Training in progress, epoch 1

logs/events.out.tfevents.1709698885.a2333cf40ebd.21010.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eeeae1cf4bd1c4385d65776fd394417a48d71605fdbdf861474c4cd42fa3735
-size 5314
+oid sha256:594c61336eef6cb803fd88c4b3ac045afad37a3e181816501de20c0c698646be
+size 5997

logs/events.out.tfevents.1709699116.a2333cf40ebd.21010.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b55eba6e2336b83fd44fe038aaa899dfc2eb5d8626b122b1fb32e5c24a338b
+size 5315

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3d5013c372a5947b32b031143fbc7101dda946be4238065d68dc49617514d5
+oid sha256:84bec5042b87086a45dca7b3c56d04cf79d83ed1b52a762adc677152de33272c
 size 17549312

run-8/checkpoint-96/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-8/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84bec5042b87086a45dca7b3c56d04cf79d83ed1b52a762adc677152de33272c
+size 17549312

run-8/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da6291d75080430d6c4ab323e31c11d497e573a325f8f4db8e787327b6178a6
+size 35122746

run-8/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
+size 14054

run-8/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d32b52b4cbac032624e075d8b37b40470a77d3ab11ecb407b7b2017aefcbcc
+size 1064

run-8/checkpoint-96/special_tokens_map.json

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

run-8/checkpoint-96/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-8/checkpoint-96/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.5,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-96",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.41845789551734924,
+      "learning_rate": 1.3576479969391517e-05,
+      "loss": 0.1501,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.0910131111741066,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 28.1809,
+      "eval_samples_per_second": 36.266,
+      "eval_steps_per_second": 1.136,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.06528729720326021,
+    "learning_rate": 1.6970599961739396e-05,
+    "num_train_epochs": 5,
+    "temperature": 4
+  }
+}

run-8/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669b7645cf6dd2271363aa4a300b453105055ad2059ef2460a17a64f32148151
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6414f6be732ee57073e5f592a5247b185b7396f73a2b3657516052a59ffee832
+oid sha256:669b7645cf6dd2271363aa4a300b453105055ad2059ef2460a17a64f32148151
 size 4920