Initial model upload

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: albert/albert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: classify-bluesky-1000-v2
+  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. -->
+
+# classify-bluesky-1000-v2
+
+This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1265
+- Accuracy: 1.0
+- F1: 1.0
+- Precision: 1.0
+- Recall: 1.0
+- Accuracy Label Bluesky: 1.0
+- Accuracy Label Specific: 1.0
+
+## 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
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.1

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "albert/albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "bluesky",
+    "1": "specific"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bluesky": 0,
+    "specific": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0198cfa34374703bbbd83d4f3575d6364d1183319cc0ca2edde4e9b75664e22
+size 46743912

runs/Oct15_06-15-58_3a6228660927/events.out.tfevents.1728973095.3a6228660927.1914.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20947d5ac625a1aa3cc428d64f9ee183e6a23cd35cc09e855eb0b97506ba1654
+size 6829

runs/Oct15_06-15-58_3a6228660927/events.out.tfevents.1728973124.3a6228660927.1914.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33dc46d961ce4581655a9ab3063442e55bd1c78b7ddbbddb9a17b1fe6d7013d
+size 682

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9333333333333336,
+  "eval_steps": 100,
+  "global_step": 66,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 24.911563873291016,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 0.6944,
+      "step": 10
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 20.48420524597168,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.6317,
+      "step": 20
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 21.66866111755371,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.5401,
+      "step": 30
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 12.989063262939453,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.4192,
+      "step": 40
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 8.98383617401123,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.29,
+      "step": 50
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 5.708517074584961,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.2052,
+      "step": 60
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "step": 66,
+      "total_flos": 3605999510880.0,
+      "train_loss": 0.4347104240547527,
+      "train_runtime": 17.5364,
+      "train_samples_per_second": 121.12,
+      "train_steps_per_second": 3.764
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "eval_accuracy": 1.0,
+      "eval_accuracy_label_bluesky": 1.0,
+      "eval_accuracy_label_specific": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.1264917105436325,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 0.8403,
+      "eval_samples_per_second": 361.76,
+      "eval_steps_per_second": 22.61,
+      "step": 66
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 66,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3605999510880.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830d97dfa959466668a482c555597fa3325e36badcad0caf953958026c40a8ae
+size 5176