updated

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_samples": 438,
+    "test_accuracy": 0.7328767123287672,
+    "test_loss": 0.8578213453292847,
+    "test_macro_f1": 0.5900120784858806,
+    "test_micro_f1": 0.7328767123287672,
+    "test_runtime": 1.8885,
+    "test_samples_per_second": 231.936,
+    "test_steps_per_second": 2.118,
+    "train_loss": 0.9607851643207644,
+    "train_runtime": 121.7053,
+    "train_samples": 3861,
+    "train_samples_per_second": 95.172,
+    "train_steps_per_second": 2.983
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_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": "NGO",
+    "1": "Witness",
+    "2": "Cannot Determine",
+    "3": "Religious Group",
+    "4": "Political Group",
+    "5": "Victim",
+    "6": "Media",
+    "7": "Union",
+    "8": "Industry Group",
+    "9": "Corporate",
+    "10": "Government",
+    "11": "Other Group",
+    "12": "Academic",
+    "13": "Actor"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Academic": 12,
+    "Actor": 13,
+    "Cannot Determine": 2,
+    "Corporate": 9,
+    "Government": 10,
+    "Industry Group": 8,
+    "Media": 6,
+    "NGO": 0,
+    "Other Group": 11,
+    "Political Group": 4,
+    "Religious Group": 3,
+    "Union": 7,
+    "Victim": 5,
+    "Witness": 1
+  },
+  "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 sha256:9506e4bc2e013a9874713db6d130769815bbba8754b61ad700279548d549e016
+size 498649736

post-training eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_samples": 438,
+    "test_accuracy": 0.7328767123287672,
+    "test_loss": 0.8578213453292847,
+    "test_macro_f1": 0.5900120784858806,
+    "test_micro_f1": 0.7328767123287672,
+    "test_runtime": 1.8885,
+    "test_samples_per_second": 231.936,
+    "test_steps_per_second": 2.118
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9607851643207644,
+    "train_runtime": 121.7053,
+    "train_samples": 3861,
+    "train_samples_per_second": 95.172,
+    "train_steps_per_second": 2.983
+}

trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 363,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.65,
+      "eval_accuracy": 0.7214611872146118,
+      "eval_loss": 0.8989303708076477,
+      "eval_macro_f1": 0.5005038448277949,
+      "eval_micro_f1": 0.7214611872146118,
+      "eval_runtime": 1.6443,
+      "eval_samples_per_second": 266.38,
+      "eval_steps_per_second": 2.433,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "step": 363,
+      "total_flos": 2222916882315228.0,
+      "train_loss": 0.9607851643207644,
+      "train_runtime": 121.7053,
+      "train_samples_per_second": 95.172,
+      "train_steps_per_second": 2.983
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 363,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2222916882315228.0,
+  "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 sha256:458ddb10bc9c9465cbf24aba1fde1b8d9c28107e49a4bc2d47e5cbfe8bad3e7d
+size 4664