add files

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: xlm-roberta-base_squad
+  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. -->
+
+# xlm-roberta-base_squad
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the squad dataset.
+
+## 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
+- 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 4.14.1
+- Pytorch 1.9.0
+- Datasets 1.16.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 82.69631031220435,
+    "eval_f1": 89.4562841806503,
+    "eval_samples": 10918,
+    "train_loss": 0.9259976813906715,
+    "train_runtime": 7183.2279,
+    "train_samples": 89597,
+    "train_samples_per_second": 37.419,
+    "train_steps_per_second": 1.169
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "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": "4.14.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 82.69631031220435,
+    "eval_f1": 89.4562841806503,
+    "eval_samples": 10918
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24a471d1b568201a406ab444b5261fce071615dad5aef694ad4e2573d4b659a
+size 1109903089

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, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9259976813906715,
+    "train_runtime": 7183.2279,
+    "train_samples": 89597,
+    "train_samples_per_second": 37.419,
+    "train_steps_per_second": 1.169
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 8400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.8214285714285714e-05,
+      "loss": 2.1218,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.6428571428571428e-05,
+      "loss": 1.254,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.464285714285714e-05,
+      "loss": 1.1716,
+      "step": 1500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 1.0937,
+      "step": 2000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.107142857142857e-05,
+      "loss": 1.0459,
+      "step": 2500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.9711,
+      "step": 3000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.8414,
+      "step": 3500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 0.8165,
+      "step": 4000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.3928571428571429e-05,
+      "loss": 0.8204,
+      "step": 4500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.2142857142857144e-05,
+      "loss": 0.8327,
+      "step": 5000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.0357142857142857e-05,
+      "loss": 0.8118,
+      "step": 5500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.6869,
+      "step": 6000
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 6.785714285714286e-06,
+      "loss": 0.6618,
+      "step": 6500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 0.6381,
+      "step": 7000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 3.2142857142857143e-06,
+      "loss": 0.6532,
+      "step": 7500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.6188,
+      "step": 8000
+    },
+    {
+      "epoch": 3.0,
+      "step": 8400,
+      "total_flos": 5.267566240486963e+16,
+      "train_loss": 0.9259976813906715,
+      "train_runtime": 7183.2279,
+      "train_samples_per_second": 37.419,
+      "train_steps_per_second": 1.169
+    }
+  ],
+  "max_steps": 8400,
+  "num_train_epochs": 3,
+  "total_flos": 5.267566240486963e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d841b3c364e29fe3e8dd57af5302f7d0a5de0375078ec5e38c2bf3f96a8d0e5
+size 2927