Hugging Face's logo

Aivesa
/
d7ece7c9-f6fc-4531-8b1e-e231149e3a1d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d7ece7c9-f6fc-4531-8b1e-e231149e3a1d
File size: 2,972 Bytes 
79c5156
 
 
68713ba
79c5156
68713ba
79c5156
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ccb05e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e7e3599
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68713ba
 
 
 
 
 
 
79c5156
 
 
 
 
 
 
 
 
 
 
 
 
 
68713ba
79c5156
 
 
 
68713ba
79c5156
 
 
 
 
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": 0.007881773399014778,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007881773399014779,
      "grad_norm": 1.420249342918396,
      "learning_rate": 2e-05,
      "loss": 6.4461,
      "step": 1
    },
    {
      "epoch": 0.0015763546798029558,
      "grad_norm": 1.4954193830490112,
      "learning_rate": 4e-05,
      "loss": 6.4123,
      "step": 2
    },
    {
      "epoch": 0.0023645320197044333,
      "grad_norm": 1.5775469541549683,
      "learning_rate": 6e-05,
      "loss": 6.4432,
      "step": 3
    },
    {
      "epoch": 0.0023645320197044333,
      "eval_loss": 6.295650005340576,
      "eval_runtime": 12.3779,
      "eval_samples_per_second": 43.222,
      "eval_steps_per_second": 21.652,
      "step": 3
    },
    {
      "epoch": 0.0031527093596059115,
      "grad_norm": 1.4721767902374268,
      "learning_rate": 8e-05,
      "loss": 6.7091,
      "step": 4
    },
    {
      "epoch": 0.003940886699507389,
      "grad_norm": 1.3564282655715942,
      "learning_rate": 0.0001,
      "loss": 6.0962,
      "step": 5
    },
    {
      "epoch": 0.004729064039408867,
      "grad_norm": 1.4763870239257812,
      "learning_rate": 0.00012,
      "loss": 5.9891,
      "step": 6
    },
    {
      "epoch": 0.004729064039408867,
      "eval_loss": 6.271442413330078,
      "eval_runtime": 13.182,
      "eval_samples_per_second": 40.586,
      "eval_steps_per_second": 20.331,
      "step": 6
    },
    {
      "epoch": 0.005517241379310344,
      "grad_norm": 1.3695040941238403,
      "learning_rate": 0.00014,
      "loss": 6.6824,
      "step": 7
    },
    {
      "epoch": 0.006305418719211823,
      "grad_norm": 1.585157871246338,
      "learning_rate": 0.00016,
      "loss": 6.067,
      "step": 8
    },
    {
      "epoch": 0.007093596059113301,
      "grad_norm": 1.153540849685669,
      "learning_rate": 0.00018,
      "loss": 6.3986,
      "step": 9
    },
    {
      "epoch": 0.007093596059113301,
      "eval_loss": 6.218323707580566,
      "eval_runtime": 13.5637,
      "eval_samples_per_second": 39.443,
      "eval_steps_per_second": 19.759,
      "step": 9
    },
    {
      "epoch": 0.007881773399014778,
      "grad_norm": 1.253097414970398,
      "learning_rate": 0.0002,
      "loss": 6.2311,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 852261076992.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}