Training in progress, epoch 1

logs/events.out.tfevents.1711304801.73e3a81c01ef.4225.41

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e91cbc3e5fbf6748cdb24d2a228a22bb16c7d71ef551e1a222bfae053e0bed
+size 5407

logs/events.out.tfevents.1711305082.73e3a81c01ef.4225.42

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b0318d3aec86b6f9b332f71f247eb5c4e52d650c3bed116c2f4118a8342350
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37b46f809be7637226b117d7d5fd64179492b64b28949537075c7d42ad6ee5ef
+oid sha256:cba9d44cc26a534b44a89dcf28fe58b0bef3207c59033a469b45cbbc740e91f8
 size 17549312

run-42/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-42/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba9d44cc26a534b44a89dcf28fe58b0bef3207c59033a469b45cbbc740e91f8
+size 17549312

run-42/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a9524464f152553311487e92d4ccd27c428f17e9b7ef8c88899f87b973d05d
+size 35122746

run-42/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
+size 14054

run-42/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47d7eb50efbc06f7a77880ad4deb7f45da55280c2daba7a52e0308ce279a562
+size 1064

run-42/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-42/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-42/checkpoint-192/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.8033268101761253,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-42/checkpoint-192",
+  "epoch": 1.0,
+  "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": 3.1318306922912598,
+      "learning_rate": 0.0001222965835274321,
+      "loss": 0.5547,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8033268101761253,
+      "eval_f1": 0.8076555023923445,
+      "eval_loss": 0.4663587808609009,
+      "eval_mcc": 0.607269059552277,
+      "eval_precision": 0.7902621722846442,
+      "eval_recall": 0.8258317025440313,
+      "eval_runtime": 66.9367,
+      "eval_samples_per_second": 15.268,
+      "eval_steps_per_second": 0.478,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 384,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.946682979258311,
+    "learning_rate": 0.0002445931670548642,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "temperature": 14
+  }
+}

run-42/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09f6e3007799f4d90af21ec2c7261c6a15eb8e5c390bbc135f1f4ce7735edeb
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9eb176719296b7eda907810ef79c5712ba925be55e9de51dc1da95d3b26e91c
+oid sha256:f09f6e3007799f4d90af21ec2c7261c6a15eb8e5c390bbc135f1f4ce7735edeb
 size 4984