Hugging Face's logo

matthewleechen
/
roberta-blbooks-pt-1510-1879

Safetensors
roberta
Model card Files Community
roberta-blbooks-pt-1510-1879
File size: 2,866 Bytes 
b731863
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "input_file": "data/1870-1879.txt",
    "continued_from": "output/model_to_1869",
    "training_date": "2025-01-18 15:03:41",
    "config": {
        "return_dict": true,
        "output_hidden_states": false,
        "output_attentions": false,
        "torchscript": false,
        "torch_dtype": "float32",
        "use_bfloat16": false,
        "tf_legacy_loss": false,
        "pruned_heads": {},
        "tie_word_embeddings": true,
        "chunk_size_feed_forward": 0,
        "is_encoder_decoder": false,
        "is_decoder": false,
        "cross_attention_hidden_size": null,
        "add_cross_attention": false,
        "tie_encoder_decoder": false,
        "max_length": 20,
        "min_length": 0,
        "do_sample": false,
        "early_stopping": false,
        "num_beams": 1,
        "num_beam_groups": 1,
        "diversity_penalty": 0.0,
        "temperature": 1.0,
        "top_k": 50,
        "top_p": 1.0,
        "typical_p": 1.0,
        "repetition_penalty": 1.0,
        "length_penalty": 1.0,
        "no_repeat_ngram_size": 0,
        "encoder_no_repeat_ngram_size": 0,
        "bad_words_ids": null,
        "num_return_sequences": 1,
        "output_scores": false,
        "return_dict_in_generate": false,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "remove_invalid_values": false,
        "exponential_decay_length_penalty": null,
        "suppress_tokens": null,
        "begin_suppress_tokens": null,
        "architectures": [
            "RobertaForMaskedLM"
        ],
        "finetuning_task": null,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "tokenizer_class": null,
        "prefix": null,
        "bos_token_id": 0,
        "pad_token_id": 1,
        "eos_token_id": 2,
        "sep_token_id": null,
        "decoder_start_token_id": null,
        "task_specific_params": null,
        "problem_type": null,
        "_name_or_path": "output/model_to_1869",
        "_attn_implementation_autoset": false,
        "transformers_version": "4.47.1",
        "model_type": "roberta",
        "vocab_size": 50265,
        "hidden_size": 768,
        "num_hidden_layers": 12,
        "num_attention_heads": 12,
        "hidden_act": "gelu",
        "intermediate_size": 3072,
        "hidden_dropout_prob": 0.1,
        "attention_probs_dropout_prob": 0.1,
        "max_position_embeddings": 514,
        "type_vocab_size": 1,
        "initializer_range": 0.02,
        "layer_norm_eps": 1e-12,
        "position_embedding_type": "absolute",
        "use_cache": true,
        "classifier_dropout": null
    },
    "best_epoch": 0.41913657864798515,
    "best_eval_loss": 2.3632972240448,
    "training_stopped_at_epoch": 0.7185198491108317
}