Hugging Face's logo

havinash-ai
/
d98d3321-60db-471e-abd0-d3f440ba325e

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
d98d3321-60db-471e-abd0-d3f440ba325e
File size: 3,198 Bytes 
9dd6d0e
 
 
e3c16b6
9dd6d0e
e3c16b6
9dd6d0e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fea5da4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed7bad1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e3c16b6
 
 
 
 
 
 
9dd6d0e
 
 
 
 
 
 
 
 
 
 
 
 
 
e3c16b6
9dd6d0e
 
 
 
e3c16b6
9dd6d0e
 
 
 
 
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": 0.005198180636777128,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005198180636777127,
      "grad_norm": 23.709779739379883,
      "learning_rate": 2e-05,
      "loss": 6.7677,
      "step": 1
    },
    {
      "epoch": 0.0005198180636777127,
      "eval_loss": 1.7232974767684937,
      "eval_runtime": 11.0332,
      "eval_samples_per_second": 73.505,
      "eval_steps_per_second": 36.798,
      "step": 1
    },
    {
      "epoch": 0.0010396361273554255,
      "grad_norm": 22.800851821899414,
      "learning_rate": 4e-05,
      "loss": 6.6812,
      "step": 2
    },
    {
      "epoch": 0.0015594541910331384,
      "grad_norm": 20.774221420288086,
      "learning_rate": 6e-05,
      "loss": 6.322,
      "step": 3
    },
    {
      "epoch": 0.0015594541910331384,
      "eval_loss": 1.7247177362442017,
      "eval_runtime": 10.0207,
      "eval_samples_per_second": 80.933,
      "eval_steps_per_second": 40.516,
      "step": 3
    },
    {
      "epoch": 0.002079272254710851,
      "grad_norm": 21.69985008239746,
      "learning_rate": 8e-05,
      "loss": 6.3464,
      "step": 4
    },
    {
      "epoch": 0.002599090318388564,
      "grad_norm": 22.491409301757812,
      "learning_rate": 0.0001,
      "loss": 6.5938,
      "step": 5
    },
    {
      "epoch": 0.0031189083820662767,
      "grad_norm": 16.3961124420166,
      "learning_rate": 0.00012,
      "loss": 7.0652,
      "step": 6
    },
    {
      "epoch": 0.0031189083820662767,
      "eval_loss": 1.7147853374481201,
      "eval_runtime": 10.1211,
      "eval_samples_per_second": 80.129,
      "eval_steps_per_second": 40.114,
      "step": 6
    },
    {
      "epoch": 0.0036387264457439896,
      "grad_norm": 21.415868759155273,
      "learning_rate": 0.00014,
      "loss": 7.4779,
      "step": 7
    },
    {
      "epoch": 0.004158544509421702,
      "grad_norm": 21.27906608581543,
      "learning_rate": 0.00016,
      "loss": 7.0148,
      "step": 8
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 22.285511016845703,
      "learning_rate": 0.00018,
      "loss": 6.5852,
      "step": 9
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 1.6819708347320557,
      "eval_runtime": 10.1342,
      "eval_samples_per_second": 80.026,
      "eval_steps_per_second": 40.062,
      "step": 9
    },
    {
      "epoch": 0.005198180636777128,
      "grad_norm": 25.407556533813477,
      "learning_rate": 0.0002,
      "loss": 6.4671,
      "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": 175457131560960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}