Hugging Face's logo

guru1116
/
d742afaa-e567-4204-997e-0a066ead646b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
d742afaa-e567-4204-997e-0a066ead646b
File size: 3,202 Bytes 
815ba2d
 
 
925ddd2
815ba2d
925ddd2
815ba2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
527bd22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a5f8f0d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
925ddd2
 
 
 
 
 
 
815ba2d
 
 
 
 
 
 
 
 
 
 
 
 
 
925ddd2
815ba2d
 
 
 
925ddd2
815ba2d
 
 
 
 
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": 0.03319502074688797,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033195020746887966,
      "grad_norm": 0.1223829835653305,
      "learning_rate": 2e-05,
      "loss": 10.3834,
      "step": 1
    },
    {
      "epoch": 0.0033195020746887966,
      "eval_loss": 10.375598907470703,
      "eval_runtime": 2.5882,
      "eval_samples_per_second": 196.276,
      "eval_steps_per_second": 49.069,
      "step": 1
    },
    {
      "epoch": 0.006639004149377593,
      "grad_norm": 0.1390531361103058,
      "learning_rate": 4e-05,
      "loss": 10.3776,
      "step": 2
    },
    {
      "epoch": 0.00995850622406639,
      "grad_norm": 0.12366314232349396,
      "learning_rate": 6e-05,
      "loss": 10.3773,
      "step": 3
    },
    {
      "epoch": 0.00995850622406639,
      "eval_loss": 10.37536334991455,
      "eval_runtime": 2.6742,
      "eval_samples_per_second": 189.966,
      "eval_steps_per_second": 47.492,
      "step": 3
    },
    {
      "epoch": 0.013278008298755186,
      "grad_norm": 0.11774402111768723,
      "learning_rate": 8e-05,
      "loss": 10.3769,
      "step": 4
    },
    {
      "epoch": 0.016597510373443983,
      "grad_norm": 0.12266664206981659,
      "learning_rate": 0.0001,
      "loss": 10.3728,
      "step": 5
    },
    {
      "epoch": 0.01991701244813278,
      "grad_norm": 0.11839405447244644,
      "learning_rate": 0.00012,
      "loss": 10.3754,
      "step": 6
    },
    {
      "epoch": 0.01991701244813278,
      "eval_loss": 10.374419212341309,
      "eval_runtime": 2.8668,
      "eval_samples_per_second": 177.202,
      "eval_steps_per_second": 44.301,
      "step": 6
    },
    {
      "epoch": 0.023236514522821577,
      "grad_norm": 0.12177033722400665,
      "learning_rate": 0.00014,
      "loss": 10.36,
      "step": 7
    },
    {
      "epoch": 0.026556016597510373,
      "grad_norm": 0.11929324269294739,
      "learning_rate": 0.00016,
      "loss": 10.3723,
      "step": 8
    },
    {
      "epoch": 0.02987551867219917,
      "grad_norm": 0.12620662152767181,
      "learning_rate": 0.00018,
      "loss": 10.3648,
      "step": 9
    },
    {
      "epoch": 0.02987551867219917,
      "eval_loss": 10.372748374938965,
      "eval_runtime": 2.6384,
      "eval_samples_per_second": 192.538,
      "eval_steps_per_second": 48.134,
      "step": 9
    },
    {
      "epoch": 0.03319502074688797,
      "grad_norm": 0.13468249142169952,
      "learning_rate": 0.0002,
      "loss": 10.3804,
      "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": 2459163426816.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}