Upload 7 files

config.json

@@ -0,0 +1,45 @@
+{
+  "_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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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 sha256:2c4dea2e96568be769acf0e311559907eb14c7f32831098c12a0a09e7e842142
+size 567601628

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269cb574758c92ed3501c61680318254faa37fbebf90ab2047fc519c3073cc55
+size 1135266618

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 sha256:5675f2ba4fb76233f42ffe2a251efd812c7e8221d997ae840eaffdce175814d5
+size 1064

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.6252309316442333,
+  "best_model_checkpoint": "model_checkpoints/fine-tuned_blog-authorship-age/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": 16.06877326965332,
+      "learning_rate": 3.341103341103341e-05,
+      "loss": 0.8989,
+      "step": 429
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6025336500395883,
+      "eval_f1": 0.6025336500395883,
+      "eval_loss": 0.8372386693954468,
+      "eval_runtime": 263.0843,
+      "eval_samples_per_second": 14.402,
+      "eval_steps_per_second": 3.603,
+      "step": 429
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 28.210113525390625,
+      "learning_rate": 1.6744366744366746e-05,
+      "loss": 0.7219,
+      "step": 858
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6252309316442333,
+      "eval_f1": 0.6252309316442333,
+      "eval_loss": 0.8790310621261597,
+      "eval_runtime": 263.0807,
+      "eval_samples_per_second": 14.402,
+      "eval_steps_per_second": 3.603,
+      "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": 908907404645376.0,
+  "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 sha256:53d2b9b00602c6602be592fc6acf1cd9fe93eafb32a3112da84c17af9e04c211
+size 5304