Hugging Face's logo

vermoney
/
e5006e22-5802-46da-b1d5-ff13a9e779fc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e5006e22-5802-46da-b1d5-ff13a9e779fc
File size: 3,108 Bytes 
daea079
fba331c
 
 
daea079
fba331c
daea079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fba331c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
daea079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fba331c
daea079
 
 
 
 
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": 1.3194067478179932,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.01634988759452279,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008174943797261394,
      "eval_loss": 1.6600309610366821,
      "eval_runtime": 20.0591,
      "eval_samples_per_second": 25.674,
      "eval_steps_per_second": 12.862,
      "step": 1
    },
    {
      "epoch": 0.002452483139178418,
      "grad_norm": 0.657343327999115,
      "learning_rate": 6e-05,
      "loss": 1.6849,
      "step": 3
    },
    {
      "epoch": 0.004087471898630697,
      "eval_loss": 1.6067190170288086,
      "eval_runtime": 19.7624,
      "eval_samples_per_second": 26.06,
      "eval_steps_per_second": 13.055,
      "step": 5
    },
    {
      "epoch": 0.004904966278356836,
      "grad_norm": 0.6308304667472839,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.6658,
      "step": 6
    },
    {
      "epoch": 0.007357449417535254,
      "grad_norm": 0.6857329607009888,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.534,
      "step": 9
    },
    {
      "epoch": 0.008174943797261395,
      "eval_loss": 1.456212043762207,
      "eval_runtime": 20.3175,
      "eval_samples_per_second": 25.348,
      "eval_steps_per_second": 12.698,
      "step": 10
    },
    {
      "epoch": 0.009809932556713672,
      "grad_norm": 0.7650735974311829,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.4606,
      "step": 12
    },
    {
      "epoch": 0.012262415695892091,
      "grad_norm": 0.7929948568344116,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3442,
      "step": 15
    },
    {
      "epoch": 0.012262415695892091,
      "eval_loss": 1.3643509149551392,
      "eval_runtime": 20.8425,
      "eval_samples_per_second": 24.709,
      "eval_steps_per_second": 12.379,
      "step": 15
    },
    {
      "epoch": 0.014714898835070508,
      "grad_norm": 0.6958890557289124,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.3561,
      "step": 18
    },
    {
      "epoch": 0.01634988759452279,
      "eval_loss": 1.3194067478179932,
      "eval_runtime": 21.3468,
      "eval_samples_per_second": 24.125,
      "eval_steps_per_second": 12.086,
      "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": 1040301762281472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}