Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac4fff988cff8f41399e3bc5e0056ab4a2e773203ebf59722ca08fc3ad14a73
+oid sha256:f6019332a2405ed45327de26e1fab37257eda70217b9e85d82c7fa6039c4973d
 size 437958648

run-12/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-12/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4d91e52c74c1d2e55851f1c42d857b482054f364ba6012d946acc8907d7ecc
+size 437958648

run-12/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5660c6255152ebb6d6795e5328b16627f7bb7ea30f6d7b9ef80aa501c404834b
+size 876038394

run-12/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3115cbdc08b9836a393efb499f011b65a6649e6c5cc563d236e33e683532ac2
+size 14244

run-12/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f71bd40cffa49cff7d370e79345c8799336990a8135b44d986e8e8d6156a24
+size 1064

run-12/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-12/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-12/checkpoint-78/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_global_step": 78,
+  "best_metric": 0.6642599277978339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-12/checkpoint-78",
+  "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": 0.6173285198555957,
+      "eval_loss": 0.6622068285942078,
+      "eval_runtime": 0.6355,
+      "eval_samples_per_second": 435.909,
+      "eval_steps_per_second": 14.163,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6550388336181641,
+      "eval_runtime": 0.6383,
+      "eval_samples_per_second": 433.987,
+      "eval_steps_per_second": 14.101,
+      "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": {
+    "learning_rate": 6.947760674588204e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64
+  }
+}

run-12/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab26e476d09936510eaa482033bae6d756d1816469903d3e01b40fe9b9032bf0
+size 5432

run-13/checkpoint-39/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-13/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6019332a2405ed45327de26e1fab37257eda70217b9e85d82c7fa6039c4973d
+size 437958648

run-13/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2307116750d0bcaccf41d95c536274a80a9c3cb60bf1982ea72ec994d8af26b3
+size 876038394

run-13/checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce2001d6c41d462c4a530df5214c4ba6ac04088f8883ec9b91629a00a7da50d
+size 14244

run-13/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4888230e8e4b0dc12ad8d003c178dad6057727d6001addede627c5411c67cfb8
+size 1064

run-13/checkpoint-39/special_tokens_map.json

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

run-13/checkpoint-39/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-13/checkpoint-39/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.5956678700361011,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-13/checkpoint-39",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5956678700361011,
+      "eval_loss": 0.6718657612800598,
+      "eval_runtime": 0.6364,
+      "eval_samples_per_second": 435.249,
+      "eval_steps_per_second": 14.142,
+      "step": 39
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.879377704760648e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64
+  }
+}

run-13/checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23a0a2a7111710f92f2d16d832bc9c9e37aa87c708e0778665c9b74b4307367
+size 5432

runs/Apr01_21-40-42_1357c7d90830/events.out.tfevents.1743547261.1357c7d90830.592.108

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6088f80d389a8fd44785e32af49a0c200d6ccfb6766ef6d45cf2830a5165d7fc
+size 6083

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab26e476d09936510eaa482033bae6d756d1816469903d3e01b40fe9b9032bf0
+oid sha256:e23a0a2a7111710f92f2d16d832bc9c9e37aa87c708e0778665c9b74b4307367
 size 5432