Hugging Face's logo

kostiantynk-out
/
5ccd1428-91f0-4fbe-a8cd-0c6faed6dde3

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
5ccd1428-91f0-4fbe-a8cd-0c6faed6dde3
File size: 3,203 Bytes 
1a738e9
 
 
1640172
1a738e9
1640172
1a738e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c34358a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22d54dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1640172
 
 
 
 
 
 
1a738e9
 
 
 
 
 
 
 
 
 
 
 
 
 
1640172
1a738e9
 
 
 
1640172
1a738e9
 
 
 
 
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": 0.0017720285296593276,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017720285296593275,
      "grad_norm": 68.23906707763672,
      "learning_rate": 2e-05,
      "loss": 20.6003,
      "step": 1
    },
    {
      "epoch": 0.00017720285296593275,
      "eval_loss": 4.623178482055664,
      "eval_runtime": 34.268,
      "eval_samples_per_second": 69.365,
      "eval_steps_per_second": 34.697,
      "step": 1
    },
    {
      "epoch": 0.0003544057059318655,
      "grad_norm": 47.974525451660156,
      "learning_rate": 4e-05,
      "loss": 18.135,
      "step": 2
    },
    {
      "epoch": 0.0005316085588977983,
      "grad_norm": 67.08570861816406,
      "learning_rate": 6e-05,
      "loss": 18.75,
      "step": 3
    },
    {
      "epoch": 0.0005316085588977983,
      "eval_loss": 4.618465423583984,
      "eval_runtime": 32.7311,
      "eval_samples_per_second": 72.622,
      "eval_steps_per_second": 36.326,
      "step": 3
    },
    {
      "epoch": 0.000708811411863731,
      "grad_norm": 59.070701599121094,
      "learning_rate": 8e-05,
      "loss": 17.0189,
      "step": 4
    },
    {
      "epoch": 0.0008860142648296638,
      "grad_norm": 53.60502624511719,
      "learning_rate": 0.0001,
      "loss": 18.4737,
      "step": 5
    },
    {
      "epoch": 0.0010632171177955966,
      "grad_norm": 62.920711517333984,
      "learning_rate": 0.00012,
      "loss": 18.7371,
      "step": 6
    },
    {
      "epoch": 0.0010632171177955966,
      "eval_loss": 4.5854315757751465,
      "eval_runtime": 32.4984,
      "eval_samples_per_second": 73.142,
      "eval_steps_per_second": 36.586,
      "step": 6
    },
    {
      "epoch": 0.0012404199707615293,
      "grad_norm": 96.0009765625,
      "learning_rate": 0.00014,
      "loss": 21.3063,
      "step": 7
    },
    {
      "epoch": 0.001417622823727462,
      "grad_norm": 56.73752975463867,
      "learning_rate": 0.00016,
      "loss": 16.3515,
      "step": 8
    },
    {
      "epoch": 0.0015948256766933947,
      "grad_norm": 55.107513427734375,
      "learning_rate": 0.00018,
      "loss": 19.0825,
      "step": 9
    },
    {
      "epoch": 0.0015948256766933947,
      "eval_loss": 4.481025218963623,
      "eval_runtime": 32.4589,
      "eval_samples_per_second": 73.231,
      "eval_steps_per_second": 36.631,
      "step": 9
    },
    {
      "epoch": 0.0017720285296593276,
      "grad_norm": 64.37794494628906,
      "learning_rate": 0.0002,
      "loss": 18.2627,
      "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": 122819992092672.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}