Hugging Face's logo

havinash-ai
/
8d0e860d-d138-46af-991f-eb37f54bc7af

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
8d0e860d-d138-46af-991f-eb37f54bc7af
File size: 3,205 Bytes 
8686afe
 
 
08c38e3
8686afe
08c38e3
8686afe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa02483
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90dfab2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
08c38e3
 
 
 
 
 
 
8686afe
 
 
 
 
 
 
 
 
 
 
 
 
 
08c38e3
8686afe
 
 
 
08c38e3
8686afe
 
 
 
 
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": 0.0032144005143040825,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003214400514304082,
      "grad_norm": 2.2572340965270996,
      "learning_rate": 2e-05,
      "loss": 8.2829,
      "step": 1
    },
    {
      "epoch": 0.0003214400514304082,
      "eval_loss": 2.0177955627441406,
      "eval_runtime": 60.9708,
      "eval_samples_per_second": 21.486,
      "eval_steps_per_second": 10.743,
      "step": 1
    },
    {
      "epoch": 0.0006428801028608164,
      "grad_norm": 2.169924736022949,
      "learning_rate": 4e-05,
      "loss": 7.2637,
      "step": 2
    },
    {
      "epoch": 0.0009643201542912247,
      "grad_norm": 1.8544375896453857,
      "learning_rate": 6e-05,
      "loss": 7.9408,
      "step": 3
    },
    {
      "epoch": 0.0009643201542912247,
      "eval_loss": 2.0139975547790527,
      "eval_runtime": 59.6992,
      "eval_samples_per_second": 21.943,
      "eval_steps_per_second": 10.972,
      "step": 3
    },
    {
      "epoch": 0.0012857602057216328,
      "grad_norm": 2.2169251441955566,
      "learning_rate": 8e-05,
      "loss": 8.4545,
      "step": 4
    },
    {
      "epoch": 0.0016072002571520412,
      "grad_norm": 2.4655027389526367,
      "learning_rate": 0.0001,
      "loss": 9.0766,
      "step": 5
    },
    {
      "epoch": 0.0019286403085824494,
      "grad_norm": 1.885632038116455,
      "learning_rate": 0.00012,
      "loss": 7.623,
      "step": 6
    },
    {
      "epoch": 0.0019286403085824494,
      "eval_loss": 1.981154441833496,
      "eval_runtime": 59.8218,
      "eval_samples_per_second": 21.898,
      "eval_steps_per_second": 10.949,
      "step": 6
    },
    {
      "epoch": 0.0022500803600128574,
      "grad_norm": 1.9592024087905884,
      "learning_rate": 0.00014,
      "loss": 7.3957,
      "step": 7
    },
    {
      "epoch": 0.0025715204114432656,
      "grad_norm": 3.445594310760498,
      "learning_rate": 0.00016,
      "loss": 8.7616,
      "step": 8
    },
    {
      "epoch": 0.0028929604628736743,
      "grad_norm": 2.8671069145202637,
      "learning_rate": 0.00018,
      "loss": 6.9782,
      "step": 9
    },
    {
      "epoch": 0.0028929604628736743,
      "eval_loss": 1.8752474784851074,
      "eval_runtime": 59.7402,
      "eval_samples_per_second": 21.928,
      "eval_steps_per_second": 10.964,
      "step": 9
    },
    {
      "epoch": 0.0032144005143040825,
      "grad_norm": 3.177637815475464,
      "learning_rate": 0.0002,
      "loss": 7.9653,
      "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": 4065247635701760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}