my_awesome_model

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: allenai/longformer-base-4096
+tags:
+- generated_from_trainer
+datasets:
+- imdb
+metrics:
+- accuracy
+model-index:
+- name: my_awesome_model
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: imdb
+      type: imdb
+      config: plain_text
+      split: test
+      args: plain_text
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.95528
+---
+
+<!-- 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. -->
+
+# my_awesome_model
+
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the imdb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2141
+- Accuracy: 0.9553
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3358        | 0.32  | 1000 | 0.2286          | 0.9349   |
+| 0.2658        | 0.64  | 2000 | 0.2036          | 0.9447   |
+| 0.2392        | 0.96  | 3000 | 0.2294          | 0.9504   |
+| 0.1648        | 1.28  | 4000 | 0.2288          | 0.9518   |
+| 0.1477        | 1.6   | 5000 | 0.2190          | 0.9532   |
+| 0.1404        | 1.92  | 6000 | 0.2141          | 0.9553   |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

runs/Nov04_21-33-46_6f29081d301d/events.out.tfevents.1699133626.6f29081d301d.5809.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa9ebe5c08e24d5abbd57ff515ec6fb99a2bb6669e33d121c4ea4b5d32fdbb5
+size 4184

runs/Nov04_21-34-04_6f29081d301d/events.out.tfevents.1699133645.6f29081d301d.5809.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41aae9a995b407037ba2bf55df43f03c098894c8bd2d69ede170c6b802d18dc6
+size 4184

runs/Nov04_21-34-45_6f29081d301d/events.out.tfevents.1699133687.6f29081d301d.6502.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c2173f219f844fbdbc49e3ad06cb6f45c2482248dabc3b35c68ea4e4f59e9e
+size 8104

runs/Nov04_22-29-29_6f29081d301d/events.out.tfevents.1699136969.6f29081d301d.6502.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f1473b60efd37abe1ac50ae9e47fb77f8ac56afff05ba346c099166271cade
+size 4184

runs/Nov04_22-30-30_6f29081d301d/events.out.tfevents.1699137032.6f29081d301d.20438.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffbcf8af72b6e917c7cee365f123ae2e3a552a9eade87f15da8360b00ab2af4
+size 7728

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643333107f0b09bfe6d80d716a7899d8208849e1b4d06f1c3e21b2adacd480d9
+size 4536