Hugging Face's logo

philip-hightech
/
8cedf432-fbc8-4bdb-978e-558450a6f1dc

PEFT
Safetensors
gpt_neo
axolotl
Generated from Trainer
Model card Files Community
8cedf432-fbc8-4bdb-978e-558450a6f1dc
File size: 3,214 Bytes 
e76205a
 
 
b9c0012
e76205a
b9c0012
e76205a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7b623d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ef71608
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9c0012
 
 
 
 
 
 
e76205a
 
 
 
 
 
 
 
 
 
 
 
 
 
b9c0012
e76205a
 
 
 
b9c0012
e76205a
 
 
 
 
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": 0.0003739296264443032,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.739296264443032e-05,
      "grad_norm": 0.5257403254508972,
      "learning_rate": 2e-05,
      "loss": 3.872,
      "step": 1
    },
    {
      "epoch": 3.739296264443032e-05,
      "eval_loss": 0.6931043863296509,
      "eval_runtime": 149.8911,
      "eval_samples_per_second": 75.128,
      "eval_steps_per_second": 37.567,
      "step": 1
    },
    {
      "epoch": 7.478592528886064e-05,
      "grad_norm": 0.5068989396095276,
      "learning_rate": 4e-05,
      "loss": 2.8316,
      "step": 2
    },
    {
      "epoch": 0.00011217888793329095,
      "grad_norm": 0.6643518209457397,
      "learning_rate": 6e-05,
      "loss": 3.1932,
      "step": 3
    },
    {
      "epoch": 0.00011217888793329095,
      "eval_loss": 0.6930645704269409,
      "eval_runtime": 149.8487,
      "eval_samples_per_second": 75.149,
      "eval_steps_per_second": 37.578,
      "step": 3
    },
    {
      "epoch": 0.00014957185057772127,
      "grad_norm": 0.5338044166564941,
      "learning_rate": 8e-05,
      "loss": 2.8836,
      "step": 4
    },
    {
      "epoch": 0.0001869648132221516,
      "grad_norm": 0.6110092997550964,
      "learning_rate": 0.0001,
      "loss": 3.4155,
      "step": 5
    },
    {
      "epoch": 0.0002243577758665819,
      "grad_norm": 0.4845415949821472,
      "learning_rate": 0.00012,
      "loss": 2.6348,
      "step": 6
    },
    {
      "epoch": 0.0002243577758665819,
      "eval_loss": 0.6917085647583008,
      "eval_runtime": 149.9897,
      "eval_samples_per_second": 75.078,
      "eval_steps_per_second": 37.543,
      "step": 6
    },
    {
      "epoch": 0.0002617507385110122,
      "grad_norm": 0.5297170877456665,
      "learning_rate": 0.00014,
      "loss": 2.4877,
      "step": 7
    },
    {
      "epoch": 0.00029914370115544255,
      "grad_norm": 0.7077357769012451,
      "learning_rate": 0.00016,
      "loss": 3.1547,
      "step": 8
    },
    {
      "epoch": 0.0003365366637998729,
      "grad_norm": 0.5892812013626099,
      "learning_rate": 0.00018,
      "loss": 2.7252,
      "step": 9
    },
    {
      "epoch": 0.0003365366637998729,
      "eval_loss": 0.6855435967445374,
      "eval_runtime": 125.6436,
      "eval_samples_per_second": 89.627,
      "eval_steps_per_second": 44.817,
      "step": 9
    },
    {
      "epoch": 0.0003739296264443032,
      "grad_norm": 0.699952244758606,
      "learning_rate": 0.0002,
      "loss": 2.732,
      "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": 23344988553216.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}