Hugging Face's logo

VERSIL91
/
aba53603-c1e7-44b1-a8d2-a464157f7d35

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
aba53603-c1e7-44b1-a8d2-a464157f7d35
File size: 3,309 Bytes 
52f956c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00851900393184797,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000655307994757536,
      "grad_norm": 0.016265055164694786,
      "learning_rate": 1e-05,
      "loss": 11.9312,
      "step": 1
    },
    {
      "epoch": 0.000655307994757536,
      "eval_loss": 11.931286811828613,
      "eval_runtime": 28.0473,
      "eval_samples_per_second": 91.667,
      "eval_steps_per_second": 45.851,
      "step": 1
    },
    {
      "epoch": 0.001310615989515072,
      "grad_norm": 0.014278396964073181,
      "learning_rate": 2e-05,
      "loss": 11.9309,
      "step": 2
    },
    {
      "epoch": 0.001965923984272608,
      "grad_norm": 0.011991339735686779,
      "learning_rate": 3e-05,
      "loss": 11.9327,
      "step": 3
    },
    {
      "epoch": 0.002621231979030144,
      "grad_norm": 0.01234712265431881,
      "learning_rate": 4e-05,
      "loss": 11.9315,
      "step": 4
    },
    {
      "epoch": 0.00327653997378768,
      "grad_norm": 0.017012331634759903,
      "learning_rate": 5e-05,
      "loss": 11.9296,
      "step": 5
    },
    {
      "epoch": 0.003931847968545216,
      "grad_norm": 0.014782086946070194,
      "learning_rate": 6e-05,
      "loss": 11.9329,
      "step": 6
    },
    {
      "epoch": 0.0045871559633027525,
      "grad_norm": 0.020223338156938553,
      "learning_rate": 7e-05,
      "loss": 11.9317,
      "step": 7
    },
    {
      "epoch": 0.005242463958060288,
      "grad_norm": 0.013544556684792042,
      "learning_rate": 8e-05,
      "loss": 11.9312,
      "step": 8
    },
    {
      "epoch": 0.005897771952817824,
      "grad_norm": 0.012503627687692642,
      "learning_rate": 9e-05,
      "loss": 11.9315,
      "step": 9
    },
    {
      "epoch": 0.00655307994757536,
      "grad_norm": 0.012558264657855034,
      "learning_rate": 0.0001,
      "loss": 11.9305,
      "step": 10
    },
    {
      "epoch": 0.007208387942332897,
      "grad_norm": 0.015282824635505676,
      "learning_rate": 9.98458666866564e-05,
      "loss": 11.9317,
      "step": 11
    },
    {
      "epoch": 0.007863695937090432,
      "grad_norm": 0.01448417454957962,
      "learning_rate": 9.938441702975689e-05,
      "loss": 11.9314,
      "step": 12
    },
    {
      "epoch": 0.00851900393184797,
      "grad_norm": 0.012158408761024475,
      "learning_rate": 9.861849601988383e-05,
      "loss": 11.9323,
      "step": 13
    },
    {
      "epoch": 0.00851900393184797,
      "eval_loss": 11.93112564086914,
      "eval_runtime": 12.5386,
      "eval_samples_per_second": 205.047,
      "eval_steps_per_second": 102.563,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 77944848384.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}