Hugging Face's logo

ngocquangt2k46
/
bcaa7d79-af99-4f14-be5a-bf20da2462b4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
bcaa7d79-af99-4f14-be5a-bf20da2462b4
File size: 2,974 Bytes 
49e30da
 
 
bb76161
49e30da
bb76161
49e30da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bb76161
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49e30da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bb76161
49e30da
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03955500618046971,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003955500618046972,
      "grad_norm": 66.62299346923828,
      "learning_rate": 1e-05,
      "loss": 128.6241,
      "step": 1
    },
    {
      "epoch": 0.003955500618046972,
      "eval_loss": 4.237987995147705,
      "eval_runtime": 307.5537,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 1.385,
      "step": 1
    },
    {
      "epoch": 0.007911001236093944,
      "grad_norm": 65.98905181884766,
      "learning_rate": 2e-05,
      "loss": 138.1243,
      "step": 2
    },
    {
      "epoch": 0.011866501854140914,
      "grad_norm": 68.6584243774414,
      "learning_rate": 3e-05,
      "loss": 136.2323,
      "step": 3
    },
    {
      "epoch": 0.015822002472187888,
      "grad_norm": 70.29867553710938,
      "learning_rate": 4e-05,
      "loss": 133.9982,
      "step": 4
    },
    {
      "epoch": 0.019777503090234856,
      "grad_norm": 67.28761291503906,
      "learning_rate": 5e-05,
      "loss": 129.0051,
      "step": 5
    },
    {
      "epoch": 0.019777503090234856,
      "eval_loss": 4.1191630363464355,
      "eval_runtime": 307.5897,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 1.385,
      "step": 5
    },
    {
      "epoch": 0.023733003708281828,
      "grad_norm": 78.57897186279297,
      "learning_rate": 6e-05,
      "loss": 144.2249,
      "step": 6
    },
    {
      "epoch": 0.0276885043263288,
      "grad_norm": 94.01433563232422,
      "learning_rate": 7e-05,
      "loss": 131.2312,
      "step": 7
    },
    {
      "epoch": 0.031644004944375775,
      "grad_norm": 93.0120620727539,
      "learning_rate": 8e-05,
      "loss": 114.7555,
      "step": 8
    },
    {
      "epoch": 0.035599505562422744,
      "grad_norm": 103.75362396240234,
      "learning_rate": 9e-05,
      "loss": 117.9606,
      "step": 9
    },
    {
      "epoch": 0.03955500618046971,
      "grad_norm": 101.03894805908203,
      "learning_rate": 0.0001,
      "loss": 109.0838,
      "step": 10
    },
    {
      "epoch": 0.03955500618046971,
      "eval_loss": 3.0349903106689453,
      "eval_runtime": 307.556,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 1.385,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "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": 1.0455331230449664e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}