Hugging Face's logo

great0001
/
cbf504c8-2143-440a-8d79-e3cb2bf8433c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cbf504c8-2143-440a-8d79-e3cb2bf8433c
File size: 2,980 Bytes 
5462ba9
 
 
a3c5987
5462ba9
a3c5987
5462ba9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5b4c44b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7007bdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a3c5987
 
 
 
 
 
 
5462ba9
 
 
 
 
 
 
 
 
 
 
 
 
 
a3c5987
5462ba9
 
 
 
a3c5987
5462ba9
 
 
 
 
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": 0.00047224386673278083,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.722438667327808e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 4.722438667327808e-05,
      "eval_loss": NaN,
      "eval_runtime": 583.464,
      "eval_samples_per_second": 15.281,
      "eval_steps_per_second": 7.641,
      "step": 1
    },
    {
      "epoch": 9.444877334655616e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00014167316001983425,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00014167316001983425,
      "eval_loss": NaN,
      "eval_runtime": 582.2448,
      "eval_samples_per_second": 15.313,
      "eval_steps_per_second": 7.657,
      "step": 3
    },
    {
      "epoch": 0.00018889754669311232,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00023612193336639041,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0002833463200396685,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0002833463200396685,
      "eval_loss": NaN,
      "eval_runtime": 581.9904,
      "eval_samples_per_second": 15.32,
      "eval_steps_per_second": 7.66,
      "step": 6
    },
    {
      "epoch": 0.00033057070671294655,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00037779509338622464,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00042501948005950273,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00042501948005950273,
      "eval_loss": NaN,
      "eval_runtime": 582.595,
      "eval_samples_per_second": 15.304,
      "eval_steps_per_second": 7.652,
      "step": 9
    },
    {
      "epoch": 0.00047224386673278083,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 1.4104,
      "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": 3984672593805312.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}