Training in progress, epoch 1

config.json

@@ -19,7 +19,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.50.2",
+  "transformers_version": "4.50.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8bc7ff6423b9f68c311410a15bfa93c645e4f0b20e9763d3799b699d06ad97
+oid sha256:06d9914e81cec8e3215f1eca0331276a95a68849325a8b484e4ca1a9e925140e
 size 437958648

run-0/checkpoint-20/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-20/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d9914e81cec8e3215f1eca0331276a95a68849325a8b484e4ca1a9e925140e
+size 437958648

run-0/checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d348a999cfd9946953737d3991f5760b8493132321d63f212f53d0406a4acc1a
+size 876038394

run-0/checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d249365322d9cd9ca0a99138c2524c4957fa5a674e00c43d74faa273ad01aa70
+size 14244

run-0/checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64aeb0924d23025bb172d2b306d8eee9bdb0f12bccef6e4483dd14dc44359b1c
+size 1064

run-0/checkpoint-20/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-20/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-0/checkpoint-20/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 20,
+  "best_metric": 0.5956678700361011,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-20",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5956678700361011,
+      "eval_loss": 0.6706013083457947,
+      "eval_runtime": 0.6366,
+      "eval_samples_per_second": 435.113,
+      "eval_steps_per_second": 14.137,
+      "step": 20
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.019392246684570038,
+    "learning_rate": 4.838698947659533e-05,
+    "max_length": 32,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 128
+  }
+}

run-0/checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f664add8698af8a4abc1dce1f6af20e3257e1c01a25344f73aa3b046bebeddf5
+size 5432

runs/Apr03_17-48-13_677fb5893cf0/events.out.tfevents.1743702783.677fb5893cf0.2669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac5a1454c840f2689fc5e674bcb77c125b8343446e0c0d69a26572c51874fda
+size 5454

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49e5c1eb3079fc3edb91b45aa50ab6d4a2db5a6b0735403b06bf8187df97914f
+oid sha256:f664add8698af8a4abc1dce1f6af20e3257e1c01a25344f73aa3b046bebeddf5
 size 5432