Hugging Face's logo

nathanialhunt
/
22458975-15f2-431e-8c2e-077a46c49c98

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
22458975-15f2-431e-8c2e-077a46c49c98
File size: 3,128 Bytes 
09df0cd
 
 
21f2e76
09df0cd
21f2e76
09df0cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63d5fc1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de6b048
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21f2e76
 
 
 
 
 
 
09df0cd
 
 
 
 
 
 
 
 
 
 
 
 
 
21f2e76
09df0cd
 
 
 
21f2e76
09df0cd
 
 
 
 
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": 0.0025152486952147394,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025152486952147396,
      "grad_norm": 0.19798757135868073,
      "learning_rate": 2e-05,
      "loss": 0.8211,
      "step": 1
    },
    {
      "epoch": 0.00025152486952147396,
      "eval_loss": NaN,
      "eval_runtime": 57.5657,
      "eval_samples_per_second": 29.097,
      "eval_steps_per_second": 14.557,
      "step": 1
    },
    {
      "epoch": 0.0005030497390429479,
      "grad_norm": 0.19033122062683105,
      "learning_rate": 4e-05,
      "loss": 0.6942,
      "step": 2
    },
    {
      "epoch": 0.0007545746085644218,
      "grad_norm": 0.2211087942123413,
      "learning_rate": 6e-05,
      "loss": 0.9675,
      "step": 3
    },
    {
      "epoch": 0.0007545746085644218,
      "eval_loss": NaN,
      "eval_runtime": 56.1471,
      "eval_samples_per_second": 29.832,
      "eval_steps_per_second": 14.925,
      "step": 3
    },
    {
      "epoch": 0.0010060994780858958,
      "grad_norm": 0.23829740285873413,
      "learning_rate": 8e-05,
      "loss": 0.8838,
      "step": 4
    },
    {
      "epoch": 0.0012576243476073697,
      "grad_norm": 0.18251283466815948,
      "learning_rate": 0.0001,
      "loss": 0.4454,
      "step": 5
    },
    {
      "epoch": 0.0015091492171288435,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.703,
      "step": 6
    },
    {
      "epoch": 0.0015091492171288435,
      "eval_loss": NaN,
      "eval_runtime": 56.3421,
      "eval_samples_per_second": 29.729,
      "eval_steps_per_second": 14.873,
      "step": 6
    },
    {
      "epoch": 0.0017606740866503176,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.8471,
      "step": 7
    },
    {
      "epoch": 0.0020121989561717917,
      "grad_norm": 0.2415139526128769,
      "learning_rate": 0.00016,
      "loss": 0.7513,
      "step": 8
    },
    {
      "epoch": 0.0022637238256932655,
      "grad_norm": 0.21635624766349792,
      "learning_rate": 0.00018,
      "loss": 0.5943,
      "step": 9
    },
    {
      "epoch": 0.0022637238256932655,
      "eval_loss": NaN,
      "eval_runtime": 56.2065,
      "eval_samples_per_second": 29.801,
      "eval_steps_per_second": 14.909,
      "step": 9
    },
    {
      "epoch": 0.0025152486952147394,
      "grad_norm": 0.25000667572021484,
      "learning_rate": 0.0002,
      "loss": 0.8634,
      "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": 1391446091366400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}