Hugging Face's logo

tuanna08go
/
236afb2b-70bc-4f99-aec5-db7be14a2434

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files Community
236afb2b-70bc-4f99-aec5-db7be14a2434
File size: 2,797 Bytes 
21edd21
 
 
1d97e7b
917e187
1d97e7b
21edd21
 
 
 
 
 
 
917e187
 
 
21edd21
917e187
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c362e9b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1d97e7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21edd21
 
 
917e187
21edd21
 
917e187
21edd21
 
 
 
 
 
 
917e187
21edd21
 
 
 
1d97e7b
21edd21
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0035929798700999587,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.212768897692202e-05,
      "eval_loss": 3.2426815032958984,
      "eval_runtime": 267.9849,
      "eval_samples_per_second": 17.057,
      "eval_steps_per_second": 8.53,
      "step": 1
    },
    {
      "epoch": 0.0004606384448846101,
      "grad_norm": 2.7321012020111084,
      "learning_rate": 5e-05,
      "loss": 13.2688,
      "step": 5
    },
    {
      "epoch": 0.0009212768897692202,
      "grad_norm": 3.018977403640747,
      "learning_rate": 0.0001,
      "loss": 11.4541,
      "step": 10
    },
    {
      "epoch": 0.0009212768897692202,
      "eval_loss": 3.052807331085205,
      "eval_runtime": 268.2599,
      "eval_samples_per_second": 17.039,
      "eval_steps_per_second": 8.522,
      "step": 10
    },
    {
      "epoch": 0.0013819153346538303,
      "grad_norm": 5.066298961639404,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.4043,
      "step": 15
    },
    {
      "epoch": 0.0018425537795384403,
      "grad_norm": 2.848259687423706,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.0901,
      "step": 20
    },
    {
      "epoch": 0.0018425537795384403,
      "eval_loss": 2.4847605228424072,
      "eval_runtime": 267.7916,
      "eval_samples_per_second": 17.069,
      "eval_steps_per_second": 8.536,
      "step": 20
    },
    {
      "epoch": 0.0023031922244230504,
      "grad_norm": 3.9828901290893555,
      "learning_rate": 6.91341716182545e-05,
      "loss": 9.5732,
      "step": 25
    },
    {
      "epoch": 0.0027638306693076606,
      "grad_norm": 3.964927911758423,
      "learning_rate": 5e-05,
      "loss": 9.1613,
      "step": 30
    },
    {
      "epoch": 0.0027638306693076606,
      "eval_loss": 2.22302508354187,
      "eval_runtime": 268.9169,
      "eval_samples_per_second": 16.998,
      "eval_steps_per_second": 8.501,
      "step": 30
    },
    {
      "epoch": 0.0032244691141922704,
      "grad_norm": 3.796499013900757,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.9359,
      "step": 35
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4222585537560576.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}