upload model

README.md

@@ -1,3 +1,57 @@
 ---
 license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: mlm_modelbert
+  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. -->
+
+# mlm_modelbert
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2484
+- Accuracy: 0.7225
+
+## 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: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.14.0

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7224581641901442,
+    "eval_loss": 1.2484219074249268,
+    "eval_runtime": 39.4232,
+    "eval_samples": 4004,
+    "eval_samples_per_second": 101.565,
+    "eval_steps_per_second": 3.196,
+    "perplexity": 3.4848392170043856,
+    "train_loss": 1.70131384965624,
+    "train_runtime": 4587.4305,
+    "train_samples": 96558,
+    "train_samples_per_second": 63.145,
+    "train_steps_per_second": 1.974
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7224581641901442,
+    "eval_loss": 1.2484219074249268,
+    "eval_runtime": 39.4232,
+    "eval_samples": 4004,
+    "eval_samples_per_second": 101.565,
+    "eval_steps_per_second": 3.196,
+    "perplexity": 3.4848392170043856
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec7f82f0d14d97cb1dc5a3c937bec848b14573b673f79aeb2c196929f2c327f
+size 433432181

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 +1,56 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.70131384965624,
+    "train_runtime": 4587.4305,
+    "train_samples": 96558,
+    "train_samples_per_second": 63.145,
+    "train_steps_per_second": 1.974
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9054,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.723878948531036e-05,
+      "loss": 2.7103,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.447757897062072e-05,
+      "loss": 1.9564,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.171636845593108e-05,
+      "loss": 1.8423,
+      "step": 1500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.895515794124144e-05,
+      "loss": 1.778,
+      "step": 2000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.61939474265518e-05,
+      "loss": 1.7212,
+      "step": 2500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.343273691186216e-05,
+      "loss": 1.6849,
+      "step": 3000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.0671526397172526e-05,
+      "loss": 1.6508,
+      "step": 3500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.791031588248288e-05,
+      "loss": 1.6336,
+      "step": 4000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5149105367793242e-05,
+      "loss": 1.6204,
+      "step": 4500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2.2387894853103602e-05,
+      "loss": 1.6058,
+      "step": 5000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.962668433841396e-05,
+      "loss": 1.5936,
+      "step": 5500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.686547382372432e-05,
+      "loss": 1.5766,
+      "step": 6000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.4104263309034682e-05,
+      "loss": 1.5578,
+      "step": 6500
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.1343052794345042e-05,
+      "loss": 1.548,
+      "step": 7000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.581842279655401e-06,
+      "loss": 1.5482,
+      "step": 7500
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 5.820631764965762e-06,
+      "loss": 1.5412,
+      "step": 8000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.059421250276121e-06,
+      "loss": 1.5365,
+      "step": 8500
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.982107355864811e-07,
+      "loss": 1.535,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "step": 9054,
+      "total_flos": 7.624223298839347e+16,
+      "train_loss": 1.70131384965624,
+      "train_runtime": 4587.4305,
+      "train_samples_per_second": 63.145,
+      "train_steps_per_second": 1.974
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9054,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7.624223298839347e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c3de4b5904cde1d280d95653332d5b8748f4e8a6725260fdcc2d2cf8049156
+size 4155