Hugging Face's logo

lesso10
/
0f124b71-5e61-4f0e-8653-ac475dce633a

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
custom_code
8-bit precision
bitsandbytes
Model card Files Community
0f124b71-5e61-4f0e-8653-ac475dce633a
File size: 3,082 Bytes 
1a92006
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0036383481899217754,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036383481899217757,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00036383481899217757,
      "eval_loss": NaN,
      "eval_runtime": 152.6143,
      "eval_samples_per_second": 15.169,
      "eval_steps_per_second": 3.794,
      "step": 1
    },
    {
      "epoch": 0.0007276696379843551,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0010915044569765327,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0014553392759687103,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0018191740949608877,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0018191740949608877,
      "eval_loss": NaN,
      "eval_runtime": 151.8408,
      "eval_samples_per_second": 15.246,
      "eval_steps_per_second": 3.813,
      "step": 5
    },
    {
      "epoch": 0.0021830089139530653,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0025468437329452427,
      "grad_norm": NaN,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0029106785519374206,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.003274513370929598,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0036383481899217754,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0036383481899217754,
      "eval_loss": NaN,
      "eval_runtime": 150.9627,
      "eval_samples_per_second": 15.335,
      "eval_steps_per_second": 3.835,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1803914789781504.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}