Hugging Face's logo

lesso05
/
27e72eaf-2503-48c8-bf0c-7dfae7663c14

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
8-bit precision
bitsandbytes
Model card Files Community
27e72eaf-2503-48c8-bf0c-7dfae7663c14
File size: 3,233 Bytes 
bedb172
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.227739691734314,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.006278449223041909,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006278449223041908,
      "grad_norm": 1.7238279581069946,
      "learning_rate": 2e-05,
      "loss": 7.385,
      "step": 1
    },
    {
      "epoch": 0.0006278449223041908,
      "eval_loss": 2.143244743347168,
      "eval_runtime": 129.9707,
      "eval_samples_per_second": 5.163,
      "eval_steps_per_second": 2.585,
      "step": 1
    },
    {
      "epoch": 0.0012556898446083817,
      "grad_norm": 2.936279773712158,
      "learning_rate": 4e-05,
      "loss": 10.7244,
      "step": 2
    },
    {
      "epoch": 0.0018835347669125726,
      "grad_norm": 2.1784932613372803,
      "learning_rate": 6e-05,
      "loss": 8.0292,
      "step": 3
    },
    {
      "epoch": 0.0025113796892167633,
      "grad_norm": 1.9787063598632812,
      "learning_rate": 8e-05,
      "loss": 6.6026,
      "step": 4
    },
    {
      "epoch": 0.0031392246115209545,
      "grad_norm": 3.616180896759033,
      "learning_rate": 0.0001,
      "loss": 10.2764,
      "step": 5
    },
    {
      "epoch": 0.0031392246115209545,
      "eval_loss": 2.0979456901550293,
      "eval_runtime": 127.4876,
      "eval_samples_per_second": 5.263,
      "eval_steps_per_second": 2.636,
      "step": 5
    },
    {
      "epoch": 0.003767069533825145,
      "grad_norm": 4.404942512512207,
      "learning_rate": 0.00012,
      "loss": 8.2857,
      "step": 6
    },
    {
      "epoch": 0.004394914456129336,
      "grad_norm": 3.9975357055664062,
      "learning_rate": 0.00014,
      "loss": 10.9445,
      "step": 7
    },
    {
      "epoch": 0.005022759378433527,
      "grad_norm": 5.789132118225098,
      "learning_rate": 0.00016,
      "loss": 8.4633,
      "step": 8
    },
    {
      "epoch": 0.005650604300737718,
      "grad_norm": 3.1519086360931396,
      "learning_rate": 0.00018,
      "loss": 5.339,
      "step": 9
    },
    {
      "epoch": 0.006278449223041909,
      "grad_norm": 3.596461057662964,
      "learning_rate": 0.0002,
      "loss": 5.4954,
      "step": 10
    },
    {
      "epoch": 0.006278449223041909,
      "eval_loss": 1.227739691734314,
      "eval_runtime": 127.6723,
      "eval_samples_per_second": 5.256,
      "eval_steps_per_second": 2.632,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3166224305356800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}