Training in progress, epoch 1

logs/events.out.tfevents.1699953304.45c71320b2c6.349.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b86dd29bcedb744226d739672726bd9429ba75cf823ff0ca813caa9839d6b31
+size 4772

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387804aaac1307a0dda54cd2e3a850e98c4eccc790302d5218e69a5045f5e231
+oid sha256:7c46b48f73ddb7840f4804498cc01b69dcb4cf934318a055b997d1a14d95ca47
 size 17549312

run-22/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-22/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c46b48f73ddb7840f4804498cc01b69dcb4cf934318a055b997d1a14d95ca47
+size 17549312

run-22/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067c4f3cf0316618c4e743674fc1c9daee1e86a4a93271cd36d47e787c72e050
+size 35123898

run-22/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
+size 14308

run-22/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1e8a7ebc5a9553e9173b558c6f9b095a2f64eab07b11147daeb5e688108473
+size 1064

run-22/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-22/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-22/checkpoint-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8176605504587156,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/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,
+      "learning_rate": 0.000320734933434032,
+      "loss": 1.0808,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 1.2343355417251587,
+      "eval_runtime": 0.8412,
+      "eval_samples_per_second": 1036.59,
+      "eval_steps_per_second": 8.321,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1581,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4891386871509458,
+    "learning_rate": 0.000481102400151048,
+    "num_train_epochs": 3,
+    "temperature": 30
+  }
+}

run-22/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fc2d78262a65b3f93f6c8dfdc1c6b72e555a43a57229fea5a3a48e48fe8653
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f567c625879c30dcc813883119961ee81cc8406afa56e743fbc3a4cb7486ba7
+oid sha256:14fc2d78262a65b3f93f6c8dfdc1c6b72e555a43a57229fea5a3a48e48fe8653
 size 4664