Hugging Face's logo

ardaspear
/
ee1dcdaf-4c63-4037-a8dd-e9d476c5a849

PEFT
Safetensors
phi
axolotl
Generated from Trainer
Model card Files Community
ee1dcdaf-4c63-4037-a8dd-e9d476c5a849
File size: 3,113 Bytes 
2075230
 
 
a1540c7
2075230
a1540c7
2075230
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
02c0083
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1540c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2075230
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1540c7
2075230
 
 
 
 
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": 0.1377551020408163,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00510204081632653,
      "eval_loss": 6.939616680145264,
      "eval_runtime": 1.0293,
      "eval_samples_per_second": 160.296,
      "eval_steps_per_second": 40.803,
      "step": 1
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 0.4716786742210388,
      "learning_rate": 3e-05,
      "loss": 6.9394,
      "step": 3
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.49812349677085876,
      "learning_rate": 6e-05,
      "loss": 6.9356,
      "step": 6
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 0.5289084911346436,
      "learning_rate": 9e-05,
      "loss": 6.933,
      "step": 9
    },
    {
      "epoch": 0.04591836734693878,
      "eval_loss": 6.927786350250244,
      "eval_runtime": 0.2695,
      "eval_samples_per_second": 612.282,
      "eval_steps_per_second": 155.854,
      "step": 9
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 0.4804115891456604,
      "learning_rate": 9.987820251299122e-05,
      "loss": 6.9266,
      "step": 12
    },
    {
      "epoch": 0.07653061224489796,
      "grad_norm": 0.5177415013313293,
      "learning_rate": 9.924038765061042e-05,
      "loss": 6.9163,
      "step": 15
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": 0.5697883367538452,
      "learning_rate": 9.806308479691595e-05,
      "loss": 6.9044,
      "step": 18
    },
    {
      "epoch": 0.09183673469387756,
      "eval_loss": 6.897478103637695,
      "eval_runtime": 0.271,
      "eval_samples_per_second": 608.897,
      "eval_steps_per_second": 154.992,
      "step": 18
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.5388941168785095,
      "learning_rate": 9.635919272833938e-05,
      "loss": 6.8956,
      "step": 21
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 0.5204723477363586,
      "learning_rate": 9.414737964294636e-05,
      "loss": 6.885,
      "step": 24
    },
    {
      "epoch": 0.1377551020408163,
      "grad_norm": 0.4605754613876343,
      "learning_rate": 9.145187862775209e-05,
      "loss": 6.8733,
      "step": 27
    },
    {
      "epoch": 0.1377551020408163,
      "eval_loss": 6.866656303405762,
      "eval_runtime": 0.2715,
      "eval_samples_per_second": 607.839,
      "eval_steps_per_second": 154.723,
      "step": 27
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 259504570368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}