Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23407069a55e22e6c8c37ce6bf6dfe0ffb52e3ee46b5a342cf5fd6b7106a9f2c
+oid sha256:a040e99e848dbed9a359bf32d3518cfeb9ff58bc7401cb2c4970629aae9542cd
 size 437958648

run-1/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-1/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc3c17c0e28f0d99ddf93e15ca85bd8f5b5115bfeb97418733a181c63fd8511
+size 437958648

run-1/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f6e913c5b6f9a0706fb04ba21db8e70d7fe67384a5167dc5480581a92a08da
+size 876038394

run-1/checkpoint-156/rng_state.pth

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

run-1/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8c04bc9c22f54eba6a3b21b45f59ff5d779a31f5915a1316f9ac093cb2d250
+size 1064

run-1/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-1/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-1/checkpoint-156/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.5631768953068592,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-1/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": 0.5234657039711191,
+      "eval_loss": 0.6910961866378784,
+      "eval_runtime": 0.6762,
+      "eval_samples_per_second": 409.637,
+      "eval_steps_per_second": 13.31,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5631768953068592,
+      "eval_loss": 0.6854330897331238,
+      "eval_runtime": 0.6842,
+      "eval_samples_per_second": 404.836,
+      "eval_steps_per_second": 13.154,
+      "step": 156
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.47315201494777315,
+    "learning_rate": 1.1601157014258523e-05,
+    "max_seq_length": 32,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-1/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7f9c89da7fef02fc90d0e151b49ef276f71cf188cc8e07d9d3f594f6c53ceb
+size 5240

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:ed51ef81c95076054b5359f48fd50a8b24b389b05e123a5cc8342f7930ba54e8
+size 437958648

run-1/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d5bb90fa2db5a2548d03c057a9ea4588a36402116cdc47d7e872bf9591db91
+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:ac86eda825a300b6e7e6564d2c6a5fa943d12e4fbafecbe51f00ad0e5e89aaaa
+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": 0.5740072202166066,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/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": 0.5234657039711191,
+      "eval_loss": 0.6910961866378784,
+      "eval_runtime": 0.6762,
+      "eval_samples_per_second": 409.637,
+      "eval_steps_per_second": 13.31,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5631768953068592,
+      "eval_loss": 0.6854330897331238,
+      "eval_runtime": 0.6842,
+      "eval_samples_per_second": 404.836,
+      "eval_steps_per_second": 13.154,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5740072202166066,
+      "eval_loss": 0.6843420267105103,
+      "eval_runtime": 0.6963,
+      "eval_samples_per_second": 397.815,
+      "eval_steps_per_second": 12.925,
+      "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": 0.47315201494777315,
+    "learning_rate": 1.1601157014258523e-05,
+    "max_seq_length": 32,
+    "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 sha256:8b7f9c89da7fef02fc90d0e151b49ef276f71cf188cc8e07d9d3f594f6c53ceb
+size 5240

run-2/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-2/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c805f8113500772a72690f77fb2900675f7a0f4d14c9bc9029b40d658b2239f
+oid sha256:a040e99e848dbed9a359bf32d3518cfeb9ff58bc7401cb2c4970629aae9542cd
 size 437958648

run-2/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905c8c0f4db658a801d1a71461b4d8234c9af0642e77f04929a44bb3d3d901e2
+oid sha256:073332a0b747295c5c7ecdee9ecc6773313c250a4b89fee343f2d1f686d8d044
 size 876038394

run-2/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-2/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a4ddb60b114de2f231eca662d77dbbd41440ecf361b4caffe5e2567f7d6c48f
+oid sha256:66ed913796d0841d9127eb456a7c094b58bac76bc75618530695aa529dedbdc7
 size 1064

run-2/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-2/checkpoint-78/trainer_state.json

@@ -1,8 +1,7 @@
 {
-  "best_global_step": 39,
-  "best_metric": 0.4657039711191336,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-2/checkpoint-39",
-  "epoch": 2.0,
+  "best_metric": 0.5306859205776173,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-2/checkpoint-78",
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 78,
   "is_hyper_param_search": true,
@@ -11,25 +10,16 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.710749089717865,
-      "eval_runtime": 1.9931,
-      "eval_samples_per_second": 138.981,
-      "eval_steps_per_second": 2.509,
-      "step": 39
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4620938628158845,
-      "eval_loss": 0.7048717737197876,
-      "eval_runtime": 1.9387,
-      "eval_samples_per_second": 142.881,
-      "eval_steps_per_second": 2.579,
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 78,
+  "max_steps": 156,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,
@@ -40,19 +30,19 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.4829965966194095,
-    "learning_rate": 3.297651789500977e-06,
+    "dropout_rate": 0.22916043310370748,
+    "learning_rate": 2.8113763118186958e-05,
     "max_seq_length": 128,
     "num_train_epochs": 2,
-    "per_device_train_batch_size": 64
+    "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:c92319a9291c2950bc58902fdbdfc01c8adc9c12189f811495e2b99ba0ea7422
-size 5432
+oid sha256:83f802f6180f2481d72cca73fb8b638357519b39f879bf12e5ed15cc69b245f3
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7f9c89da7fef02fc90d0e151b49ef276f71cf188cc8e07d9d3f594f6c53ceb
+oid sha256:83f802f6180f2481d72cca73fb8b638357519b39f879bf12e5ed15cc69b245f3
 size 5240