Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "BigBirdForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79869c61af9da4984ba2ed25e956e20e41c28fc350008f93dc13ba52d77873c5
+size 511446657

runs/Jan30_10-52-37_tardis/1675072367.2792327/events.out.tfevents.1675072367.tardis.1539963.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba99ff28b8b4a5af51e97ff07ad0b753876fdade855a7ad9bf091140b725f7f
+size 5473

runs/Jan30_10-52-37_tardis/events.out.tfevents.1675072367.tardis.1539963.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac05860df5ca38775e5d70a94dc0dc8d0273c6cbde455a9a86943b2f5625661
+size 4181

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "huggingface-course/code-search-net-tokenizer",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09cb11374fdd2b70d8194e680f96c3ef461b1b74316bbd0fbe8b971ef7a2be63
+size 3387