Training in progress, epoch 3

logs/events.out.tfevents.1701758098.joseph_legion.10272.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fafe238f874b90713911fad5ed614314ad0335c421dc65d8aee4499d955bd9a
-size 5255
+oid sha256:33c0e2f24c9d99b2f69842905a2cc400074e3f3b6823e1e10da0fcadad9b8461
+size 5735

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87945423296251d4fd569bd263891bbaf7cec91881c4736611d61c5a69dee2dd
+oid sha256:f1e4a23fd476ebb8e1bf6e7cf9efd8daaf51a91944df82b620f4ab2b2ea001de
 size 17549312

run-11/checkpoint-1581/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-11/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e4a23fd476ebb8e1bf6e7cf9efd8daaf51a91944df82b620f4ab2b2ea001de
+size 17549312

run-11/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d801db2f809402c5b2fa1ac0e59e5d45e0641833df7fa1d5e5091742ad3bab
+size 35123898

run-11/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53765ad23da24706e731ce61d5accccafd402ac6b818a36d6ccba54c7e99b054
+size 14308

run-11/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d814199eda89477519c96d47810be66e4d57a435915711863337e9c599c498
+size 1064

run-11/checkpoint-1581/special_tokens_map.json

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

run-11/checkpoint-1581/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-11/checkpoint-1581/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.8302752293577982,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-11\\checkpoint-1054",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1581,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00018146994805344583,
+      "loss": 0.5299,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.5735568404197693,
+      "eval_runtime": 1.6581,
+      "eval_samples_per_second": 525.898,
+      "eval_steps_per_second": 4.222,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001555456697600964,
+      "loss": 0.2972,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.6297323703765869,
+      "eval_runtime": 1.6463,
+      "eval_samples_per_second": 529.683,
+      "eval_steps_per_second": 4.252,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.000129621391466747,
+      "loss": 0.2227,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.7183768153190613,
+      "eval_runtime": 1.7083,
+      "eval_samples_per_second": 510.435,
+      "eval_steps_per_second": 4.098,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 24250810958940.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7309291121922327,
+    "learning_rate": 0.00020739422634679522,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-11/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145839f54a5a626f3e4088fabae28ecd1671f8911e84c67f5728017d401bb3fe
+size 4664