Hugging Face's logo

robiual-awal
/
33289e61-d618-46d8-a533-709428c58484

PEFT
Safetensors
gpt_neo
axolotl
Generated from Trainer
Model card Files Community
33289e61-d618-46d8-a533-709428c58484
File size: 3,202 Bytes 
bb2d0e0
 
 
d7ae977
bb2d0e0
d7ae977
bb2d0e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7ea523
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b55400f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d7ae977
 
 
 
 
 
 
bb2d0e0
 
 
 
 
 
 
 
 
 
 
 
 
 
d7ae977
bb2d0e0
 
 
 
d7ae977
bb2d0e0
 
 
 
 
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": 0.0025935291447837646,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025935291447837645,
      "grad_norm": 5.132763385772705,
      "learning_rate": 2e-05,
      "loss": 27.91,
      "step": 1
    },
    {
      "epoch": 0.00025935291447837645,
      "eval_loss": 4.831871509552002,
      "eval_runtime": 28.6728,
      "eval_samples_per_second": 56.639,
      "eval_steps_per_second": 28.32,
      "step": 1
    },
    {
      "epoch": 0.0005187058289567529,
      "grad_norm": 4.572207450866699,
      "learning_rate": 4e-05,
      "loss": 19.1465,
      "step": 2
    },
    {
      "epoch": 0.0007780587434351293,
      "grad_norm": 4.086507320404053,
      "learning_rate": 6e-05,
      "loss": 20.8536,
      "step": 3
    },
    {
      "epoch": 0.0007780587434351293,
      "eval_loss": 4.829874038696289,
      "eval_runtime": 28.4488,
      "eval_samples_per_second": 57.085,
      "eval_steps_per_second": 28.543,
      "step": 3
    },
    {
      "epoch": 0.0010374116579135058,
      "grad_norm": 3.4174814224243164,
      "learning_rate": 8e-05,
      "loss": 17.5205,
      "step": 4
    },
    {
      "epoch": 0.0012967645723918823,
      "grad_norm": 3.08579158782959,
      "learning_rate": 0.0001,
      "loss": 17.1885,
      "step": 5
    },
    {
      "epoch": 0.0015561174868702586,
      "grad_norm": 2.652798891067505,
      "learning_rate": 0.00012,
      "loss": 12.6005,
      "step": 6
    },
    {
      "epoch": 0.0015561174868702586,
      "eval_loss": 4.7930426597595215,
      "eval_runtime": 28.532,
      "eval_samples_per_second": 56.919,
      "eval_steps_per_second": 28.459,
      "step": 6
    },
    {
      "epoch": 0.0018154704013486351,
      "grad_norm": 4.396174907684326,
      "learning_rate": 0.00014,
      "loss": 16.8671,
      "step": 7
    },
    {
      "epoch": 0.0020748233158270116,
      "grad_norm": 5.884392261505127,
      "learning_rate": 0.00016,
      "loss": 19.9732,
      "step": 8
    },
    {
      "epoch": 0.002334176230305388,
      "grad_norm": 5.952862739562988,
      "learning_rate": 0.00018,
      "loss": 19.1747,
      "step": 9
    },
    {
      "epoch": 0.002334176230305388,
      "eval_loss": 4.522780418395996,
      "eval_runtime": 28.5558,
      "eval_samples_per_second": 56.871,
      "eval_steps_per_second": 28.436,
      "step": 9
    },
    {
      "epoch": 0.0025935291447837646,
      "grad_norm": 5.507638931274414,
      "learning_rate": 0.0002,
      "loss": 18.321,
      "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": 328602344226816.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}