Hugging Face's logo

infogep
/
0652b690-7959-4e95-b763-f218f66ff4dc

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
0652b690-7959-4e95-b763-f218f66ff4dc
File size: 2,280 Bytes 
5f3f9a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 2.4909262657165527,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.028409090909090908,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005681818181818182,
      "eval_loss": 6.134354591369629,
      "eval_runtime": 47.1556,
      "eval_samples_per_second": 15.714,
      "eval_steps_per_second": 3.944,
      "step": 1
    },
    {
      "epoch": 0.005681818181818182,
      "grad_norm": 10.32190227508545,
      "learning_rate": 5.05e-06,
      "loss": 4.6056,
      "step": 10
    },
    {
      "epoch": 0.011363636363636364,
      "grad_norm": 8.61007022857666,
      "learning_rate": 1.01e-05,
      "loss": 4.191,
      "step": 20
    },
    {
      "epoch": 0.017045454545454544,
      "grad_norm": 8.55370044708252,
      "learning_rate": 9.323076923076924e-06,
      "loss": 3.2708,
      "step": 30
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 8.809952735900879,
      "learning_rate": 8.546153846153847e-06,
      "loss": 2.3297,
      "step": 40
    },
    {
      "epoch": 0.028409090909090908,
      "grad_norm": 19.515151977539062,
      "learning_rate": 7.76923076923077e-06,
      "loss": 1.6582,
      "step": 50
    },
    {
      "epoch": 0.028409090909090908,
      "eval_loss": 2.4909262657165527,
      "eval_runtime": 47.5356,
      "eval_samples_per_second": 15.588,
      "eval_steps_per_second": 3.913,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 1.9931848859713536e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}