Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af1e566937108e24d62038dd47e8b508443926eaad838b5667f24d0105e5b1f9
+oid sha256:02f3a7dfc896bd60e170888ddf42bcc5d715abeeb2bd569a7d39ff47573f5375
 size 267835644

run-4/checkpoint-293/config.json

@@ -0,0 +1,35 @@
+{
+  "_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"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.38.1",
+  "vocab_size": 30522
+}

run-4/checkpoint-293/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f3a7dfc896bd60e170888ddf42bcc5d715abeeb2bd569a7d39ff47573f5375
+size 267835644

run-4/checkpoint-293/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a81490ad8db38e3965f94099c134e180bbea30e2cd0f683e800c2322f4ab3d4
+size 535733434

run-4/checkpoint-293/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1fc0dda0b2aff3c062c7b5857174366463eba871ff58c8c4eb004e8265fa38
+size 14244

run-4/checkpoint-293/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbc9d0c0fb00491a6a324efdc5f5c8c476fe90b58c8872e9e90c3feb1d41b1a
+size 1064

run-4/checkpoint-293/special_tokens_map.json

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

run-4/checkpoint-293/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]"
+}

run-4/checkpoint-293/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6284246575342466,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-4/checkpoint-293",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 293,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6284246575342466,
+      "eval_loss": 0.8663890361785889,
+      "eval_runtime": 3.3834,
+      "eval_samples_per_second": 172.608,
+      "eval_steps_per_second": 10.936,
+      "step": 293
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 293,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.17452250531557e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 5
+  }
+}

run-4/checkpoint-293/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab9f9c1efed08032ad2ba29f15473b7aeac2dd477211af6a7fc97beb59a2bb2
+size 4984

runs/Apr02_02-49-58_ef019a3ab26d/events.out.tfevents.1712027737.ef019a3ab26d.26.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7f2e241bc8f409629b046f541e0cc8d5767b5b0e835917f326404158b1917b
+size 5332

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d9d1105cc4b9bcdf98ecaa311fc178c26eab7b3d8c2383569f6d255249d6fb
+oid sha256:9ab9f9c1efed08032ad2ba29f15473b7aeac2dd477211af6a7fc97beb59a2bb2
 size 4984