {
      "epoch": 0.0014810896588204178,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0016926738957947632,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0019042581327691087,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0019042581327691087,
      "eval_loss": NaN,
      "eval_runtime": 97.9844,
      "eval_samples_per_second": 20.309,
      "eval_steps_per_second": 10.155,
      "step": 9
    },
    {
      "epoch": 0.0021158423697434543,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 1.4298,
      "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": 3122012029452288.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}