Training in progress, epoch 1

logs/events.out.tfevents.1719238510.f94f01b9b918.2392.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61c7ea9eebdf2c466355de8871dead7312023b5e58b7d22f8c4570fed7b1004
-size 8082
+oid sha256:902d79782222116c03df19b55720fb41c602d9056b418976dc68068f0045c3b6
+size 8970

logs/events.out.tfevents.1719239773.f94f01b9b918.2392.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455eae2b3fc0233166363b7e82fc59f25dbe5bfefad95a96c8c97fa621a194db
+size 5428

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a13836289e6eefc86cb0f2b9483433924e24598a29d2746c3e5a0a19b1e62ed
+oid sha256:7f7788cab7841f4a2f3693dc0c0ee6f814742ac5ce16528a51f55dad86befccf
 size 17549312

run-0/checkpoint-527/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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7788cab7841f4a2f3693dc0c0ee6f814742ac5ce16528a51f55dad86befccf
+size 17549312

run-0/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f84bb8008e162dd46d32fa4ebb51a54d7b995433819da88db2eaf40d2b42793
+size 35123898

run-0/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
+size 14308

run-0/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5456c00e41cc97e97f791dcd94d7d9bfdced990f7de7a36119b3adedfff1dc
+size 1064

run-0/checkpoint-527/special_tokens_map.json

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

run-0/checkpoint-527/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-0/checkpoint-527/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8061926605504587,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.55626678466797,
+      "learning_rate": 5.1383294230414005e-05,
+      "loss": 1.5907,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 1.2464169263839722,
+      "eval_runtime": 2.4007,
+      "eval_samples_per_second": 363.232,
+      "eval_steps_per_second": 2.916,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5167874928728581,
+    "learning_rate": 5.872376483475886e-05,
+    "num_train_epochs": 8,
+    "temperature": 5
+  }
+}

run-0/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28149fe21091b257234d7cbe1611ee6ca88e3a7cef675e40e6d90410e6fc1a6
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5545da457be455b9fa669b75066fa81388bce5bf3c53a14ec99db8d75316339b
+oid sha256:f28149fe21091b257234d7cbe1611ee6ca88e3a7cef675e40e6d90410e6fc1a6
 size 5176