Training in progress, step 500

config.json

@@ -0,0 +1,67 @@
+{
+ "_name_or_path": "facebook/bart-large-xsum",
+ "_num_labels": 3,
+ "activation_dropout": 0.0,
+ "activation_function": "gelu",
+ "add_bias_logits": false,
+ "add_final_layer_norm": false,
+ "architectures": [
+ "BartForConditionalGeneration"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 0,
+ "classif_dropout": 0.0,
+ "classifier_dropout": 0.0,
+ "d_model": 1024,
+ "decoder_attention_heads": 16,
+ "decoder_ffn_dim": 4096,
+ "decoder_layerdrop": 0.0,
+ "decoder_layers": 12,
+ "decoder_start_token_id": 2,
+ "dropout": 0.1,
+ "early_stopping": true,
+ "encoder_attention_heads": 16,
+ "encoder_ffn_dim": 4096,
+ "encoder_layerdrop": 0.0,
+ "encoder_layers": 12,
+ "eos_token_id": 2,
+ "eos_token_ids": [
+ 2
+ ],
+ "forced_eos_token_id": 2,
+ "gradient_checkpointing": false,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2"
+ },
+ "init_std": 0.02,
+ "is_encoder_decoder": true,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2
+ },
+ "max_length": 62,
+ "max_position_embeddings": 1024,
+ "min_length": 11,
+ "model_type": "bart",
+ "no_repeat_ngram_size": 3,
+ "normalize_before": false,
+ "normalize_embedding": true,
+ "num_beams": 6,
+ "num_hidden_layers": 12,
+ "output_past": true,
+ "pad_token_id": 1,
+ "prefix": " ",
+ "replacing_rate": 0,
+ "scale_embedding": false,
+ "static_position_embeddings": false,
+ "student_decoder_layers": null,
+ "student_encoder_layers": null,
+ "task_specific_params": {},
+ "torch_dtype": "float32",
+ "transformers_version": "4.35.2",
+ "use_cache": true,
+ "vocab_size": 50264
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8442b99bfe744d242cfa3624542a618bde3a2a27ef877a83f9519b9155c43a
+size 1625422896

runs/Jan13_14-46-47_fca3447cf82f/events.out.tfevents.1705157221.fca3447cf82f.5279.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431086989b295597af908787ce09ffbd381bced40d6abaca7c1468a00388471a
+size 5473

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+ "cls_token": "[CLS]",
+ "mask_token": "[MASK]",
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_basic_tokenize": true,
+ "do_lower_case": false,
+ "full_tokenizer_file": null,
+ "mask_token": "[MASK]",
+ "model_max_length": 1000000000000000019884624838656,
+ "never_split": null,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": false,
+ "tokenizer_class": "ElectraTokenizer",
+ "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fe812b8812ef6a6b9719c6de07cbbf38f29f40a061e4c437af8a4125086472
+size 4792