Hugging Face's logo

vermoney
/
05f7bfa3-eeb2-4706-8b3c-e7046cad1d9c

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
05f7bfa3-eeb2-4706-8b3c-e7046cad1d9c
File size: 3,123 Bytes 
1be6ce5
f4e2651
 
 
1be6ce5
f4e2651
1be6ce5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f4e2651
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1be6ce5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f4e2651
1be6ce5
 
 
 
 
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
 
{
  "best_metric": 1.1126813888549805,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0010031725331360428,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0158626656802136e-05,
      "eval_loss": 1.8039422035217285,
      "eval_runtime": 812.9865,
      "eval_samples_per_second": 10.326,
      "eval_steps_per_second": 5.164,
      "step": 1
    },
    {
      "epoch": 0.00015047587997040642,
      "grad_norm": 0.5721948146820068,
      "learning_rate": 6e-05,
      "loss": 1.7091,
      "step": 3
    },
    {
      "epoch": 0.0002507931332840107,
      "eval_loss": 1.6594451665878296,
      "eval_runtime": 843.2851,
      "eval_samples_per_second": 9.955,
      "eval_steps_per_second": 4.978,
      "step": 5
    },
    {
      "epoch": 0.00030095175994081285,
      "grad_norm": 1.1099064350128174,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.7172,
      "step": 6
    },
    {
      "epoch": 0.00045142763991121924,
      "grad_norm": 0.8487201929092407,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.4969,
      "step": 9
    },
    {
      "epoch": 0.0005015862665680214,
      "eval_loss": 1.317108392715454,
      "eval_runtime": 843.8013,
      "eval_samples_per_second": 9.949,
      "eval_steps_per_second": 4.975,
      "step": 10
    },
    {
      "epoch": 0.0006019035198816257,
      "grad_norm": 0.7829315662384033,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.318,
      "step": 12
    },
    {
      "epoch": 0.0007523793998520321,
      "grad_norm": 0.8488056063652039,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1823,
      "step": 15
    },
    {
      "epoch": 0.0007523793998520321,
      "eval_loss": 1.142626166343689,
      "eval_runtime": 843.7972,
      "eval_samples_per_second": 9.949,
      "eval_steps_per_second": 4.975,
      "step": 15
    },
    {
      "epoch": 0.0009028552798224385,
      "grad_norm": 0.34353208541870117,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.2084,
      "step": 18
    },
    {
      "epoch": 0.0010031725331360428,
      "eval_loss": 1.1126813888549805,
      "eval_runtime": 844.4224,
      "eval_samples_per_second": 9.942,
      "eval_steps_per_second": 4.971,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2791603735363584.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}