initial model smallbenchnlp/bert-small trained on imdb

checkpoint-12500/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "smallbenchnlp/bert-small",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-12500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e735aa18572bbae5af312c1f9a9d3e1fb5700425799dae603bb43490432a1c
+size 140029725

checkpoint-12500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ad234ea471e21b70c5d4895bce11fd91f6d497cf57cfc1ada51323dd6b29b1
+size 70027629

checkpoint-12500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccbe87fc3ca89faab8fc0671f8a2f292ffe6952fa45bf34491038cb6a6d8062
+size 14503

checkpoint-12500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12e6a0a755b23af10a9b049028af1a7562d339c7726bfffd3db7aaad0d3a962
+size 623

checkpoint-12500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-12500/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "smallbenchnlp/bert-small",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-12500/trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.6684188842773438,
+  "best_model_checkpoint": "my_awesome_model/checkpoint-12500",
+  "epoch": 1.0,
+  "global_step": 12500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.6978,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.6951,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.76e-05,
+      "loss": 0.6948,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.6757,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.6541,
+      "step": 2500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.7619,
+      "step": 3000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.7755,
+      "step": 3500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.8347,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.7848,
+      "step": 4500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7772,
+      "step": 5000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.6601,
+      "step": 5500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.04e-05,
+      "loss": 0.7317,
+      "step": 6000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.7202,
+      "step": 6500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.8e-06,
+      "loss": 0.6754,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.7578,
+      "step": 7500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.7782,
+      "step": 8000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.6967,
+      "step": 8500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.6118,
+      "step": 9000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.6468,
+      "step": 9500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.64,
+      "step": 10000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.7285,
+      "step": 10500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.6744,
+      "step": 11000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.7347,
+      "step": 11500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.6218,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.7703,
+      "step": 12500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.85048,
+      "eval_loss": 0.6684188842773438,
+      "eval_runtime": 256.7866,
+      "eval_samples_per_second": 97.357,
+      "eval_steps_per_second": 48.679,
+      "step": 12500
+    }
+  ],
+  "max_steps": 12500,
+  "num_train_epochs": 1,
+  "total_flos": 506545463743800.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6005a8dbbeaf7fa1e5d44e146225df46606430ab46bf38394b1e0f0709e011b
+size 3439