Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks_1p

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_1p
File size: 3,122 Bytes
d8c6aa5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 3.0,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 3.9646038631444687,
      "learning_rate": 5e-06,
      "loss": 0.996,
      "step": 10
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 4.918642638371639,
      "learning_rate": 5e-06,
      "loss": 0.8944,
      "step": 20
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.3108211729045733,
      "learning_rate": 5e-06,
      "loss": 0.8572,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8312200307846069,
      "eval_runtime": 110.2707,
      "eval_samples_per_second": 8.561,
      "eval_steps_per_second": 0.272,
      "step": 35
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.3985649962465836,
      "learning_rate": 5e-06,
      "loss": 0.8205,
      "step": 40
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.990368274403578,
      "learning_rate": 5e-06,
      "loss": 0.792,
      "step": 50
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.9663231906613171,
      "learning_rate": 5e-06,
      "loss": 0.7814,
      "step": 60
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6499452853977579,
      "learning_rate": 5e-06,
      "loss": 0.7768,
      "step": 70
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8017017245292664,
      "eval_runtime": 110.3066,
      "eval_samples_per_second": 8.558,
      "eval_steps_per_second": 0.272,
      "step": 70
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.1076482815278739,
      "learning_rate": 5e-06,
      "loss": 0.723,
      "step": 80
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.6444807327009624,
      "learning_rate": 5e-06,
      "loss": 0.7163,
      "step": 90
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.6105018774007208,
      "learning_rate": 5e-06,
      "loss": 0.7145,
      "step": 100
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7955389618873596,
      "eval_runtime": 120.7051,
      "eval_samples_per_second": 7.821,
      "eval_steps_per_second": 0.249,
      "step": 105
    },
    {
      "epoch": 3.0,
      "step": 105,
      "total_flos": 175669531115520.0,
      "train_loss": 0.23945580210004533,
      "train_runtime": 5809.6465,
      "train_samples_per_second": 9.253,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 10,
  "max_steps": 105,
  "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": 175669531115520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}