imdb_text_classification

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3574
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.2839        | 1.0   | 3125 | 0.2983          |
+| 0.1714        | 2.0   | 6250 | 0.3002          |
+| 0.0776        | 3.0   | 9375 | 0.3574          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1 @@
+{"eval_loss": 0.35744309425354004, "eval_runtime": 110.9426, "eval_samples_per_second": 225.342, "eval_steps_per_second": 28.168, "epoch": 3.0}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e2ba2304a9c0e23b6d54aafae9cd5b556225b579729bb2196dc0a50534e357
+size 267832560

runs/Oct21_23-45-08_cf4540768754/events.out.tfevents.1729554334.cf4540768754.1358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784961f45b48aedd3e334c4dd0974bb51364719494b5f3ff2a381d2f2161f2ce
+size 9741

runs/Oct21_23-45-08_cf4540768754/events.out.tfevents.1729556102.cf4540768754.1358.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5729f5fd02ed3a3fcf3ffa708c3002a6876dc82499bf0927a29662fd101251dc
+size 359

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 25.028797149658203,
+      "learning_rate": 4.7333333333333336e-05,
+      "loss": 0.4107,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.398056507110596,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 0.3382,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 17.56199073791504,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3389,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 32.491722106933594,
+      "learning_rate": 3.933333333333333e-05,
+      "loss": 0.3043,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 12.640718460083008,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.3006,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.034324645996094,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.2839,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.29832616448402405,
+      "eval_runtime": 109.9495,
+      "eval_samples_per_second": 227.377,
+      "eval_steps_per_second": 28.422,
+      "step": 3125
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 32.539512634277344,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 0.2058,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.0097203254699707,
+      "learning_rate": 2.8666666666666668e-05,
+      "loss": 0.182,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.1602770835161209,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.1614,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.056532543152570724,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.1726,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 21.226852416992188,
+      "learning_rate": 2.0666666666666666e-05,
+      "loss": 0.1867,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 14.321476936340332,
+      "learning_rate": 1.8e-05,
+      "loss": 0.1714,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3002217710018158,
+      "eval_runtime": 110.1479,
+      "eval_samples_per_second": 226.968,
+      "eval_steps_per_second": 28.371,
+      "step": 6250
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.014615637250244617,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.1151,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.2536245286464691,
+      "learning_rate": 1.2666666666666668e-05,
+      "loss": 0.074,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.25840720534324646,
+      "learning_rate": 1e-05,
+      "loss": 0.0538,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.008101879619061947,
+      "learning_rate": 7.333333333333334e-06,
+      "loss": 0.0659,
+      "step": 8000
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.056057158857584,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.0691,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.04367438703775406,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0776,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.35744309425354004,
+      "eval_runtime": 110.1571,
+      "eval_samples_per_second": 226.949,
+      "eval_steps_per_second": 28.369,
+      "step": 9375
+    },
+    {
+      "epoch": 3.0,
+      "step": 9375,
+      "total_flos": 9935054899200000.0,
+      "train_loss": 0.18996990498860677,
+      "train_runtime": 1346.0972,
+      "train_samples_per_second": 55.717,
+      "train_steps_per_second": 6.965
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9935054899200000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbc9933bc9d68594c7d7df0830d5b3b8d87d71036ff60a78ef05041b18cdb90
+size 5176