Hugging Face's logo

tuanna08go
/
98e9fcdb-5dc3-4c9e-87cf-6d4c3ba3f193

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files
xet
Community
98e9fcdb-5dc3-4c9e-87cf-6d4c3ba3f193
File size: 3,697 Bytes 
2b12c92
 
 
6d16001
c9e9396
6d16001
2b12c92
 
 
 
 
 
 
c9e9396
 
 
2b12c92
c9e9396
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a97b615
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d368a61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6d16001
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2b12c92
 
 
c9e9396
2b12c92
 
c9e9396
2b12c92
 
 
 
 
 
 
6d16001
2b12c92
 
 
 
6d16001
2b12c92
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08688097306689835,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017376194613379669,
      "eval_loss": 6.652885437011719,
      "eval_runtime": 2.6405,
      "eval_samples_per_second": 92.028,
      "eval_steps_per_second": 46.203,
      "step": 1
    },
    {
      "epoch": 0.008688097306689836,
      "grad_norm": 4713.6005859375,
      "learning_rate": 5e-05,
      "loss": 27.0279,
      "step": 5
    },
    {
      "epoch": 0.01737619461337967,
      "grad_norm": 4841.03955078125,
      "learning_rate": 0.0001,
      "loss": 26.4966,
      "step": 10
    },
    {
      "epoch": 0.01737619461337967,
      "eval_loss": 6.604281425476074,
      "eval_runtime": 1.6508,
      "eval_samples_per_second": 147.206,
      "eval_steps_per_second": 73.906,
      "step": 10
    },
    {
      "epoch": 0.026064291920069503,
      "grad_norm": 6471.283203125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 26.1516,
      "step": 15
    },
    {
      "epoch": 0.03475238922675934,
      "grad_norm": 5566.80908203125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 25.9504,
      "step": 20
    },
    {
      "epoch": 0.03475238922675934,
      "eval_loss": 6.513936519622803,
      "eval_runtime": 1.6905,
      "eval_samples_per_second": 143.742,
      "eval_steps_per_second": 72.167,
      "step": 20
    },
    {
      "epoch": 0.043440486533449174,
      "grad_norm": 4252.45458984375,
      "learning_rate": 6.91341716182545e-05,
      "loss": 26.1708,
      "step": 25
    },
    {
      "epoch": 0.052128583840139006,
      "grad_norm": 3892.208740234375,
      "learning_rate": 5e-05,
      "loss": 26.0941,
      "step": 30
    },
    {
      "epoch": 0.052128583840139006,
      "eval_loss": 6.443342685699463,
      "eval_runtime": 1.7024,
      "eval_samples_per_second": 142.739,
      "eval_steps_per_second": 71.663,
      "step": 30
    },
    {
      "epoch": 0.060816681146828845,
      "grad_norm": 4265.82373046875,
      "learning_rate": 3.086582838174551e-05,
      "loss": 25.3217,
      "step": 35
    },
    {
      "epoch": 0.06950477845351868,
      "grad_norm": 3242.72119140625,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 25.3607,
      "step": 40
    },
    {
      "epoch": 0.06950477845351868,
      "eval_loss": 6.420129776000977,
      "eval_runtime": 1.6872,
      "eval_samples_per_second": 144.022,
      "eval_steps_per_second": 72.307,
      "step": 40
    },
    {
      "epoch": 0.07819287576020852,
      "grad_norm": 3691.49462890625,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 25.7192,
      "step": 45
    },
    {
      "epoch": 0.08688097306689835,
      "grad_norm": 4117.0908203125,
      "learning_rate": 0.0,
      "loss": 25.7918,
      "step": 50
    },
    {
      "epoch": 0.08688097306689835,
      "eval_loss": 6.41416072845459,
      "eval_runtime": 1.7003,
      "eval_samples_per_second": 142.919,
      "eval_steps_per_second": 71.753,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11014275858432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}