Training in progress, epoch 5

logs/events.out.tfevents.1719308784.852b1e905a9a.223.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4eaf56f14daed769c22cd0da3e87ce0125bee842d4bec6ecb7c39552d871b3
-size 7030
+oid sha256:f686028ea082d55a3a3697bf1e8edb9cf5d8e5562e25fda73a7f8c1ffa93311e
+size 7564

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c39b691e161b67f75e7cd5261afcc215d97049c35a71583fef319cd2c06200
+oid sha256:957a82fa99114649a04bc99d6cf73a08d75382fe915b3d4033b919814f1dc519
 size 17549312

run-3/checkpoint-2635/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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957a82fa99114649a04bc99d6cf73a08d75382fe915b3d4033b919814f1dc519
+size 17549312

run-3/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206eaf9099444b3da32b9a5940b11906b318f979ec4b6810de3606e92969b298
+size 35123898

run-3/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5f82fd2fccfa1c0aeaf300c430a1e8a7f5356a548a23bb187c50e623fde970
+size 14308

run-3/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c1a7a614befedce27bd5c9cb589d52719507b7dede30287881e50f76bfab89
+size 1064

run-3/checkpoint-2635/special_tokens_map.json

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

run-3/checkpoint-2635/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-3/checkpoint-2635/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-1581",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 31.228694915771484,
+      "learning_rate": 7.086160775881376e-05,
+      "loss": 2.5988,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 1.924224615097046,
+      "eval_runtime": 2.5772,
+      "eval_samples_per_second": 338.351,
+      "eval_steps_per_second": 2.716,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 51.49909591674805,
+      "learning_rate": 5.9055073680756574e-05,
+      "loss": 1.2849,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 1.7333961725234985,
+      "eval_runtime": 2.54,
+      "eval_samples_per_second": 343.313,
+      "eval_steps_per_second": 2.756,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 84.45722961425781,
+      "learning_rate": 4.72485396026994e-05,
+      "loss": 0.9617,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.7150405645370483,
+      "eval_runtime": 2.5578,
+      "eval_samples_per_second": 340.916,
+      "eval_steps_per_second": 2.737,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 30.98444938659668,
+      "learning_rate": 3.5442005524642224e-05,
+      "loss": 0.8154,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.6820627450942993,
+      "eval_runtime": 2.5749,
+      "eval_samples_per_second": 338.654,
+      "eval_steps_per_second": 2.719,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 18.188648223876953,
+      "learning_rate": 2.3635471446585048e-05,
+      "loss": 0.7233,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.7338383197784424,
+      "eval_runtime": 2.5776,
+      "eval_samples_per_second": 338.302,
+      "eval_steps_per_second": 2.716,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 40447180739880.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.1351029311037084,
+    "learning_rate": 8.264573854640023e-05,
+    "num_train_epochs": 7,
+    "temperature": 16
+  }
+}

run-3/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb39e5a6519b65bdbd04bcdb6f5e6f1991f6196e0c3617b3126fe14176729f26
+size 5176