Model save

README.md

@@ -0,0 +1,83 @@
+---
+base_model: bigcode/starencoder
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: stack-edu-classifier-ruby
+  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. -->
+
+# stack-edu-classifier-ruby
+
+This model is a fine-tuned version of [bigcode/starencoder](https://huggingface.co/bigcode/starencoder) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3282
+- Precision: 0.4623
+- Recall: 0.3260
+- F1 Macro: 0.3536
+- Accuracy: 0.6657
+- F1 Binary Minimum3: 0.6101
+
+## 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: 0.0003
+- train_batch_size: 64
+- eval_batch_size: 256
+- seed: 0
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Precision | Recall | F1 Macro | Accuracy | F1 Binary Minimum3 |
+|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:--------:|:--------:|:------------------:|
+| No log        | 0       | 0     | 4.7647          | 0.0010    | 0.1667 | 0.0020   | 0.0062   | 0                  |
+| 0.358         | 1.4368  | 1000  | 0.3549          | 0.4093    | 0.2953 | 0.3072   | 0.6513   | 0.5882             |
+| 0.3559        | 2.8736  | 2000  | 0.3425          | 0.4649    | 0.3087 | 0.3294   | 0.6571   | 0.6143             |
+| 0.3534        | 4.3103  | 3000  | 0.3391          | 0.4318    | 0.3144 | 0.3349   | 0.6586   | 0.6149             |
+| 0.3539        | 5.7471  | 4000  | 0.3394          | 0.4219    | 0.3244 | 0.3446   | 0.6579   | 0.6298             |
+| 0.3585        | 7.1839  | 5000  | 0.3359          | 0.4756    | 0.3106 | 0.3350   | 0.6622   | 0.6069             |
+| 0.3476        | 8.6207  | 6000  | 0.3339          | 0.4551    | 0.3178 | 0.3415   | 0.6638   | 0.6082             |
+| 0.3496        | 10.0575 | 7000  | 0.3307          | 0.4512    | 0.3263 | 0.3505   | 0.6656   | 0.6204             |
+| 0.3362        | 11.4943 | 8000  | 0.3307          | 0.4657    | 0.3228 | 0.3485   | 0.6640   | 0.6178             |
+| 0.3442        | 12.9310 | 9000  | 0.3307          | 0.4771    | 0.3248 | 0.3517   | 0.6677   | 0.6095             |
+| 0.344         | 14.3678 | 10000 | 0.3287          | 0.4774    | 0.3222 | 0.3496   | 0.6660   | 0.6147             |
+| 0.3332        | 15.8046 | 11000 | 0.3281          | 0.4678    | 0.3240 | 0.3504   | 0.6658   | 0.6168             |
+| 0.3359        | 17.2414 | 12000 | 0.3300          | 0.4658    | 0.3203 | 0.3471   | 0.6643   | 0.6100             |
+| 0.3306        | 18.6782 | 13000 | 0.3282          | 0.4623    | 0.3260 | 0.3536   | 0.6657   | 0.6101             |
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

final/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigcode/starencoder",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 49152,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 49156
+}

final/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55701de2dc003be4e880e1dbf6da28b2ec32ba14aa1447dd91e8b9edfe48075e
+size 496772092

final/special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

final/tokenizer_config.json

@@ -0,0 +1,186 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

final/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d587393a307d59f9d8244620850fd328058df0a578b5ba9e6e275cca61432a99
+size 5304

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1ada38b3d8ed4dae4a0b04a7bc837a8a47d1c05b1c71ce767760544aab339f
+oid sha256:55701de2dc003be4e880e1dbf6da28b2ec32ba14aa1447dd91e8b9edfe48075e
 size 496772092