Initial Commit

.gitignore

@@ -0,0 +1,2 @@
+# MacOS Stuff
+**/.DS_Store

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "../input/huggingface-question-answering-models/en/roberta-base-squad2",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "name": "Roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6dff53de90be91b73822a3338a3d7ac37721c842b4754244f8d1906368a356c
+size 992577517

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbb4a7a7439d1e964809cb7e5dd10498791b7dee5f4ffc0964393fdb3900148
+size 496316087

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563af826de3c7370a00ec81522cd4d85ffec138fe049c0d1df13d424396b1513
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de25df3666e3383b7730b4499da53be7c04890d1eda884a940d3e22ed090ea0
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null, "special_tokens_map_file": "../input/huggingface-question-answering-models/en/roberta-base-squad2/special_tokens_map.json", "name_or_path": "../input/huggingface-question-answering-models/en/roberta-base-squad2"}

trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999576791231114,
+  "global_step": 11814,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.460236886632826e-06,
+      "loss": 0.4255,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6920473773265652e-05,
+      "loss": 0.3691,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.940180586907449e-05,
+      "loss": 0.3549,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8461249059443193e-05,
+      "loss": 0.3573,
+      "step": 2000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.752069224981189e-05,
+      "loss": 0.3383,
+      "step": 2500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.658013544018059e-05,
+      "loss": 0.2995,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5639578630549285e-05,
+      "loss": 0.3225,
+      "step": 3500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4699021820917985e-05,
+      "loss": 0.3038,
+      "step": 4000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3758465011286683e-05,
+      "loss": 0.2974,
+      "step": 4500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.281790820165538e-05,
+      "loss": 0.28,
+      "step": 5000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1877351392024078e-05,
+      "loss": 0.2854,
+      "step": 5500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0936794582392779e-05,
+      "loss": 0.2989,
+      "step": 6000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.996237772761475e-06,
+      "loss": 0.264,
+      "step": 6500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.055680963130174e-06,
+      "loss": 0.2623,
+      "step": 7000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.115124153498872e-06,
+      "loss": 0.2778,
+      "step": 7500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.17456734386757e-06,
+      "loss": 0.2785,
+      "step": 8000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 6.234010534236269e-06,
+      "loss": 0.2563,
+      "step": 8500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.293453724604967e-06,
+      "loss": 0.2891,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.352896914973665e-06,
+      "loss": 0.2653,
+      "step": 9500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.4123401053423627e-06,
+      "loss": 0.2413,
+      "step": 10000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.471783295711061e-06,
+      "loss": 0.2601,
+      "step": 10500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5312264860797594e-06,
+      "loss": 0.2534,
+      "step": 11000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.906696764484576e-07,
+      "loss": 0.236,
+      "step": 11500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.35328546166419983,
+      "eval_runtime": 25.6194,
+      "eval_samples_per_second": 50.47,
+      "step": 11814
+    }
+  ],
+  "max_steps": 11814,
+  "num_train_epochs": 1,
+  "total_flos": 5.402804106210509e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a1da7c83e14e21a6db5ee8c8f77bcfbda3aefc77e9d22de4437a98e442d5e8
+size 2415