Hugging Face's logo

kostiantynk1205
/
ed72accf-be41-4104-adb0-9dd343812b3f

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
ed72accf-be41-4104-adb0-9dd343812b3f
File size: 3,042 Bytes 
49eb952
 
 
4f5e75c
49eb952
4f5e75c
49eb952
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f08c7b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4f5e75c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49eb952
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4f5e75c
49eb952
 
 
 
 
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": 0.0028929604628736743,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003214400514304082,
      "grad_norm": 2.314427375793457,
      "learning_rate": 2e-05,
      "loss": 8.2829,
      "step": 1
    },
    {
      "epoch": 0.0003214400514304082,
      "eval_loss": 2.0177955627441406,
      "eval_runtime": 60.7423,
      "eval_samples_per_second": 21.567,
      "eval_steps_per_second": 10.783,
      "step": 1
    },
    {
      "epoch": 0.0006428801028608164,
      "grad_norm": 2.2097456455230713,
      "learning_rate": 4e-05,
      "loss": 7.2637,
      "step": 2
    },
    {
      "epoch": 0.0009643201542912247,
      "grad_norm": 1.8961241245269775,
      "learning_rate": 6e-05,
      "loss": 7.943,
      "step": 3
    },
    {
      "epoch": 0.0009643201542912247,
      "eval_loss": 2.014782428741455,
      "eval_runtime": 59.5967,
      "eval_samples_per_second": 21.981,
      "eval_steps_per_second": 10.991,
      "step": 3
    },
    {
      "epoch": 0.0012857602057216328,
      "grad_norm": 2.344888925552368,
      "learning_rate": 8e-05,
      "loss": 8.4286,
      "step": 4
    },
    {
      "epoch": 0.0016072002571520412,
      "grad_norm": 2.6145517826080322,
      "learning_rate": 0.0001,
      "loss": 9.0661,
      "step": 5
    },
    {
      "epoch": 0.0019286403085824494,
      "grad_norm": 1.9498443603515625,
      "learning_rate": 0.00012,
      "loss": 7.5982,
      "step": 6
    },
    {
      "epoch": 0.0019286403085824494,
      "eval_loss": 1.9811270236968994,
      "eval_runtime": 59.6772,
      "eval_samples_per_second": 21.951,
      "eval_steps_per_second": 10.976,
      "step": 6
    },
    {
      "epoch": 0.0022500803600128574,
      "grad_norm": 2.0184409618377686,
      "learning_rate": 0.00014,
      "loss": 7.381,
      "step": 7
    },
    {
      "epoch": 0.0025715204114432656,
      "grad_norm": 3.489924669265747,
      "learning_rate": 0.00016,
      "loss": 8.7444,
      "step": 8
    },
    {
      "epoch": 0.0028929604628736743,
      "grad_norm": 2.901017904281616,
      "learning_rate": 0.00018,
      "loss": 6.9573,
      "step": 9
    },
    {
      "epoch": 0.0028929604628736743,
      "eval_loss": 1.8749172687530518,
      "eval_runtime": 59.6544,
      "eval_samples_per_second": 21.96,
      "eval_steps_per_second": 10.98,
      "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": 3637326831943680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}