Upload model from Google Drive

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "result/ViNLI-XNLI/xlm-roberta-large-hnw1-fix",
+  "architectures": [
+    "XLMRobertaForCL"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6920d4d0ebc22eb189756113b3164469a5f0b722c7d63055353f20fe9d700951
+size 4479353225

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae11c9ea17c09ba66839fab6753a34bcd7d37d0f1f4cc35d1423bb65f0b318b0
+size 2239728109

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68f0b21aa19f27e9f6efaed286f795fcfb40ccd9e85cdf646c2f23f3f97a215
+size 627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "use_fast": true, "model_max_length": 512, "name_or_path": "xlm-roberta-large"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 1.0
+train_runtime = 330.2529
+train_samples_per_second = 0.815

trainer_state.json

@@ -0,0 +1,29 @@
+{
+  "best_metric": 0.6281346167564243,
+  "best_model_checkpoint": "result/ViNLI-XNLI/xlm-roberta-large-hnw1-fix",
+  "epoch": 1.0,
+  "global_step": 269,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.74,
+      "eval_avg_sts": 0.5976045544187802,
+      "eval_sickr_spearman": 0.5670744920811361,
+      "eval_stsb_spearman": 0.6281346167564243,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "step": 269,
+      "train_runtime": 330.2529,
+      "train_samples_per_second": 0.815
+    }
+  ],
+  "max_steps": 269,
+  "num_train_epochs": 1,
+  "total_flos": 5435685061263360,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a127c0f2e66914c498db111c46478741c960f901f787188de585242f431458dd
+size 2107