Hugging Face's logo

tum-nlp
/
neural-news-generator-llama-7b-fa

Text Generation
Transformers
Safetensors
Persian
llama
text-generation-inference
Inference Endpoints
Model card Files Community
neural-news-generator-llama-7b-fa
File size: 2,425 Bytes 
f31d796
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.1237905025482178,
  "best_model_checkpoint": "model_llama2_7b_pre_fa_v2/checkpoint-30000",
  "epoch": 1.5,
  "eval_steps": 6000,
  "global_step": 36000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 1.95e-05,
      "loss": 1.4763,
      "step": 6000
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.215256690979004,
      "eval_runtime": 3808.4515,
      "eval_samples_per_second": 1.575,
      "eval_steps_per_second": 1.575,
      "step": 6000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9e-05,
      "loss": 1.194,
      "step": 12000
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.1560847759246826,
      "eval_runtime": 4331.4845,
      "eval_samples_per_second": 1.385,
      "eval_steps_per_second": 1.385,
      "step": 12000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 1.1423,
      "step": 18000
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.1338403224945068,
      "eval_runtime": 4323.9918,
      "eval_samples_per_second": 1.388,
      "eval_steps_per_second": 1.388,
      "step": 18000
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.8e-05,
      "loss": 1.1314,
      "step": 24000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1248250007629395,
      "eval_runtime": 3781.6164,
      "eval_samples_per_second": 1.587,
      "eval_steps_per_second": 1.587,
      "step": 24000
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.1134,
      "step": 30000
    },
    {
      "epoch": 1.25,
      "eval_loss": 1.1237905025482178,
      "eval_runtime": 4344.7683,
      "eval_samples_per_second": 1.381,
      "eval_steps_per_second": 1.381,
      "step": 30000
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.7e-05,
      "loss": 1.1102,
      "step": 36000
    },
    {
      "epoch": 1.5,
      "eval_loss": 1.1263515949249268,
      "eval_runtime": 4343.9602,
      "eval_samples_per_second": 1.381,
      "eval_steps_per_second": 1.381,
      "step": 36000
    }
  ],
  "logging_steps": 6000,
  "max_steps": 240000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 6000,
  "total_flos": 2.9590328180736e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}