Training in progress, epoch 4

logs/events.out.tfevents.1713441164.ec9626078864.14834.42

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa6f3d3584d24089c8cd59255e0560138ed1546bdf6e75d148af4d0d81cd56b
-size 6867
+oid sha256:a9bdebb75b1f1b0c596417a80a6d09d7bc6077791b536d2c8d12a8a86015bff5
+size 7597

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78adfbef90cbc1f6c100081fee41aa6ffd0e6534d6e07ea350a8896f14e2f7ce
+oid sha256:c212da5e78b3dc0916d6b3ec544ffcc87266d951703399a5ae8cdb9816885a70
 size 17549312

run-41/checkpoint-2580/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-41/checkpoint-2580/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c212da5e78b3dc0916d6b3ec544ffcc87266d951703399a5ae8cdb9816885a70
+size 17549312

run-41/checkpoint-2580/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142d33cb7a48d301be0926c7a623f52d7248d7f6e5b06ddbadfb3011bdc14262
+size 35123898

run-41/checkpoint-2580/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a023a654d9d331ee734f6327c4a0681d27975c593b68916f513cbf43ea84370
+size 14308

run-41/checkpoint-2580/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86107d141ef9b5fdac0c703d17e97c5c1e599c47e70bfffc9e79d76274a7e975
+size 1064

run-41/checkpoint-2580/special_tokens_map.json

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

run-41/checkpoint-2580/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-41/checkpoint-2580/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9001550988755331,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-41/checkpoint-2580",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2580,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1879228353500366,
+      "learning_rate": 0.0001500473390748166,
+      "loss": 0.31,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8937572702597906,
+      "eval_f1": 0.1189710610932476,
+      "eval_loss": 0.288364440202713,
+      "eval_mcc": 0.19117679563293483,
+      "eval_precision": 0.6981132075471698,
+      "eval_recall": 0.06502636203866433,
+      "eval_runtime": 9.9344,
+      "eval_samples_per_second": 519.205,
+      "eval_steps_per_second": 16.307,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5299654006958008,
+      "learning_rate": 0.00012861200492127138,
+      "loss": 0.2852,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8978286157425359,
+      "eval_f1": 0.20030349013657056,
+      "eval_loss": 0.2860374450683594,
+      "eval_mcc": 0.2650150871029742,
+      "eval_precision": 0.7333333333333333,
+      "eval_recall": 0.11599297012302284,
+      "eval_runtime": 9.9216,
+      "eval_samples_per_second": 519.878,
+      "eval_steps_per_second": 16.328,
+      "step": 1290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.777714729309082,
+      "learning_rate": 0.00010717667076772616,
+      "loss": 0.2784,
+      "step": 1935
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8984102365257852,
+      "eval_f1": 0.19384615384615386,
+      "eval_loss": 0.27609962224960327,
+      "eval_mcc": 0.26911180968873705,
+      "eval_precision": 0.7777777777777778,
+      "eval_recall": 0.11072056239015818,
+      "eval_runtime": 9.9163,
+      "eval_samples_per_second": 520.153,
+      "eval_steps_per_second": 16.337,
+      "step": 1935
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.847649097442627,
+      "learning_rate": 8.574133661418092e-05,
+      "loss": 0.2737,
+      "step": 2580
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9001550988755331,
+      "eval_f1": 0.31057563587684067,
+      "eval_loss": 0.27698394656181335,
+      "eval_mcc": 0.3267057277830052,
+      "eval_precision": 0.651685393258427,
+      "eval_recall": 0.2038664323374341,
+      "eval_runtime": 9.9379,
+      "eval_samples_per_second": 519.024,
+      "eval_steps_per_second": 16.301,
+      "step": 2580
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 6347770130400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.886564686264361,
+    "learning_rate": 0.00017148267322836185,
+    "num_train_epochs": 8,
+    "temperature": 15
+  }
+}

run-41/checkpoint-2580/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdec132d1ee47713f9969a512f129a126f5c53f2ad8f57d6f193b73d3904ac8f
+size 4984