Training in progress, epoch 6

logs/events.out.tfevents.1702287558.joseph_legion.22340.22

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9a5d0a01ba7559bacc4b4c96b980e0fcc0ce72b8375b98d46aac76794787e0
-size 6846
+oid sha256:106afa701d9a4f921e7fe645c3cd4bb4a16b13a642b18b1d0d5fae3f26249721
+size 7326

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2471b235af39d0bc9a00db78dbcf28282e5723d50a16a0295e851a5105a5aa
+oid sha256:c3b9519cfea052b3221cded839aace5900142b45f72be332a5ba5723fe9dd44c
 size 44692608

run-9/checkpoint-1182/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-9/checkpoint-1182/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b9519cfea052b3221cded839aace5900142b45f72be332a5ba5723fe9dd44c
+size 44692608

run-9/checkpoint-1182/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae9a7c51ba7b1cba06f97cf29bc0ae28619634c082a5405ecd9b94c7e7555ca
+size 89430010

run-9/checkpoint-1182/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9511e5e4163d669edd4526e0777794d8936c52493f7e77dc7be042cfeed886
+size 14308

run-9/checkpoint-1182/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4d9c239b0bf8c5969509718412c705b4007611c535e2e97080a80174611b58
+size 1064

run-9/checkpoint-1182/special_tokens_map.json

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

run-9/checkpoint-1182/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-9/checkpoint-1182/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.8100333518621456,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-9\\checkpoint-1182",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1182,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.1884492449582221e-05,
+      "loss": 0.3771,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7761256253474152,
+      "eval_loss": 0.35103824734687805,
+      "eval_runtime": 125.0972,
+      "eval_samples_per_second": 57.523,
+      "eval_steps_per_second": 0.456,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0186707813927618e-05,
+      "loss": 0.356,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7898832684824902,
+      "eval_loss": 0.3439778685569763,
+      "eval_runtime": 125.0439,
+      "eval_samples_per_second": 57.548,
+      "eval_steps_per_second": 0.456,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.488923178273016e-06,
+      "loss": 0.3473,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.797526403557532,
+      "eval_loss": 0.34075456857681274,
+      "eval_runtime": 125.2215,
+      "eval_samples_per_second": 57.466,
+      "eval_steps_per_second": 0.455,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.791138542618412e-06,
+      "loss": 0.3428,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8030850472484714,
+      "eval_loss": 0.33721399307250977,
+      "eval_runtime": 124.8586,
+      "eval_samples_per_second": 57.633,
+      "eval_steps_per_second": 0.457,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.093353906963809e-06,
+      "loss": 0.3391,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8060033351862146,
+      "eval_loss": 0.33657532930374146,
+      "eval_runtime": 125.0566,
+      "eval_samples_per_second": 57.542,
+      "eval_steps_per_second": 0.456,
+      "step": 985
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.395569271309206e-06,
+      "loss": 0.3354,
+      "step": 1182
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8100333518621456,
+      "eval_loss": 0.33524009585380554,
+      "eval_runtime": 124.7339,
+      "eval_samples_per_second": 57.691,
+      "eval_steps_per_second": 0.457,
+      "step": 1182
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 265501203931764.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.625656755680376,
+    "learning_rate": 1.3582277085236825e-05,
+    "num_train_epochs": 8,
+    "temperature": 10
+  }
+}

run-9/checkpoint-1182/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c910c119accf4bbf865cec75218ffcb177b5dd17c6f67c36518b8f592afcb473
+size 4792