Training in progress, epoch 2

logs/events.out.tfevents.1713438345.ec9626078864.14834.23

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cea53af2887d60843d61f7b65c8635e4bb00997b6927acbe25ced2788ccbf87
-size 5407
+oid sha256:e649642e17a78fdac6d5c568dbc2bd3296a4b92d86cee5877d1cbd7bc811b24b
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0f6599d392c90e9528fe8546a8df09766fdfc9d1d7a34f944b1777ed6258f7
+oid sha256:fa3fcc93cda8084c0dc3d735fb7d21e507af573161e7b05204f7b8f74510d918
 size 17549312

run-22/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-22/checkpoint-1290/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3fcc93cda8084c0dc3d735fb7d21e507af573161e7b05204f7b8f74510d918
+size 17549312

run-22/checkpoint-1290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eba7a9856f1f1eb46449aef1bd257bf2adf6d8650fad14a858ca251eb45edcb
+size 35123898

run-22/checkpoint-1290/rng_state.pth

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

run-22/checkpoint-1290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a38f972851c7585c9b8fc3c90718879ca25d6e6c0faaf32ee0673f730db261
+size 1064

run-22/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-22/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-22/checkpoint-1290/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.8997673516867003,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-1290",
+  "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": 2.1603200435638428,
+      "learning_rate": 0.00015804016249699036,
+      "loss": 0.3253,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8945327646374563,
+      "eval_f1": 0.19047619047619047,
+      "eval_loss": 0.29357558488845825,
+      "eval_mcc": 0.23285387927696083,
+      "eval_precision": 0.6213592233009708,
+      "eval_recall": 0.11247803163444639,
+      "eval_runtime": 9.9704,
+      "eval_samples_per_second": 517.33,
+      "eval_steps_per_second": 16.248,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3251060247421265,
+      "learning_rate": 0.00011853012187274275,
+      "loss": 0.2915,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8997673516867003,
+      "eval_f1": 0.2385861561119293,
+      "eval_loss": 0.2915143072605133,
+      "eval_mcc": 0.2949928981799802,
+      "eval_precision": 0.7363636363636363,
+      "eval_recall": 0.14235500878734622,
+      "eval_runtime": 9.9347,
+      "eval_samples_per_second": 519.192,
+      "eval_steps_per_second": 16.307,
+      "step": 1290
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3173885065200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9879592289455201,
+    "learning_rate": 0.00019755020312123793,
+    "num_train_epochs": 5,
+    "temperature": 26
+  }
+}

run-22/checkpoint-1290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463d23df8f476e3af460c3bc4425d71e9123ebed51ff3120d6a6683ba8684432
+size 4984