Hugging Face's logo

dzanbek
/
ec5d741e-2d5f-41c3-adf6-c54d102cf960

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ec5d741e-2d5f-41c3-adf6-c54d102cf960
File size: 3,089 Bytes 
9094753
748ac95
 
 
9094753
748ac95
9094753
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
748ac95
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9094753
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
748ac95
9094753
 
 
 
 
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": 1.1814048290252686,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.006811409110259685,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034057045551298427,
      "eval_loss": 1.4796533584594727,
      "eval_runtime": 164.2532,
      "eval_samples_per_second": 7.531,
      "eval_steps_per_second": 3.769,
      "step": 1
    },
    {
      "epoch": 0.0010217113665389529,
      "grad_norm": 0.384747713804245,
      "learning_rate": 6e-05,
      "loss": 1.3415,
      "step": 3
    },
    {
      "epoch": 0.0017028522775649213,
      "eval_loss": 1.4507091045379639,
      "eval_runtime": 165.8491,
      "eval_samples_per_second": 7.459,
      "eval_steps_per_second": 3.732,
      "step": 5
    },
    {
      "epoch": 0.0020434227330779057,
      "grad_norm": 0.5841999053955078,
      "learning_rate": 0.00012,
      "loss": 1.2883,
      "step": 6
    },
    {
      "epoch": 0.0030651340996168583,
      "grad_norm": 0.470478892326355,
      "learning_rate": 0.00018,
      "loss": 1.2974,
      "step": 9
    },
    {
      "epoch": 0.0034057045551298426,
      "eval_loss": 1.2941644191741943,
      "eval_runtime": 165.8717,
      "eval_samples_per_second": 7.458,
      "eval_steps_per_second": 3.732,
      "step": 10
    },
    {
      "epoch": 0.004086845466155811,
      "grad_norm": 0.5516128540039062,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.2105,
      "step": 12
    },
    {
      "epoch": 0.005108556832694764,
      "grad_norm": 0.6083524227142334,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.3534,
      "step": 15
    },
    {
      "epoch": 0.005108556832694764,
      "eval_loss": 1.2232894897460938,
      "eval_runtime": 165.8974,
      "eval_samples_per_second": 7.456,
      "eval_steps_per_second": 3.731,
      "step": 15
    },
    {
      "epoch": 0.006130268199233717,
      "grad_norm": 0.38056692481040955,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1349,
      "step": 18
    },
    {
      "epoch": 0.006811409110259685,
      "eval_loss": 1.1814048290252686,
      "eval_runtime": 165.895,
      "eval_samples_per_second": 7.457,
      "eval_steps_per_second": 3.731,
      "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": 7354672050339840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}