Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1c8505a3d98caf69319b632f908efd5c022cfda85639edc8bfdebc19b019b1
+oid sha256:56d314e8075f92f99275cb3632e8787de4dd97f559b26d92dee27c6a396fb668
 size 437958648

run-6/checkpoint-78/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-6/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a4f24d88fe9ee1b61bf5d41eaaf59a69395cafbe33645bea0870aa56f6d552
+size 437958648

run-6/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:565b1f63dec6295b58d65b2557073b4048ace6c18b378032b5380c543e25de72
+size 876038394

run-6/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2359103b6aecc5a33be9630634e2521d802ca571eca1b4adeac3ec6496c46f19
+size 14244

run-6/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a1e16a8bebf443f23c5087ca59e781b0e85990463d4ec5e9e1ffc94a3feca8
+size 1064

run-6/checkpoint-78/special_tokens_map.json

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

run-6/checkpoint-78/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-6/checkpoint-78/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-6/checkpoint-39",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7149667143821716,
+      "eval_runtime": 2.0061,
+      "eval_samples_per_second": 138.082,
+      "eval_steps_per_second": 2.492,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4657039711191336,
+      "eval_loss": 0.7101424336433411,
+      "eval_runtime": 2.0197,
+      "eval_samples_per_second": 137.148,
+      "eval_steps_per_second": 2.476,
+      "step": 78
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 78,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.24731337204257017,
+    "learning_rate": 2.562962993915051e-06,
+    "max_seq_length": 64,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64
+  }
+}

run-6/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2139ce59617d1c3c0f3f6bb813e51d0935c05374b0aee675ffb4b0117c98ea
+size 5432

run-7/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a498878b141a5f23f654b9db264b0e1a933b3e96b0788709ad4bf0b333b738
+oid sha256:56d314e8075f92f99275cb3632e8787de4dd97f559b26d92dee27c6a396fb668
 size 437958648

run-7/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3593e926f72a2603adbd20f73933896d9ec2c6bd9cf33e496a620318b49f760
+oid sha256:21c13e8394a43eca527521c648071f9370a54778e6c770c825f9909dbb0e5544
 size 876038394

run-7/checkpoint-39/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38f17160af42aa13aa858786a215bcf556b823f592fb270d6b697c0672f8ed5
+oid sha256:36377acd165aa6ae43ebb4a3a3ee78c58c569caae7808915c27322a1fdb550eb
 size 1064

run-7/checkpoint-39/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.47653429602888087,
+  "best_metric": 0.4729241877256318,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-7/checkpoint-39",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,11 +11,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.47653429602888087,
-      "eval_loss": 0.7149794101715088,
-      "eval_runtime": 2.0177,
-      "eval_samples_per_second": 137.288,
-      "eval_steps_per_second": 2.478,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.719865620136261,
+      "eval_runtime": 2.0266,
+      "eval_samples_per_second": 136.685,
+      "eval_steps_per_second": 2.467,
       "step": 39
     }
   ],
@@ -40,9 +40,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.3236303352568187,
-    "learning_rate": 4.109038271791985e-06,
-    "max_seq_length": 64,
+    "dropout_rate": 0.41027454763470284,
+    "learning_rate": 2.598925870941367e-06,
+    "max_seq_length": 128,
     "num_train_epochs": 1,
     "per_device_train_batch_size": 64
   }

run-7/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced7859a3f9ea14f01dce3b688bb334176b1cd5a218abb62ba6821a5a9234e68
+oid sha256:3e179d5c74f14a4304083f143d98724b39039a05148d9b3c500dc7e129143700
 size 5432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2139ce59617d1c3c0f3f6bb813e51d0935c05374b0aee675ffb4b0117c98ea
+oid sha256:3e179d5c74f14a4304083f143d98724b39039a05148d9b3c500dc7e129143700
 size 5432