End of training

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: allenai/longformer-base-4096
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: job_interview_STAR_transcript_classifier_long
+  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. -->
+
+# job_interview_STAR_transcript_classifier_long
+
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2128
+- Accuracy: 0.9667
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 60   | 0.2217          | 0.9333   |
+| No log        | 2.0   | 120  | 0.2318          | 0.9667   |
+| No log        | 3.0   | 180  | 0.2169          | 0.9667   |
+| No log        | 4.0   | 240  | 0.2128          | 0.9667   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "FAIL",
+    "1": "SUCCESS"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "FAIL": 0,
+    "SUCCESS": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ccb7ba82080a9ed8107c12c59416fedbb8f5c2590d3027ee29b96251f0bd82
+size 594678184

runs/Jun10_07-31-33_592c97bb8d71/events.out.tfevents.1718004694.592c97bb8d71.217.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe17afb4ec45fd77d31a722ad3dd6aaae9c067cb74ccba9434bc55898243e14b
+size 5169

runs/Jun10_07-31-47_592c97bb8d71/events.out.tfevents.1718004707.592c97bb8d71.217.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98ae72c93086f46f30dd23d8680e293ec540894bd5505ad5ed10b777ed2b2e5
+size 5169

runs/Jun10_07-32-10_592c97bb8d71/events.out.tfevents.1718004731.592c97bb8d71.217.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5d5ad0adbb9ae76469242cf08c0b3928132127de43abde2d2799ad94adfb6b
+size 5169

runs/Jun10_07-33-01_592c97bb8d71/events.out.tfevents.1718004782.592c97bb8d71.217.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cef2581d2d1ebd21b739707e9c1f36a90e7755388b37c9bc2c0fa0b76df2e6f
+size 5169

runs/Jun10_07-33-57_592c97bb8d71/events.out.tfevents.1718004839.592c97bb8d71.217.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da04f6ea02170f309960370c5f075c1fc07e8de0a4b310c5b31c186b11b2ba8
+size 5169

runs/Jun10_07-34-52_592c97bb8d71/events.out.tfevents.1718004893.592c97bb8d71.217.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9797012b11b26d25cbe9cc93143ac882175fcc12d778da806ade74155b66b597
+size 5169

runs/Jun10_07-37-22_592c97bb8d71/events.out.tfevents.1718005043.592c97bb8d71.217.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245ddb6c0711efb91d73edc01c2ac6eaeacb404f491c605824eee18bcca2f33b
+size 5169

runs/Jun10_07-38-42_592c97bb8d71/events.out.tfevents.1718005123.592c97bb8d71.217.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c76313db7488411a620a953045c3f081a9a4e46466f2269423464863c6e4f8
+size 5167

runs/Jun10_07-38-56_592c97bb8d71/events.out.tfevents.1718005136.592c97bb8d71.217.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17a98b92672b3109daac2a23cef09aeb03d74ff967e550f0157c95313b74414
+size 5216

runs/Jun10_07-41-28_592c97bb8d71/events.out.tfevents.1718005289.592c97bb8d71.217.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04816c3032e9b05725292bd472b503bc2665e127399a2d809e8e56ff1500b7a5
+size 5216

runs/Jun10_07-42-02_592c97bb8d71/events.out.tfevents.1718005323.592c97bb8d71.217.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403e297f88929107549bf219b1208e2a39e47fa4a7ba465410d211b8ee0e73af
+size 6850

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": 1000000000000000019884624838656,
+  "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 sha256:7dab8b92a210f7f916621e616cc943b792e069d7510ae194e76e14c49f129798
+size 5176