Hugging Face's logo

cwaud
/
20f392cb-b15d-444d-8afb-15d71c8c7b91

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
20f392cb-b15d-444d-8afb-15d71c8c7b91
File size: 3,201 Bytes 
891ae62
 
 
b378bfb
891ae62
b378bfb
891ae62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8154be2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
615466d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b378bfb
 
 
 
 
 
 
891ae62
 
 
 
 
 
 
 
 
 
 
 
 
 
b378bfb
891ae62
 
 
 
b378bfb
891ae62
 
 
 
 
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": 0.000140491368561544,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.40491368561544e-05,
      "grad_norm": 11.456639289855957,
      "learning_rate": 2e-05,
      "loss": 10.8262,
      "step": 1
    },
    {
      "epoch": 1.40491368561544e-05,
      "eval_loss": 12.163054466247559,
      "eval_runtime": 413.6256,
      "eval_samples_per_second": 72.457,
      "eval_steps_per_second": 36.228,
      "step": 1
    },
    {
      "epoch": 2.80982737123088e-05,
      "grad_norm": 5.828180313110352,
      "learning_rate": 4e-05,
      "loss": 10.0953,
      "step": 2
    },
    {
      "epoch": 4.21474105684632e-05,
      "grad_norm": 7.734110355377197,
      "learning_rate": 6e-05,
      "loss": 10.6375,
      "step": 3
    },
    {
      "epoch": 4.21474105684632e-05,
      "eval_loss": 12.15479564666748,
      "eval_runtime": 419.0796,
      "eval_samples_per_second": 71.514,
      "eval_steps_per_second": 35.757,
      "step": 3
    },
    {
      "epoch": 5.61965474246176e-05,
      "grad_norm": 5.531479835510254,
      "learning_rate": 8e-05,
      "loss": 11.6567,
      "step": 4
    },
    {
      "epoch": 7.0245684280772e-05,
      "grad_norm": 4.737807273864746,
      "learning_rate": 0.0001,
      "loss": 11.0582,
      "step": 5
    },
    {
      "epoch": 8.42948211369264e-05,
      "grad_norm": 26.38648223876953,
      "learning_rate": 0.00012,
      "loss": 11.8254,
      "step": 6
    },
    {
      "epoch": 8.42948211369264e-05,
      "eval_loss": 12.05859088897705,
      "eval_runtime": 414.2123,
      "eval_samples_per_second": 72.354,
      "eval_steps_per_second": 36.177,
      "step": 6
    },
    {
      "epoch": 9.83439579930808e-05,
      "grad_norm": 13.912890434265137,
      "learning_rate": 0.00014,
      "loss": 12.4402,
      "step": 7
    },
    {
      "epoch": 0.0001123930948492352,
      "grad_norm": 3.7871077060699463,
      "learning_rate": 0.00016,
      "loss": 10.6176,
      "step": 8
    },
    {
      "epoch": 0.0001264422317053896,
      "grad_norm": 7.042935848236084,
      "learning_rate": 0.00018,
      "loss": 10.2955,
      "step": 9
    },
    {
      "epoch": 0.0001264422317053896,
      "eval_loss": 11.75953197479248,
      "eval_runtime": 408.0518,
      "eval_samples_per_second": 73.447,
      "eval_steps_per_second": 36.723,
      "step": 9
    },
    {
      "epoch": 0.000140491368561544,
      "grad_norm": 6.2739386558532715,
      "learning_rate": 0.0002,
      "loss": 11.6255,
      "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": 34292650475520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}