Training in progress, epoch 2

logs/events.out.tfevents.1709718777.adc675a344d5.67573.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d745bcdeefaa5fcf0d992d30806763a0fd865c8f3f00622e1ea794f94f4a153
-size 5315
+oid sha256:0f74c7f4bbbf539916499b6f7a0294a8df410211b8a2b9e80dcc0f171e6fe790
+size 5998

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490f0363ce94024364841fd7a0a06bf8589adbba7a9ab31207817f7711e2a787
+oid sha256:d4f01d5dab37e1e8fef2f5b1537216c3563f941204a503f30cf966cb78acb2f3
 size 17549312

run-6/checkpoint-192/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f01d5dab37e1e8fef2f5b1537216c3563f941204a503f30cf966cb78acb2f3
+size 17549312

run-6/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b399d78dcf4c34bd4f3b66c0c644a2f6d3403a84acd6b59ab9c7429d12c06d8
+size 35122746

run-6/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+size 14054

run-6/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e23a83d5e78f92cb65215e1b8246a0684e8bc0adc57405a2d9715be2c80568
+size 1064

run-6/checkpoint-192/special_tokens_map.json

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

run-6/checkpoint-192/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-6/checkpoint-192/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.7925636007827789,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/checkpoint-192",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7334731817245483,
+      "learning_rate": 0.00019089508944155825,
+      "loss": 0.4515,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.761252446183953,
+      "eval_f1": 0.7676190476190476,
+      "eval_loss": 0.40420547127723694,
+      "eval_precision": 0.7476808905380334,
+      "eval_recall": 0.7886497064579256,
+      "eval_runtime": 28.5902,
+      "eval_samples_per_second": 35.747,
+      "eval_steps_per_second": 1.119,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9262505769729614,
+      "learning_rate": 0.00015907924120129856,
+      "loss": 0.3979,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7925636007827789,
+      "eval_f1": 0.800376647834275,
+      "eval_loss": 0.38181060552597046,
+      "eval_precision": 0.7713248638838476,
+      "eval_recall": 0.8317025440313112,
+      "eval_runtime": 28.4377,
+      "eval_samples_per_second": 35.938,
+      "eval_steps_per_second": 1.125,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 672,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6366473529685639,
+    "learning_rate": 0.00022271093768181798,
+    "num_train_epochs": 7,
+    "temperature": 14
+  }
+}

run-6/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11cd627d32c55435bd1d55cca3ffe9ac8a08ee3c4b43c65b7e3f22d01d249f85
+size 4920