add finetuned files

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: distilroberta-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. -->
+
+# distilroberta-base_squad
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-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": 80.97445600756859,
+    "eval_f1": 88.0153886332912,
+    "eval_samples": 10790,
+    "train_loss": 0.9979496314576136,
+    "train_runtime": 2629.392,
+    "train_samples": 88568,
+    "train_samples_per_second": 101.051,
+    "train_steps_per_second": 3.158
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "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": 6,
+  "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": 50265
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 80.97445600756859,
+    "eval_f1": 88.0153886332912,
+    "eval_samples": 10790
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b27bf75e3f5e900b248962863a39b539cc53997161f2c36466186457abef50
+size 326162801

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 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9979496314576136,
+    "train_runtime": 2629.392,
+    "train_samples": 88568,
+    "train_samples_per_second": 101.051,
+    "train_steps_per_second": 3.158
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 8304,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.8193641618497108e-05,
+      "loss": 2.0414,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.6387283236994222e-05,
+      "loss": 1.3717,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.458092485549133e-05,
+      "loss": 1.2339,
+      "step": 1500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.277456647398844e-05,
+      "loss": 1.1651,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.0968208092485548e-05,
+      "loss": 1.1147,
+      "step": 2500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.9161849710982662e-05,
+      "loss": 1.0155,
+      "step": 3000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.735549132947977e-05,
+      "loss": 0.9151,
+      "step": 3500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.5549132947976876e-05,
+      "loss": 0.9212,
+      "step": 4000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.3742774566473989e-05,
+      "loss": 0.8868,
+      "step": 4500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.19364161849711e-05,
+      "loss": 0.8968,
+      "step": 5000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0130057803468209e-05,
+      "loss": 0.8776,
+      "step": 5500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 8.323699421965318e-06,
+      "loss": 0.747,
+      "step": 6000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 6.517341040462428e-06,
+      "loss": 0.7403,
+      "step": 6500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.710982658959537e-06,
+      "loss": 0.741,
+      "step": 7000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.9046242774566473e-06,
+      "loss": 0.7416,
+      "step": 7500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.0982658959537572e-06,
+      "loss": 0.7207,
+      "step": 8000
+    },
+    {
+      "epoch": 3.0,
+      "step": 8304,
+      "total_flos": 2.6036288468176896e+16,
+      "train_loss": 0.9979496314576136,
+      "train_runtime": 2629.392,
+      "train_samples_per_second": 101.051,
+      "train_steps_per_second": 3.158
+    }
+  ],
+  "max_steps": 8304,
+  "num_train_epochs": 3,
+  "total_flos": 2.6036288468176896e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515fdb101497837a86bf2972ceba99d8e3b8aad2966a3e34fc2c3e2066014898
+size 2927