Hugging Face's logo

filipesantoscv11
/
ac08da8c-2e12-4a65-8f2e-58f25789c041

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
ac08da8c-2e12-4a65-8f2e-58f25789c041
File size: 3,319 Bytes 
7850d72
 
 
70a356b
7850d72
70a356b
7850d72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ceab4c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70a356b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7850d72
 
 
 
 
 
 
 
 
 
 
 
 
 
70a356b
7850d72
 
 
 
70a356b
7850d72
 
 
 
 
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": 0.0005095909258842464,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6986364196141547e-05,
      "eval_loss": 1.3468103408813477,
      "eval_runtime": 1823.6205,
      "eval_samples_per_second": 13.593,
      "eval_steps_per_second": 6.796,
      "step": 1
    },
    {
      "epoch": 5.095909258842464e-05,
      "grad_norm": 15.388035774230957,
      "learning_rate": 3e-05,
      "loss": 5.8321,
      "step": 3
    },
    {
      "epoch": 0.00010191818517684929,
      "grad_norm": 12.621480941772461,
      "learning_rate": 6e-05,
      "loss": 5.5541,
      "step": 6
    },
    {
      "epoch": 0.00013589091356913237,
      "eval_loss": 1.3425273895263672,
      "eval_runtime": 1823.6309,
      "eval_samples_per_second": 13.593,
      "eval_steps_per_second": 6.796,
      "step": 8
    },
    {
      "epoch": 0.00015287727776527394,
      "grad_norm": 40.26927947998047,
      "learning_rate": 9e-05,
      "loss": 5.5315,
      "step": 9
    },
    {
      "epoch": 0.00020383637035369857,
      "grad_norm": 47.04484176635742,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.9109,
      "step": 12
    },
    {
      "epoch": 0.0002547954629421232,
      "grad_norm": 6.6766252517700195,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.7547,
      "step": 15
    },
    {
      "epoch": 0.00027178182713826475,
      "eval_loss": 1.2962453365325928,
      "eval_runtime": 1823.5636,
      "eval_samples_per_second": 13.593,
      "eval_steps_per_second": 6.797,
      "step": 16
    },
    {
      "epoch": 0.0003057545555305479,
      "grad_norm": 2.574517250061035,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.7193,
      "step": 18
    },
    {
      "epoch": 0.0003567136481189725,
      "grad_norm": 2.4038732051849365,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 4.4778,
      "step": 21
    },
    {
      "epoch": 0.00040767274070739715,
      "grad_norm": 2.2437119483947754,
      "learning_rate": 2.061073738537635e-05,
      "loss": 5.2389,
      "step": 24
    },
    {
      "epoch": 0.00040767274070739715,
      "eval_loss": 1.2343007326126099,
      "eval_runtime": 1823.5812,
      "eval_samples_per_second": 13.593,
      "eval_steps_per_second": 6.797,
      "step": 24
    },
    {
      "epoch": 0.00045863183329582176,
      "grad_norm": 2.8667590618133545,
      "learning_rate": 5.449673790581611e-06,
      "loss": 5.1294,
      "step": 27
    },
    {
      "epoch": 0.0005095909258842464,
      "grad_norm": 2.4659061431884766,
      "learning_rate": 0.0,
      "loss": 4.3906,
      "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": 1.0128701987487744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}