Upload 11 files

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "computer vision",
+    "1": "natural language processing"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "computer vision": 0,
+    "natural language processing": 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": "4.41.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c384be2dc8ecb0346ef19c277917d74b78395d207dcecffa57c57cec2212673
+size 267832560

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91be53fc9634e03b47d950176e62e8c26439022fa5f830e664785739b2f890d
+size 535724410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6636971625e66f87ccc7a97658a28e9cb9e1b0ed3de7c8cb9527aabf994f8965
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.40592309832572937,
+  "best_model_checkpoint": "output/checkpoint-100",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5189873417721519,
+      "eval_loss": 0.6217403411865234,
+      "eval_runtime": 7.9638,
+      "eval_samples_per_second": 9.92,
+      "eval_steps_per_second": 0.628,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7468354430379747,
+      "eval_loss": 0.49112987518310547,
+      "eval_runtime": 5.4261,
+      "eval_samples_per_second": 14.559,
+      "eval_steps_per_second": 0.921,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8354430379746836,
+      "eval_loss": 0.40680351853370667,
+      "eval_runtime": 5.7332,
+      "eval_samples_per_second": 13.779,
+      "eval_steps_per_second": 0.872,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.810126582278481,
+      "eval_loss": 0.42049866914749146,
+      "eval_runtime": 4.7735,
+      "eval_samples_per_second": 16.55,
+      "eval_steps_per_second": 1.047,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.810126582278481,
+      "eval_loss": 0.40592309832572937,
+      "eval_runtime": 6.5454,
+      "eval_samples_per_second": 12.07,
+      "eval_steps_per_second": 0.764,
+      "step": 100
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 100,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 153307987384788.0,
+  "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:cd51eac1f3b5daf2be84d6b52d46a693d876645a59af2cd716972b2073d7a8c2
+size 5048