Upload folder using huggingface_hub

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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": "4.38.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae25466e69baf96d8931a9d55c08fcfb423a1043114d5d116a7ca6c8ca8bfe51
+size 267832560

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7304e013ba093fa19df3f96e807cfd7207cb544db5369dd0d95678e5e0b62e
+size 535727290

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39c5f1b45e621b899a7a49f6241a4a0422d23936b1667a5e547cd9cee1e9601
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a40ecfa3f3fd838108dc1603326181f7cc7fa9cd66a24dab20698df0575be28
+size 1064

trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8710801393728222,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.18273070454597473,
+      "learning_rate": 1e-05,
+      "loss": 1.1276,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "eval_acc": 0.9980372914622179,
+      "eval_f1 score": 0.9988269794721408,
+      "eval_loss": 0.009664908051490784,
+      "eval_precision": 0.9994131455399061,
+      "eval_recall": 0.9982415005861665,
+      "eval_runtime": 35.543,
+      "eval_samples_per_second": 57.339,
+      "eval_steps_per_second": 1.801,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.015436016023159027,
+      "learning_rate": 2e-05,
+      "loss": 0.0073,
+      "step": 200
+    },
+    {
+      "epoch": 0.35,
+      "eval_acc": 0.9980372914622179,
+      "eval_f1 score": 0.9988283538371412,
+      "eval_loss": 0.004532838240265846,
+      "eval_precision": 0.9982435597189696,
+      "eval_recall": 0.9994138335287222,
+      "eval_runtime": 35.7648,
+      "eval_samples_per_second": 56.983,
+      "eval_steps_per_second": 1.789,
+      "step": 200
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.009873462840914726,
+      "learning_rate": 3e-05,
+      "loss": 0.0029,
+      "step": 300
+    },
+    {
+      "epoch": 0.52,
+      "eval_acc": 0.9995093228655545,
+      "eval_f1 score": 0.9997068308413954,
+      "eval_loss": 0.0031382227316498756,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9994138335287222,
+      "eval_runtime": 35.8701,
+      "eval_samples_per_second": 56.816,
+      "eval_steps_per_second": 1.784,
+      "step": 300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.00707666901871562,
+      "learning_rate": 4e-05,
+      "loss": 0.008,
+      "step": 400
+    },
+    {
+      "epoch": 0.7,
+      "eval_acc": 1.0,
+      "eval_f1 score": 1.0,
+      "eval_loss": 0.00025456614093855023,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 35.7717,
+      "eval_samples_per_second": 56.972,
+      "eval_steps_per_second": 1.789,
+      "step": 400
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.05433596670627594,
+      "learning_rate": 5e-05,
+      "loss": 0.0103,
+      "step": 500
+    },
+    {
+      "epoch": 0.87,
+      "eval_acc": 0.9985279685966634,
+      "eval_f1 score": 0.9991199765327076,
+      "eval_loss": 0.005017507821321487,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9982415005861665,
+      "eval_runtime": 35.9127,
+      "eval_samples_per_second": 56.749,
+      "eval_steps_per_second": 1.782,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 574,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2119478378496000.0,
+  "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:da2a13164a13e988fa8b8ab0b65a5be0c788467ee40f4ebcd9f2d992d98f88e8
+size 4792