Hugging Face's logo

adammandic87
/
6b984d96-a9eb-43dc-a3a1-3dc096d54e5d

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
6b984d96-a9eb-43dc-a3a1-3dc096d54e5d
File size: 3,044 Bytes 
a249784
 
 
cc05ae8
a249784
cc05ae8
a249784
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31eacaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cc05ae8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a249784
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cc05ae8
a249784
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002184002184002184,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.42666909333576e-05,
      "grad_norm": 8.195829391479492,
      "learning_rate": 2e-05,
      "loss": 13.288,
      "step": 1
    },
    {
      "epoch": 2.42666909333576e-05,
      "eval_loss": 3.190768003463745,
      "eval_runtime": 287.5377,
      "eval_samples_per_second": 60.343,
      "eval_steps_per_second": 30.173,
      "step": 1
    },
    {
      "epoch": 4.85333818667152e-05,
      "grad_norm": 5.681870460510254,
      "learning_rate": 4e-05,
      "loss": 13.1977,
      "step": 2
    },
    {
      "epoch": 7.28000728000728e-05,
      "grad_norm": 8.005084991455078,
      "learning_rate": 6e-05,
      "loss": 13.2657,
      "step": 3
    },
    {
      "epoch": 7.28000728000728e-05,
      "eval_loss": 3.1813180446624756,
      "eval_runtime": 286.5928,
      "eval_samples_per_second": 60.542,
      "eval_steps_per_second": 30.273,
      "step": 3
    },
    {
      "epoch": 9.70667637334304e-05,
      "grad_norm": 9.094429016113281,
      "learning_rate": 8e-05,
      "loss": 13.8729,
      "step": 4
    },
    {
      "epoch": 0.000121333454666788,
      "grad_norm": 9.367225646972656,
      "learning_rate": 0.0001,
      "loss": 13.548,
      "step": 5
    },
    {
      "epoch": 0.0001456001456001456,
      "grad_norm": 5.921675205230713,
      "learning_rate": 0.00012,
      "loss": 11.6533,
      "step": 6
    },
    {
      "epoch": 0.0001456001456001456,
      "eval_loss": 3.0957133769989014,
      "eval_runtime": 287.9578,
      "eval_samples_per_second": 60.255,
      "eval_steps_per_second": 30.129,
      "step": 6
    },
    {
      "epoch": 0.0001698668365335032,
      "grad_norm": 4.545871257781982,
      "learning_rate": 0.00014,
      "loss": 11.2224,
      "step": 7
    },
    {
      "epoch": 0.0001941335274668608,
      "grad_norm": 11.329343795776367,
      "learning_rate": 0.00016,
      "loss": 14.2415,
      "step": 8
    },
    {
      "epoch": 0.0002184002184002184,
      "grad_norm": 6.399060249328613,
      "learning_rate": 0.00018,
      "loss": 11.4404,
      "step": 9
    },
    {
      "epoch": 0.0002184002184002184,
      "eval_loss": 2.872811794281006,
      "eval_runtime": 287.5926,
      "eval_samples_per_second": 60.332,
      "eval_steps_per_second": 30.168,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 603978124492800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}