Hugging Face's logo

nat-hunt
/
2ec16142-f7ad-48bd-a7fc-6f501b205271

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
2ec16142-f7ad-48bd-a7fc-6f501b205271
File size: 2,484 Bytes 
1048f24
 
 
40965e3
1048f24
40965e3
1048f24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6636152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d4734b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40965e3
 
 
 
 
 
 
1048f24
 
 
 
 
 
 
 
 
 
 
 
 
 
40965e3
1048f24
 
 
 
40965e3
1048f24
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008982891674492672,
  "eval_steps": 14,
  "global_step": 55,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016332530317259402,
      "eval_loss": 2.5971131324768066,
      "eval_runtime": 98.8794,
      "eval_samples_per_second": 26.072,
      "eval_steps_per_second": 13.036,
      "step": 1
    },
    {
      "epoch": 0.0016332530317259401,
      "grad_norm": 2.0664286613464355,
      "learning_rate": 0.00019510565162951537,
      "loss": 9.928,
      "step": 10
    },
    {
      "epoch": 0.0022865542444163163,
      "eval_loss": 2.4638168811798096,
      "eval_runtime": 98.8933,
      "eval_samples_per_second": 26.068,
      "eval_steps_per_second": 13.034,
      "step": 14
    },
    {
      "epoch": 0.0032665060634518802,
      "grad_norm": 3.385493278503418,
      "learning_rate": 0.00015877852522924732,
      "loss": 9.6198,
      "step": 20
    },
    {
      "epoch": 0.0045731084888326326,
      "eval_loss": 2.3797528743743896,
      "eval_runtime": 98.9153,
      "eval_samples_per_second": 26.063,
      "eval_steps_per_second": 13.031,
      "step": 28
    },
    {
      "epoch": 0.0048997590951778205,
      "grad_norm": 2.9848153591156006,
      "learning_rate": 0.0001,
      "loss": 9.679,
      "step": 30
    },
    {
      "epoch": 0.0065330121269037604,
      "grad_norm": 3.4589827060699463,
      "learning_rate": 4.12214747707527e-05,
      "loss": 9.7902,
      "step": 40
    },
    {
      "epoch": 0.006859662733248948,
      "eval_loss": 2.3425304889678955,
      "eval_runtime": 98.9387,
      "eval_samples_per_second": 26.057,
      "eval_steps_per_second": 13.028,
      "step": 42
    },
    {
      "epoch": 0.0081662651586297,
      "grad_norm": 5.682126522064209,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 9.2943,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 55,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 14,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0057526569598976e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}