Hugging Face's logo

mlfoundations-dev
/
stackoverflow_5000tasks_.75p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
stackoverflow_5000tasks_.75p
File size: 3,204 Bytes
1290c43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
  "best_model_checkpoint": null,
  "epoch": 2.981818181818182,
  "eval_steps": 500,
  "global_step": 102,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 6.897545667801919,
      "learning_rate": 5e-06,
      "loss": 0.9216,
      "step": 10
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 3.7987497029563437,
      "learning_rate": 5e-06,
      "loss": 0.8217,
      "step": 20
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 1.6786976414779686,
      "learning_rate": 5e-06,
      "loss": 0.784,
      "step": 30
    },
    {
      "epoch": 0.9890909090909091,
      "eval_loss": 0.7713841795921326,
      "eval_runtime": 24.4352,
      "eval_samples_per_second": 37.896,
      "eval_steps_per_second": 0.614,
      "step": 34
    },
    {
      "epoch": 1.170909090909091,
      "grad_norm": 1.3947991819307355,
      "learning_rate": 5e-06,
      "loss": 0.8212,
      "step": 40
    },
    {
      "epoch": 1.461818181818182,
      "grad_norm": 1.4557421257115206,
      "learning_rate": 5e-06,
      "loss": 0.7242,
      "step": 50
    },
    {
      "epoch": 1.7527272727272727,
      "grad_norm": 1.6761487724396338,
      "learning_rate": 5e-06,
      "loss": 0.7099,
      "step": 60
    },
    {
      "epoch": 1.9854545454545454,
      "eval_loss": 0.7391919493675232,
      "eval_runtime": 24.121,
      "eval_samples_per_second": 38.39,
      "eval_steps_per_second": 0.622,
      "step": 68
    },
    {
      "epoch": 2.050909090909091,
      "grad_norm": 0.87855024715639,
      "learning_rate": 5e-06,
      "loss": 0.7641,
      "step": 70
    },
    {
      "epoch": 2.341818181818182,
      "grad_norm": 1.7629080076755046,
      "learning_rate": 5e-06,
      "loss": 0.6552,
      "step": 80
    },
    {
      "epoch": 2.632727272727273,
      "grad_norm": 0.9203794085894584,
      "learning_rate": 5e-06,
      "loss": 0.6497,
      "step": 90
    },
    {
      "epoch": 2.923636363636364,
      "grad_norm": 0.6126232896883246,
      "learning_rate": 5e-06,
      "loss": 0.6438,
      "step": 100
    },
    {
      "epoch": 2.981818181818182,
      "eval_loss": 0.7303929924964905,
      "eval_runtime": 23.3096,
      "eval_samples_per_second": 39.726,
      "eval_steps_per_second": 0.644,
      "step": 102
    },
    {
      "epoch": 2.981818181818182,
      "step": 102,
      "total_flos": 170644419379200.0,
      "train_loss": 0.7476259855663075,
      "train_runtime": 3636.8482,
      "train_samples_per_second": 14.512,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 10,
  "max_steps": 102,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 170644419379200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}