Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dbd76b53649a2e698dd2acdb87ce73fd734705433351eab27f1c382d596a715
+oid sha256:78bec9f41298f06244922d5e03af313d5240421a1b2f8eff6f75c814352ccfbe
 size 437958648

run-2/checkpoint-2105/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.4,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.4,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-2105/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78bec9f41298f06244922d5e03af313d5240421a1b2f8eff6f75c814352ccfbe
+size 437958648

run-2/checkpoint-2105/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c65f0cda99836f8567fc042b93e46b8396f9a616e9ba8293d6b6559f2cef2a0
+size 876038394

run-2/checkpoint-2105/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476ee2efce4b217aad0d755825f1a834ab406c7a8a98fefa377212d962beb604
+size 14308

run-2/checkpoint-2105/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6da7f643e1b8af98acb6858075787208a08885eba5c968323a71a0f0656e7a
+size 1064

run-2/checkpoint-2105/special_tokens_map.json

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

run-2/checkpoint-2105/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-2105/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.5745412844036697,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-2/checkpoint-2105",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2105,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5745412844036697,
+      "eval_loss": 0.658979058265686,
+      "eval_runtime": 2.4031,
+      "eval_samples_per_second": 362.862,
+      "eval_steps_per_second": 22.887,
+      "step": 2105
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 8420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.004779601947806e-07,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 37,
+    "weight_decay": 0.24080188545658526
+  }
+}

run-2/checkpoint-2105/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab85adc03c06c516aa29acaf676259ddec6473900c9e4098cbbdb0d71ae75d15
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709755237.e017d622c671.539.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad8573fd7ccf70e6eabbd78e7e5597b97202564ac51afa759f383fb8228e2a4
+size 5074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1319ddc45a70cf6c8258282d58f5ce2a722664ee561e40f594d0b44a8d8c1fb6
+oid sha256:ab85adc03c06c516aa29acaf676259ddec6473900c9e4098cbbdb0d71ae75d15
 size 4984