Hugging Face's logo

kk-aivio
/
93845642-941b-4de3-bdbe-cb8146a52b66

PEFT
Safetensors
phi
axolotl
Generated from Trainer
Model card Files Community
93845642-941b-4de3-bdbe-cb8146a52b66
File size: 2,474 Bytes 
d661a01
 
 
1224f12
d661a01
1224f12
d661a01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3e733c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1cb9549
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1224f12
 
 
 
 
 
 
 
 
 
 
 
 
 
d661a01
 
 
 
 
 
 
 
 
 
 
 
 
 
1224f12
d661a01
 
 
 
1224f12
d661a01
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00843775049571784,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016875500991435683,
      "eval_loss": 1.6930816173553467,
      "eval_runtime": 57.8268,
      "eval_samples_per_second": 43.146,
      "eval_steps_per_second": 21.582,
      "step": 1
    },
    {
      "epoch": 0.0016875500991435683,
      "grad_norm": 3.9818174839019775,
      "learning_rate": 0.00019396926207859084,
      "loss": 1.7126,
      "step": 10
    },
    {
      "epoch": 0.0021938151288866388,
      "eval_loss": 1.502448320388794,
      "eval_runtime": 56.5446,
      "eval_samples_per_second": 44.124,
      "eval_steps_per_second": 22.071,
      "step": 13
    },
    {
      "epoch": 0.0033751001982871365,
      "grad_norm": 5.268524169921875,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5099,
      "step": 20
    },
    {
      "epoch": 0.0043876302577732776,
      "eval_loss": 1.3147406578063965,
      "eval_runtime": 56.6894,
      "eval_samples_per_second": 44.012,
      "eval_steps_per_second": 22.015,
      "step": 26
    },
    {
      "epoch": 0.005062650297430705,
      "grad_norm": 8.063873291015625,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.3195,
      "step": 30
    },
    {
      "epoch": 0.006581445386659917,
      "eval_loss": 1.2810492515563965,
      "eval_runtime": 56.5925,
      "eval_samples_per_second": 44.087,
      "eval_steps_per_second": 22.052,
      "step": 39
    },
    {
      "epoch": 0.006750200396574273,
      "grad_norm": 6.396270751953125,
      "learning_rate": 2.339555568810221e-05,
      "loss": 1.3132,
      "step": 40
    },
    {
      "epoch": 0.00843775049571784,
      "grad_norm": 6.293328285217285,
      "learning_rate": 0.0,
      "loss": 1.2793,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": 3269109743616000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}