Hugging Face's logo

trenden
/
fea6a7f6-5768-46b2-8073-ff96f567f2c9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
fea6a7f6-5768-46b2-8073-ff96f567f2c9
File size: 3,210 Bytes 
8d9b472
 
 
cefb405
8d9b472
cefb405
8d9b472
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4407efd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1592b40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cefb405
 
 
 
 
 
 
8d9b472
 
 
 
 
 
 
 
 
 
 
 
 
 
cefb405
8d9b472
 
 
 
cefb405
8d9b472
 
 
 
 
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": 0.0003727831054696601,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.727831054696601e-05,
      "grad_norm": 10.861333847045898,
      "learning_rate": 2e-05,
      "loss": 13.1054,
      "step": 1
    },
    {
      "epoch": 3.727831054696601e-05,
      "eval_loss": 9.946808815002441,
      "eval_runtime": 508.0043,
      "eval_samples_per_second": 22.234,
      "eval_steps_per_second": 11.118,
      "step": 1
    },
    {
      "epoch": 7.455662109393202e-05,
      "grad_norm": 6.481636047363281,
      "learning_rate": 4e-05,
      "loss": 9.4534,
      "step": 2
    },
    {
      "epoch": 0.00011183493164089804,
      "grad_norm": 17.837316513061523,
      "learning_rate": 6e-05,
      "loss": 11.985,
      "step": 3
    },
    {
      "epoch": 0.00011183493164089804,
      "eval_loss": 9.895621299743652,
      "eval_runtime": 506.0864,
      "eval_samples_per_second": 22.318,
      "eval_steps_per_second": 11.16,
      "step": 3
    },
    {
      "epoch": 0.00014911324218786404,
      "grad_norm": 4.463501930236816,
      "learning_rate": 8e-05,
      "loss": 5.4877,
      "step": 4
    },
    {
      "epoch": 0.00018639155273483004,
      "grad_norm": 7.662845611572266,
      "learning_rate": 0.0001,
      "loss": 7.9353,
      "step": 5
    },
    {
      "epoch": 0.00022366986328179608,
      "grad_norm": 5.951407432556152,
      "learning_rate": 0.00012,
      "loss": 5.9694,
      "step": 6
    },
    {
      "epoch": 0.00022366986328179608,
      "eval_loss": 8.601508140563965,
      "eval_runtime": 505.7711,
      "eval_samples_per_second": 22.332,
      "eval_steps_per_second": 11.167,
      "step": 6
    },
    {
      "epoch": 0.0002609481738287621,
      "grad_norm": 14.010904312133789,
      "learning_rate": 0.00014,
      "loss": 9.0872,
      "step": 7
    },
    {
      "epoch": 0.00029822648437572807,
      "grad_norm": 7.74440336227417,
      "learning_rate": 0.00016,
      "loss": 4.2274,
      "step": 8
    },
    {
      "epoch": 0.0003355047949226941,
      "grad_norm": 15.858744621276855,
      "learning_rate": 0.00018,
      "loss": 7.5469,
      "step": 9
    },
    {
      "epoch": 0.0003355047949226941,
      "eval_loss": 4.148334503173828,
      "eval_runtime": 506.2852,
      "eval_samples_per_second": 22.31,
      "eval_steps_per_second": 11.156,
      "step": 9
    },
    {
      "epoch": 0.0003727831054696601,
      "grad_norm": 10.15648078918457,
      "learning_rate": 0.0002,
      "loss": 4.5332,
      "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": 2820585478422528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}