Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks_0p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks_0p
File size: 3,048 Bytes
5f7c77a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9962264150943394,
  "eval_steps": 500,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 21.225251759950595,
      "learning_rate": 5e-06,
      "loss": 0.731,
      "step": 10
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 1.0446485810142683,
      "learning_rate": 5e-06,
      "loss": 0.6309,
      "step": 20
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 0.7875866396966491,
      "learning_rate": 5e-06,
      "loss": 0.5802,
      "step": 30
    },
    {
      "epoch": 0.9962264150943396,
      "eval_loss": 0.5490819811820984,
      "eval_runtime": 104.8082,
      "eval_samples_per_second": 8.52,
      "eval_steps_per_second": 0.267,
      "step": 33
    },
    {
      "epoch": 1.2075471698113207,
      "grad_norm": 1.0679356010512076,
      "learning_rate": 5e-06,
      "loss": 0.5315,
      "step": 40
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.8804894677784992,
      "learning_rate": 5e-06,
      "loss": 0.5003,
      "step": 50
    },
    {
      "epoch": 1.8113207547169812,
      "grad_norm": 0.8917839639052948,
      "learning_rate": 5e-06,
      "loss": 0.4917,
      "step": 60
    },
    {
      "epoch": 1.9924528301886792,
      "eval_loss": 0.511838436126709,
      "eval_runtime": 105.8422,
      "eval_samples_per_second": 8.437,
      "eval_steps_per_second": 0.265,
      "step": 66
    },
    {
      "epoch": 2.120754716981132,
      "grad_norm": 1.36131330698531,
      "learning_rate": 5e-06,
      "loss": 0.4456,
      "step": 70
    },
    {
      "epoch": 2.422641509433962,
      "grad_norm": 1.2433331474192404,
      "learning_rate": 5e-06,
      "loss": 0.431,
      "step": 80
    },
    {
      "epoch": 2.7245283018867923,
      "grad_norm": 1.139861283901317,
      "learning_rate": 5e-06,
      "loss": 0.4262,
      "step": 90
    },
    {
      "epoch": 2.9962264150943394,
      "eval_loss": 0.5040494799613953,
      "eval_runtime": 106.7796,
      "eval_samples_per_second": 8.363,
      "eval_steps_per_second": 0.262,
      "step": 99
    },
    {
      "epoch": 2.9962264150943394,
      "step": 99,
      "total_flos": 166038066954240.0,
      "train_loss": 0.14297527737087673,
      "train_runtime": 5416.3296,
      "train_samples_per_second": 9.388,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 10,
  "max_steps": 99,
  "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": 166038066954240.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}