e

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_samples": 2737,
+    "test_accuracy": 0.7168432590427475,
+    "test_loss": 0.8912712335586548,
+    "test_macro_f1": 0.5103889782929176,
+    "test_micro_f1": 0.7168432590427475,
+    "test_runtime": 5.8747,
+    "test_samples_per_second": 465.9,
+    "test_steps_per_second": 3.745,
+    "train_loss": 0.7604470539181076,
+    "train_runtime": 647.9763,
+    "train_samples": 23080,
+    "train_samples_per_second": 106.856,
+    "train_steps_per_second": 3.343
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "Direct Quote",
+    "1": "Published Work/Press Report",
+    "2": "Court Proceeding",
+    "3": "Email/Social Media Post",
+    "4": "Proposal/Order/Law",
+    "5": "Direct Observation",
+    "6": "Other",
+    "7": "No Quote",
+    "8": "Statement/Public Speech",
+    "9": "Background/Narrative",
+    "10": "Indirect Quote"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Background/Narrative": 9,
+    "Court Proceeding": 2,
+    "Direct Observation": 5,
+    "Direct Quote": 0,
+    "Email/Social Media Post": 3,
+    "Indirect Quote": 10,
+    "No Quote": 7,
+    "Other": 6,
+    "Proposal/Order/Law": 4,
+    "Published Work/Press Report": 1,
+    "Statement/Public Speech": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e7bcd3681e3c7e8127e2723af17aa406046af02ebe04c54d9af7e58224acd3
+size 498640508

post-training eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_samples": 2737,
+    "test_accuracy": 0.7168432590427475,
+    "test_loss": 0.8912712335586548,
+    "test_macro_f1": 0.5103889782929176,
+    "test_micro_f1": 0.7168432590427475,
+    "test_runtime": 5.8747,
+    "test_samples_per_second": 465.9,
+    "test_steps_per_second": 3.745
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.7604470539181076,
+    "train_runtime": 647.9763,
+    "train_samples": 23080,
+    "train_samples_per_second": 106.856,
+    "train_steps_per_second": 3.343
+}

trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.845798707294552e-05,
+      "loss": 1.029,
+      "step": 500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.6915974145891044e-05,
+      "loss": 0.8087,
+      "step": 1000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.5373961218836565e-05,
+      "loss": 0.7124,
+      "step": 1500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.831948291782087e-06,
+      "loss": 0.5622,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2166,
+      "total_flos": 2284847800184592.0,
+      "train_loss": 0.7604470539181076,
+      "train_runtime": 647.9763,
+      "train_samples_per_second": 106.856,
+      "train_steps_per_second": 3.343
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2166,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2284847800184592.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd96a87f6ea8cb4b9067f99fa288c2401138faa9da7097c470093e09fa8d196
+size 4728