train

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.6387994374017087,
+    "train_runtime": 34407.9029,
+    "train_samples": 88568,
+    "train_samples_per_second": 5.148,
+    "train_steps_per_second": 0.215
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepset/roberta-base-squad2",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f35b01b606756064c3154bc3b7e59a54e2f011aa8ee4425d307be5b1b77b58
+size 496311985

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 @@
+{"errors": "replace", "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"}, "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"}, "unk_token": {"content": "<unk>", "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"}, "add_prefix_space": false, "trim_offsets": true, "do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null, "special_tokens_map_file": "/home/popos/.cache/huggingface/transformers/c9d2c178fac8d40234baa1833a3b1903d393729bf93ea34da247c07db24900d0.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "deepset/roberta-base-squad2", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.6387994374017087,
+    "train_runtime": 34407.9029,
+    "train_samples": 88568,
+    "train_samples_per_second": 5.148,
+    "train_steps_per_second": 0.215
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 7382,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.7968030344080195e-05,
+      "loss": 0.7919,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5936060688160393e-05,
+      "loss": 0.7709,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3904091032240584e-05,
+      "loss": 0.7652,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.187212137632078e-05,
+      "loss": 0.7589,
+      "step": 2000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9840151720400976e-05,
+      "loss": 0.7355,
+      "step": 2500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7808182064481173e-05,
+      "loss": 0.7263,
+      "step": 3000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5776212408561364e-05,
+      "loss": 0.7287,
+      "step": 3500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.374424275264156e-05,
+      "loss": 0.614,
+      "step": 4000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1712273096721756e-05,
+      "loss": 0.5337,
+      "step": 4500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 9.68030344080195e-06,
+      "loss": 0.533,
+      "step": 5000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.648333784882147e-06,
+      "loss": 0.5237,
+      "step": 5500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.616364128962341e-06,
+      "loss": 0.5267,
+      "step": 6000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.584394473042536e-06,
+      "loss": 0.5262,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.552424817122731e-06,
+      "loss": 0.5105,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0,
+      "step": 7382,
+      "total_flos": 3.471379672589107e+16,
+      "train_loss": 0.6387994374017087,
+      "train_runtime": 34407.9029,
+      "train_samples_per_second": 5.148,
+      "train_steps_per_second": 0.215
+    }
+  ],
+  "max_steps": 7382,
+  "num_train_epochs": 2,
+  "total_flos": 3.471379672589107e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44dca61e73a457780e3093cd6a96cc4872e7c30841fceecc132da6d0ce08dc8f
+size 3055