Training in progress, epoch 1

logs/events.out.tfevents.1711297478.8cc2eef2edb7.2942.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce0a4815cb92ce67da2db5ebb61f95dca21d81a6fbcd325f2a4ca10d224fa0b
-size 5406
+oid sha256:6355d460459e415b4e008a5014c1837248850fae6827dc451f4b6256cfbd008c
+size 6136

logs/events.out.tfevents.1711297517.8cc2eef2edb7.2942.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83faa7bff79ec7aefb054f243e8f378873ee9df8237e1f57ee3544c9410fb296
+size 5408

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72048966fe81dc5e8ef70a94b006d8d8b0733227ba1aa895b63d164364e2b3be
+oid sha256:c64c6a28bc7f30b9890b5e97ddeee5599b2c0fcd7b7d1b1051fe1f1869be56e4
 size 17549312

run-9/checkpoint-297/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-9/checkpoint-297/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64c6a28bc7f30b9890b5e97ddeee5599b2c0fcd7b7d1b1051fe1f1869be56e4
+size 17549312

run-9/checkpoint-297/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c248e9f219d3273c9d60b8df57d41a04250d96ceacc32edee94db3a84dc607d
+size 35123898

run-9/checkpoint-297/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
+size 14308

run-9/checkpoint-297/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40a3aa8f61e2686209f05264ccd5ed6f862a79351755819d6ddf47ba9ebd235
+size 1064

run-9/checkpoint-297/special_tokens_map.json

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

run-9/checkpoint-297/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-9/checkpoint-297/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5108910891089109,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-297",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 297,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9651498198509216,
+      "learning_rate": 0.0001109020423696917,
+      "loss": 0.2922,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5108910891089109,
+      "eval_f1": 0.13333333333333333,
+      "eval_loss": 0.28215324878692627,
+      "eval_mcc": 0.04058654139490483,
+      "eval_precision": 0.5757575757575758,
+      "eval_recall": 0.07539682539682539,
+      "eval_runtime": 0.9382,
+      "eval_samples_per_second": 538.244,
+      "eval_steps_per_second": 17.053,
+      "step": 297
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 730701265980.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3502992230885441,
+    "learning_rate": 0.00012322449152187966,
+    "num_train_epochs": 10,
+    "temperature": 8
+  }
+}

run-9/checkpoint-297/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f96baad28063e07ee02c90f12fb0709604394a8c6151ec82813622f7cfde881
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782b721b0f5a4f9b3d592f4dc5b34b82a1ad0a98a12b31e9f254049de6fd6f96
+oid sha256:8f96baad28063e07ee02c90f12fb0709604394a8c6151ec82813622f7cfde881
 size 4920