Training in progress, epoch 1

config.json

@@ -5,7 +5,7 @@
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.1891988684237177,
   "hidden_size": 512,
   "initializer_range": 0.02,
   "intermediate_size": 2048,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb370303224481377bfbaca3e7254f82a70d9e57e8ba28b1480d1ad2634d4871
+oid sha256:e523ef390379259e2d519e2d17198780a1cde58ae8503b3aba68131e7af118d0
 size 165512728

run-0/checkpoint-156/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1891988684237177,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e523ef390379259e2d519e2d17198780a1cde58ae8503b3aba68131e7af118d0
+size 165512728

run-0/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f751b3beeba64cf089f013861f9f46c10c3a7a35cc7d1fbe1d9a54c6499cb452
+size 331108474

run-0/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957b2bc679131c2bcb60ab7040f6ead1f0d3b094fbfaabc3aba5dc3ab78ade86
+size 14244

run-0/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c504aa00e570dc675c82f1818a4568fe15a929890ef14b78d7e6d653a6ea55
+size 1064

run-0/checkpoint-156/special_tokens_map.json

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

run-0/checkpoint-156/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-156/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.5090252707581228,
+  "best_model_checkpoint": "bert_uncased_L-8_H-512_A-8-finetuned-rte-run_1/run-0/checkpoint-156",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5090252707581228,
+      "eval_loss": 0.690215528011322,
+      "eval_runtime": 0.9783,
+      "eval_samples_per_second": 283.148,
+      "eval_steps_per_second": 5.111,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.1891988684237177,
+    "learning_rate": 4.546022869296215e-06,
+    "max_length": 256,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-0/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5f34da6ceb66aad0eb63c414662f43a60eed98b09cbecadb2699ba48e9f997
+size 5432

runs/Apr03_13-50-26_435476ce9a2d/events.out.tfevents.1743689038.435476ce9a2d.544.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692e5a910a6cc37ed6bb0f89297927ee0f556fe28febe6017a182ae77a3e22ab
+size 5416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3606533878e517af1d7cc9277441e2c2d519b9b51e149d3ad35aa25a774571
+oid sha256:3c5f34da6ceb66aad0eb63c414662f43a60eed98b09cbecadb2699ba48e9f997
 size 5432