Hugging Face's logo

ardaspear
/
791b0035-ff48-42a1-ba16-1c53402e5220

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
791b0035-ff48-42a1-ba16-1c53402e5220
File size: 3,108 Bytes 
503d527
 
 
2ee8b73
503d527
2ee8b73
503d527
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14dac17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2ee8b73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
503d527
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2ee8b73
503d527
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5454545454545454,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020202020202020204,
      "eval_loss": 4.9802985191345215,
      "eval_runtime": 2.3092,
      "eval_samples_per_second": 36.376,
      "eval_steps_per_second": 4.764,
      "step": 1
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 3.5151710510253906,
      "learning_rate": 1.5e-05,
      "loss": 4.8465,
      "step": 3
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 3.6303155422210693,
      "learning_rate": 3e-05,
      "loss": 4.8307,
      "step": 6
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.675507068634033,
      "learning_rate": 4.5e-05,
      "loss": 4.7838,
      "step": 9
    },
    {
      "epoch": 0.18181818181818182,
      "eval_loss": 4.756908893585205,
      "eval_runtime": 2.3145,
      "eval_samples_per_second": 36.293,
      "eval_steps_per_second": 4.753,
      "step": 9
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 3.3855478763580322,
      "learning_rate": 4.993910125649561e-05,
      "loss": 4.3757,
      "step": 12
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.789888858795166,
      "learning_rate": 4.962019382530521e-05,
      "loss": 4.1669,
      "step": 15
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.9098223447799683,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 3.689,
      "step": 18
    },
    {
      "epoch": 0.36363636363636365,
      "eval_loss": 3.8252432346343994,
      "eval_runtime": 2.3162,
      "eval_samples_per_second": 36.267,
      "eval_steps_per_second": 4.749,
      "step": 18
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 1.645618200302124,
      "learning_rate": 4.817959636416969e-05,
      "loss": 3.6643,
      "step": 21
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 1.723616361618042,
      "learning_rate": 4.707368982147318e-05,
      "loss": 3.5012,
      "step": 24
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.6863574981689453,
      "learning_rate": 4.572593931387604e-05,
      "loss": 3.3348,
      "step": 27
    },
    {
      "epoch": 0.5454545454545454,
      "eval_loss": 3.322596311569214,
      "eval_runtime": 2.3165,
      "eval_samples_per_second": 36.261,
      "eval_steps_per_second": 4.748,
      "step": 27
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7053851718844416.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}