Upload 5 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "vinai/phobert-large",
+  "architectures": [
+    "MRCQuestionAnswering"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf27e4d1e169b46b3124f49b48d0f435a29b3f55a44e65ca349e44346a6ba6b4
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e550c23dfc6084a4118dfb5ddda1cadb25c51c6e2a109aa8c03b8330ccf2f49
+size 623

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 1.1196151971817017,
+  "best_model_checkpoint": "model-bin/checkpoint-1962",
+  "epoch": 2.0,
+  "global_step": 3924,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8374027367856188e-05,
+      "loss": 3.3707,
+      "step": 500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5690904212503355e-05,
+      "loss": 1.6297,
+      "step": 1000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.3007781057150523e-05,
+      "loss": 1.3695,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 52.208835341365464,
+      "eval_f1": 77.43637296399675,
+      "eval_loss": 1.1196151971817017,
+      "eval_runtime": 126.4696,
+      "eval_samples_per_second": 13.782,
+      "eval_steps_per_second": 1.724,
+      "step": 1962
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0324657901797695e-05,
+      "loss": 1.239,
+      "step": 2000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 7.641534746444862e-06,
+      "loss": 0.832,
+      "step": 2500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.958411591092032e-06,
+      "loss": 0.8444,
+      "step": 3000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.2752884357392007e-06,
+      "loss": 0.7784,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 54.44635685599541,
+      "eval_f1": 78.60432014685901,
+      "eval_loss": 1.141330599784851,
+      "eval_runtime": 122.7068,
+      "eval_samples_per_second": 14.205,
+      "eval_steps_per_second": 1.777,
+      "step": 3924
+    }
+  ],
+  "max_steps": 3924,
+  "num_train_epochs": 2,
+  "total_flos": 1.178860206264462e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf67d002b058dd1efe31adffbd590fcd7f6e87a647042acf8ade1de8211d13f6
+size 3503