Hugging Face's logo

vermoney
/
1d66f576-71bc-4847-8e9a-4aa658c0e23d

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
1d66f576-71bc-4847-8e9a-4aa658c0e23d
File size: 3,319 Bytes 
f6f3301
 
 
8d7c576
f6f3301
8d7c576
f6f3301
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1a092ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8d7c576
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f6f3301
 
 
 
 
 
 
 
 
 
 
 
 
 
8d7c576
f6f3301
 
 
 
8d7c576
f6f3301
 
 
 
 
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": 0.00047824770042564045,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5941590014188015e-05,
      "eval_loss": 1.6990032196044922,
      "eval_runtime": 5081.1835,
      "eval_samples_per_second": 5.198,
      "eval_steps_per_second": 2.599,
      "step": 1
    },
    {
      "epoch": 4.7824770042564044e-05,
      "grad_norm": 0.6024008393287659,
      "learning_rate": 3e-05,
      "loss": 7.4336,
      "step": 3
    },
    {
      "epoch": 9.564954008512809e-05,
      "grad_norm": 0.5880036354064941,
      "learning_rate": 6e-05,
      "loss": 6.6894,
      "step": 6
    },
    {
      "epoch": 0.00012753272011350412,
      "eval_loss": 1.6758214235305786,
      "eval_runtime": 5106.4017,
      "eval_samples_per_second": 5.173,
      "eval_steps_per_second": 2.586,
      "step": 8
    },
    {
      "epoch": 0.00014347431012769212,
      "grad_norm": 0.6464680433273315,
      "learning_rate": 9e-05,
      "loss": 7.0782,
      "step": 9
    },
    {
      "epoch": 0.00019129908017025618,
      "grad_norm": 0.8096962571144104,
      "learning_rate": 9.755282581475769e-05,
      "loss": 6.3456,
      "step": 12
    },
    {
      "epoch": 0.00023912385021282023,
      "grad_norm": 0.9577824473381042,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.6146,
      "step": 15
    },
    {
      "epoch": 0.00025506544022700823,
      "eval_loss": 1.4773930311203003,
      "eval_runtime": 5097.0629,
      "eval_samples_per_second": 5.182,
      "eval_steps_per_second": 2.591,
      "step": 16
    },
    {
      "epoch": 0.00028694862025538425,
      "grad_norm": 1.3272778987884521,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.7386,
      "step": 18
    },
    {
      "epoch": 0.0003347733902979483,
      "grad_norm": 1.0558263063430786,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 5.9583,
      "step": 21
    },
    {
      "epoch": 0.00038259816034051235,
      "grad_norm": 1.1874443292617798,
      "learning_rate": 2.061073738537635e-05,
      "loss": 5.8447,
      "step": 24
    },
    {
      "epoch": 0.00038259816034051235,
      "eval_loss": 1.394423007965088,
      "eval_runtime": 5098.0672,
      "eval_samples_per_second": 5.181,
      "eval_steps_per_second": 2.591,
      "step": 24
    },
    {
      "epoch": 0.00043042293038307643,
      "grad_norm": 3.1952991485595703,
      "learning_rate": 5.449673790581611e-06,
      "loss": 5.8477,
      "step": 27
    },
    {
      "epoch": 0.00047824770042564045,
      "grad_norm": 1.4119552373886108,
      "learning_rate": 0.0,
      "loss": 5.749,
      "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": 2.027730090590208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}