Training in progress, epoch 3

logs/events.out.tfevents.1713440900.ec9626078864.14834.40

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c119f2d82ea8d5c9fc283cc655b6718849c01fda759541de6a91f217426eff3
-size 6138
+oid sha256:300a7f3a2fbdd0455bb5ab8184eaa551bc3e05523ef1bb25d824575e123c7a1c
+size 6868

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433c9a556bc2347c51bee55814abc83307859b9bbd4c61f4908355742db59420
+oid sha256:246d59c57442e797a82684bc134e64ac3e82b24660c21e1414bf74ae08399222
 size 17549312

run-39/checkpoint-1935/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-39/checkpoint-1935/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246d59c57442e797a82684bc134e64ac3e82b24660c21e1414bf74ae08399222
+size 17549312

run-39/checkpoint-1935/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fea334a7d185e4f3a6e5778cbe593d39d72d88ff27ec847b95804224c47c499
+size 35123898

run-39/checkpoint-1935/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52accd942491f2dc7d4a75134a3eb6fb2aad787ad955e2de73fb9398b7a6277c
+size 14308

run-39/checkpoint-1935/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be64a07d3c78d4c91901d4c1d101bca6d397438df03e025289521d87732e92d2
+size 1064

run-39/checkpoint-1935/special_tokens_map.json

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

run-39/checkpoint-1935/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-39/checkpoint-1935/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.8968592477704537,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-39/checkpoint-1290",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1935,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5754092931747437,
+      "learning_rate": 0.0002792573994181373,
+      "loss": 0.2921,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.893951143854207,
+      "eval_f1": 0.21968616262482166,
+      "eval_loss": 0.2762198746204376,
+      "eval_mcc": 0.24469253589704112,
+      "eval_precision": 0.5833333333333334,
+      "eval_recall": 0.13532513181019332,
+      "eval_runtime": 9.9239,
+      "eval_samples_per_second": 519.755,
+      "eval_steps_per_second": 16.324,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5258708000183105,
+      "learning_rate": 0.0002482287994827887,
+      "loss": 0.2756,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8968592477704537,
+      "eval_f1": 0.18153846153846154,
+      "eval_loss": 0.2713065445423126,
+      "eval_mcc": 0.24920140552364634,
+      "eval_precision": 0.7283950617283951,
+      "eval_recall": 0.10369068541300527,
+      "eval_runtime": 9.9253,
+      "eval_samples_per_second": 519.679,
+      "eval_steps_per_second": 16.322,
+      "step": 1290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9706701040267944,
+      "learning_rate": 0.0002172001995474401,
+      "loss": 0.2683,
+      "step": 1935
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8962776269872044,
+      "eval_f1": 0.1272430668841762,
+      "eval_loss": 0.26737910509109497,
+      "eval_mcc": 0.2297743836439136,
+      "eval_precision": 0.8863636363636364,
+      "eval_recall": 0.06854130052724078,
+      "eval_runtime": 9.9187,
+      "eval_samples_per_second": 520.03,
+      "eval_steps_per_second": 16.333,
+      "step": 1935
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4760827597800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8141838638911323,
+    "learning_rate": 0.00031028599935348586,
+    "num_train_epochs": 10,
+    "temperature": 13
+  }
+}

run-39/checkpoint-1935/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5eeff28dcf35175f2f32c9f8ab63da75907945abaf10afd049da11dbba5e957
+size 4984