Hugging Face's logo

laquythang
/
c0ea47d1-26f2-4180-8f45-7bddb8dea95d

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
c0ea47d1-26f2-4180-8f45-7bddb8dea95d
File size: 3,051 Bytes 
e381419
 
 
c0c469b
e381419
c0c469b
e381419
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
845ee50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c0c469b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e381419
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c0c469b
e381419
 
 
 
 
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": 0.0001334930305513633,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4832558950151478e-05,
      "grad_norm": 1058.962646484375,
      "learning_rate": 2e-05,
      "loss": 95.6979,
      "step": 1
    },
    {
      "epoch": 1.4832558950151478e-05,
      "eval_loss": 23.534069061279297,
      "eval_runtime": 2771.2737,
      "eval_samples_per_second": 10.243,
      "eval_steps_per_second": 5.122,
      "step": 1
    },
    {
      "epoch": 2.9665117900302956e-05,
      "grad_norm": 1248.5556640625,
      "learning_rate": 4e-05,
      "loss": 96.301,
      "step": 2
    },
    {
      "epoch": 4.449767685045443e-05,
      "grad_norm": 1384.484130859375,
      "learning_rate": 6e-05,
      "loss": 95.2121,
      "step": 3
    },
    {
      "epoch": 4.449767685045443e-05,
      "eval_loss": 23.525821685791016,
      "eval_runtime": 2674.4343,
      "eval_samples_per_second": 10.614,
      "eval_steps_per_second": 5.307,
      "step": 3
    },
    {
      "epoch": 5.933023580060591e-05,
      "grad_norm": 1268.106689453125,
      "learning_rate": 8e-05,
      "loss": 93.7818,
      "step": 4
    },
    {
      "epoch": 7.416279475075739e-05,
      "grad_norm": 1168.54541015625,
      "learning_rate": 0.0001,
      "loss": 95.2982,
      "step": 5
    },
    {
      "epoch": 8.899535370090886e-05,
      "grad_norm": 1219.5244140625,
      "learning_rate": 0.00012,
      "loss": 94.5744,
      "step": 6
    },
    {
      "epoch": 8.899535370090886e-05,
      "eval_loss": 23.49866485595703,
      "eval_runtime": 2649.0765,
      "eval_samples_per_second": 10.716,
      "eval_steps_per_second": 5.358,
      "step": 6
    },
    {
      "epoch": 0.00010382791265106034,
      "grad_norm": 1748.5992431640625,
      "learning_rate": 0.00014,
      "loss": 92.2292,
      "step": 7
    },
    {
      "epoch": 0.00011866047160121182,
      "grad_norm": 1009.4827880859375,
      "learning_rate": 0.00016,
      "loss": 93.0452,
      "step": 8
    },
    {
      "epoch": 0.0001334930305513633,
      "grad_norm": 1561.128173828125,
      "learning_rate": 0.00018,
      "loss": 94.7347,
      "step": 9
    },
    {
      "epoch": 0.0001334930305513633,
      "eval_loss": 23.4540958404541,
      "eval_runtime": 2399.9327,
      "eval_samples_per_second": 11.828,
      "eval_steps_per_second": 5.914,
      "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": 80435610648576.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}