Hugging Face's logo

chauhoang
/
620be513-90da-06ab-a04f-bd410a8cf8d3

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
620be513-90da-06ab-a04f-bd410a8cf8d3
File size: 2,775 Bytes 
a75dccf
 
 
c15822c
a18b4f9
c15822c
a75dccf
 
 
 
 
 
 
a18b4f9
 
 
a75dccf
a18b4f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
adf11d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c15822c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a75dccf
 
 
a18b4f9
a75dccf
 
a18b4f9
a75dccf
 
 
 
 
 
 
a18b4f9
a75dccf
 
 
 
c15822c
a75dccf
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10893854748603352,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002793296089385475,
      "eval_loss": 2.4049742221832275,
      "eval_runtime": 13.2901,
      "eval_samples_per_second": 11.362,
      "eval_steps_per_second": 5.719,
      "step": 1
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 2.8598062992095947,
      "learning_rate": 5e-05,
      "loss": 9.1267,
      "step": 5
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 4.437131881713867,
      "learning_rate": 0.0001,
      "loss": 8.7871,
      "step": 10
    },
    {
      "epoch": 0.027932960893854747,
      "eval_loss": 2.1106879711151123,
      "eval_runtime": 12.4419,
      "eval_samples_per_second": 12.136,
      "eval_steps_per_second": 6.108,
      "step": 10
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 3.954702854156494,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.7161,
      "step": 15
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 4.341027736663818,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.666,
      "step": 20
    },
    {
      "epoch": 0.055865921787709494,
      "eval_loss": 1.68687903881073,
      "eval_runtime": 12.5323,
      "eval_samples_per_second": 12.049,
      "eval_steps_per_second": 6.064,
      "step": 20
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 4.4329705238342285,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.7389,
      "step": 25
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 4.825051307678223,
      "learning_rate": 5e-05,
      "loss": 6.4153,
      "step": 30
    },
    {
      "epoch": 0.08379888268156424,
      "eval_loss": 1.5849660634994507,
      "eval_runtime": 12.6209,
      "eval_samples_per_second": 11.964,
      "eval_steps_per_second": 6.022,
      "step": 30
    },
    {
      "epoch": 0.09776536312849161,
      "grad_norm": 4.308661937713623,
      "learning_rate": 3.086582838174551e-05,
      "loss": 6.0258,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112594089771008e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}