Hugging Face's logo

nicholasKluge
/
Aux-RewardModelPT

Text Classification
Transformers
Safetensors
Portuguese
bert
reward model
alignment
preference model
RLHF
Inference Endpoints
Model card Files Community
Aux-RewardModelPT
File size: 1,987 Bytes 
9c46d58
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.8626609442060085,
  "eval_steps": 300,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2875536480686696,
      "grad_norm": 0.001025281846523285,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0089,
      "step": 300
    },
    {
      "epoch": 1.2875536480686696,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0007540204096585512,
      "eval_runtime": 2.866,
      "eval_samples_per_second": 289.256,
      "eval_steps_per_second": 9.072,
      "step": 300
    },
    {
      "epoch": 2.575107296137339,
      "grad_norm": 0.0004946357221342623,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0001,
      "step": 600
    },
    {
      "epoch": 2.575107296137339,
      "eval_accuracy": 1.0,
      "eval_loss": 0.00020219432190060616,
      "eval_runtime": 2.8542,
      "eval_samples_per_second": 290.45,
      "eval_steps_per_second": 9.109,
      "step": 600
    },
    {
      "epoch": 3.8626609442060085,
      "grad_norm": 0.00040382734732702374,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 900
    },
    {
      "epoch": 3.8626609442060085,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0003535090072546154,
      "eval_runtime": 2.8648,
      "eval_samples_per_second": 289.378,
      "eval_steps_per_second": 9.076,
      "step": 900
    }
  ],
  "logging_steps": 300,
  "max_steps": 900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}