Hugging Face's logo

great0001
/
e855a9f0-9dac-4a2a-a918-ce25bde13dde

PEFT
Safetensors
gpt_neo
axolotl
Generated from Trainer
Model card Files Community
e855a9f0-9dac-4a2a-a918-ce25bde13dde
File size: 3,222 Bytes 
fca6400
 
 
884377d
fca6400
884377d
fca6400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b37dbdc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
374d95f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
884377d
 
 
 
 
 
 
fca6400
 
 
 
 
 
 
 
 
 
 
 
 
 
884377d
fca6400
 
 
 
884377d
fca6400
 
 
 
 
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": 0.000127712289753643,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2771228975364299e-05,
      "grad_norm": 1.7874619960784912,
      "learning_rate": 2e-05,
      "loss": 12.8567,
      "step": 1
    },
    {
      "epoch": 1.2771228975364299e-05,
      "eval_loss": 3.4389500617980957,
      "eval_runtime": 284.6198,
      "eval_samples_per_second": 115.835,
      "eval_steps_per_second": 57.919,
      "step": 1
    },
    {
      "epoch": 2.5542457950728598e-05,
      "grad_norm": 1.8470408916473389,
      "learning_rate": 4e-05,
      "loss": 12.9693,
      "step": 2
    },
    {
      "epoch": 3.8313686926092896e-05,
      "grad_norm": 1.853289008140564,
      "learning_rate": 6e-05,
      "loss": 14.4906,
      "step": 3
    },
    {
      "epoch": 3.8313686926092896e-05,
      "eval_loss": 3.439675807952881,
      "eval_runtime": 283.588,
      "eval_samples_per_second": 116.257,
      "eval_steps_per_second": 58.13,
      "step": 3
    },
    {
      "epoch": 5.1084915901457196e-05,
      "grad_norm": 1.82938814163208,
      "learning_rate": 8e-05,
      "loss": 13.5146,
      "step": 4
    },
    {
      "epoch": 6.38561448768215e-05,
      "grad_norm": 1.9475919008255005,
      "learning_rate": 0.0001,
      "loss": 12.9003,
      "step": 5
    },
    {
      "epoch": 7.662737385218579e-05,
      "grad_norm": 1.7962164878845215,
      "learning_rate": 0.00012,
      "loss": 13.3743,
      "step": 6
    },
    {
      "epoch": 7.662737385218579e-05,
      "eval_loss": 3.4317994117736816,
      "eval_runtime": 283.8601,
      "eval_samples_per_second": 116.145,
      "eval_steps_per_second": 58.074,
      "step": 6
    },
    {
      "epoch": 8.93986028275501e-05,
      "grad_norm": 1.9254177808761597,
      "learning_rate": 0.00014,
      "loss": 14.1191,
      "step": 7
    },
    {
      "epoch": 0.00010216983180291439,
      "grad_norm": 1.966262936592102,
      "learning_rate": 0.00016,
      "loss": 13.6299,
      "step": 8
    },
    {
      "epoch": 0.0001149410607782787,
      "grad_norm": 2.2013680934906006,
      "learning_rate": 0.00018,
      "loss": 14.1981,
      "step": 9
    },
    {
      "epoch": 0.0001149410607782787,
      "eval_loss": 3.4004440307617188,
      "eval_runtime": 286.8421,
      "eval_samples_per_second": 114.938,
      "eval_steps_per_second": 57.471,
      "step": 9
    },
    {
      "epoch": 0.000127712289753643,
      "grad_norm": 2.237434148788452,
      "learning_rate": 0.0002,
      "loss": 14.5226,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 21222716866560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}