Hugging Face's logo

lesso
/
67e39ad1-2d82-4aa9-b6f0-74831c4b5dd2

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
67e39ad1-2d82-4aa9-b6f0-74831c4b5dd2
File size: 3,153 Bytes 
0af0b2c
 
 
66895e8
0af0b2c
66895e8
0af0b2c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e477626
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a3d8c86
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66895e8
 
 
 
 
 
 
0af0b2c
 
 
 
 
 
 
 
 
 
 
 
 
 
66895e8
0af0b2c
 
 
 
66895e8
0af0b2c
 
 
 
 
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": 0.0001391715811631265,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.391715811631265e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 4.5194,
      "step": 1
    },
    {
      "epoch": 1.391715811631265e-05,
      "eval_loss": 5.923115253448486,
      "eval_runtime": 1534.7897,
      "eval_samples_per_second": 9.857,
      "eval_steps_per_second": 9.857,
      "step": 1
    },
    {
      "epoch": 2.78343162326253e-05,
      "grad_norm": 3.8339357376098633,
      "learning_rate": 2e-05,
      "loss": 6.9966,
      "step": 2
    },
    {
      "epoch": 4.1751474348937944e-05,
      "grad_norm": 1.9755796194076538,
      "learning_rate": 4e-05,
      "loss": 3.8321,
      "step": 3
    },
    {
      "epoch": 4.1751474348937944e-05,
      "eval_loss": 5.91879415512085,
      "eval_runtime": 1532.6296,
      "eval_samples_per_second": 9.871,
      "eval_steps_per_second": 9.871,
      "step": 3
    },
    {
      "epoch": 5.56686324652506e-05,
      "grad_norm": 4.169151782989502,
      "learning_rate": 6e-05,
      "loss": 5.5239,
      "step": 4
    },
    {
      "epoch": 6.958579058156325e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 5.6624,
      "step": 5
    },
    {
      "epoch": 8.350294869787589e-05,
      "grad_norm": 2.504304885864258,
      "learning_rate": 8e-05,
      "loss": 3.8521,
      "step": 6
    },
    {
      "epoch": 8.350294869787589e-05,
      "eval_loss": 5.870975494384766,
      "eval_runtime": 1533.6973,
      "eval_samples_per_second": 9.864,
      "eval_steps_per_second": 9.864,
      "step": 6
    },
    {
      "epoch": 9.742010681418854e-05,
      "grad_norm": 2.4749975204467773,
      "learning_rate": 0.0001,
      "loss": 3.6626,
      "step": 7
    },
    {
      "epoch": 0.0001113372649305012,
      "grad_norm": 3.602562427520752,
      "learning_rate": 0.00012,
      "loss": 5.4928,
      "step": 8
    },
    {
      "epoch": 0.00012525442304681385,
      "grad_norm": 4.245274066925049,
      "learning_rate": 0.00014,
      "loss": 3.3841,
      "step": 9
    },
    {
      "epoch": 0.00012525442304681385,
      "eval_loss": 5.604666233062744,
      "eval_runtime": 1537.609,
      "eval_samples_per_second": 9.839,
      "eval_steps_per_second": 9.839,
      "step": 9
    },
    {
      "epoch": 0.0001391715811631265,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 6.5318,
      "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": 3173290868736000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}