Hugging Face's logo

trenden
/
aea93864-f490-4dad-a398-5693412882f1

PEFT
Safetensors
phi
axolotl
Generated from Trainer
Model card Files Community
aea93864-f490-4dad-a398-5693412882f1
File size: 3,223 Bytes 
a026eb8
 
 
a68c9f3
a026eb8
a68c9f3
a026eb8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
558186a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
211d334
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a68c9f3
 
 
 
 
 
 
a026eb8
 
 
 
 
 
 
 
 
 
 
 
 
 
a68c9f3
a026eb8
 
 
 
a68c9f3
a026eb8
 
 
 
 
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": 0.00034903100267881293,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.490310026788129e-05,
      "grad_norm": 0.5575522184371948,
      "learning_rate": 2e-05,
      "loss": 6.9513,
      "step": 1
    },
    {
      "epoch": 3.490310026788129e-05,
      "eval_loss": 6.950506687164307,
      "eval_runtime": 29.0808,
      "eval_samples_per_second": 414.844,
      "eval_steps_per_second": 207.422,
      "step": 1
    },
    {
      "epoch": 6.980620053576259e-05,
      "grad_norm": 0.46428191661834717,
      "learning_rate": 4e-05,
      "loss": 6.9515,
      "step": 2
    },
    {
      "epoch": 0.00010470930080364388,
      "grad_norm": 0.6071829199790955,
      "learning_rate": 6e-05,
      "loss": 6.9461,
      "step": 3
    },
    {
      "epoch": 0.00010470930080364388,
      "eval_loss": 6.949868202209473,
      "eval_runtime": 28.4926,
      "eval_samples_per_second": 423.409,
      "eval_steps_per_second": 211.704,
      "step": 3
    },
    {
      "epoch": 0.00013961240107152517,
      "grad_norm": 0.49404385685920715,
      "learning_rate": 8e-05,
      "loss": 6.9545,
      "step": 4
    },
    {
      "epoch": 0.00017451550133940646,
      "grad_norm": 0.48088663816452026,
      "learning_rate": 0.0001,
      "loss": 6.9399,
      "step": 5
    },
    {
      "epoch": 0.00020941860160728776,
      "grad_norm": 0.5026301145553589,
      "learning_rate": 0.00012,
      "loss": 6.9608,
      "step": 6
    },
    {
      "epoch": 0.00020941860160728776,
      "eval_loss": 6.946343898773193,
      "eval_runtime": 28.6679,
      "eval_samples_per_second": 420.819,
      "eval_steps_per_second": 210.41,
      "step": 6
    },
    {
      "epoch": 0.0002443217018751691,
      "grad_norm": 0.5813419222831726,
      "learning_rate": 0.00014,
      "loss": 6.9556,
      "step": 7
    },
    {
      "epoch": 0.00027922480214305034,
      "grad_norm": 0.6712679266929626,
      "learning_rate": 0.00016,
      "loss": 6.9495,
      "step": 8
    },
    {
      "epoch": 0.00031412790241093166,
      "grad_norm": 0.5434843897819519,
      "learning_rate": 0.00018,
      "loss": 6.9555,
      "step": 9
    },
    {
      "epoch": 0.00031412790241093166,
      "eval_loss": 6.940571308135986,
      "eval_runtime": 28.3785,
      "eval_samples_per_second": 425.111,
      "eval_steps_per_second": 212.555,
      "step": 9
    },
    {
      "epoch": 0.00034903100267881293,
      "grad_norm": 0.6451368927955627,
      "learning_rate": 0.0002,
      "loss": 6.9503,
      "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": 16808712192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}