Training in progress, epoch 2

logs/events.out.tfevents.1700097911.0ef7b67c0c07.8576.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ed3bd33dedf54f8dbec4b2811abe79edd0f5585a04168b4c2e841dfbe96b71
-size 4774
+oid sha256:1dd709c32505d7a7864690ec816eff74d102fb8e2647365c9451d1047ffcff06
+size 5254

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0384a7e788e01cfc1a0a496c74d1a709c2c10fb868d0c3cb533a0156c1c397cc
+oid sha256:fdcb79d03e36e8724a017eb5d8410cd9f760de06381973b7af7eaedc06d351d2
 size 17549312

run-1/checkpoint-1054/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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcb79d03e36e8724a017eb5d8410cd9f760de06381973b7af7eaedc06d351d2
+size 17549312

run-1/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de1d5932bd1e57484d5aac6f665b0a76e57e552fe2ba7066e11351032927606
+size 35123898

run-1/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257145d19710cbf39344544002ce35377faa97e289b8c6f1104c9033e98d4161
+size 14308

run-1/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f226365d73eaf2b522c90f11a9598134b1bfbe2948fc0fd50ffaecb0853ec7
+size 1064

run-1/checkpoint-1054/special_tokens_map.json

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

run-1/checkpoint-1054/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-1/checkpoint-1054/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.823394495412844,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-527",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00014946971324611056,
+      "loss": 2.145,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.8049757480621338,
+      "eval_runtime": 2.6317,
+      "eval_samples_per_second": 331.345,
+      "eval_steps_per_second": 2.66,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013079042966045718,
+      "loss": 0.9755,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.9008780717849731,
+      "eval_runtime": 2.6239,
+      "eval_samples_per_second": 332.334,
+      "eval_steps_per_second": 2.668,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 16194449161860.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.052937085110831505,
+    "learning_rate": 0.00016811355227088032,
+    "num_train_epochs": 9,
+    "temperature": 28
+  }
+}

run-1/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9778c4a9b9e0841a37887d1e9944802b8b476bac60a9e2178954f797fa2f6f75
+size 4664