Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: imdb_42
+  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. -->
+
+# imdb_42
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0838
+- eval_accuracy: 0.9781
+- eval_runtime: 20.6358
+- eval_samples_per_second: 1211.49
+- eval_steps_per_second: 4.749
+- step: 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.97808,
+    "eval_loss": 0.0838116779923439,
+    "eval_runtime": 20.6358,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 1211.49,
+    "eval_steps_per_second": 4.749,
+    "train_loss": 0.07839516550683609,
+    "train_runtime": 418.6292,
+    "train_samples": 25000,
+    "train_samples_per_second": 597.187,
+    "train_steps_per_second": 18.68
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "text-classification",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "4.28.0",
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.87392,
+    "eval_loss": 0.3133154809474945,
+    "eval_runtime": 24.0502,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 1039.49,
+    "eval_steps_per_second": 4.075
+}

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9130026e7c07ecaa7d0570d803efc6848ce04b23096615ce4059c0b8870c3b
+size 200128

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9130026e7c07ecaa7d0570d803efc6848ce04b23096615ce4059c0b8870c3b
+size 200128

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ee86be5d3df9cd9f69f02973592a6e3f5656a8042a1568de78d8885268a962
+size 200128

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32ce46471955018916130a430e53ed53ca71df217b10f3db8b5447a15cf5a1d
+size 267854321

runs/Apr21_18-50-36_clu/events.out.tfevents.1713725484.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4777ff8661c69cb27a892e87aba3ada813b05df6621c12b6c0cb81b50845b58
+size 814

runs/Mar18_09-33-46_clu/1710754452.2684553/events.out.tfevents.1710754452.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fa44f729d1d5f5b88ac783d6a4273a082da823293906f349bf156daf174474
+size 5643

runs/Mar18_09-33-46_clu/events.out.tfevents.1710754452.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a69d9fea6b888f957bd9cb8f0bed6eb312b31a86e0a1a7fd40a74ace302503
+size 8785

runs/Mar18_09-33-46_clu/events.out.tfevents.1710754879.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58be613696db520d4418e80e443d64022d39cabddc2c2525712b7e6a7edcada2
+size 363

special_tokens_map.json

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

test_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.87392,
+    "eval_loss": 0.3133154809474945,
+    "eval_runtime": 20.5489,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 1216.609,
+    "eval_steps_per_second": 4.769
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.97808,
+    "eval_loss": 0.0838116779923439,
+    "eval_runtime": 20.6358,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 1211.49,
+    "eval_steps_per_second": 4.749
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.87396,
+  "best_model_checkpoint": "checkpoint/distilbert-base/imdb_42/checkpoint-1564",
+  "epoch": 10.0,
+  "global_step": 7820,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.87392,
+      "eval_loss": 0.29652780294418335,
+      "eval_runtime": 8.5888,
+      "eval_samples_per_second": 2910.752,
+      "eval_steps_per_second": 11.41,
+      "step": 782
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.3243,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.87396,
+      "eval_loss": 0.3133092522621155,
+      "eval_runtime": 8.2501,
+      "eval_samples_per_second": 3030.277,
+      "eval_steps_per_second": 11.879,
+      "step": 1564
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.1574,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8712,
+      "eval_loss": 0.5505877137184143,
+      "eval_runtime": 8.2054,
+      "eval_samples_per_second": 3046.769,
+      "eval_steps_per_second": 11.943,
+      "step": 2346
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.066,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.86316,
+      "eval_loss": 0.6083658337593079,
+      "eval_runtime": 8.1073,
+      "eval_samples_per_second": 3083.646,
+      "eval_steps_per_second": 12.088,
+      "step": 3128
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.87084,
+      "eval_loss": 0.6640308499336243,
+      "eval_runtime": 8.1424,
+      "eval_samples_per_second": 3070.331,
+      "eval_steps_per_second": 12.036,
+      "step": 3910
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.0308,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.87112,
+      "eval_loss": 0.8268970251083374,
+      "eval_runtime": 8.1225,
+      "eval_samples_per_second": 3077.853,
+      "eval_steps_per_second": 12.065,
+      "step": 4692
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.0167,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.87168,
+      "eval_loss": 0.8184564709663391,
+      "eval_runtime": 8.134,
+      "eval_samples_per_second": 3073.521,
+      "eval_steps_per_second": 12.048,
+      "step": 5474
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0099,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.87244,
+      "eval_loss": 0.9372827410697937,
+      "eval_runtime": 8.0981,
+      "eval_samples_per_second": 3087.162,
+      "eval_steps_per_second": 12.102,
+      "step": 6256
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.0056,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.87288,
+      "eval_loss": 0.994419276714325,
+      "eval_runtime": 8.137,
+      "eval_samples_per_second": 3072.372,
+      "eval_steps_per_second": 12.044,
+      "step": 7038
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.87356,
+      "eval_loss": 0.9994614720344543,
+      "eval_runtime": 8.1462,
+      "eval_samples_per_second": 3068.914,
+      "eval_steps_per_second": 12.03,
+      "step": 7820
+    },
+    {
+      "epoch": 10.0,
+      "step": 7820,
+      "total_flos": 8279212416000000.0,
+      "train_loss": 0.07839516550683609,
+      "train_runtime": 418.6292,
+      "train_samples_per_second": 597.187,
+      "train_steps_per_second": 18.68
+    }
+  ],
+  "max_steps": 7820,
+  "num_train_epochs": 10,
+  "total_flos": 8279212416000000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c29e65f58c26651757d7c6541708c6083f8fd4a3f5bd980beafabc774e8dcc
+size 3631