Hugging Face's logo

tuantmdev
/
488f68bf-4d64-40fa-b526-250ba8ed54f9

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
488f68bf-4d64-40fa-b526-250ba8ed54f9
File size: 2,730 Bytes 
b7919b7
 
 
6837ef5
b7919b7
6837ef5
b7919b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d6fe38c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6452ae2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6837ef5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b7919b7
 
 
 
 
 
 
 
 
 
 
 
 
 
6837ef5
b7919b7
 
 
 
 
 
 
 
6837ef5
b7919b7
 
 
 
6837ef5
b7919b7
 
 
 
 
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
 
{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.23959269242288112,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011979634621144056,
      "eval_loss": NaN,
      "eval_runtime": 18.4623,
      "eval_samples_per_second": 38.078,
      "eval_steps_per_second": 19.066,
      "step": 1
    },
    {
      "epoch": 0.04791853848457622,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.05989817310572028,
      "eval_loss": NaN,
      "eval_runtime": 17.786,
      "eval_samples_per_second": 39.525,
      "eval_steps_per_second": 19.791,
      "step": 50
    },
    {
      "epoch": 0.09583707696915245,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.11979634621144056,
      "eval_loss": NaN,
      "eval_runtime": 17.5398,
      "eval_samples_per_second": 40.08,
      "eval_steps_per_second": 20.069,
      "step": 100
    },
    {
      "epoch": 0.14375561545372867,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.17969451931716082,
      "eval_loss": NaN,
      "eval_runtime": 17.4881,
      "eval_samples_per_second": 40.199,
      "eval_steps_per_second": 20.128,
      "step": 150
    },
    {
      "epoch": 0.1916741539383049,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.23959269242288112,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.23959269242288112,
      "eval_loss": NaN,
      "eval_runtime": 17.4628,
      "eval_samples_per_second": 40.257,
      "eval_steps_per_second": 20.157,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.32442044235776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}