Hugging Face's logo

winnieyangwannan
/
Llama-3.1-8B-Instruct_sft_to_honest_lora_True

Transformers
Safetensors
Generated from Trainer
Llama-3.1-8B-Instruct
honest_lying
sft_to_honest
lora_True
trl
sft
Inference Endpoints
Model card Files Community
Llama-3.1-8B-Instruct_sft_to_honest_lora_True
File size: 2,310 Bytes 
8b92dd4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04214963119072708,
  "eval_steps": 10,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01053740779768177,
      "grad_norm": 3.3616116046905518,
      "learning_rate": 4.982437653670531e-05,
      "loss": 1.7881,
      "step": 10
    },
    {
      "epoch": 0.01053740779768177,
      "eval_loss": 0.6833231449127197,
      "eval_runtime": 13.3064,
      "eval_samples_per_second": 36.073,
      "eval_steps_per_second": 2.255,
      "step": 10
    },
    {
      "epoch": 0.02107481559536354,
      "grad_norm": 1.3658663034439087,
      "learning_rate": 4.964875307341061e-05,
      "loss": 0.5571,
      "step": 20
    },
    {
      "epoch": 0.02107481559536354,
      "eval_loss": 0.5293903350830078,
      "eval_runtime": 13.4286,
      "eval_samples_per_second": 35.745,
      "eval_steps_per_second": 2.234,
      "step": 20
    },
    {
      "epoch": 0.03161222339304531,
      "grad_norm": 1.0748717784881592,
      "learning_rate": 4.947312961011591e-05,
      "loss": 0.4482,
      "step": 30
    },
    {
      "epoch": 0.03161222339304531,
      "eval_loss": 0.47912800312042236,
      "eval_runtime": 13.4918,
      "eval_samples_per_second": 35.577,
      "eval_steps_per_second": 2.224,
      "step": 30
    },
    {
      "epoch": 0.04214963119072708,
      "grad_norm": 0.890529215335846,
      "learning_rate": 4.929750614682122e-05,
      "loss": 0.3722,
      "step": 40
    },
    {
      "epoch": 0.04214963119072708,
      "eval_loss": 0.44374603033065796,
      "eval_runtime": 13.5807,
      "eval_samples_per_second": 35.344,
      "eval_steps_per_second": 2.209,
      "step": 40
    }
  ],
  "logging_steps": 10,
  "max_steps": 2847,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4788215876026368.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}