Training in progress, epoch 1

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: test_model2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# test_model2
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3250
+- Accuracy: 0.863
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5093        | 1.0   | 625  | 0.3441          | 0.852    |
+| 0.3595        | 2.0   | 1250 | 0.3250          | 0.863    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cpu
+- Datasets 2.18.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 320
+}

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "google/reformer-crime-and-punishment",
+  "architectures": [
+    "ReformerForSequenceClassification"
+  ],
+  "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": true,
+  "axial_pos_embds_dim": [
+    128,
+    128
+  ],
+  "axial_pos_shape": [
+    12,
+    16
+  ],
+  "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,
+  "is_decoder": true,
+  "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": 524288,
+  "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,
+  "problem_type": "single_label_classification",
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 100
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 321
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8230de5998d7dcd00225fefd1301896d0808b2eb8aa596f6fc6a7220bd0d4d
+size 9971008

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 +1,11 @@
+{
+  "eos_token": "</s>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14478412faa9cfe39a1a77ddf447f2466ae5eabc3d389d73e2444cf47001e260
+size 241801

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "320": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 524288,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "ReformerTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082838a5d99337078207c8fd512568dcb6c7b4621a2ead586140668c3947a3e9
+size 5048