initial model upload

README.md

@@ -0,0 +1,79 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- sst2
+metrics:
+- accuracy
+model-index:
+- name: '42'
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9254587155963303
+---
+
+<!-- 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. -->
+
+# 42
+
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the SST2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3109
+- Accuracy: 0.9255
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: not_parallel
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| No log        | 1.0   | 2105  | 0.2167          | 0.9232   |
+| 0.2049        | 2.0   | 4210  | 0.2375          | 0.9278   |
+| 0.123         | 3.0   | 6315  | 0.2636          | 0.9243   |
+| 0.0839        | 4.0   | 8420  | 0.2865          | 0.9243   |
+| 0.058         | 5.0   | 10525 | 0.3109          | 0.9255   |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.10.0+cu113
+- Datasets 2.7.1
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.11400984666692955,
+    "train_runtime": 1175.3679,
+    "train_samples": 67349,
+    "train_samples_per_second": 286.502,
+    "train_steps_per_second": 8.955,
+    "validation_accuracy": 0.9254587155963303,
+    "validation_loss": 0.31086066365242004,
+    "validation_runtime": 1.4824,
+    "validation_samples": 872,
+    "validation_samples_per_second": 588.248,
+    "validation_steps_per_second": 18.889
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8f72f9faf75a8974600ed89fcfb19eeca26a537c5511166d2e26d4fe02781b
+size 1340739309

run_arguments.json

@@ -0,0 +1,25 @@
+{
+    "model_name_or_path": "bert-large-uncased",
+    "task_name": "sst2",
+    "output_dir": "./output/bert-large/sst2/0001/42/",
+    "learning_rate": 3e-05,
+    "num_train_epochs": 5,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 0.1,
+    "seed": 42,
+    "warmup_steps": 0,
+    "do_train": true,
+    "do_eval": true,
+    "do_predict": false,
+    "pad_to_max_length": false,
+    "max_seq_length": 128,
+    "report_to": [],
+    "save_strategy": "no",
+    "evaluation_strategy": "epoch",
+    "logging_steps": 2500,
+    "use_fast_tokenizer": true,
+    "group_by_length": true,
+    "save_training_dynamics": false,
+    "save_training_dynamics_after_epoch": false
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.11400984666692955,
+    "train_runtime": 1175.3679,
+    "train_samples": 67349,
+    "train_samples_per_second": 286.502,
+    "train_steps_per_second": 8.955
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 10525,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.21673926711082458,
+      "eval_runtime": 1.4821,
+      "eval_samples_per_second": 588.353,
+      "eval_steps_per_second": 18.892,
+      "step": 2105
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.2874109263657958e-05,
+      "loss": 0.2049,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9277522935779816,
+      "eval_loss": 0.23751771450042725,
+      "eval_runtime": 1.48,
+      "eval_samples_per_second": 589.207,
+      "eval_steps_per_second": 18.919,
+      "step": 4210
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.5748218527315915e-05,
+      "loss": 0.123,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9243119266055045,
+      "eval_loss": 0.2635619044303894,
+      "eval_runtime": 1.4812,
+      "eval_samples_per_second": 588.699,
+      "eval_steps_per_second": 18.903,
+      "step": 6315
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 8.622327790973872e-06,
+      "loss": 0.0839,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9243119266055045,
+      "eval_loss": 0.28654733300209045,
+      "eval_runtime": 1.4787,
+      "eval_samples_per_second": 589.696,
+      "eval_steps_per_second": 18.935,
+      "step": 8420
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 1.496437054631829e-06,
+      "loss": 0.058,
+      "step": 10000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9254587155963303,
+      "eval_loss": 0.31086066365242004,
+      "eval_runtime": 1.4857,
+      "eval_samples_per_second": 586.933,
+      "eval_steps_per_second": 18.846,
+      "step": 10525
+    },
+    {
+      "epoch": 5.0,
+      "step": 10525,
+      "total_flos": 8559638497356828.0,
+      "train_loss": 0.11400984666692955,
+      "train_runtime": 1175.3679,
+      "train_samples_per_second": 286.502,
+      "train_steps_per_second": 8.955
+    }
+  ],
+  "max_steps": 10525,
+  "num_train_epochs": 5,
+  "total_flos": 8559638497356828.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8541b1339e53d1240efed18ebe6a2b59474d8e9e899771c348cb0008415d92ef
+size 3119

validation_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "validation_accuracy": 0.9254587155963303,
+    "validation_loss": 0.31086066365242004,
+    "validation_runtime": 1.4824,
+    "validation_samples": 872,
+    "validation_samples_per_second": 588.248,
+    "validation_steps_per_second": 18.889
+}