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 sha256:64890673e3fcf39918322f227f16808352dbfd5d537754a0aff4ff537a8131e5
+size 657420741

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31438c07e0c80e9beebed1c2ffa4df0084150a6f5c6658ef791f90305d9c9973
+size 328719737

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7375cda285e50265fa3b943abc1cf4315f11ca102bfd014d6f3d1642787094b8
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8c2bbbb5492513915aa388df581d1e5e9531f0da22ffd1f67a25e209482c78
+size 627

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8125,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7916666666666667e-05,
+      "loss": 1.247,
+      "step": 500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.9325,
+      "step": 1000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.375e-05,
+      "loss": 0.815,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6791346073150635,
+      "eval_runtime": 4932.0243,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 0.411,
+      "step": 1600
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.7479,
+      "step": 2000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 0.7055,
+      "step": 2500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.6726,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5686362981796265,
+      "eval_runtime": 5197.6249,
+      "eval_samples_per_second": 3.12,
+      "eval_steps_per_second": 0.39,
+      "step": 3200
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 0.6568,
+      "step": 3500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6281,
+      "step": 4000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.25e-06,
+      "loss": 0.6213,
+      "step": 4500
+    }
+  ],
+  "max_steps": 4800,
+  "num_train_epochs": 3,
+  "total_flos": 4660672199238000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba387c02987067bb241b05cb572165f111f50e6908a0dcc62b0cbb0260cb5ecd
+size 3579