Initial commit

README.md

@@ -0,0 +1,54 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: roberta
+  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. -->
+
+# roberta
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4144
+
+## 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: 12
+- eval_batch_size: 16
+- seed: 1337
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.11.2
+- Pytorch 1.10.0
+- Datasets 1.8.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 1.4143636226654053,
+    "eval_runtime": 208.1899,
+    "eval_samples": 9430,
+    "eval_samples_per_second": 45.295,
+    "eval_steps_per_second": 2.834,
+    "perplexity": 4.113867660650703,
+    "train_loss": 1.4635986100275606,
+    "train_runtime": 50086.6399,
+    "train_samples": 102856,
+    "train_samples_per_second": 10.268,
+    "train_steps_per_second": 0.214
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 1.4143636226654053,
+    "eval_runtime": 208.1899,
+    "eval_samples": 9430,
+    "eval_samples_per_second": 45.295,
+    "eval_steps_per_second": 2.834,
+    "perplexity": 4.113867660650703
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97cca272842c816748ba3b4a189dd1f5842da7319acb323854138990a9909b3
+size 1113252715

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.4635986100275606,
+    "train_runtime": 50086.6399,
+    "train_samples": 102856,
+    "train_samples_per_second": 10.268,
+    "train_steps_per_second": 0.214
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 10715,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.7666822211852545e-05,
+      "loss": 1.8978,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.5333644423705094e-05,
+      "loss": 1.6943,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.300046663555763e-05,
+      "loss": 1.6273,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.066728884741017e-05,
+      "loss": 1.59,
+      "step": 2000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.8334111059262714e-05,
+      "loss": 1.5531,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.600093327111526e-05,
+      "loss": 1.5196,
+      "step": 3000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.3667755482967805e-05,
+      "loss": 1.4976,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.133457769482035e-05,
+      "loss": 1.4651,
+      "step": 4000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.9001399906672887e-05,
+      "loss": 1.4498,
+      "step": 4500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.6668222118525432e-05,
+      "loss": 1.4301,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.4335044330377978e-05,
+      "loss": 1.4194,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.200186654223052e-05,
+      "loss": 1.4035,
+      "step": 6000
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.9668688754083062e-05,
+      "loss": 1.3985,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.7335510965935605e-05,
+      "loss": 1.3829,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.5002333177788147e-05,
+      "loss": 1.3729,
+      "step": 7500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.2669155389640691e-05,
+      "loss": 1.3654,
+      "step": 8000
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.0335977601493233e-05,
+      "loss": 1.3587,
+      "step": 8500
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 8.002799813345777e-06,
+      "loss": 1.3466,
+      "step": 9000
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 5.6696220251983205e-06,
+      "loss": 1.3435,
+      "step": 9500
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 3.3364442370508633e-06,
+      "loss": 1.3398,
+      "step": 10000
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 1.0032664489034066e-06,
+      "loss": 1.3377,
+      "step": 10500
+    },
+    {
+      "epoch": 5.0,
+      "step": 10715,
+      "total_flos": 1.357077205905408e+17,
+      "train_loss": 1.4635986100275606,
+      "train_runtime": 50086.6399,
+      "train_samples_per_second": 10.268,
+      "train_steps_per_second": 0.214
+    }
+  ],
+  "max_steps": 10715,
+  "num_train_epochs": 5,
+  "total_flos": 1.357077205905408e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd8638cc26261c629b23f2cad547208ef9ca44441e2a198dd8503750c2d4dc4
+size 2927