Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dcdcb1f1b6e7c31feaa9714b113863285f71213f4050d8f8e1e8368c49cbc8d
+oid sha256:0b6b16f7a7da0900019e1f77cb501fd89b6d9d5c43023285cb903da7c01cf169
 size 437958648

run-3/checkpoint-156/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-3/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14559bd9d478131cb16a7bfc7777abbbbcd86f972723b74902dfb0ddf2b0319c
+size 437958648

run-3/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf62cdb3756e13ef0fb5f1893666d55a020359f233371f21d12b4dba6490cba6
+size 876038394

run-3/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b06d22713ab0eccf6163f8b0ec7376abad69fdc0b947461e0b301173cdd320
+size 14244

run-3/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f93254082f16a258040160ea0e6bb69ec805e4830769e27bfe40dc40fe80fe17
+size 1064

run-3/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-3/checkpoint-156/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-3/checkpoint-156/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.4693140794223827,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-3/checkpoint-78",
+  "epoch": 2.0,
+  "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": 0.4693140794223827,
+      "eval_loss": 0.7107913494110107,
+      "eval_runtime": 0.675,
+      "eval_samples_per_second": 410.389,
+      "eval_steps_per_second": 13.334,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.7062165141105652,
+      "eval_runtime": 1.0234,
+      "eval_samples_per_second": 270.666,
+      "eval_steps_per_second": 8.794,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 156,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.29412092726837363,
+    "learning_rate": 2.1156293226344175e-06,
+    "max_seq_length": 64,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32
+  }
+}

run-3/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecd4dd949417edd978f459fbaf152e991e4d079e0f5959c96a5c0379f9a1e95
+size 5240

run-4/checkpoint-78/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -19,7 +20,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.44.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-4/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed12413a78a5820ab2c4ab01bfad7a21eba7c8b2ce1a2ee5bd44fee72d1e7e0
+oid sha256:0b6b16f7a7da0900019e1f77cb501fd89b6d9d5c43023285cb903da7c01cf169
 size 437958648

run-4/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2471d9ad4cb454843be8e9f248895d3f54bbfa272529e044e887f70d8aa28682
+oid sha256:f9a56467b16d1806d3b70531d42690db7a47401c588851416339cc442c88df4b
 size 876038394

run-4/checkpoint-78/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2359103b6aecc5a33be9630634e2521d802ca571eca1b4adeac3ec6496c46f19
+oid sha256:bd53c5c3dd7d411230f105bda2473d2a3923ae5b6e14f965bb99d91f5a28c9b2
 size 14244

run-4/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1765c70c3ecce838f35a9b9da22365ff312697bec6161477288f9bd41cc533
+oid sha256:4c04c957a5092cf8e4865d74822ca2280cf48e9ccdf02776ba6a55b3e20ebcc8
 size 1064

run-4/checkpoint-78/tokenizer_config.json

@@ -41,10 +41,9 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
-  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

run-4/checkpoint-78/trainer_state.json

@@ -1,8 +1,7 @@
 {
-  "best_global_step": 78,
-  "best_metric": 0.4729241877256318,
+  "best_metric": 0.4657039711191336,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-4/checkpoint-78",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 78,
   "is_hyper_param_search": true,
@@ -11,27 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4548736462093863,
-      "eval_loss": 0.6974011659622192,
-      "eval_runtime": 2.044,
-      "eval_samples_per_second": 135.516,
-      "eval_steps_per_second": 2.446,
-      "step": 39
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6938932538032532,
-      "eval_runtime": 2.0092,
-      "eval_samples_per_second": 137.867,
-      "eval_steps_per_second": 2.489,
+      "eval_accuracy": 0.4657039711191336,
+      "eval_loss": 0.6980094909667969,
+      "eval_runtime": 0.6946,
+      "eval_samples_per_second": 398.789,
+      "eval_steps_per_second": 12.957,
       "step": 78
     }
   ],
   "logging_steps": 500,
   "max_steps": 78,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -46,13 +36,13 @@
     }
   },
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.4407801684939425,
-    "learning_rate": 6.14706717379554e-06,
-    "max_seq_length": 256,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 64
+    "dropout_rate": 0.41500781489341676,
+    "learning_rate": 6.349040683142055e-06,
+    "max_seq_length": 32,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32
   }
 }

run-4/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4cc6501d1b38dbc34775f0b9df2455a0400a6b9f97257af4d9b51f4b12b7d0f
-size 5432
+oid sha256:049df9dca24175056e76249fdce3b716c8df0248f13e43515a706585cada19d6
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecd4dd949417edd978f459fbaf152e991e4d079e0f5959c96a5c0379f9a1e95
+oid sha256:049df9dca24175056e76249fdce3b716c8df0248f13e43515a706585cada19d6
 size 5240