Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3327f4a45624b24852d1cf0314edde5a2bd2f2bb844a21ee997f973958c068
+oid sha256:39468e1256e8687240939b153b00a9110b07f752b59907671d9c1e1e0285d728
 size 437958648

run-1/checkpoint-234/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-234/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1fde957ffbff0d671726339771f4bf9c5f5cfc22dcda644937b38636bedd19
+size 437958648

run-1/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f149ace8c7dd9a7eac7446f0c2a997eebe7dcca4400b7154f507b07e862fd81
+size 876038394

run-1/checkpoint-234/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5893971a43e53d8cccb69cbc77f5b88d424dd9d85114d1b21fc0c54c6cb446cf
+size 14244

run-1/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af71516663a3cfb61868807b34d6781d05c933d57a9498213e7778b71b92ede1
+size 1064

run-1/checkpoint-234/special_tokens_map.json

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

run-1/checkpoint-234/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-1/checkpoint-234/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6137184115523465,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-1/checkpoint-234",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 234,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 0.6887229084968567,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 409.255,
+      "eval_steps_per_second": 13.297,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5884476534296029,
+      "eval_loss": 0.672937273979187,
+      "eval_runtime": 0.6928,
+      "eval_samples_per_second": 399.854,
+      "eval_steps_per_second": 12.992,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6137184115523465,
+      "eval_loss": 0.6694894433021545,
+      "eval_runtime": 0.7129,
+      "eval_samples_per_second": 388.554,
+      "eval_steps_per_second": 12.625,
+      "step": 234
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.186349260590997,
+    "learning_rate": 8.992145512689151e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-1/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088703d1ec91cce96a1f78205fe905d0ccd04ee20140a96d92891d553f213068
+size 5240

run-2/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e18f1f81e023c8b25dab78577dc481e274296d4abd3acf7203d0e19e8599020
+oid sha256:39468e1256e8687240939b153b00a9110b07f752b59907671d9c1e1e0285d728
 size 437958648

run-2/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2fd6a69deac2e53ae05b6cce032a27c1c7f518328854b395bd7b3fbf839501
+oid sha256:8c8176b10769b4078e54396c9b38acd8fe1ddd719e08bddfa6c4fd8611c41db8
 size 876038394

run-2/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f649045559aed62ea18e0202c23ba000ca86642aa93f3c206cbee2ad660fd1
+oid sha256:0a901be7f18e6e5785d470b18880b1475f3f4abfe336b82318d6eeb84d7c89c5
 size 1064

run-2/checkpoint-78/tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

run-2/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5451263537906137,
+  "best_metric": 0.4729241877256318,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-2/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5451263537906137,
-      "eval_loss": 0.6886031627655029,
-      "eval_runtime": 0.7783,
-      "eval_samples_per_second": 355.92,
-      "eval_steps_per_second": 11.564,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.712794303894043,
+      "eval_runtime": 0.878,
+      "eval_samples_per_second": 315.506,
+      "eval_steps_per_second": 10.251,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 78,
+  "max_steps": 234,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -30,7 +30,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
@@ -39,10 +39,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.44204273950377526,
-    "learning_rate": 2.058161735932423e-05,
+    "dropout_rate": 0.4076930534485722,
+    "learning_rate": 1.6570112389077426e-06,
     "max_seq_length": 64,
-    "num_train_epochs": 1,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }
 }

run-2/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e5194653184e8e5b32b0ae0661ee374784719298d557b5983898cb4983f831
+oid sha256:75a9aec886ff51f25b037080344f18ba7135f32f683e36490270e5f0adbb586f
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088703d1ec91cce96a1f78205fe905d0ccd04ee20140a96d92891d553f213068
+oid sha256:75a9aec886ff51f25b037080344f18ba7135f32f683e36490270e5f0adbb586f
 size 5240