Training in progress, epoch 2

logs/events.out.tfevents.1713438663.ec9626078864.14834.25

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5164fe9ff1c3479c74443d245857d81a71e234f26d7de5347dae946f3be62c8
-size 5406
+oid sha256:cd5a6ed726904a4431eef178c21b588b94e99520658775b7ee841c21749a3eb8
+size 6136

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae878e89ffd1c421171b279fea59f664c2c3fecd5c19cac9c9978ea09dcd292
+oid sha256:79324ee299446ba31cf44449c80edf4d74a27ee08f8555b5d96f48fb5a7bac75
 size 17549312

run-24/checkpoint-1290/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-24/checkpoint-1290/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79324ee299446ba31cf44449c80edf4d74a27ee08f8555b5d96f48fb5a7bac75
+size 17549312

run-24/checkpoint-1290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd51717c2c9fcf8b1c5a07cd09ab7e3c5224bcde1fb0f3adf486afad146965ea
+size 35123898

run-24/checkpoint-1290/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7f2a5e16989d9df1a9f119f3a022ead0c31636524de5ea431eca109ab65358
+size 14308

run-24/checkpoint-1290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b9a0a14b4ef592a0cfcc4ce62c56b85488a45379abd12f90bbcbe8f50dbb2f
+size 1064

run-24/checkpoint-1290/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-1290/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-1290/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.8937572702597906,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-645",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1290,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1594387292861938,
+      "learning_rate": 0.0003669096859466192,
+      "loss": 0.3104,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8937572702597906,
+      "eval_f1": 0.17717717717717715,
+      "eval_loss": 0.29782024025917053,
+      "eval_mcc": 0.22004174832122259,
+      "eval_precision": 0.6082474226804123,
+      "eval_recall": 0.10369068541300527,
+      "eval_runtime": 9.922,
+      "eval_samples_per_second": 519.854,
+      "eval_steps_per_second": 16.327,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.089403510093689,
+      "learning_rate": 0.0003210459752032918,
+      "loss": 0.2989,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8937572702597906,
+      "eval_f1": 0.1217948717948718,
+      "eval_loss": 0.29260244965553284,
+      "eval_mcc": 0.19240131656369383,
+      "eval_precision": 0.6909090909090909,
+      "eval_recall": 0.06678383128295255,
+      "eval_runtime": 9.8986,
+      "eval_samples_per_second": 521.085,
+      "eval_steps_per_second": 16.366,
+      "step": 1290
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5805,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 3173885065200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8984215980104533,
+    "learning_rate": 0.0004127733966899466,
+    "num_train_epochs": 9,
+    "temperature": 29
+  }
+}

run-24/checkpoint-1290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456127f7769e7956edafc511b28db8949081a7bcc64e2dae6a89559f359d58a4
+size 4984