Hugging Face's logo

error577
/
58b9523a-8576-4309-80c7-060f2d6bf699

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
4-bit precision
bitsandbytes
Model card Files Community
58b9523a-8576-4309-80c7-060f2d6bf699
File size: 3,193 Bytes 
a2507ec
 
 
5821c9e
a2507ec
5821c9e
a2507ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
423499d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82bc349
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5821c9e
 
 
 
 
 
 
a2507ec
 
 
 
 
 
 
 
 
 
 
 
 
 
5821c9e
a2507ec
 
 
 
5821c9e
a2507ec
 
 
 
 
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": 0.007416334476684898,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007416334476684898,
      "grad_norm": 12.539473533630371,
      "learning_rate": 2e-05,
      "loss": 18.8184,
      "step": 1
    },
    {
      "epoch": 0.0007416334476684898,
      "eval_loss": 2.656465768814087,
      "eval_runtime": 71.3819,
      "eval_samples_per_second": 7.957,
      "eval_steps_per_second": 7.957,
      "step": 1
    },
    {
      "epoch": 0.0014832668953369797,
      "grad_norm": 14.706053733825684,
      "learning_rate": 4e-05,
      "loss": 24.6349,
      "step": 2
    },
    {
      "epoch": 0.0022249003430054697,
      "grad_norm": 11.934353828430176,
      "learning_rate": 6e-05,
      "loss": 19.4363,
      "step": 3
    },
    {
      "epoch": 0.0022249003430054697,
      "eval_loss": 2.645974636077881,
      "eval_runtime": 71.0304,
      "eval_samples_per_second": 7.997,
      "eval_steps_per_second": 7.997,
      "step": 3
    },
    {
      "epoch": 0.0029665337906739594,
      "grad_norm": 12.361547470092773,
      "learning_rate": 8e-05,
      "loss": 19.716,
      "step": 4
    },
    {
      "epoch": 0.003708167238342449,
      "grad_norm": 20.54907989501953,
      "learning_rate": 0.0001,
      "loss": 20.2049,
      "step": 5
    },
    {
      "epoch": 0.004449800686010939,
      "grad_norm": 16.191509246826172,
      "learning_rate": 0.00012,
      "loss": 19.7239,
      "step": 6
    },
    {
      "epoch": 0.004449800686010939,
      "eval_loss": 2.478991985321045,
      "eval_runtime": 71.1391,
      "eval_samples_per_second": 7.984,
      "eval_steps_per_second": 7.984,
      "step": 6
    },
    {
      "epoch": 0.005191434133679429,
      "grad_norm": 27.116924285888672,
      "learning_rate": 0.00014,
      "loss": 16.9851,
      "step": 7
    },
    {
      "epoch": 0.005933067581347919,
      "grad_norm": 19.143783569335938,
      "learning_rate": 0.00016,
      "loss": 19.1227,
      "step": 8
    },
    {
      "epoch": 0.006674701029016409,
      "grad_norm": 26.77751922607422,
      "learning_rate": 0.00018,
      "loss": 20.1204,
      "step": 9
    },
    {
      "epoch": 0.006674701029016409,
      "eval_loss": 1.68876051902771,
      "eval_runtime": 71.0849,
      "eval_samples_per_second": 7.99,
      "eval_steps_per_second": 7.99,
      "step": 9
    },
    {
      "epoch": 0.007416334476684898,
      "grad_norm": 27.757686614990234,
      "learning_rate": 0.0002,
      "loss": 11.5992,
      "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": 813146528808960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}