Hugging Face's logo

vermoney
/
1ac386c7-c595-44ec-9039-b83dd87f852a

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files Community
1ac386c7-c595-44ec-9039-b83dd87f852a
File size: 3,087 Bytes 
196d37f
36d27c7
 
 
196d37f
36d27c7
196d37f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36d27c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
196d37f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36d27c7
196d37f
 
 
 
 
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
 
{
  "best_metric": 0.5212913155555725,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.09111617312072894,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004555808656036446,
      "eval_loss": 0.6795058846473694,
      "eval_runtime": 15.6799,
      "eval_samples_per_second": 5.931,
      "eval_steps_per_second": 2.997,
      "step": 1
    },
    {
      "epoch": 0.01366742596810934,
      "grad_norm": 1.5004208087921143,
      "learning_rate": 6e-05,
      "loss": 2.8563,
      "step": 3
    },
    {
      "epoch": 0.022779043280182234,
      "eval_loss": 0.6548665165901184,
      "eval_runtime": 15.9971,
      "eval_samples_per_second": 5.814,
      "eval_steps_per_second": 2.938,
      "step": 5
    },
    {
      "epoch": 0.02733485193621868,
      "grad_norm": 1.222702145576477,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.6377,
      "step": 6
    },
    {
      "epoch": 0.04100227790432802,
      "grad_norm": 1.2079116106033325,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.425,
      "step": 9
    },
    {
      "epoch": 0.04555808656036447,
      "eval_loss": 0.5925781726837158,
      "eval_runtime": 16.4774,
      "eval_samples_per_second": 5.644,
      "eval_steps_per_second": 2.852,
      "step": 10
    },
    {
      "epoch": 0.05466970387243736,
      "grad_norm": 1.1079726219177246,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.3765,
      "step": 12
    },
    {
      "epoch": 0.0683371298405467,
      "grad_norm": 0.9152125120162964,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1722,
      "step": 15
    },
    {
      "epoch": 0.0683371298405467,
      "eval_loss": 0.5529842972755432,
      "eval_runtime": 17.0438,
      "eval_samples_per_second": 5.457,
      "eval_steps_per_second": 2.758,
      "step": 15
    },
    {
      "epoch": 0.08200455580865604,
      "grad_norm": 1.1765227317810059,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.0581,
      "step": 18
    },
    {
      "epoch": 0.09111617312072894,
      "eval_loss": 0.5212913155555725,
      "eval_runtime": 17.5468,
      "eval_samples_per_second": 5.3,
      "eval_steps_per_second": 2.679,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4467071907790848.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}