Hugging Face's logo

nathanialhunt
/
3fea1ecc-324d-4d8f-b997-834278aa79bc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3fea1ecc-324d-4d8f-b997-834278aa79bc
File size: 2,952 Bytes 
a97384b
 
 
bc234fb
a97384b
bc234fb
a97384b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2b632a2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f396276
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bc234fb
 
 
 
 
 
 
a97384b
 
 
 
 
 
 
 
 
 
 
 
 
 
bc234fb
a97384b
 
 
 
bc234fb
a97384b
 
 
 
 
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": 0.009706381946129581,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000970638194612958,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.000970638194612958,
      "eval_loss": NaN,
      "eval_runtime": 10.8021,
      "eval_samples_per_second": 40.177,
      "eval_steps_per_second": 20.089,
      "step": 1
    },
    {
      "epoch": 0.001941276389225916,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.002911914583838874,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.002911914583838874,
      "eval_loss": NaN,
      "eval_runtime": 9.8676,
      "eval_samples_per_second": 43.982,
      "eval_steps_per_second": 21.991,
      "step": 3
    },
    {
      "epoch": 0.003882552778451832,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0048531909730647905,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.005823829167677748,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.005823829167677748,
      "eval_loss": NaN,
      "eval_runtime": 9.9026,
      "eval_samples_per_second": 43.827,
      "eval_steps_per_second": 21.913,
      "step": 6
    },
    {
      "epoch": 0.006794467362290706,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.007765105556903664,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.008735743751516622,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.008735743751516622,
      "eval_loss": NaN,
      "eval_runtime": 9.8513,
      "eval_samples_per_second": 44.055,
      "eval_steps_per_second": 22.028,
      "step": 9
    },
    {
      "epoch": 0.009706381946129581,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 40051149373440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}