Upload 7 files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b928db5eedd0e2586f10a9c16df95da9d5839d89e859c199df58a1dc013115
+size 657420741

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ccb75f4cbcd7fd35f1008083800270ef6d984c5bc228a62fc73d724a86feaf
+size 328719737

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc4569d6fc38078f499d7dfcf48f9f7c51ab423f6bfd7d7d2fda17f687c2089
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b0cedc0ad5cc6458fc21930ec184be4ec53e574f0f6c38e02f50cf9bf0cd78
+size 627

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.962962962962963,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.506172839506173e-05,
+      "loss": 1.0616,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5579138398170471,
+      "eval_runtime": 1778.2352,
+      "eval_samples_per_second": 3.14,
+      "eval_steps_per_second": 0.393,
+      "step": 675
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0123456790123458e-05,
+      "loss": 0.6432,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4459874629974365,
+      "eval_runtime": 1778.2941,
+      "eval_samples_per_second": 3.14,
+      "eval_steps_per_second": 0.393,
+      "step": 1350
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.5407,
+      "step": 1500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.469135802469136e-07,
+      "loss": 0.499,
+      "step": 2000
+    }
+  ],
+  "max_steps": 2025,
+  "num_train_epochs": 3,
+  "total_flos": 2071956701034000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24442702435088b95f5c96f2a87ccc21fc24d3bcac11ea3406b2ec1e0ac61e56
+size 3579