Hugging Face's logo

dzanbek
/
9b21cf64-fc30-4c3d-8702-45e030485aac

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
9b21cf64-fc30-4c3d-8702-45e030485aac
File size: 2,948 Bytes 
e5be168
 
 
3a51f4a
e5be168
3a51f4a
e5be168
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae598bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f64c934
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a51f4a
 
 
 
 
 
 
e5be168
 
 
 
 
 
 
 
 
 
 
 
 
 
3a51f4a
e5be168
 
 
 
3a51f4a
e5be168
 
 
 
 
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": 0.022611644997173545,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022611644997173543,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0022611644997173543,
      "eval_loss": NaN,
      "eval_runtime": 22.0437,
      "eval_samples_per_second": 8.483,
      "eval_steps_per_second": 4.264,
      "step": 1
    },
    {
      "epoch": 0.0045223289994347085,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.006783493499152063,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006783493499152063,
      "eval_loss": NaN,
      "eval_runtime": 21.0904,
      "eval_samples_per_second": 8.867,
      "eval_steps_per_second": 4.457,
      "step": 3
    },
    {
      "epoch": 0.009044657998869417,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.011305822498586773,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.013566986998304126,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.013566986998304126,
      "eval_loss": NaN,
      "eval_runtime": 21.0654,
      "eval_samples_per_second": 8.877,
      "eval_steps_per_second": 4.462,
      "step": 6
    },
    {
      "epoch": 0.01582815149802148,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.018089315997738834,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.02035048049745619,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.02035048049745619,
      "eval_loss": NaN,
      "eval_runtime": 21.0564,
      "eval_samples_per_second": 8.881,
      "eval_steps_per_second": 4.464,
      "step": 9
    },
    {
      "epoch": 0.022611644997173545,
      "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": 3296153189744640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}