Training complete

runs/Mar06_12-40-47_44c845a0a897/events.out.tfevents.1678106482.44c845a0a897.210.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720643d739ff4c7581e9023e8cc9fe692810e39dc8729b16d7e923900fc01bb0
-size 12946
+oid sha256:9230fa8be024c86ffc07b913c7447eb61d32a73a46b77b0b2163bad66764f165
+size 13683

tiny-mbart/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "sshleifer/tiny-mbart",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 2,
+  "decoder_attention_heads": 1,
+  "decoder_ffn_dim": 4,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 1,
+  "encoder_ffn_dim": 4,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 2,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "forced_eos_token_id": 2,
+  "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_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 2,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 250027
+}

tiny-mbart/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "num_beams": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.1"
+}

tiny-mbart/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337b8deeb586e6f74d3ba4eac8aeea27eaeec23ebee09ec0e8c570d3d569114f
+size 3048849

tiny-mbart/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tiny-mbart/special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tiny-mbart/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596c5a4c6d3f1a30908406c2b02396ed0a927c18342237b32ac8bd2fff7322a3
+size 17103694

tiny-mbart/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "name_or_path": "sshleifer/tiny-mbart",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--sshleifer--tiny-mbart/snapshots/9d6b9b3b2774b464bb6b14eda4efe30f82846136/special_tokens_map.json",
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "MBartTokenizer",
+  "unk_token": "<unk>"
+}

tiny-mbart/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9354bad34a7e6aaeb63f9d37e4b98c6c8a087359aee3a6dea4b36fd97e706d
+size 3579