upload model

README.md

@@ -1,3 +1,57 @@
 ---
-license: apache-2.0
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: mlm_modelrob
+  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_modelrob
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1397
+- Accuracy: 0.7373
+
+## 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 @@
+{
+  "</s>": 2,
+  "<mask>": 50264,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7373422261789581,
+    "eval_loss": 1.1397300958633423,
+    "eval_runtime": 53.6547,
+    "eval_samples": 3793,
+    "eval_samples_per_second": 70.693,
+    "eval_steps_per_second": 2.218,
+    "perplexity": 3.125924551349567,
+    "train_loss": 1.3888828911883806,
+    "train_runtime": 5861.5075,
+    "train_samples": 95750,
+    "train_samples_per_second": 49.006,
+    "train_steps_per_second": 1.532
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7373422261789581,
+    "eval_loss": 1.1397300958633423,
+    "eval_runtime": 53.6547,
+    "eval_samples": 3793,
+    "eval_samples_per_second": 70.693,
+    "eval_steps_per_second": 2.218,
+    "perplexity": 3.125924551349567
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a402ede3a242266020037a51a81da4a9199b0e1d06b4eef7d11a9f9fe11025
+size 498859189

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.3888828911883806,
+    "train_runtime": 5861.5075,
+    "train_samples": 95750,
+    "train_samples_per_second": 49.006,
+    "train_steps_per_second": 1.532
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 8979,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7215725581913354e-05,
+      "loss": 1.6236,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.443145116382671e-05,
+      "loss": 1.525,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.164717674574006e-05,
+      "loss": 1.4783,
+      "step": 1500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.8862902327653414e-05,
+      "loss": 1.4528,
+      "step": 2000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.607862790956677e-05,
+      "loss": 1.4441,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.329435349148012e-05,
+      "loss": 1.4137,
+      "step": 3000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.0510079073393477e-05,
+      "loss": 1.3863,
+      "step": 3500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.7725804655306832e-05,
+      "loss": 1.3796,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.4941530237220183e-05,
+      "loss": 1.3692,
+      "step": 4500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.2157255819133534e-05,
+      "loss": 1.3598,
+      "step": 5000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.937298140104689e-05,
+      "loss": 1.3458,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6588706982960243e-05,
+      "loss": 1.3418,
+      "step": 6000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3804432564873596e-05,
+      "loss": 1.3283,
+      "step": 6500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1020158146786947e-05,
+      "loss": 1.3118,
+      "step": 7000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.235883728700302e-06,
+      "loss": 1.3161,
+      "step": 7500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.451609310613654e-06,
+      "loss": 1.3111,
+      "step": 8000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.6673348925270076e-06,
+      "loss": 1.3042,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "step": 8979,
+      "total_flos": 7.5623004331776e+16,
+      "train_loss": 1.3888828911883806,
+      "train_runtime": 5861.5075,
+      "train_samples_per_second": 49.006,
+      "train_steps_per_second": 1.532
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8979,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7.5623004331776e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86b9b35b2398a8a749d1b7be0ef41b515a74b4d0b67429d088cf98df4aa759f
+size 4155