Hugging Face's logo

eeeebbb2
/
ff43f662-ed9d-4656-8fc4-2a767b85aeab

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
ff43f662-ed9d-4656-8fc4-2a767b85aeab
File size: 2,681 Bytes 
b7a5841
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.1067961165048543,
  "eval_steps": 25,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3106796116504854,
      "grad_norm": NaN,
      "learning_rate": 9.779754323328192e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.3106796116504854,
      "eval_loss": NaN,
      "eval_runtime": 3.851,
      "eval_samples_per_second": 12.984,
      "eval_steps_per_second": 3.376,
      "step": 1
    },
    {
      "epoch": 0.6213592233009708,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.9320388349514563,
      "grad_norm": NaN,
      "learning_rate": 8.14503363531613e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 1.2427184466019416,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 1.5533980582524272,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 1.8640776699029127,
      "grad_norm": NaN,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 2.174757281553398,
      "grad_norm": NaN,
      "learning_rate": 2.854966364683872e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 2.4854368932038833,
      "grad_norm": NaN,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 2.796116504854369,
      "grad_norm": NaN,
      "learning_rate": 1.2202456766718093e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 3.1067961165048543,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1248115621298176e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}