Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02768d16dc84fafd9a2b755d758aa6aea8181634cbbe1798f6f0fba0b4181246
+oid sha256:90c3bba3d98eaf314c60d2fc168121839d36d100cda7aebd13208aa2cbecdb2e
 size 263144680

run-7/checkpoint-6/config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

run-7/checkpoint-6/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1431fc20a421c73065c61dc1d709397576ae3adae1815419f1972a42f08ba0
+size 263144680

run-7/checkpoint-6/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60d69061e0b2e09e87359293748ca228d80e04e05ff3f66fed24631ede3ebb6
+size 526353483

run-7/checkpoint-6/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39ebe8c0db3aa2b1bd5b37318b91fb151061e1229f465e5537963b9c275bb0c
+size 14645

run-7/checkpoint-6/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ec26081acf8ba12c22e78b67c72eec64d21b857966199b6392c29ce35c385b
+size 1465

run-7/checkpoint-6/special_tokens_map.json

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

run-7/checkpoint-6/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": false,
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-7/checkpoint-6/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": 6,
+  "best_metric": 0.6583439707756042,
+  "best_model_checkpoint": "distilbert-base-cased-finetuned-acuteCinderellaAphasiaDetection/run-7/checkpoint-6",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6593298316001892,
+      "eval_runtime": 0.0614,
+      "eval_samples_per_second": 179.143,
+      "eval_steps_per_second": 97.714,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6583439707756042,
+      "eval_runtime": 0.0589,
+      "eval_samples_per_second": 186.833,
+      "eval_steps_per_second": 101.909,
+      "step": 6
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5865862292666785e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 18
+  }
+}

run-7/checkpoint-6/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ded677475c575079d117a2816b9895358de61f0c2e715d2c2f3a8f42b9766d7
+size 5969

run-8/checkpoint-3/config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.3",
+  "vocab_size": 28996
+}

run-8/checkpoint-3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c3bba3d98eaf314c60d2fc168121839d36d100cda7aebd13208aa2cbecdb2e
+size 263144680

run-8/checkpoint-3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a9682772ab6aa4aedc0c077ca89f3a6bfd7cd481197de08d6ebb6ac00ecbad
+size 526353483

run-8/checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f061a9413ed7a3a8166cb2949dfaa39e64e2eb84f8f8963561754c929f3c470c
+size 14709

run-8/checkpoint-3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fcb151a3af4d5d19fa01a32f55c5fcf616b0e91928465c166ac77a9a2cc1c3
+size 1465

run-8/checkpoint-3/special_tokens_map.json

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

run-8/checkpoint-3/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": false,
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-3/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.6801238656044006,
+  "best_model_checkpoint": "distilbert-base-cased-finetuned-acuteCinderellaAphasiaDetection/run-8/checkpoint-3",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_balanced_accuracy": 0.5,
+      "eval_loss": 0.6801238656044006,
+      "eval_runtime": 0.0608,
+      "eval_samples_per_second": 180.963,
+      "eval_steps_per_second": 98.707,
+      "step": 3
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.116886577484365e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 29
+  }
+}

run-8/checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f27edd6b8c804ed21e0e9919d0799306cdf81f66d70410ffae8126c7e83df2
+size 5969

runs/Jan13_11-08-43_4fecd63b14b3/events.out.tfevents.1768303189.4fecd63b14b3.1428.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cef937b38e21e694d953189ba28a1c6c9b4c1232ce4da4727e45d7ab5a53f7b
+size 5709

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ded677475c575079d117a2816b9895358de61f0c2e715d2c2f3a8f42b9766d7
+oid sha256:03f27edd6b8c804ed21e0e9919d0799306cdf81f66d70410ffae8126c7e83df2
 size 5969