Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_10000tasks__5p

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_10000tasks__5p
File size: 2,825 Bytes
650f0b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9171270718232045,
  "eval_steps": 500,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2946593001841621,
      "grad_norm": 2.4692469653351874,
      "learning_rate": 5e-06,
      "loss": 0.8598,
      "step": 10
    },
    {
      "epoch": 0.5893186003683242,
      "grad_norm": 1.1829109342265023,
      "learning_rate": 5e-06,
      "loss": 0.7522,
      "step": 20
    },
    {
      "epoch": 0.8839779005524862,
      "grad_norm": 2.3810607640229704,
      "learning_rate": 5e-06,
      "loss": 0.7103,
      "step": 30
    },
    {
      "epoch": 0.9723756906077348,
      "eval_loss": 0.6921380162239075,
      "eval_runtime": 105.6301,
      "eval_samples_per_second": 8.653,
      "eval_steps_per_second": 0.275,
      "step": 33
    },
    {
      "epoch": 1.1786372007366483,
      "grad_norm": 2.070195253913277,
      "learning_rate": 5e-06,
      "loss": 0.6749,
      "step": 40
    },
    {
      "epoch": 1.4732965009208103,
      "grad_norm": 1.189689433003807,
      "learning_rate": 5e-06,
      "loss": 0.6447,
      "step": 50
    },
    {
      "epoch": 1.7679558011049723,
      "grad_norm": 1.2811868301588352,
      "learning_rate": 5e-06,
      "loss": 0.6364,
      "step": 60
    },
    {
      "epoch": 1.9742173112338857,
      "eval_loss": 0.6614336371421814,
      "eval_runtime": 105.345,
      "eval_samples_per_second": 8.676,
      "eval_steps_per_second": 0.275,
      "step": 67
    },
    {
      "epoch": 2.0626151012891345,
      "grad_norm": 0.796453744547378,
      "learning_rate": 5e-06,
      "loss": 0.6182,
      "step": 70
    },
    {
      "epoch": 2.3572744014732967,
      "grad_norm": 2.537451226370363,
      "learning_rate": 5e-06,
      "loss": 0.5796,
      "step": 80
    },
    {
      "epoch": 2.6519337016574585,
      "grad_norm": 0.9119097844237827,
      "learning_rate": 5e-06,
      "loss": 0.5746,
      "step": 90
    },
    {
      "epoch": 2.9171270718232045,
      "step": 99,
      "total_flos": 165723997470720.0,
      "train_loss": 0.0,
      "train_runtime": 2.9957,
      "train_samples_per_second": 17384.187,
      "train_steps_per_second": 33.048
    }
  ],
  "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": 165723997470720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}