Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+base_model: microsoft/mpnet-base
+tags:
+- edu score
+- data filter
+inference: false
+datasets:
+- HuggingFaceFW/fineweb-edu-llama3-annotations
+license: mit
+language:
+- en
+---
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pszemraj/eduscore-regression/runs/k2lc9nx3)
+# mpnet-base-edu-classifier
+
+This model is a fine-tuned version of [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the HuggingFaceFW/fineweb-edu-llama3-annotations dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2105
+- Mse: 0.2105
+
+## Usage 
+
+Note this is for CPU, for GPU you will need to make some (small) changes.
+
+```py
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("pszemraj/mpnet-base-edu-classifier")
+model = AutoModelForSequenceClassification.from_pretrained("pszemraj/mpnet-base-edu-classifier")
+
+text = "This is a test sentence."
+inputs = tokenizer(text, return_tensors="pt", padding="longest", truncation=True)
+outputs = model(**inputs)
+logits = outputs.logits.squeeze(-1).float().detach().numpy()
+score = logits.item()
+result = {
+    "text": text,
+    "score": score,
+    "int_score": int(round(max(0, min(score, 5)))),
+}
+
+print(result)
+# {'text': 'This is a test sentence.', 'score': 0.3350256383419037, 'int_score': 0}
+```
+
+## Intended uses & limitations
+
+Refer to the hf classifier's [model card](https://huggingface.co/HuggingFaceFW/fineweb-edu-classifier#limitations) for more details
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 90085
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-09
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1.0

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.9999459527627146,
+    "eval_loss": 0.2105061411857605,
+    "eval_mse": 0.21050613161735238,
+    "eval_runtime": 6.5728,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 152.141,
+    "eval_steps_per_second": 19.018,
+    "total_flos": 1.1682867916662374e+17,
+    "train_loss": 0.2771636627187094,
+    "train_runtime": 4603.777,
+    "train_samples": 444052,
+    "train_samples_per_second": 96.454,
+    "train_steps_per_second": 0.754
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "microsoft/mpnet-base",
+  "architectures": [
+    "MPNetForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "regression",
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "vocab_size": 30527
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999459527627146,
+    "eval_loss": 0.2105061411857605,
+    "eval_mse": 0.21050613161735238,
+    "eval_runtime": 6.5728,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 152.141,
+    "eval_steps_per_second": 19.018
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b9eacc68a7e97479d1d9ee79ec6ad17547298feed17cafbcfe66c770ff42fc
+size 437972124

regression_config.json

@@ -0,0 +1,15 @@
+{
+  "min_value": 0.0,
+  "max_value": 5.0,
+  "metadata": {
+    "dataset": "HuggingFaceFW/fineweb-edu-llama3-annotations",
+    "task": "regression",
+    "num_examples": 444052,
+    "stats": {
+      "mean": 1.2964269950366174,
+      "min": 0.0,
+      "max": 5.0,
+      "std_dev": 0.8377157123327311
+    }
+  }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999459527627146,
+    "total_flos": 1.1682867916662374e+17,
+    "train_loss": 0.2771636627187094,
+    "train_runtime": 4603.777,
+    "train_samples": 444052,
+    "train_samples_per_second": 96.454,
+    "train_steps_per_second": 0.754
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64616dfde8eed804f3193de525a28dbd34808f3c5e9786fa31c75d797799482a
+size 5304