init

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "joeddav/xlm-roberta-large-xnli",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "contradiction",
+    "1": "neutral",
+    "2": "entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 0,
+    "entailment": 2,
+    "neutral": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "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 sha256:95713ef0814771831011d52e1260b6591730482a3866ecc7521eff5af861b97b
+size 4479377425

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7252032a8e646e06981833dae87fd089e0952e30e3c9e9a3f0bc3a6b0e4c99
+size 2239711213

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7223d1f21f85cd545e8c8d81821c810a53fbefdee2060044b1a0c7ef9008e68d
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e512717c051bd5ada11c1d32a5e524e6add99637caa37481aa1461115864b4
+size 623

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.932551319648094,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.7781036168132945e-05,
+      "loss": 0.5315,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9261092775944261,
+      "eval_loss": 0.21968263387680054,
+      "eval_runtime": 262.5074,
+      "eval_samples_per_second": 41.553,
+      "eval_steps_per_second": 5.196,
+      "step": 682
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5562072336265887e-05,
+      "loss": 0.4054,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9733223322332233,
+      "eval_loss": 0.09609706699848175,
+      "eval_runtime": 262.661,
+      "eval_samples_per_second": 41.529,
+      "eval_steps_per_second": 5.193,
+      "step": 1364
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.3343108504398828e-05,
+      "loss": 0.2765,
+      "step": 1500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.1241446725317694e-06,
+      "loss": 0.165,
+      "step": 2000
+    }
+  ],
+  "max_steps": 2046,
+  "num_train_epochs": 3,
+  "total_flos": 2.9814448911998976e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17875f16162edc142f40fc0348854aa63934444e1aa55d1dfd529d9e0394041
+size 3375