Hugging Face's logo

lesso01
/
974d860b-ca15-4c5f-8553-b9e13ecdcb69

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
974d860b-ca15-4c5f-8553-b9e13ecdcb69
File size: 3,332 Bytes 
ae28b11
a1f7b52
 
 
ae28b11
a1f7b52
ae28b11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1f7b52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae28b11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1f7b52
ae28b11
 
 
 
 
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": 1.49298894405365,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.03678499172337686,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003678499172337686,
      "eval_loss": 2.6280200481414795,
      "eval_runtime": 65.3457,
      "eval_samples_per_second": 17.522,
      "eval_steps_per_second": 4.392,
      "step": 1
    },
    {
      "epoch": 0.0036784991723376862,
      "grad_norm": 1.1987358331680298,
      "learning_rate": 4.02e-05,
      "loss": 2.5141,
      "step": 10
    },
    {
      "epoch": 0.0073569983446753725,
      "grad_norm": 1.3015245199203491,
      "learning_rate": 8.04e-05,
      "loss": 1.9684,
      "step": 20
    },
    {
      "epoch": 0.011035497517013059,
      "grad_norm": 1.007439136505127,
      "learning_rate": 0.0001206,
      "loss": 1.6286,
      "step": 30
    },
    {
      "epoch": 0.014713996689350745,
      "grad_norm": 1.1959398984909058,
      "learning_rate": 0.0001608,
      "loss": 1.5259,
      "step": 40
    },
    {
      "epoch": 0.01839249586168843,
      "grad_norm": 1.1850124597549438,
      "learning_rate": 0.000201,
      "loss": 1.373,
      "step": 50
    },
    {
      "epoch": 0.01839249586168843,
      "eval_loss": 1.5826470851898193,
      "eval_runtime": 65.3579,
      "eval_samples_per_second": 17.519,
      "eval_steps_per_second": 4.391,
      "step": 50
    },
    {
      "epoch": 0.022070995034026118,
      "grad_norm": 0.9022707939147949,
      "learning_rate": 0.00020075518705111234,
      "loss": 1.6254,
      "step": 60
    },
    {
      "epoch": 0.025749494206363802,
      "grad_norm": 0.8804805874824524,
      "learning_rate": 0.00020002194090852784,
      "loss": 1.5379,
      "step": 70
    },
    {
      "epoch": 0.02942799337870149,
      "grad_norm": 0.9261283874511719,
      "learning_rate": 0.00019880383387374748,
      "loss": 1.4729,
      "step": 80
    },
    {
      "epoch": 0.033106492551039174,
      "grad_norm": 0.9060719013214111,
      "learning_rate": 0.00019710680044180106,
      "loss": 1.4268,
      "step": 90
    },
    {
      "epoch": 0.03678499172337686,
      "grad_norm": 1.1774567365646362,
      "learning_rate": 0.0001949391083889838,
      "loss": 1.383,
      "step": 100
    },
    {
      "epoch": 0.03678499172337686,
      "eval_loss": 1.49298894405365,
      "eval_runtime": 65.3303,
      "eval_samples_per_second": 17.526,
      "eval_steps_per_second": 4.393,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7773608566784e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}