Hugging Face's logo

vmpsergio
/
53bebc2c-2009-4e61-8778-a4e969ea5ef9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
53bebc2c-2009-4e61-8778-a4e969ea5ef9
File size: 3,309 Bytes 
5a73f72
 
 
89c08be
5a73f72
89c08be
5a73f72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8d66d5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89c08be
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5a73f72
 
 
 
 
 
 
 
 
 
 
 
 
 
89c08be
5a73f72
 
 
 
89c08be
5a73f72
 
 
 
 
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": 0.0006740437004999157,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.246812334999719e-05,
      "eval_loss": 2.708707571029663,
      "eval_runtime": 2271.309,
      "eval_samples_per_second": 8.251,
      "eval_steps_per_second": 4.125,
      "step": 1
    },
    {
      "epoch": 6.740437004999158e-05,
      "grad_norm": 1.9373347759246826,
      "learning_rate": 6e-05,
      "loss": 2.5699,
      "step": 3
    },
    {
      "epoch": 0.00013480874009998316,
      "grad_norm": 1.7457520961761475,
      "learning_rate": 0.00012,
      "loss": 2.4162,
      "step": 6
    },
    {
      "epoch": 0.00017974498679997753,
      "eval_loss": 2.27852725982666,
      "eval_runtime": 2282.078,
      "eval_samples_per_second": 8.212,
      "eval_steps_per_second": 4.106,
      "step": 8
    },
    {
      "epoch": 0.00020221311014997472,
      "grad_norm": 1.6379685401916504,
      "learning_rate": 0.00018,
      "loss": 2.1973,
      "step": 9
    },
    {
      "epoch": 0.0002696174801999663,
      "grad_norm": 1.656538724899292,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.8866,
      "step": 12
    },
    {
      "epoch": 0.00033702185024995785,
      "grad_norm": 2.4117918014526367,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.5794,
      "step": 15
    },
    {
      "epoch": 0.00035948997359995505,
      "eval_loss": 1.7519029378890991,
      "eval_runtime": 2278.5479,
      "eval_samples_per_second": 8.225,
      "eval_steps_per_second": 4.112,
      "step": 16
    },
    {
      "epoch": 0.00040442622029994945,
      "grad_norm": 2.3444559574127197,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5926,
      "step": 18
    },
    {
      "epoch": 0.00047183059034994104,
      "grad_norm": 1.3818286657333374,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.692,
      "step": 21
    },
    {
      "epoch": 0.0005392349603999326,
      "grad_norm": 1.7987537384033203,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.5461,
      "step": 24
    },
    {
      "epoch": 0.0005392349603999326,
      "eval_loss": 1.6750073432922363,
      "eval_runtime": 2283.4584,
      "eval_samples_per_second": 8.207,
      "eval_steps_per_second": 4.103,
      "step": 24
    },
    {
      "epoch": 0.0006066393304499242,
      "grad_norm": 2.41343092918396,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.5868,
      "step": 27
    },
    {
      "epoch": 0.0006740437004999157,
      "grad_norm": 1.2482473850250244,
      "learning_rate": 0.0,
      "loss": 1.6203,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9916411753267200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}