Hugging Face's logo

nathanialhunt
/
bf9107f4-9dbf-4e2d-9a52-6f28799c01dc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
bf9107f4-9dbf-4e2d-9a52-6f28799c01dc
File size: 3,207 Bytes 
cf586a4
 
 
7247900
cf586a4
7247900
cf586a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6afc251
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f1ca55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7247900
 
 
 
 
 
 
cf586a4
 
 
 
 
 
 
 
 
 
 
 
 
 
7247900
cf586a4
 
 
 
7247900
cf586a4
 
 
 
 
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": 0.0008509733007126901,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.509733007126901e-05,
      "grad_norm": 1.3498567342758179,
      "learning_rate": 2e-05,
      "loss": 2.3186,
      "step": 1
    },
    {
      "epoch": 8.509733007126901e-05,
      "eval_loss": 2.56070876121521,
      "eval_runtime": 243.497,
      "eval_samples_per_second": 20.321,
      "eval_steps_per_second": 10.16,
      "step": 1
    },
    {
      "epoch": 0.00017019466014253802,
      "grad_norm": 1.514957070350647,
      "learning_rate": 4e-05,
      "loss": 2.3577,
      "step": 2
    },
    {
      "epoch": 0.00025529199021380705,
      "grad_norm": 1.549290657043457,
      "learning_rate": 6e-05,
      "loss": 2.5595,
      "step": 3
    },
    {
      "epoch": 0.00025529199021380705,
      "eval_loss": 2.550555944442749,
      "eval_runtime": 242.0581,
      "eval_samples_per_second": 20.441,
      "eval_steps_per_second": 10.221,
      "step": 3
    },
    {
      "epoch": 0.00034038932028507605,
      "grad_norm": 1.6015673875808716,
      "learning_rate": 8e-05,
      "loss": 2.3968,
      "step": 4
    },
    {
      "epoch": 0.00042548665035634504,
      "grad_norm": 1.0087080001831055,
      "learning_rate": 0.0001,
      "loss": 1.9501,
      "step": 5
    },
    {
      "epoch": 0.0005105839804276141,
      "grad_norm": 1.1886836290359497,
      "learning_rate": 0.00012,
      "loss": 1.9399,
      "step": 6
    },
    {
      "epoch": 0.0005105839804276141,
      "eval_loss": 2.40423846244812,
      "eval_runtime": 241.8495,
      "eval_samples_per_second": 20.459,
      "eval_steps_per_second": 10.23,
      "step": 6
    },
    {
      "epoch": 0.0005956813104988831,
      "grad_norm": 2.069767713546753,
      "learning_rate": 0.00014,
      "loss": 2.3984,
      "step": 7
    },
    {
      "epoch": 0.0006807786405701521,
      "grad_norm": 1.9127330780029297,
      "learning_rate": 0.00016,
      "loss": 2.1522,
      "step": 8
    },
    {
      "epoch": 0.0007658759706414211,
      "grad_norm": 1.5159175395965576,
      "learning_rate": 0.00018,
      "loss": 1.9218,
      "step": 9
    },
    {
      "epoch": 0.0007658759706414211,
      "eval_loss": 1.8095495700836182,
      "eval_runtime": 242.5412,
      "eval_samples_per_second": 20.401,
      "eval_steps_per_second": 10.2,
      "step": 9
    },
    {
      "epoch": 0.0008509733007126901,
      "grad_norm": 1.6734718084335327,
      "learning_rate": 0.0002,
      "loss": 2.0069,
      "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": 3166205430988800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}