Hugging Face's logo

nblinh
/
492b3f9c-0871-437e-826e-9b4f6ea86813

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
492b3f9c-0871-437e-826e-9b4f6ea86813
File size: 3,213 Bytes 
f00106c
 
 
57fda82
f00106c
57fda82
f00106c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb55f60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c5d0474
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57fda82
 
 
 
 
 
 
f00106c
 
 
 
 
 
 
 
 
 
 
 
 
 
57fda82
f00106c
 
 
 
57fda82
f00106c
 
 
 
 
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": 0.0005026072752403091,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.026072752403091e-05,
      "grad_norm": 2.132338762283325,
      "learning_rate": 2e-05,
      "loss": 2.5557,
      "step": 1
    },
    {
      "epoch": 5.026072752403091e-05,
      "eval_loss": 2.631843328475952,
      "eval_runtime": 1241.7974,
      "eval_samples_per_second": 6.747,
      "eval_steps_per_second": 3.373,
      "step": 1
    },
    {
      "epoch": 0.00010052145504806182,
      "grad_norm": 2.1546549797058105,
      "learning_rate": 4e-05,
      "loss": 2.7389,
      "step": 2
    },
    {
      "epoch": 0.00015078218257209272,
      "grad_norm": 2.0972418785095215,
      "learning_rate": 6e-05,
      "loss": 2.3617,
      "step": 3
    },
    {
      "epoch": 0.00015078218257209272,
      "eval_loss": 2.6196017265319824,
      "eval_runtime": 1305.1031,
      "eval_samples_per_second": 6.419,
      "eval_steps_per_second": 3.21,
      "step": 3
    },
    {
      "epoch": 0.00020104291009612364,
      "grad_norm": 1.7208608388900757,
      "learning_rate": 8e-05,
      "loss": 2.1952,
      "step": 4
    },
    {
      "epoch": 0.00025130363762015457,
      "grad_norm": 1.6549865007400513,
      "learning_rate": 0.0001,
      "loss": 2.5855,
      "step": 5
    },
    {
      "epoch": 0.00030156436514418544,
      "grad_norm": 2.5987608432769775,
      "learning_rate": 0.00012,
      "loss": 2.8653,
      "step": 6
    },
    {
      "epoch": 0.00030156436514418544,
      "eval_loss": 2.5160012245178223,
      "eval_runtime": 2098.8915,
      "eval_samples_per_second": 3.992,
      "eval_steps_per_second": 1.996,
      "step": 6
    },
    {
      "epoch": 0.00035182509266821636,
      "grad_norm": 1.7206662893295288,
      "learning_rate": 0.00014,
      "loss": 2.234,
      "step": 7
    },
    {
      "epoch": 0.0004020858201922473,
      "grad_norm": 1.7196815013885498,
      "learning_rate": 0.00016,
      "loss": 2.1952,
      "step": 8
    },
    {
      "epoch": 0.0004523465477162782,
      "grad_norm": 2.0840251445770264,
      "learning_rate": 0.00018,
      "loss": 2.5875,
      "step": 9
    },
    {
      "epoch": 0.0004523465477162782,
      "eval_loss": 2.3682916164398193,
      "eval_runtime": 1865.3751,
      "eval_samples_per_second": 4.491,
      "eval_steps_per_second": 2.246,
      "step": 9
    },
    {
      "epoch": 0.0005026072752403091,
      "grad_norm": 2.020665407180786,
      "learning_rate": 0.0002,
      "loss": 2.2747,
      "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": 360477150412800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}