Hugging Face's logo

ivangrapher
/
98247abe-1673-4171-a4d1-801699c79408

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
98247abe-1673-4171-a4d1-801699c79408
File size: 3,290 Bytes 
5263a43
 
 
d24f92a
5263a43
d24f92a
5263a43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d24f92a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5263a43
 
 
 
 
 
 
 
 
 
 
 
 
 
d24f92a
5263a43
 
 
 
d24f92a
5263a43
 
 
 
 
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": 0.00039876471552568267,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3292157184189422e-05,
      "eval_loss": 2.3748350143432617,
      "eval_runtime": 2056.8986,
      "eval_samples_per_second": 11.55,
      "eval_steps_per_second": 5.775,
      "step": 1
    },
    {
      "epoch": 3.987647155256827e-05,
      "grad_norm": 0.8939356803894043,
      "learning_rate": 4e-05,
      "loss": 2.1183,
      "step": 3
    },
    {
      "epoch": 7.975294310513654e-05,
      "grad_norm": 1.2293646335601807,
      "learning_rate": 8e-05,
      "loss": 2.5036,
      "step": 6
    },
    {
      "epoch": 0.00010633725747351538,
      "eval_loss": 2.133735418319702,
      "eval_runtime": 2065.5153,
      "eval_samples_per_second": 11.502,
      "eval_steps_per_second": 5.751,
      "step": 8
    },
    {
      "epoch": 0.0001196294146577048,
      "grad_norm": 1.169637680053711,
      "learning_rate": 0.00012,
      "loss": 2.2538,
      "step": 9
    },
    {
      "epoch": 0.00015950588621027308,
      "grad_norm": 0.7869271636009216,
      "learning_rate": 0.00016,
      "loss": 1.9268,
      "step": 12
    },
    {
      "epoch": 0.00019938235776284133,
      "grad_norm": 1.1890661716461182,
      "learning_rate": 0.0002,
      "loss": 1.8888,
      "step": 15
    },
    {
      "epoch": 0.00021267451494703075,
      "eval_loss": 1.7299827337265015,
      "eval_runtime": 2067.6299,
      "eval_samples_per_second": 11.49,
      "eval_steps_per_second": 5.745,
      "step": 16
    },
    {
      "epoch": 0.0002392588293154096,
      "grad_norm": 1.4860124588012695,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.7889,
      "step": 18
    },
    {
      "epoch": 0.00027913530086797785,
      "grad_norm": 0.8257107138633728,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7835,
      "step": 21
    },
    {
      "epoch": 0.00031901177242054616,
      "grad_norm": 0.6575050950050354,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.5446,
      "step": 24
    },
    {
      "epoch": 0.00031901177242054616,
      "eval_loss": 1.5880478620529175,
      "eval_runtime": 2067.4112,
      "eval_samples_per_second": 11.492,
      "eval_steps_per_second": 5.746,
      "step": 24
    },
    {
      "epoch": 0.0003588882439731144,
      "grad_norm": 0.6337928175926208,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.7106,
      "step": 27
    },
    {
      "epoch": 0.00039876471552568267,
      "grad_norm": 0.7751510739326477,
      "learning_rate": 0.0,
      "loss": 1.5877,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7519945579560960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}