Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackexchange_scifi

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
llama3-1_8b_mlfoundations-dev-stackexchange_scifi
File size: 2,574 Bytes 
59df24f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.991097922848665,
  "eval_steps": 500,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47477744807121663,
      "grad_norm": 7.287866142815707,
      "learning_rate": 5e-06,
      "loss": 1.3702,
      "step": 10
    },
    {
      "epoch": 0.9495548961424333,
      "grad_norm": 11.95220386398438,
      "learning_rate": 5e-06,
      "loss": 1.2286,
      "step": 20
    },
    {
      "epoch": 0.9970326409495549,
      "eval_loss": 1.193329095840454,
      "eval_runtime": 65.8348,
      "eval_samples_per_second": 8.612,
      "eval_steps_per_second": 0.273,
      "step": 21
    },
    {
      "epoch": 1.4243323442136497,
      "grad_norm": 2.603188301936332,
      "learning_rate": 5e-06,
      "loss": 1.162,
      "step": 30
    },
    {
      "epoch": 1.8991097922848663,
      "grad_norm": 1.480853911439061,
      "learning_rate": 5e-06,
      "loss": 1.122,
      "step": 40
    },
    {
      "epoch": 1.9940652818991098,
      "eval_loss": 1.1249243021011353,
      "eval_runtime": 65.7564,
      "eval_samples_per_second": 8.623,
      "eval_steps_per_second": 0.274,
      "step": 42
    },
    {
      "epoch": 2.373887240356083,
      "grad_norm": 1.09348710471121,
      "learning_rate": 5e-06,
      "loss": 1.0642,
      "step": 50
    },
    {
      "epoch": 2.8486646884272995,
      "grad_norm": 1.193278031805213,
      "learning_rate": 5e-06,
      "loss": 1.0335,
      "step": 60
    },
    {
      "epoch": 2.991097922848665,
      "eval_loss": 1.0986876487731934,
      "eval_runtime": 65.1855,
      "eval_samples_per_second": 8.698,
      "eval_steps_per_second": 0.276,
      "step": 63
    },
    {
      "epoch": 2.991097922848665,
      "step": 63,
      "total_flos": 105422656634880.0,
      "train_loss": 1.1566594176822238,
      "train_runtime": 10280.3361,
      "train_samples_per_second": 3.142,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 10,
  "max_steps": 63,
  "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": 105422656634880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}