Training in progress, step 500, checkpoint

last-checkpoint/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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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": "4.44.2",
+  "vocab_size": 30522
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a49ce476ce25fb8f59f194b7ee8dcbd54c7ed9b29498db44d64d455c49fe720
+size 267841796

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda8f9a2635a73ea6ece3ba5bfea39916c1a581c9ee7bf67f6a93a025eaa77e2
+size 535745722

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42af4289e0114191fc9e8ce7f1b2330a011f00b6431a48cc3c602a486780b82
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e1abe568f79c654af9f14796de50d6057468072e44df705c1a8d292ff6bcd7
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 1.1796199083328247,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
+  "epoch": 0.16,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.1486153602600098,
+      "learning_rate": 2.133105802047782e-06,
+      "loss": 1.5322,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.6822207084468664,
+      "eval_f1": 0.6711737667050809,
+      "eval_loss": 1.1796199083328247,
+      "eval_precision": 0.6833120550639381,
+      "eval_recall": 0.6822207084468664,
+      "eval_runtime": 134.8614,
+      "eval_samples_per_second": 108.852,
+      "eval_steps_per_second": 0.853,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2119591772160000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80840a874d0517d96566f685f49eddb6929ee834dcb1aae19a32a27f7e050d80
+size 5240