Hugging Face's logo

vijay-ravichander
/
Llama-1B-Summarization-LoRA-All-r128

Transformers
Safetensors
unsloth
Inference Endpoints
Model card Files Community
Llama-1B-Summarization-LoRA-All-r128
File size: 2,505 Bytes 
12accad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24390243902439024,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 0.13146615028381348,
      "learning_rate": 0.00019631901840490797,
      "loss": 2.6062,
      "step": 20
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.11177688837051392,
      "learning_rate": 0.0001914110429447853,
      "loss": 2.3258,
      "step": 40
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 0.1093992292881012,
      "learning_rate": 0.00018650306748466258,
      "loss": 2.327,
      "step": 60
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.1171504482626915,
      "learning_rate": 0.00018159509202453987,
      "loss": 2.2707,
      "step": 80
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 0.10171514004468918,
      "learning_rate": 0.0001766871165644172,
      "loss": 2.2441,
      "step": 100
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.12730270624160767,
      "learning_rate": 0.0001717791411042945,
      "loss": 2.1971,
      "step": 120
    },
    {
      "epoch": 0.17073170731707318,
      "grad_norm": 0.15077818930149078,
      "learning_rate": 0.00016687116564417177,
      "loss": 2.2968,
      "step": 140
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.10773204267024994,
      "learning_rate": 0.00016196319018404909,
      "loss": 2.188,
      "step": 160
    },
    {
      "epoch": 0.21951219512195122,
      "grad_norm": 0.16448411345481873,
      "learning_rate": 0.0001570552147239264,
      "loss": 2.1903,
      "step": 180
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.1230635941028595,
      "learning_rate": 0.0001521472392638037,
      "loss": 2.2464,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 820,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.20194941779968e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}