Training in progress, epoch 2

logs/events.out.tfevents.1711295423.73e3a81c01ef.4225.24

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1fb95d3693662a0d6c1edc8a9bf334596920eec8fe4649a9a48dc326704dec
-size 5407
+oid sha256:b6424598aad99ea77edb4c97da14b185a7cef4322d61f37dea3d4b03373a965e
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5d6a7d2e429d3d43405de9843117f06bee223fb6d80a4ebaa24deaf9367ae2
+oid sha256:3eaf1002250d7bbffac71f9f2df96c1df8bb06414650bac5364380291bb1b647
 size 17549312

run-24/checkpoint-384/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-24/checkpoint-384/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eaf1002250d7bbffac71f9f2df96c1df8bb06414650bac5364380291bb1b647
+size 17549312

run-24/checkpoint-384/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314a8e23098748ec3435bfbac4c582cac7bf1a98dddbd14bfc5a924acbdfd6e5
+size 35122746

run-24/checkpoint-384/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2558f72cda987826e5e7caf54cc6282fe335ebecbddfed7bb83f0184d1f54cc
+size 14054

run-24/checkpoint-384/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143535c44d720b0819d98ca088b0ae49696495ec3137556dcce9402337847b70
+size 1064

run-24/checkpoint-384/special_tokens_map.json

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

run-24/checkpoint-384/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-24/checkpoint-384/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.8131115459882583,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-384",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 384,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.648065090179443,
+      "learning_rate": 0.00012494952559183724,
+      "loss": 0.5711,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8043052837573386,
+      "eval_f1": 0.8178506375227687,
+      "eval_loss": 0.44779932498931885,
+      "eval_mcc": 0.6154555748616207,
+      "eval_precision": 0.7649063032367973,
+      "eval_recall": 0.8786692759295499,
+      "eval_runtime": 66.7583,
+      "eval_samples_per_second": 15.309,
+      "eval_steps_per_second": 0.479,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.388855934143066,
+      "learning_rate": 6.247476279591862e-05,
+      "loss": 0.461,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8131115459882583,
+      "eval_f1": 0.8239631336405531,
+      "eval_loss": 0.4190569818019867,
+      "eval_mcc": 0.631037291856266,
+      "eval_precision": 0.7787456445993032,
+      "eval_recall": 0.8747553816046967,
+      "eval_runtime": 66.8351,
+      "eval_samples_per_second": 15.291,
+      "eval_steps_per_second": 0.479,
+      "step": 384
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9973571924957664,
+    "learning_rate": 0.00018742428838775587,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "temperature": 50
+  }
+}

run-24/checkpoint-384/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c5d3018229d2667ade19316e65e309d90ed770cbee817143182a01f8c881eb
+size 4984