Hugging Face's logo

clarxus
/
c7ab2427-81e8-4fa7-95a1-febc62fa7678

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c7ab2427-81e8-4fa7-95a1-febc62fa7678
File size: 2,393 Bytes 
0f3f984
 
 
00e7ad2
0f3f984
00e7ad2
0f3f984
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00e7ad2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0f3f984
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00e7ad2
0f3f984
 
 
 
 
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": 0.00984009840098401,
  "eval_steps": 9,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005466721333880005,
      "eval_loss": 0.947159469127655,
      "eval_runtime": 419.8436,
      "eval_samples_per_second": 7.338,
      "eval_steps_per_second": 0.919,
      "step": 1
    },
    {
      "epoch": 0.0016400164001640015,
      "grad_norm": 0.40049853920936584,
      "learning_rate": 3e-05,
      "loss": 0.9586,
      "step": 3
    },
    {
      "epoch": 0.003280032800328003,
      "grad_norm": 0.5728951096534729,
      "learning_rate": 6e-05,
      "loss": 0.899,
      "step": 6
    },
    {
      "epoch": 0.004920049200492005,
      "grad_norm": 0.5787760615348816,
      "learning_rate": 9e-05,
      "loss": 0.9511,
      "step": 9
    },
    {
      "epoch": 0.004920049200492005,
      "eval_loss": 0.8331949710845947,
      "eval_runtime": 422.8511,
      "eval_samples_per_second": 7.286,
      "eval_steps_per_second": 0.913,
      "step": 9
    },
    {
      "epoch": 0.006560065600656006,
      "grad_norm": 0.3018288016319275,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8476,
      "step": 12
    },
    {
      "epoch": 0.008200082000820008,
      "grad_norm": 0.2912035286426544,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6816,
      "step": 15
    },
    {
      "epoch": 0.00984009840098401,
      "grad_norm": 0.39786526560783386,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.7029,
      "step": 18
    },
    {
      "epoch": 0.00984009840098401,
      "eval_loss": 0.6832850575447083,
      "eval_runtime": 422.898,
      "eval_samples_per_second": 7.285,
      "eval_steps_per_second": 0.913,
      "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": 4.693768229879808e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}