Upload 6 files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "distilroberta-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,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8edf96dba7803f86313508b0258092a2e90755c9ac1b501d8e5d3a20e1eac7
+size 328519925

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c147dfd5ccb494fc5368ad502d0a57b117bc94e6ff44eff54a852c125e47bab5
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64956a5fe71c1a518061f8bffa719352096df626499928b5ab5ba28eb5527ed8
+size 627

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 0.9789915966386554,
+  "best_model_checkpoint": "/mnt/data02/luca_newswire/wire_classifier/trained_models/wire/2024-05-29_23-47-53/checkpoint-150",
+  "epoch": 6.521739130434782,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.17,
+      "eval_accuracy": 0.7023809523809523,
+      "eval_f1": 0.8251748251748251,
+      "eval_loss": 0.542344331741333,
+      "eval_precision": 0.7023809523809523,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.9215,
+      "eval_samples_per_second": 174.867,
+      "eval_steps_per_second": 3.123,
+      "step": 50
+    },
+    {
+      "epoch": 4.35,
+      "eval_accuracy": 0.8988095238095238,
+      "eval_f1": 0.9317269076305221,
+      "eval_loss": 0.3049139976501465,
+      "eval_precision": 0.8854961832061069,
+      "eval_recall": 0.9830508474576272,
+      "eval_runtime": 1.6739,
+      "eval_samples_per_second": 200.728,
+      "eval_steps_per_second": 3.584,
+      "step": 100
+    },
+    {
+      "epoch": 6.52,
+      "eval_accuracy": 0.9702380952380952,
+      "eval_f1": 0.9789915966386554,
+      "eval_loss": 0.11797040700912476,
+      "eval_precision": 0.9708333333333333,
+      "eval_recall": 0.9872881355932204,
+      "eval_runtime": 1.6614,
+      "eval_samples_per_second": 202.241,
+      "eval_steps_per_second": 3.611,
+      "step": 150
+    }
+  ],
+  "max_steps": 460,
+  "num_train_epochs": 20,
+  "total_flos": 1261354570002432.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7658120cc6dec537d9809085edeb6bdc99a9291e4e186825d178678bc2e8d781
+size 4027