Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

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": "4.12.5",
+  "use_cache": true,
+  "vocab_size": 250027
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a79c83b4b901d353495525de8288449c71412498b8ac525bdc4b25dce0a01a8
+size 3052101

runs/Nov30_09-25-09_ffsouza/events.out.tfevents.1638275329.ffsouza.168285.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84aac783351aabd2d4e7bd20ad1b24b0c5e31279213ea9b892e61649bbd1a594
+size 342

runs/Nov30_09-56-25_ffsouza/1638276995.0311055/events.out.tfevents.1638276995.ffsouza.168285.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd4f1afdda16b757a671185a382c553d8f318f5cf2bdf3459cec9d32bec6561
+size 4923

runs/Nov30_09-56-25_ffsouza/events.out.tfevents.1638276994.ffsouza.168285.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aee1428067fcbee4c5fa631b8ae90ff148a1b4f7f7271378a6321cfd2dd6e78
+size 4203

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "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"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "src_lang": null, "tgt_lang": null, "additional_special_tokens": null, "model_max_length": 1024, "special_tokens_map_file": "/home/ffsouza/.cache/huggingface/transformers/33fa7894ab257a74cede3060dca6d2fc609918785e80160f6c057723ece47292.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "sshleifer/tiny-mbart", "sp_model_kwargs": {}, "tokenizer_class": "MBartTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3973adf927081cb429c13c01d8769088fd49382cee8250d88754e40bec3e9c32
+size 3055