Hugging Face's logo

nathanialhunt
/
1abc2a9b-f457-4a52-8a86-4e414a3afd6a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
1abc2a9b-f457-4a52-8a86-4e414a3afd6a
File size: 3,224 Bytes 
b9ac629
 
 
7b5f42f
b9ac629
7b5f42f
b9ac629
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4a98f1f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ec5338
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b5f42f
 
 
 
 
 
 
b9ac629
 
 
 
 
 
 
 
 
 
 
 
 
 
7b5f42f
b9ac629
 
 
 
7b5f42f
b9ac629
 
 
 
 
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": 0.0001485729567504123,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4857295675041229e-05,
      "grad_norm": 10.441267013549805,
      "learning_rate": 2e-05,
      "loss": 9.6058,
      "step": 1
    },
    {
      "epoch": 1.4857295675041229e-05,
      "eval_loss": 2.7660813331604004,
      "eval_runtime": 1149.3891,
      "eval_samples_per_second": 24.657,
      "eval_steps_per_second": 12.328,
      "step": 1
    },
    {
      "epoch": 2.9714591350082458e-05,
      "grad_norm": 10.460489273071289,
      "learning_rate": 4e-05,
      "loss": 10.7889,
      "step": 2
    },
    {
      "epoch": 4.4571887025123685e-05,
      "grad_norm": 9.41769790649414,
      "learning_rate": 6e-05,
      "loss": 10.1904,
      "step": 3
    },
    {
      "epoch": 4.4571887025123685e-05,
      "eval_loss": 2.736844539642334,
      "eval_runtime": 1154.5829,
      "eval_samples_per_second": 24.546,
      "eval_steps_per_second": 12.273,
      "step": 3
    },
    {
      "epoch": 5.9429182700164916e-05,
      "grad_norm": 9.358512878417969,
      "learning_rate": 8e-05,
      "loss": 10.6507,
      "step": 4
    },
    {
      "epoch": 7.428647837520615e-05,
      "grad_norm": 10.204730987548828,
      "learning_rate": 0.0001,
      "loss": 10.2412,
      "step": 5
    },
    {
      "epoch": 8.914377405024737e-05,
      "grad_norm": 10.428735733032227,
      "learning_rate": 0.00012,
      "loss": 9.6887,
      "step": 6
    },
    {
      "epoch": 8.914377405024737e-05,
      "eval_loss": 2.4252917766571045,
      "eval_runtime": 1153.3493,
      "eval_samples_per_second": 24.572,
      "eval_steps_per_second": 12.286,
      "step": 6
    },
    {
      "epoch": 0.00010400106972528861,
      "grad_norm": 8.287118911743164,
      "learning_rate": 0.00014,
      "loss": 9.837,
      "step": 7
    },
    {
      "epoch": 0.00011885836540032983,
      "grad_norm": 7.838613986968994,
      "learning_rate": 0.00016,
      "loss": 8.7304,
      "step": 8
    },
    {
      "epoch": 0.00013371566107537106,
      "grad_norm": 6.961249828338623,
      "learning_rate": 0.00018,
      "loss": 7.8282,
      "step": 9
    },
    {
      "epoch": 0.00013371566107537106,
      "eval_loss": 2.0542776584625244,
      "eval_runtime": 1151.0236,
      "eval_samples_per_second": 24.622,
      "eval_steps_per_second": 12.311,
      "step": 9
    },
    {
      "epoch": 0.0001485729567504123,
      "grad_norm": 6.564357280731201,
      "learning_rate": 0.0002,
      "loss": 7.6557,
      "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": 1873043106299904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}