Hugging Face's logo

nathanialhunt
/
5415e22c-fb4c-4053-9aa4-7b9b45614b0d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
5415e22c-fb4c-4053-9aa4-7b9b45614b0d
File size: 3,210 Bytes 
0dd11b4
 
 
2367d6f
0dd11b4
2367d6f
0dd11b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4e1e73c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4e4259d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2367d6f
 
 
 
 
 
 
0dd11b4
 
 
 
 
 
 
 
 
 
 
 
 
 
2367d6f
0dd11b4
 
 
 
2367d6f
0dd11b4
 
 
 
 
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": 0.0007845136995704787,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.845136995704788e-05,
      "grad_norm": 0.9127047061920166,
      "learning_rate": 2e-05,
      "loss": 2.1072,
      "step": 1
    },
    {
      "epoch": 7.845136995704788e-05,
      "eval_loss": 2.1771984100341797,
      "eval_runtime": 364.9344,
      "eval_samples_per_second": 14.709,
      "eval_steps_per_second": 7.355,
      "step": 1
    },
    {
      "epoch": 0.00015690273991409576,
      "grad_norm": 1.0036420822143555,
      "learning_rate": 4e-05,
      "loss": 2.4194,
      "step": 2
    },
    {
      "epoch": 0.00023535410987114363,
      "grad_norm": 1.1165186166763306,
      "learning_rate": 6e-05,
      "loss": 2.1131,
      "step": 3
    },
    {
      "epoch": 0.00023535410987114363,
      "eval_loss": 2.1711175441741943,
      "eval_runtime": 363.6197,
      "eval_samples_per_second": 14.763,
      "eval_steps_per_second": 7.381,
      "step": 3
    },
    {
      "epoch": 0.0003138054798281915,
      "grad_norm": 0.8401862382888794,
      "learning_rate": 8e-05,
      "loss": 1.9984,
      "step": 4
    },
    {
      "epoch": 0.00039225684978523936,
      "grad_norm": 0.746632993221283,
      "learning_rate": 0.0001,
      "loss": 2.2822,
      "step": 5
    },
    {
      "epoch": 0.00047070821974228727,
      "grad_norm": 0.830866277217865,
      "learning_rate": 0.00012,
      "loss": 2.1672,
      "step": 6
    },
    {
      "epoch": 0.00047070821974228727,
      "eval_loss": 2.1076629161834717,
      "eval_runtime": 363.7362,
      "eval_samples_per_second": 14.758,
      "eval_steps_per_second": 7.379,
      "step": 6
    },
    {
      "epoch": 0.0005491595896993352,
      "grad_norm": 0.7782320380210876,
      "learning_rate": 0.00014,
      "loss": 2.1435,
      "step": 7
    },
    {
      "epoch": 0.000627610959656383,
      "grad_norm": 0.712628960609436,
      "learning_rate": 0.00016,
      "loss": 1.8562,
      "step": 8
    },
    {
      "epoch": 0.0007060623296134309,
      "grad_norm": 0.6478232741355896,
      "learning_rate": 0.00018,
      "loss": 2.147,
      "step": 9
    },
    {
      "epoch": 0.0007060623296134309,
      "eval_loss": 1.9906666278839111,
      "eval_runtime": 363.6948,
      "eval_samples_per_second": 14.76,
      "eval_steps_per_second": 7.38,
      "step": 9
    },
    {
      "epoch": 0.0007845136995704787,
      "grad_norm": 0.7166277766227722,
      "learning_rate": 0.0002,
      "loss": 1.9556,
      "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": 3960342577152000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}