Training in progress, epoch 2

logs/events.out.tfevents.1713587703.1376c752d37a.9760.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ada4355fe30e825ab656e360b44fe26ab761ee0b5da13ed5e33c78b96ee30b
-size 5483
+oid sha256:64ee3976d5e0bd81820b27e7535795b535b15d9f8f89a4f21961891fffee2f61
+size 6213

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4676219f8ec0244853702428076b5883a44a22312686b7e456590e0158fd4b
+oid sha256:af5e7a82abd03878f588793986eb244c51243c6303cea3a5259a4b4d9971fd43
 size 17549312

run-9/checkpoint-428/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-9/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5e7a82abd03878f588793986eb244c51243c6303cea3a5259a4b4d9971fd43
+size 17549312

run-9/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f733eb37046a5dfa051a43f4cbbad8c81ae2d81937bcbe7129250ae962b80998
+size 35123898

run-9/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
+size 14308

run-9/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fa4f7ae5a732919f667a9cc9cb5317273dd0cc6e408a473e31574c29096ca3
+size 1064

run-9/checkpoint-428/special_tokens_map.json

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

run-9/checkpoint-428/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-9/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7375512595196251,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.803707122802734,
+      "learning_rate": 0.00012883203919617986,
+      "loss": 0.5857,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7106033977738723,
+      "eval_f1": 0.4665226781857451,
+      "eval_loss": 0.5316944122314453,
+      "eval_mcc": 0.2963991807057883,
+      "eval_precision": 0.6050420168067226,
+      "eval_recall": 0.37961335676625657,
+      "eval_runtime": 3.1407,
+      "eval_samples_per_second": 543.517,
+      "eval_steps_per_second": 17.194,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.514796733856201,
+      "learning_rate": 0.00010736003266348323,
+      "loss": 0.5209,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7375512595196251,
+      "eval_f1": 0.5343035343035344,
+      "eval_loss": 0.5052611827850342,
+      "eval_mcc": 0.37194852790942917,
+      "eval_precision": 0.6539440203562341,
+      "eval_recall": 0.45166959578207383,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 543.345,
+      "eval_steps_per_second": 17.188,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1049551328880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9569611105058125,
+    "learning_rate": 0.00015030404572887653,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-9/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fea319273d6fad4c679e9197d2d5d7068b8b820132928c6cc3b76d4197ed182
+size 5048