Training in progress, epoch 3

logs/events.out.tfevents.1711299333.8cc2eef2edb7.2942.44

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d651072f8b9b5191dd5e0d7b5f6daaaddcf8a46f80a8026ce98cebf766f26fd
-size 6137
+oid sha256:ee3835beab189a21569c4b4fa98817c5430b9fab60c840475e0d783520eb3592
+size 6867

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31decd0352ea2cc431caf0a33ee1a3d682ae0d49843bac98638cc8fa691b8cb6
+oid sha256:feb642c76700f2ce108f44e1b929f8a8b9f0dbbc083a47693a341fc83ab098ff
 size 17549312

run-44/checkpoint-891/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-44/checkpoint-891/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb642c76700f2ce108f44e1b929f8a8b9f0dbbc083a47693a341fc83ab098ff
+size 17549312

run-44/checkpoint-891/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6e0d886a92c21de6d184da628bb3540b101f8f6fc702420368e4c04bb0efaa
+size 35123898

run-44/checkpoint-891/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b689ca5add5bd2b3024a96e15979227e5788dfce70568554fb1702c585abab
+size 14308

run-44/checkpoint-891/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0382e1cdf3ec5f47903947b8aff9ce031e5753abcdcd3bc6b92377fdec51ad80
+size 1064

run-44/checkpoint-891/special_tokens_map.json

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

run-44/checkpoint-891/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-44/checkpoint-891/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.6772277227722773,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-44/checkpoint-891",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 891,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.536985993385315,
+      "learning_rate": 0.0001924744581380813,
+      "loss": 0.6378,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5326732673267327,
+      "eval_f1": 0.39175257731958757,
+      "eval_loss": 0.6261491775512695,
+      "eval_mcc": 0.07262518750715272,
+      "eval_precision": 0.5588235294117647,
+      "eval_recall": 0.30158730158730157,
+      "eval_runtime": 0.9367,
+      "eval_samples_per_second": 539.146,
+      "eval_steps_per_second": 17.082,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5330690145492554,
+      "learning_rate": 0.00015397956651046503,
+      "loss": 0.6119,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6554455445544555,
+      "eval_f1": 0.6824817518248175,
+      "eval_loss": 0.5914366841316223,
+      "eval_mcc": 0.31595686996005884,
+      "eval_precision": 0.6317567567567568,
+      "eval_recall": 0.7420634920634921,
+      "eval_runtime": 0.9379,
+      "eval_samples_per_second": 538.418,
+      "eval_steps_per_second": 17.059,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.7286975383758545,
+      "learning_rate": 0.00011548467488284878,
+      "loss": 0.5882,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6772277227722773,
+      "eval_f1": 0.7296849087893864,
+      "eval_loss": 0.5896957516670227,
+      "eval_mcc": 0.38579394462448086,
+      "eval_precision": 0.6267806267806267,
+      "eval_recall": 0.873015873015873,
+      "eval_runtime": 0.9307,
+      "eval_samples_per_second": 542.595,
+      "eval_steps_per_second": 17.191,
+      "step": 891
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 2192103797940.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8986952116548445,
+    "learning_rate": 0.00023096934976569756,
+    "num_train_epochs": 6,
+    "temperature": 24
+  }
+}

run-44/checkpoint-891/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2796d57e689bc2d20480ee4550b61113ad9a81ae748faa193ff9f596e1a0acd
+size 4920