Upload 7 files

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bf21dda3bb82acd42b5448b24393831ecbbec8d8ecc6acc3b09461e5673e8d
+size 567598552

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ab25f9cc18e627a36c97fb5c0871a83facb9d9afa189eeb05e600014505547
+size 1135260474

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2a96f49184b5ef8eff858f170f826c535dbc3897cb4108ba4e3109d3cb801f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc2fbed1a39f02f92c4e436062377d48c71d10a7e81ecff5f91c89e494aafa6
+size 1064

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.6848270226096431,
+  "best_model_checkpoint": "model_checkpoints/fine-tuned_blog-authorship-gender/deberta-v3-small/checkpoint-858",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 858,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 25.72825813293457,
+      "learning_rate": 3.3372183372183376e-05,
+      "loss": 0.6674,
+      "step": 429
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6743204011612562,
+      "eval_f1": 0.5927392739273928,
+      "eval_loss": 0.6185831427574158,
+      "eval_runtime": 262.6549,
+      "eval_samples_per_second": 14.426,
+      "eval_steps_per_second": 3.609,
+      "step": 429
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.697623252868652,
+      "learning_rate": 1.6705516705516705e-05,
+      "loss": 0.5889,
+      "step": 858
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6946423858537872,
+      "eval_f1": 0.6848270226096431,
+      "eval_loss": 0.5841246843338013,
+      "eval_runtime": 262.83,
+      "eval_samples_per_second": 14.416,
+      "eval_steps_per_second": 3.607,
+      "step": 858
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1287,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 908891196438528.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c9651327b7d29d3aa6cdf9e127c0990bf9702dea17213d4909d2bf7936fb49
+size 5304