Training in progress, epoch 2

logs/events.out.tfevents.1709745168.d65e8524b0f6.5185.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce437c16683c76df1c5b49c813ef9b0032fa900a0f1bf1eedf6924fbf4317ebb
-size 5315
+oid sha256:79edcc9ca75419fb7130bebe1a3b1b24f7e5bf83b908c14fa38d1ea6bb4e1058
+size 5998

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b87127e442a61d26d59b2634eed0e640f0ac6eabd4bad038eb5b7d5da4538ee
+oid sha256:6ba95c9d532c48ee17ddbdeae9c7adf668a8f0b04d554821706bfe56e3fa01c1
 size 17549312

run-12/checkpoint-220/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-12/checkpoint-220/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba95c9d532c48ee17ddbdeae9c7adf668a8f0b04d554821706bfe56e3fa01c1
+size 17549312

run-12/checkpoint-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031033098a696237d3a185f80b2bd5b4c614a4459cfe9587b2197e923b6ed75e
+size 35122746

run-12/checkpoint-220/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d92b054b51f9160f87c9d0d83bbada0c84089880a6562bfa0194228c3de19bd
+size 14054

run-12/checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26be6b2218d26d856660a42c0025fb874875d2822e71dc01aeaaadc48b6d4e4c
+size 1064

run-12/checkpoint-220/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-220/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-12/checkpoint-220/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.8091976516634051,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-220",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.2588086128234863,
+      "learning_rate": 8.732687275158285e-05,
+      "loss": 0.5286,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.764187866927593,
+      "eval_f1": 0.7826871055004507,
+      "eval_loss": 0.45278048515319824,
+      "eval_precision": 0.725752508361204,
+      "eval_recall": 0.8493150684931506,
+      "eval_runtime": 27.9751,
+      "eval_samples_per_second": 36.532,
+      "eval_steps_per_second": 1.144,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.785890579223633,
+      "learning_rate": 5.821791516772189e-05,
+      "loss": 0.4524,
+      "step": 220
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8091976516634051,
+      "eval_f1": 0.823529411764706,
+      "eval_loss": 0.4230343699455261,
+      "eval_precision": 0.765993265993266,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 28.1954,
+      "eval_samples_per_second": 36.247,
+      "eval_steps_per_second": 1.135,
+      "step": 220
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 28,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7727775292077371,
+    "learning_rate": 0.00011643583033544379,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 28,
+    "temperature": 18
+  }
+}

run-12/checkpoint-220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d326c5fe515888a81989fed6d26dc1aadeb6fd6bd4401805f0cf726489091eb5
+size 4920