Training in progress, epoch 2

logs/events.out.tfevents.1714700864.e992b94a7c88.3982.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2bf606e47b4aeeff0d05e888fe0285e07dda271a52098b247e12eb99379d851
-size 5483
+oid sha256:ce97a01e2dbed207bc6a2f7a4eeae8cb23df77714733c22575102cf9142154ef
+size 6213

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c125813a4956316ef095cd7066585d0221614128db53d055c3f9db6535cb1d
+oid sha256:3f02ecbdb99c3e1b4b64203d0713d517f195a3bac2a345f70c61ae81814d6489
 size 17549312

run-2/checkpoint-3176/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-3176/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f02ecbdb99c3e1b4b64203d0713d517f195a3bac2a345f70c61ae81814d6489
+size 17549312

run-2/checkpoint-3176/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7752e909a34b43a9f352a82599dd0599c9746d32d6111b2982261637dbaabec8
+size 35123898

run-2/checkpoint-3176/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a5639c0ad118ba9a8c782a537e44e599d8a964db5e9d2de1ad5a8f5134ec48
+size 14308

run-2/checkpoint-3176/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0446a541590ea44fc846768df43ea6c5582af89ea02616fc7a0e7bd71b864a3
+size 1064

run-2/checkpoint-3176/special_tokens_map.json

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

run-2/checkpoint-3176/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-2/checkpoint-3176/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6666929009916575,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-1588",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3176,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5482791066169739,
+      "learning_rate": 9.642076934385773e-06,
+      "loss": 0.5031,
+      "step": 1588
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666929009916575,
+      "eval_f1": 0.0,
+      "eval_loss": 0.49551922082901,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 23.2895,
+      "eval_samples_per_second": 545.567,
+      "eval_steps_per_second": 17.089,
+      "step": 1588
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0544217824935913,
+      "learning_rate": 8.436817317587551e-06,
+      "loss": 0.4941,
+      "step": 3176
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6666929009916575,
+      "eval_f1": 0.0,
+      "eval_loss": 0.48784464597702026,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 23.5003,
+      "eval_samples_per_second": 540.673,
+      "eval_steps_per_second": 16.936,
+      "step": 3176
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 7817788152600.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7681424055105933,
+    "learning_rate": 1.0847336551183995e-05,
+    "num_train_epochs": 9,
+    "temperature": 16
+  }
+}

run-2/checkpoint-3176/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af62eff3e380aae108292c73f008f9877e2ad7abffa7d67edf7a00b8980fb10b
+size 4984