Hugging Face's logo

trenden
/
388344cc-353d-46f8-a3a8-4c515af968f9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
388344cc-353d-46f8-a3a8-4c515af968f9
File size: 3,226 Bytes 
7cb7f6b
 
 
8f3b7a9
7cb7f6b
8f3b7a9
7cb7f6b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1c69ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
772f1eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f3b7a9
 
 
 
 
 
 
7cb7f6b
 
 
 
 
 
 
 
 
 
 
 
 
 
8f3b7a9
7cb7f6b
 
 
 
8f3b7a9
7cb7f6b
 
 
 
 
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
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003145395926712275,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003145395926712275,
      "grad_norm": 0.029093239456415176,
      "learning_rate": 2e-05,
      "loss": 10.3693,
      "step": 1
    },
    {
      "epoch": 0.0003145395926712275,
      "eval_loss": 10.374354362487793,
      "eval_runtime": 4.0659,
      "eval_samples_per_second": 329.325,
      "eval_steps_per_second": 164.785,
      "step": 1
    },
    {
      "epoch": 0.000629079185342455,
      "grad_norm": 0.028805788606405258,
      "learning_rate": 4e-05,
      "loss": 10.3736,
      "step": 2
    },
    {
      "epoch": 0.0009436187780136825,
      "grad_norm": 0.024539368227124214,
      "learning_rate": 6e-05,
      "loss": 10.3805,
      "step": 3
    },
    {
      "epoch": 0.0009436187780136825,
      "eval_loss": 10.374330520629883,
      "eval_runtime": 4.1038,
      "eval_samples_per_second": 326.286,
      "eval_steps_per_second": 163.265,
      "step": 3
    },
    {
      "epoch": 0.00125815837068491,
      "grad_norm": 0.02643374539911747,
      "learning_rate": 8e-05,
      "loss": 10.3747,
      "step": 4
    },
    {
      "epoch": 0.0015726979633561376,
      "grad_norm": 0.02621520310640335,
      "learning_rate": 0.0001,
      "loss": 10.3744,
      "step": 5
    },
    {
      "epoch": 0.001887237556027365,
      "grad_norm": 0.027438007295131683,
      "learning_rate": 0.00012,
      "loss": 10.3782,
      "step": 6
    },
    {
      "epoch": 0.001887237556027365,
      "eval_loss": 10.37421703338623,
      "eval_runtime": 4.2253,
      "eval_samples_per_second": 316.9,
      "eval_steps_per_second": 158.568,
      "step": 6
    },
    {
      "epoch": 0.0022017771486985923,
      "grad_norm": 0.028805077075958252,
      "learning_rate": 0.00014,
      "loss": 10.3763,
      "step": 7
    },
    {
      "epoch": 0.00251631674136982,
      "grad_norm": 0.026216376572847366,
      "learning_rate": 0.00016,
      "loss": 10.3769,
      "step": 8
    },
    {
      "epoch": 0.0028308563340410475,
      "grad_norm": 0.029605017974972725,
      "learning_rate": 0.00018,
      "loss": 10.3759,
      "step": 9
    },
    {
      "epoch": 0.0028308563340410475,
      "eval_loss": 10.374030113220215,
      "eval_runtime": 4.1887,
      "eval_samples_per_second": 319.671,
      "eval_steps_per_second": 159.955,
      "step": 9
    },
    {
      "epoch": 0.003145395926712275,
      "grad_norm": 0.03568054735660553,
      "learning_rate": 0.0002,
      "loss": 10.3718,
      "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": 168101806080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}