Training in progress, epoch 9

logs/events.out.tfevents.1701752681.joseph_legion.10272.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828d40b041dd1233d0c7949a403872d0d07ff659eacf6a837c3cd2557229085e
-size 8135
+oid sha256:a4f2f117a22160bea0fab1b93e388a89cd5bac03a062d44a503dc1cc734c2964
+size 8615

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a2ca90e7d8a120ba623c5ec4d9e8d992dbf718f4f81ff9fdf441189f06a576
+oid sha256:ade0197b9d4f319c45bc9a16c02d87d798f85d10f48a66f567186e3a44803390
 size 17549312

run-0/checkpoint-4743/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-0/checkpoint-4743/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade0197b9d4f319c45bc9a16c02d87d798f85d10f48a66f567186e3a44803390
+size 17549312

run-0/checkpoint-4743/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ed66379c296f3ff3d02f9a778924839acd343a801974a4850f6899edebdb29
+size 35123898

run-0/checkpoint-4743/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8bcb2fa6bd8c13426a639023053f8220e215b473e00dac43aa2273f2e397eab
+size 14308

run-0/checkpoint-4743/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8996203501904cc6d705fa613e61b19f57f296793e3776cb6932dda7f407fd6c
+size 1064

run-0/checkpoint-4743/special_tokens_map.json

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

run-0/checkpoint-4743/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-0/checkpoint-4743/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": 0.8153669724770642,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-0\\checkpoint-4216",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 4743,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0006568555243553003,
+      "loss": 0.9823,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.3724825382232666,
+      "eval_runtime": 1.7972,
+      "eval_samples_per_second": 485.194,
+      "eval_steps_per_second": 3.895,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0005838715772047113,
+      "loss": 0.4476,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 1.3287416696548462,
+      "eval_runtime": 1.7495,
+      "eval_samples_per_second": 498.417,
+      "eval_steps_per_second": 4.001,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0005108876300541224,
+      "loss": 0.2956,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 1.4336999654769897,
+      "eval_runtime": 1.943,
+      "eval_samples_per_second": 448.795,
+      "eval_steps_per_second": 3.603,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0004379036829035335,
+      "loss": 0.2249,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.5175449848175049,
+      "eval_runtime": 1.8297,
+      "eval_samples_per_second": 476.582,
+      "eval_steps_per_second": 3.826,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0003649197357529446,
+      "loss": 0.1785,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.4446643590927124,
+      "eval_runtime": 1.7803,
+      "eval_samples_per_second": 489.8,
+      "eval_steps_per_second": 3.932,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0002919357886023557,
+      "loss": 0.1453,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 1.5748971700668335,
+      "eval_runtime": 1.8056,
+      "eval_samples_per_second": 482.953,
+      "eval_steps_per_second": 3.877,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00021895184145176674,
+      "loss": 0.126,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 1.5490596294403076,
+      "eval_runtime": 1.8202,
+      "eval_samples_per_second": 479.074,
+      "eval_steps_per_second": 3.846,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00014596789430117784,
+      "loss": 0.1041,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 1.499665379524231,
+      "eval_runtime": 1.7762,
+      "eval_samples_per_second": 490.924,
+      "eval_steps_per_second": 3.941,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 7.298394715058892e-05,
+      "loss": 0.092,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_loss": 1.5526666641235352,
+      "eval_runtime": 1.7756,
+      "eval_samples_per_second": 491.105,
+      "eval_steps_per_second": 3.942,
+      "step": 4743
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 72834327181080.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5351224538156584,
+    "learning_rate": 0.0007298394715058892,
+    "num_train_epochs": 10,
+    "temperature": 24
+  }
+}

run-0/checkpoint-4743/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8a46880b57d8b0b9e418b052abbb3948b438121f71f7c4ea0a153d96e30889
+size 4664