Hugging Face's logo

oldiday
/
1dd795e9-ca6a-4b4f-8fc5-5a9b5a919cd9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
1dd795e9-ca6a-4b4f-8fc5-5a9b5a919cd9
File size: 2,402 Bytes 
cfa5aef
 
 
515a463
cfa5aef
515a463
cfa5aef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
515a463
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cfa5aef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
515a463
cfa5aef
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0063052806725632715,
  "eval_steps": 9,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003502933706979595,
      "eval_loss": 1.2642643451690674,
      "eval_runtime": 170.7468,
      "eval_samples_per_second": 28.159,
      "eval_steps_per_second": 3.52,
      "step": 1
    },
    {
      "epoch": 0.0010508801120938786,
      "grad_norm": 0.26421603560447693,
      "learning_rate": 3e-05,
      "loss": 1.2586,
      "step": 3
    },
    {
      "epoch": 0.002101760224187757,
      "grad_norm": 0.2573237419128418,
      "learning_rate": 6e-05,
      "loss": 1.2507,
      "step": 6
    },
    {
      "epoch": 0.0031526403362816357,
      "grad_norm": 0.23207610845565796,
      "learning_rate": 9e-05,
      "loss": 1.2601,
      "step": 9
    },
    {
      "epoch": 0.0031526403362816357,
      "eval_loss": 1.229485034942627,
      "eval_runtime": 172.5126,
      "eval_samples_per_second": 27.87,
      "eval_steps_per_second": 3.484,
      "step": 9
    },
    {
      "epoch": 0.004203520448375514,
      "grad_norm": 0.2796209156513214,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.2384,
      "step": 12
    },
    {
      "epoch": 0.005254400560469393,
      "grad_norm": 0.28329601883888245,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2393,
      "step": 15
    },
    {
      "epoch": 0.0063052806725632715,
      "grad_norm": 0.22264641523361206,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1474,
      "step": 18
    },
    {
      "epoch": 0.0063052806725632715,
      "eval_loss": 1.1840261220932007,
      "eval_runtime": 172.502,
      "eval_samples_per_second": 27.872,
      "eval_steps_per_second": 3.484,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7411455158648832.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}