Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a040e99e848dbed9a359bf32d3518cfeb9ff58bc7401cb2c4970629aae9542cd
+oid sha256:9dcdcb1f1b6e7c31feaa9714b113863285f71213f4050d8f8e1e8368c49cbc8d
 size 437958648

run-2/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-2/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca60823e76d1b3853c289f4ea956731caba6d14bc52f38fd71294e83e1754938
+size 437958648

run-2/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02369dcfe750927e73b5660290b9bdc5cc1a996e7adb12eaad509e810d83a28f
+size 876038394

run-2/checkpoint-156/rng_state.pth

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

run-2/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e50d5ef5c3f021f3972ed9b74990587c811df43ac5e4d6b0ad2b1955401e18e
+size 1064

run-2/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-2/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-2/checkpoint-156/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.6137184115523465,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-2/checkpoint-156",
+  "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": 0.5306859205776173,
+      "eval_loss": 0.6830374002456665,
+      "eval_runtime": 0.6773,
+      "eval_samples_per_second": 408.985,
+      "eval_steps_per_second": 13.288,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6137184115523465,
+      "eval_loss": 0.6502091288566589,
+      "eval_runtime": 0.7022,
+      "eval_samples_per_second": 394.459,
+      "eval_steps_per_second": 12.816,
+      "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": 0.22916043310370748,
+    "learning_rate": 2.8113763118186958e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32
+  }
+}

run-2/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f802f6180f2481d72cca73fb8b638357519b39f879bf12e5ed15cc69b245f3
+size 5240

run-3/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-3/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd4913ce348f558d502ca01511ddb81e82587892b7e1f882077cabcd1b8a35d
+oid sha256:9dcdcb1f1b6e7c31feaa9714b113863285f71213f4050d8f8e1e8368c49cbc8d
 size 437958648

run-3/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671859db3ad9a98778b7e4b8e809d4705fdc307265d2f471178b4afa27f65754
+oid sha256:9c31e2fe00c6fd09896dce0212ae6ae0f5bbd3da9a95f06a07fe016647d1b17b
 size 876038394

run-3/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-3/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589ecb2461e16e2216bde3fe5e91331709422e8f1c62ba8ff8dafc35616f6f84
+oid sha256:52ad250b9aaf8b0a9029489bc4912fd70de026ef5e764dc0ca050196696988b0
 size 1064

run-3/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-3/checkpoint-78/trainer_state.json

@@ -1,8 +1,7 @@
 {
-  "best_global_step": 78,
-  "best_metric": 0.5018050541516246,
+  "best_metric": 0.4693140794223827,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-3/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": 0.4620938628158845,
-      "eval_loss": 0.6993961334228516,
-      "eval_runtime": 2.0133,
-      "eval_samples_per_second": 137.583,
-      "eval_steps_per_second": 2.483,
-      "step": 39
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5018050541516246,
-      "eval_loss": 0.6926687359809875,
-      "eval_runtime": 2.0406,
-      "eval_samples_per_second": 135.744,
-      "eval_steps_per_second": 2.45,
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 117,
+  "max_steps": 156,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "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": 0.19092511979807322,
-    "learning_rate": 5.546555906491602e-06,
-    "max_seq_length": 256,
-    "num_train_epochs": 3,
-    "per_device_train_batch_size": 64
+    "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-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574977948b354aca70839ceacef71c7860dfc6ff222f5d96e1b3a99d03c6ab63
-size 5432
+oid sha256:3ecd4dd949417edd978f459fbaf152e991e4d079e0f5959c96a5c0379f9a1e95
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f802f6180f2481d72cca73fb8b638357519b39f879bf12e5ed15cc69b245f3
+oid sha256:3ecd4dd949417edd978f459fbaf152e991e4d079e0f5959c96a5c0379f9a1e95
 size 5240