Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: bert-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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0003
+- eval_accuracy: 1.0000
+- eval_runtime: 75.737
+- eval_samples_per_second: 330.09
+- eval_steps_per_second: 1.294
+- 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": 0.99996,
+    "eval_loss": 0.00027643845533020794,
+    "eval_runtime": 75.737,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 330.09,
+    "eval_steps_per_second": 1.294,
+    "train_loss": 0.07364957506394447,
+    "train_runtime": 797.6475,
+    "train_samples": 25000,
+    "train_samples_per_second": 313.422,
+    "train_steps_per_second": 9.804
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "text-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.88732,
+    "eval_loss": 0.8893803954124451,
+    "eval_runtime": 97.5647,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 256.24,
+    "eval_steps_per_second": 1.004
+}

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6772e889a33ddacf9c3f2d22208c2f505f4d44d301499d6adaecc5c4a489182c
+size 200128

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6772e889a33ddacf9c3f2d22208c2f505f4d44d301499d6adaecc5c4a489182c
+size 200128

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2d30ddf192e690897f9796f5554f95f32fddf421f1b531c8ee0b1599c21e98
+size 200128

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c6cf38ac6be12c428c95dc645a8468c01ba198a7f5acf735f8f31adbb83149
+size 438006125

runs/Apr17_12-06-40_clu/events.out.tfevents.1713355674.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9535b0a2f571e1555f5fd81858ceb9e072e4b734862663bfdc2d3cd4019e10aa
+size 298

runs/Apr21_13-51-18_clu/events.out.tfevents.1713707544.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95be4bd7aa54eaad75d49ee8b5039cc8bd720308d56bb9eabcea732dbb1ddb3c
+size 298

runs/Apr21_14-55-43_clu/events.out.tfevents.1713711396.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113f2c250862ff8e2f9c24b2e38b13a7f83985268399a4a6e645055d9c058349
+size 298

runs/Apr21_14-59-03_clu/events.out.tfevents.1713711635.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277fa271b4880c80f84fbf67594f637735c6b2cdcba3bf02d4739c81c7fc644d
+size 556

runs/Apr21_15-06-38_clu/events.out.tfevents.1713712100.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b23e453e692ab633faa7ad645c78c2eaa61c12269b87342f0e4cbcbc2a8ad3b
+size 814

runs/Apr21_15-51-39_clu/events.out.tfevents.1713714810.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167c13778c9a6a0127d59b521ccd47479912feab3e124cc7450bc822df4652ba
+size 814

runs/Mar18_05-43-22_clu/1710740630.8411405/events.out.tfevents.1710740630.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0692fcf5ee8524b6ea736d8bde02609f21de37fcbd98ab8d709b50c9dc3172d
+size 5619

runs/Mar18_05-43-22_clu/events.out.tfevents.1710740630.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e5b9c9e1290abda12a605c6b2474b2221b26f8a8f8acf599c9fbae1b0b1d9b8
+size 8862

runs/Mar18_05-43-22_clu/events.out.tfevents.1710741444.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f638289892453b763dfa15009b25f91433ab92aaad3c2aad3838ddc66db094a
+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": 0.88732,
+    "eval_loss": 0.8893803954124451,
+    "eval_runtime": 89.64,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 278.893,
+    "eval_steps_per_second": 1.093
+}

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": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.99996,
+    "eval_loss": 0.00027643845533020794,
+    "eval_runtime": 75.737,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 330.09,
+    "eval_steps_per_second": 1.294
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.88732,
+  "best_model_checkpoint": "checkpoint/bert-base/imdb_42/checkpoint-7820",
+  "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": 0.885,
+      "eval_loss": 0.2771714925765991,
+      "eval_runtime": 15.7601,
+      "eval_samples_per_second": 1586.288,
+      "eval_steps_per_second": 6.218,
+      "step": 782
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.3091,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.88332,
+      "eval_loss": 0.3185863494873047,
+      "eval_runtime": 14.8791,
+      "eval_samples_per_second": 1680.206,
+      "eval_steps_per_second": 6.586,
+      "step": 1564
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.1446,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.88372,
+      "eval_loss": 0.4319324493408203,
+      "eval_runtime": 15.634,
+      "eval_samples_per_second": 1599.077,
+      "eval_steps_per_second": 6.268,
+      "step": 2346
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.0654,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.88224,
+      "eval_loss": 0.527112603187561,
+      "eval_runtime": 15.5935,
+      "eval_samples_per_second": 1603.233,
+      "eval_steps_per_second": 6.285,
+      "step": 3128
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.882,
+      "eval_loss": 0.7103033065795898,
+      "eval_runtime": 15.6832,
+      "eval_samples_per_second": 1594.061,
+      "eval_steps_per_second": 6.249,
+      "step": 3910
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.0255,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.88156,
+      "eval_loss": 0.7340117692947388,
+      "eval_runtime": 15.5378,
+      "eval_samples_per_second": 1608.978,
+      "eval_steps_per_second": 6.307,
+      "step": 4692
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.0144,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.88624,
+      "eval_loss": 0.8043656945228577,
+      "eval_runtime": 15.5601,
+      "eval_samples_per_second": 1606.673,
+      "eval_steps_per_second": 6.298,
+      "step": 5474
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0106,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.88544,
+      "eval_loss": 0.8684703707695007,
+      "eval_runtime": 15.6281,
+      "eval_samples_per_second": 1599.681,
+      "eval_steps_per_second": 6.271,
+      "step": 6256
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.0049,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.88596,
+      "eval_loss": 0.8513516187667847,
+      "eval_runtime": 15.5688,
+      "eval_samples_per_second": 1605.772,
+      "eval_steps_per_second": 6.295,
+      "step": 7038
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.88732,
+      "eval_loss": 0.8893799185752869,
+      "eval_runtime": 15.6721,
+      "eval_samples_per_second": 1595.191,
+      "eval_steps_per_second": 6.253,
+      "step": 7820
+    },
+    {
+      "epoch": 10.0,
+      "step": 7820,
+      "total_flos": 1.644444096e+16,
+      "train_loss": 0.07364957506394447,
+      "train_runtime": 797.6475,
+      "train_samples_per_second": 313.422,
+      "train_steps_per_second": 9.804
+    }
+  ],
+  "max_steps": 7820,
+  "num_train_epochs": 10,
+  "total_flos": 1.644444096e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894be00755fd41b0392e4629f82e6cf25f5f5238084fede785713bbc01311ad1
+size 3631