End of training

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_exact_match": 60.37842951750237,
+    "eval_f1": 71.55258668088149,
+    "eval_samples": 10790,
+    "train_loss": 1.724749755859375,
+    "train_runtime": 103.5118,
+    "train_samples": 512,
+    "train_samples_per_second": 49.463,
+    "train_steps_per_second": 2.125
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-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": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd16c6f5914376b76720fe739425e8be50693668726391d595b92ea9906c749
+size 49264910

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 10.0,
+    "eval_exact_match": 60.37842951750237,
+    "eval_f1": 71.55258668088149,
+    "eval_samples": 10790
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b599f50b95363b3dab9c810a38be79fa0b785447346616836aca287390aee420
+size 496311025

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>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 1.724749755859375,
+    "train_runtime": 103.5118,
+    "train_samples": 512,
+    "train_samples_per_second": 49.463,
+    "train_steps_per_second": 2.125
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 10.0,
+      "step": 220,
+      "total_flos": 1003379545866240.0,
+      "train_loss": 1.724749755859375,
+      "train_runtime": 103.5118,
+      "train_samples_per_second": 49.463,
+      "train_steps_per_second": 2.125
+    }
+  ],
+  "max_steps": 220,
+  "num_train_epochs": 10,
+  "total_flos": 1003379545866240.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9dd663ae14c7f6132a6b045cbf0603770c3c466c6fecdc225fdecc33e7ee39
+size 3055