Hugging Face's logo

SystemAdmin123
/
llama-7b

Safetensors
llama
Model card Files
xet
 Community
llama-7b
File size: 2,578 Bytes
3295033
 
 
8dd8221
3295033
8dd8221
3295033
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b5a5be7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8dd8221
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3295033
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8dd8221
3295033
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5555555555555556,
  "eval_steps": 20,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009259259259259259,
      "eval_loss": 1.9010889530181885,
      "eval_runtime": 27.434,
      "eval_samples_per_second": 54.713,
      "eval_steps_per_second": 6.853,
      "step": 1
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.609375,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.6462,
      "step": 10
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.4453125,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6473,
      "step": 20
    },
    {
      "epoch": 0.18518518518518517,
      "eval_loss": 1.5201222896575928,
      "eval_runtime": 26.4539,
      "eval_samples_per_second": 56.74,
      "eval_steps_per_second": 7.107,
      "step": 20
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0002,
      "loss": 1.7007,
      "step": 30
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.984375,
      "learning_rate": 0.00019984815164333163,
      "loss": 1.8416,
      "step": 40
    },
    {
      "epoch": 0.37037037037037035,
      "eval_loss": 1.7034589052200317,
      "eval_runtime": 42.8326,
      "eval_samples_per_second": 35.043,
      "eval_steps_per_second": 4.389,
      "step": 40
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.8177,
      "step": 50
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 77.0,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.9073,
      "step": 60
    },
    {
      "epoch": 0.5555555555555556,
      "eval_loss": 1.8073501586914062,
      "eval_runtime": 45.0134,
      "eval_samples_per_second": 33.346,
      "eval_steps_per_second": 4.177,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.897170002024858e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}