Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "uclanlp/plbart-large",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "PLBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "plbart",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce3e949bccd072e4edcd336891736dc34e97311501cde8b47629d38ecd7c73a
+size 1624475405

runs/Feb20_12-36-46_db6f5b0c4128/1676896617.4634156/events.out.tfevents.1676896617.db6f5b0c4128.22230.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d636537f199d679b1e34d77e56c664e3764f89c3b74361ff63593d6c73dcc6d
+size 5972

runs/Feb20_12-36-46_db6f5b0c4128/events.out.tfevents.1676896617.db6f5b0c4128.22230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762be842691d6187fa2156bf95463135c0bef8f35aa668aaa7d2b4ed9ffe3feb
+size 4250

runs/Feb20_12-43-09_db6f5b0c4128/1676896995.434722/events.out.tfevents.1676896995.db6f5b0c4128.25241.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52190e24268a345fb1981f2f8a5a13c459c0726ca2fde71c6c4c4c55f5b7ff91
+size 5972

runs/Feb20_12-43-09_db6f5b0c4128/events.out.tfevents.1676896995.db6f5b0c4128.25241.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98fc3e3c06d6ffcdefb15bbbb281bfc16e705662a613280fb5c6e4844cb9f384
+size 4250

runs/Feb20_12-44-33_db6f5b0c4128/1676897079.907183/events.out.tfevents.1676897079.db6f5b0c4128.25732.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4678c83762b7335b655b881fa55f6de2106b80113a40d3694ffa82e864b9045d
+size 5972

runs/Feb20_12-44-33_db6f5b0c4128/events.out.tfevents.1676897079.db6f5b0c4128.25732.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f67f9fcf58c3b55e566de338883ccc03f4439176a2d912611e22904e94c12b0
+size 4250

runs/Feb20_12-46-02_db6f5b0c4128/1676897168.7182176/events.out.tfevents.1676897168.db6f5b0c4128.26288.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ad77de8f29f767f3740fd29d21964a2871090c4612f51ae8ed21d918687569
+size 5972

runs/Feb20_12-46-02_db6f5b0c4128/events.out.tfevents.1676897168.db6f5b0c4128.26288.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74bff4c3cebe77fee8bc8f1c7e17c08919b0c1de3e100e43965bae4f3af35de
+size 4250

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72f5d040a176945623a255484d24066f8c0da89a294359154e226efbe494b80
+size 985833

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "__java__",
+    "__python__",
+    "__en_XX__"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "language_codes": "base",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "uclanlp/plbart-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "PLBartTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4686666161c7a14888fbddeaa3fb6628c030dcff444097fd9890ab5c0cfdbf1
+size 3643