Upload folder using huggingface_hub

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "miscellaneous",
+    "1": "taxation",
+    "2": "insurance",
+    "3": "stocks",
+    "4": "mutualFunds"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "insurance": 2,
+    "miscellaneous": 0,
+    "mutualFunds": 4,
+    "stocks": 3,
+    "taxation": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd69d626c9ec6f972671d0c2312f7041a3aed4bef74b5bde2b7e8605e417c35e
+size 267841796

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdc8f0e1808173b785d01bcc201118b982e41827b326764d16035713e36781f
+size 535745722

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c568a1e3a7f6e1788db2f0b5223a34b157bbeb26cfb0ccfb4bece1499d51d7
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b182744ab1bcfd025dce5a9a0e89277828dccb29e9e707310ea52f02f708968d
+size 1064

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": 0.13778184354305267,
+  "best_model_checkpoint": "bert-intent-classifier/checkpoint-1071",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2142,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9990662931839402,
+      "grad_norm": 5.298245906829834,
+      "learning_rate": 1.600747663551402e-05,
+      "loss": 0.3131,
+      "step": 535
+    },
+    {
+      "epoch": 0.9990662931839402,
+      "eval_accuracy": 0.9557281024383599,
+      "eval_loss": 0.16336975991725922,
+      "eval_runtime": 25.6475,
+      "eval_samples_per_second": 286.227,
+      "eval_steps_per_second": 17.897,
+      "step": 535
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.548210620880127,
+      "learning_rate": 1.2e-05,
+      "loss": 0.1143,
+      "step": 1071
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9619942787086228,
+      "eval_loss": 0.13778184354305267,
+      "eval_runtime": 25.2843,
+      "eval_samples_per_second": 290.339,
+      "eval_steps_per_second": 18.154,
+      "step": 1071
+    },
+    {
+      "epoch": 2.9990662931839402,
+      "grad_norm": 3.810972213745117,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.0754,
+      "step": 1606
+    },
+    {
+      "epoch": 2.9990662931839402,
+      "eval_accuracy": 0.9653998092902875,
+      "eval_loss": 0.13948151469230652,
+      "eval_runtime": 25.178,
+      "eval_samples_per_second": 291.564,
+      "eval_steps_per_second": 18.23,
+      "step": 1606
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.10682384669780731,
+      "learning_rate": 3.992523364485982e-06,
+      "loss": 0.0571,
+      "step": 2142
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9644462607274213,
+      "eval_loss": 0.13912545144557953,
+      "eval_runtime": 25.6125,
+      "eval_samples_per_second": 286.618,
+      "eval_steps_per_second": 17.921,
+      "step": 2142
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9072755267279040.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c8edfbdca06cfdf3f99677f66b086a4373547e38961782d5a9931c1a141fc1
+size 5112