Training in progress, epoch 1

logs/events.out.tfevents.1709883290.6c1c016b0e3e.7263.30

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a46b2492c662bb39a405f3bd37807585ef87ad77028e72b588a149827054372
-size 5314
+oid sha256:bcf113166cfa3f2ce823ea8e78e7cda039c5d8ce9c45a0e86c8efa3ae744af11
+size 6332

logs/events.out.tfevents.1709883527.6c1c016b0e3e.7263.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946c63720529953e2be85a1694255c1f35b30dc6bc1cbc75a97cdce77e1a03cf
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00eed44cf8a96b0fa2352489e26a649f3164fb6fba762240858fc42e127ff627
+oid sha256:637f88f4ac10d8cd5d8ed682577996d08f254ad59a71bdf1ca3c4d1d72c600c2
 size 17549312

run-30/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-30/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ee2de08dc074d66cb4502c938f0526ee49270fb4fa29cd5210483becfc20e7
+size 17549312

run-30/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce2c052ba44f18d6206a7cde9bc73c34e150131b2b89f4d4ddd1099311e977b
+size 35122746

run-30/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc13e09b59a62b6fb29cad756bfeefcce6f512c71a9054cc39e336db0b532a5
+size 14054

run-30/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef347077ce6f9f10e9cc559ecc1fba5d14def3678a7bf5486de65277ad6c377a
+size 1064

run-30/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-30/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-30/checkpoint-96/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.8072407045009785,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-96",
+  "epoch": 2.0,
+  "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": 1.605053186416626,
+      "learning_rate": 0.00034121516722065634,
+      "loss": 0.5667,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7475538160469667,
+      "eval_f1": 0.792604501607717,
+      "eval_loss": 0.49347442388534546,
+      "eval_precision": 0.6725784447476125,
+      "eval_recall": 0.9647749510763209,
+      "eval_runtime": 27.2639,
+      "eval_samples_per_second": 37.486,
+      "eval_steps_per_second": 0.587,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.9404067993164062,
+      "learning_rate": 0.0,
+      "loss": 0.4806,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8072407045009785,
+      "eval_f1": 0.8233183856502243,
+      "eval_loss": 0.44217967987060547,
+      "eval_precision": 0.7599337748344371,
+      "eval_recall": 0.898238747553816,
+      "eval_runtime": 27.0528,
+      "eval_samples_per_second": 37.778,
+      "eval_steps_per_second": 0.591,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 96,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9330503881025105,
+    "learning_rate": 0.0006824303344413127,
+    "num_train_epochs": 2,
+    "temperature": 23
+  }
+}

run-30/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83fc23336837524193abc0b924ca8b0d3b3ed85e2981dd9670191b7aae665f9f
+size 4920

run-31/checkpoint-48/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-31/checkpoint-48/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637f88f4ac10d8cd5d8ed682577996d08f254ad59a71bdf1ca3c4d1d72c600c2
+size 17549312

run-31/checkpoint-48/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8530102b75b85cd599c484d82ef3e5fc19830303e9ca16e7024ca6b163bd5506
+size 35122746

run-31/checkpoint-48/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f731098665929ed6a815501631b54240caaac6508207c5c55cf0fe36ad39b17
+size 14054

run-31/checkpoint-48/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a62d138b94907251c174c345e3ae36e4ed3c28c86fb45ad4a9e901e73713852
+size 1064

run-31/checkpoint-48/special_tokens_map.json

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

run-31/checkpoint-48/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-31/checkpoint-48/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7446183953033269,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/checkpoint-48",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7282975912094116,
+      "learning_rate": 0.00030014515517910593,
+      "loss": 0.5971,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7446183953033269,
+      "eval_f1": 0.7900241351568785,
+      "eval_loss": 0.5055608749389648,
+      "eval_precision": 0.6707650273224044,
+      "eval_recall": 0.9608610567514677,
+      "eval_runtime": 27.0653,
+      "eval_samples_per_second": 37.761,
+      "eval_steps_per_second": 0.591,
+      "step": 48
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9938600685844597,
+    "learning_rate": 0.0004001935402388079,
+    "num_train_epochs": 4,
+    "temperature": 28
+  }
+}

run-31/checkpoint-48/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d8e5ab21403b6dc948eec963bb772f84f81e7ae5d32cfe70f22bbb35df8314
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83fc23336837524193abc0b924ca8b0d3b3ed85e2981dd9670191b7aae665f9f
+oid sha256:57d8e5ab21403b6dc948eec963bb772f84f81e7ae5d32cfe70f22bbb35df8314
 size 4920