Hugging Face's logo

VERSIL91
/
cdf861c6-72a4-41b4-ac3f-a9bb00013b19

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cdf861c6-72a4-41b4-ac3f-a9bb00013b19
File size: 2,935 Bytes 
4419af1
 
 
b2cb244
4419af1
b2cb244
4419af1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b2cb244
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4419af1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b2cb244
4419af1
 
 
 
 
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
126
127
128
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012415612632885854,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012415612632885853,
      "grad_norm": 0.38651901483535767,
      "learning_rate": 1e-05,
      "loss": 0.8737,
      "step": 1
    },
    {
      "epoch": 0.0012415612632885853,
      "eval_loss": NaN,
      "eval_runtime": 71.5539,
      "eval_samples_per_second": 75.831,
      "eval_steps_per_second": 9.489,
      "step": 1
    },
    {
      "epoch": 0.0024831225265771707,
      "grad_norm": 0.3346116542816162,
      "learning_rate": 2e-05,
      "loss": 0.8453,
      "step": 2
    },
    {
      "epoch": 0.003724683789865756,
      "grad_norm": 0.34337764978408813,
      "learning_rate": 3e-05,
      "loss": 0.7958,
      "step": 3
    },
    {
      "epoch": 0.004966245053154341,
      "grad_norm": 0.4059295952320099,
      "learning_rate": 4e-05,
      "loss": 0.8395,
      "step": 4
    },
    {
      "epoch": 0.006207806316442927,
      "grad_norm": 0.3587191104888916,
      "learning_rate": 5e-05,
      "loss": 0.7908,
      "step": 5
    },
    {
      "epoch": 0.006207806316442927,
      "eval_loss": NaN,
      "eval_runtime": 60.0514,
      "eval_samples_per_second": 90.356,
      "eval_steps_per_second": 11.307,
      "step": 5
    },
    {
      "epoch": 0.007449367579731512,
      "grad_norm": 0.3114588260650635,
      "learning_rate": 6e-05,
      "loss": 0.9081,
      "step": 6
    },
    {
      "epoch": 0.008690928843020097,
      "grad_norm": 0.33595696091651917,
      "learning_rate": 7e-05,
      "loss": 0.8077,
      "step": 7
    },
    {
      "epoch": 0.009932490106308683,
      "grad_norm": 0.32869091629981995,
      "learning_rate": 8e-05,
      "loss": 0.8406,
      "step": 8
    },
    {
      "epoch": 0.011174051369597269,
      "grad_norm": 0.3324941396713257,
      "learning_rate": 9e-05,
      "loss": 0.896,
      "step": 9
    },
    {
      "epoch": 0.012415612632885854,
      "grad_norm": 0.3595397472381592,
      "learning_rate": 0.0001,
      "loss": 0.7572,
      "step": 10
    },
    {
      "epoch": 0.012415612632885854,
      "eval_loss": NaN,
      "eval_runtime": 60.2689,
      "eval_samples_per_second": 90.03,
      "eval_steps_per_second": 11.266,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.293980070510592e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}