Hugging Face's logo

ardaspear
/
23c1d3fe-0c98-44fc-aece-b8eadcfbdb27

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
23c1d3fe-0c98-44fc-aece-b8eadcfbdb27
File size: 4,300 Bytes 
3983bb6
 
 
55c04d2
3983bb6
55c04d2
3983bb6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c328547
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82db6e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3bfcf5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13ba28d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
466f44f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55c04d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3983bb6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55c04d2
3983bb6
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.20497803806734993,
  "eval_steps": 5,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005856515373352855,
      "eval_loss": 8.009540557861328,
      "eval_runtime": 18.1404,
      "eval_samples_per_second": 15.876,
      "eval_steps_per_second": 1.985,
      "step": 1
    },
    {
      "epoch": 0.017569546120058566,
      "grad_norm": 24.97199821472168,
      "learning_rate": 3e-05,
      "loss": 31.8204,
      "step": 3
    },
    {
      "epoch": 0.029282576866764276,
      "eval_loss": 7.016048431396484,
      "eval_runtime": 18.3934,
      "eval_samples_per_second": 15.658,
      "eval_steps_per_second": 1.957,
      "step": 5
    },
    {
      "epoch": 0.03513909224011713,
      "grad_norm": 23.506786346435547,
      "learning_rate": 6e-05,
      "loss": 29.8118,
      "step": 6
    },
    {
      "epoch": 0.0527086383601757,
      "grad_norm": 23.666690826416016,
      "learning_rate": 9e-05,
      "loss": 21.4367,
      "step": 9
    },
    {
      "epoch": 0.05856515373352855,
      "eval_loss": 3.3852756023406982,
      "eval_runtime": 18.4101,
      "eval_samples_per_second": 15.644,
      "eval_steps_per_second": 1.955,
      "step": 10
    },
    {
      "epoch": 0.07027818448023426,
      "grad_norm": 30.18821144104004,
      "learning_rate": 9.938441702975689e-05,
      "loss": 14.3256,
      "step": 12
    },
    {
      "epoch": 0.08784773060029283,
      "grad_norm": 22.153850555419922,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.8936,
      "step": 15
    },
    {
      "epoch": 0.08784773060029283,
      "eval_loss": 1.4027457237243652,
      "eval_runtime": 18.4902,
      "eval_samples_per_second": 15.576,
      "eval_steps_per_second": 1.947,
      "step": 15
    },
    {
      "epoch": 0.1054172767203514,
      "grad_norm": 18.735877990722656,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.3689,
      "step": 18
    },
    {
      "epoch": 0.1171303074670571,
      "eval_loss": 0.8026209473609924,
      "eval_runtime": 18.4677,
      "eval_samples_per_second": 15.595,
      "eval_steps_per_second": 1.949,
      "step": 20
    },
    {
      "epoch": 0.12298682284040996,
      "grad_norm": 11.218101501464844,
      "learning_rate": 8.247240241650918e-05,
      "loss": 2.945,
      "step": 21
    },
    {
      "epoch": 0.14055636896046853,
      "grad_norm": 13.951614379882812,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.5484,
      "step": 24
    },
    {
      "epoch": 0.14641288433382138,
      "eval_loss": 0.6135609149932861,
      "eval_runtime": 18.4602,
      "eval_samples_per_second": 15.601,
      "eval_steps_per_second": 1.95,
      "step": 25
    },
    {
      "epoch": 0.1581259150805271,
      "grad_norm": 10.735950469970703,
      "learning_rate": 6.167226819279528e-05,
      "loss": 2.6784,
      "step": 27
    },
    {
      "epoch": 0.17569546120058566,
      "grad_norm": 8.114375114440918,
      "learning_rate": 5e-05,
      "loss": 2.319,
      "step": 30
    },
    {
      "epoch": 0.17569546120058566,
      "eval_loss": 0.48306477069854736,
      "eval_runtime": 18.4788,
      "eval_samples_per_second": 15.585,
      "eval_steps_per_second": 1.948,
      "step": 30
    },
    {
      "epoch": 0.19326500732064422,
      "grad_norm": 9.957014083862305,
      "learning_rate": 3.832773180720475e-05,
      "loss": 2.2084,
      "step": 33
    },
    {
      "epoch": 0.20497803806734993,
      "eval_loss": 0.4224419891834259,
      "eval_runtime": 18.4611,
      "eval_samples_per_second": 15.6,
      "eval_steps_per_second": 1.95,
      "step": 35
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.656780307070976e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}