End of training

.gitignore

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

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "robingeibel/reformer-finetuned-big_patent-wikipedia-arxiv-16384",
+  "architectures": [
+    "ReformerForMaskedLM"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "attn_layers": [
+    "local",
+    "local",
+    "lsh",
+    "local",
+    "local",
+    "local",
+    "lsh",
+    "local",
+    "local",
+    "local",
+    "lsh",
+    "local"
+  ],
+  "axial_norm_std": 1.0,
+  "axial_pos_embds": false,
+  "axial_pos_embds_dim": [
+    128,
+    128
+  ],
+  "axial_pos_shape": [
+    512,
+    1024
+  ],
+  "chunk_size_lm_head": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "feed_forward_size": 1024,
+  "hash_seed": null,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.05,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "local_attention_probs_dropout_prob": 0.05,
+  "local_attn_chunk_length": 64,
+  "local_num_chunks_after": 0,
+  "local_num_chunks_before": 1,
+  "lsh_attention_probs_dropout_prob": 0.0,
+  "lsh_attn_chunk_length": 64,
+  "lsh_num_chunks_after": 0,
+  "lsh_num_chunks_before": 1,
+  "max_position_embeddings": 16384,
+  "model_type": "reformer",
+  "num_attention_heads": 12,
+  "num_buckets": [
+    64,
+    128
+  ],
+  "num_chunks_after": 0,
+  "num_chunks_before": 1,
+  "num_hashes": 1,
+  "num_hidden_layers": 12,
+  "output_attentions": true,
+  "output_hidden_states": true,
+  "output_past": true,
+  "pad_token_id": 0,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 100
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd524557c3a39b7325995044db461e98e27b520497679cdf8b4593de4fec199b
+size 711743775

runs/Jul26_05-39-47_92dc2573e396/1658814002.7952054/events.out.tfevents.1658814002.92dc2573e396.89.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795b63215738772761204fbf480d4344beea17bb0dff9c0c81b4018310a9231d
+size 5381

runs/Jul26_05-39-47_92dc2573e396/events.out.tfevents.1658814002.92dc2573e396.89.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f64dbb9f8728bf39febf9c96473ebc327679e34742b59a132046904fd58853d7
+size 9238

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75c4ecc3f27940111a0e071df4050142c5461d9a3dee89d1bbf07c168e20280
+size 3375