Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "google/reformer-crime-and-punishment",
+  "architectures": [
+    "ReformerForMaskedLM"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "attn_layers": [
+    "local",
+    "lsh",
+    "local",
+    "lsh",
+    "local",
+    "lsh"
+  ],
+  "axial_norm_std": 1.0,
+  "axial_pos_embds": false,
+  "axial_pos_embds_dim": [
+    64,
+    64
+  ],
+  "axial_pos_shape": [
+    512,
+    1024
+  ],
+  "chunk_size_lm_head": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "feed_forward_size": 512,
+  "hash_seed": null,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.05,
+  "hidden_size": 256,
+  "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": 4096,
+  "model_type": "reformer",
+  "num_attention_heads": 2,
+  "num_buckets": [
+    64,
+    128
+  ],
+  "num_chunks_after": 0,
+  "num_chunks_before": 1,
+  "num_hashes": 1,
+  "num_hidden_layers": 6,
+  "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": 320
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bddf4b5e7244bdf7cb62aa690ce3175f1e0b3d258092a7aa63c85422f6eeb0
+size 14301070

runs/Jun22_09-43-20_f01ce8164ed2/1655891158.9861765/events.out.tfevents.1655891158.f01ce8164ed2.99.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbbfb8543d45fd85eed6b30d9650efd72a0fda4fd79d10b61d5f29799d4baee
+size 5360

runs/Jun22_09-43-20_f01ce8164ed2/1655891335.496459/events.out.tfevents.1655891335.f01ce8164ed2.99.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb0aa7971a946243c0fdeab4d0d5e0bfa217c7a98e7b688448b80899787d41f
+size 5360

runs/Jun22_09-43-20_f01ce8164ed2/events.out.tfevents.1655891124.f01ce8164ed2.99.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8420504243c6e1f29f3d679715c178f1e5ab80cd8d3355667938e3e7d6a669
+size 9302

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab5dd9a894df5a9f00d8ea85f0411e70ad923e38f91753235a0bfa19680b2ab
+size 3311