Hugging Face's logo

JacksonBrune
/
45484cf2-5440-4b64-bb17-33e44525cc50

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
45484cf2-5440-4b64-bb17-33e44525cc50
File size: 3,203 Bytes 
899b191
 
 
ed886ff
899b191
ed886ff
899b191
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a0fd58
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
427db22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed886ff
 
 
 
 
 
 
899b191
 
 
 
 
 
 
 
 
 
 
 
 
 
ed886ff
899b191
 
 
 
ed886ff
899b191
 
 
 
 
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": 0.001536688436419516,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001536688436419516,
      "grad_norm": 2.5537407398223877,
      "learning_rate": 2e-05,
      "loss": 3.6463,
      "step": 1
    },
    {
      "epoch": 0.0001536688436419516,
      "eval_loss": 3.188629388809204,
      "eval_runtime": 98.6555,
      "eval_samples_per_second": 27.773,
      "eval_steps_per_second": 13.887,
      "step": 1
    },
    {
      "epoch": 0.0003073376872839032,
      "grad_norm": 1.6175376176834106,
      "learning_rate": 4e-05,
      "loss": 3.3646,
      "step": 2
    },
    {
      "epoch": 0.0004610065309258548,
      "grad_norm": 1.179677963256836,
      "learning_rate": 6e-05,
      "loss": 2.3409,
      "step": 3
    },
    {
      "epoch": 0.0004610065309258548,
      "eval_loss": 3.179351806640625,
      "eval_runtime": 97.4705,
      "eval_samples_per_second": 28.111,
      "eval_steps_per_second": 14.056,
      "step": 3
    },
    {
      "epoch": 0.0006146753745678064,
      "grad_norm": 1.4353758096694946,
      "learning_rate": 8e-05,
      "loss": 3.1662,
      "step": 4
    },
    {
      "epoch": 0.000768344218209758,
      "grad_norm": 3.241360664367676,
      "learning_rate": 0.0001,
      "loss": 3.9191,
      "step": 5
    },
    {
      "epoch": 0.0009220130618517096,
      "grad_norm": 1.9459642171859741,
      "learning_rate": 0.00012,
      "loss": 2.5982,
      "step": 6
    },
    {
      "epoch": 0.0009220130618517096,
      "eval_loss": 3.0730576515197754,
      "eval_runtime": 97.5286,
      "eval_samples_per_second": 28.094,
      "eval_steps_per_second": 14.047,
      "step": 6
    },
    {
      "epoch": 0.0010756819054936612,
      "grad_norm": 1.4690053462982178,
      "learning_rate": 0.00014,
      "loss": 2.7402,
      "step": 7
    },
    {
      "epoch": 0.0012293507491356128,
      "grad_norm": 1.8470284938812256,
      "learning_rate": 0.00016,
      "loss": 3.0458,
      "step": 8
    },
    {
      "epoch": 0.0013830195927775643,
      "grad_norm": 1.7478736639022827,
      "learning_rate": 0.00018,
      "loss": 2.6066,
      "step": 9
    },
    {
      "epoch": 0.0013830195927775643,
      "eval_loss": 2.9789044857025146,
      "eval_runtime": 97.4701,
      "eval_samples_per_second": 28.111,
      "eval_steps_per_second": 14.056,
      "step": 9
    },
    {
      "epoch": 0.001536688436419516,
      "grad_norm": 2.394191026687622,
      "learning_rate": 0.0002,
      "loss": 3.0029,
      "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": 1895803354349568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}