Training in progress, epoch 1

logs/events.out.tfevents.1700285685.bdba95a6283e.570.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d239a4da513dede694b2811229fc86f97338872361f0e011669752fc340111
-size 5289
+oid sha256:b9e367cf4185cc6ac1a0067316a743f605ae471a8ebde0b89a5afa2297fe9c93
+size 9003

logs/events.out.tfevents.1700287458.bdba95a6283e.570.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c6e4e1bb2b462788e6461e27c55342ae411b8fa6194feaf0b65caea8917a4e
+size 4810

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c32dae09725311e3fedf28787040bfb4d508f4e793d16bcfc8667c52100506
+oid sha256:04228d8d905e0cef1773e631505f8b1499ca323f2ab321976caa6fed50d0a127
 size 17549312

run-5/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-5/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b87a831c59640363cce794e253bf39557923a2574748ede9d0ecdf84a1e4d70
+size 17549312

run-5/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a5d3badc1d1279817d763dd0e10ca372fb2020cda129acb21287eafe85bfa6
+size 35123898

run-5/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702271e787da27d0d3b72a4b86c4c100d2c46226579a1075b6bf0467661ef93f
+size 14308

run-5/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14b31cf5a5365d42e0a72347491738f6c9d01018ff9997275fd638b86bfb97f
+size 1064

run-5/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-5/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-5/checkpoint-1581/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.8222477064220184,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-5/checkpoint-1581",
+  "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": 0.0006521893115545731,
+      "loss": 1.1514,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.6072802543640137,
+      "eval_runtime": 2.6998,
+      "eval_samples_per_second": 322.982,
+      "eval_steps_per_second": 2.593,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0005706656476102516,
+      "loss": 0.5186,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 1.5554544925689697,
+      "eval_runtime": 2.7237,
+      "eval_samples_per_second": 320.153,
+      "eval_steps_per_second": 2.57,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0004892966775254068,
+      "loss": 0.3454,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.7910453081130981,
+      "eval_runtime": 2.6773,
+      "eval_samples_per_second": 325.705,
+      "eval_steps_per_second": 2.615,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 24280106603460.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.33140181919816125,
+    "learning_rate": 0.0007337129754988948,
+    "num_train_epochs": 9,
+    "temperature": 8
+  }
+}

run-5/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a07f86b5e6b9a8e9e28b1a380cc79b873a2cbfbfffbb4b2f2beac31c3225e5
+size 4664

run-5/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-5/checkpoint-4743/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2f5601d94f7ab0d2b3ab5877b3635f9968cdfc88549bc0a96020f673c60d4d
+size 17549312

run-5/checkpoint-4743/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d62c16f1866affc388be783d60a41f99cb0346e9b3e1287fc4a2ebf684cb40
+size 35123898

run-5/checkpoint-4743/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c57ce5e6b2e9f61341a63c012a7ceeecd2734f8a396f51216cd4c12a9112a1
+size 14308

run-5/checkpoint-4743/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02038442be215f5d6e3d766cfe41a1b08c0abb268ff4edfae8bc087a83d761fa
+size 1064

run-5/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-5/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-5/checkpoint-4743/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": 0.8222477064220184,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-5/checkpoint-1581",
+  "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": 0.0006521893115545731,
+      "loss": 1.1514,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.6072802543640137,
+      "eval_runtime": 2.6998,
+      "eval_samples_per_second": 322.982,
+      "eval_steps_per_second": 2.593,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0005706656476102516,
+      "loss": 0.5186,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 1.5554544925689697,
+      "eval_runtime": 2.7237,
+      "eval_samples_per_second": 320.153,
+      "eval_steps_per_second": 2.57,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0004892966775254068,
+      "loss": 0.3454,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.7910453081130981,
+      "eval_runtime": 2.6773,
+      "eval_samples_per_second": 325.705,
+      "eval_steps_per_second": 2.615,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00040777301358108515,
+      "loss": 0.2593,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 1.7951512336730957,
+      "eval_runtime": 2.7203,
+      "eval_samples_per_second": 320.554,
+      "eval_steps_per_second": 2.573,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00032624934963676347,
+      "loss": 0.2004,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.7136480808258057,
+      "eval_runtime": 2.6887,
+      "eval_samples_per_second": 324.322,
+      "eval_steps_per_second": 2.604,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00024472568569244184,
+      "loss": 0.1626,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 1.711166262626648,
+      "eval_runtime": 2.7407,
+      "eval_samples_per_second": 318.164,
+      "eval_steps_per_second": 2.554,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0001632020217481202,
+      "loss": 0.1314,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.7526990175247192,
+      "eval_runtime": 2.6978,
+      "eval_samples_per_second": 323.229,
+      "eval_steps_per_second": 2.595,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 8.167835780379854e-05,
+      "loss": 0.1125,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8142201834862385,
+      "eval_loss": 1.7434496879577637,
+      "eval_runtime": 2.7338,
+      "eval_samples_per_second": 318.966,
+      "eval_steps_per_second": 2.561,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3.0938771895378237e-07,
+      "loss": 0.0944,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.712199330329895,
+      "eval_runtime": 2.6968,
+      "eval_samples_per_second": 323.345,
+      "eval_steps_per_second": 2.596,
+      "step": 4743
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 72756683549280.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.33140181919816125,
+    "learning_rate": 0.0007337129754988948,
+    "num_train_epochs": 9,
+    "temperature": 8
+  }
+}

run-5/checkpoint-4743/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a07f86b5e6b9a8e9e28b1a380cc79b873a2cbfbfffbb4b2f2beac31c3225e5
+size 4664

run-6/checkpoint-527/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-6/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04228d8d905e0cef1773e631505f8b1499ca323f2ab321976caa6fed50d0a127
+size 17549312

run-6/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d850ddd050385d24ee9c951fa0d05c1544198740f2c17fd1c99c16f768a9a6a
+size 35123898

run-6/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df95bce5c5c16e60e49eb22753b34dbfa7966d22f239bd4ae61a5f9a0e6ccf0d
+size 14308

run-6/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b24d8a5f11cf1865cb33bf0ae12a2c6ecebc95324675cf6d56c3f62b803b096
+size 1064

run-6/checkpoint-527/special_tokens_map.json

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

run-6/checkpoint-527/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-6/checkpoint-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8222477064220184,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-6/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00011918131024105509,
+      "loss": 1.9855,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.8280006647109985,
+      "eval_runtime": 2.7111,
+      "eval_samples_per_second": 321.643,
+      "eval_steps_per_second": 2.582,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.0031432162484484882,
+    "learning_rate": 0.00023791117612513647,
+    "num_train_epochs": 2,
+    "temperature": 11
+  }
+}

run-6/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3528e6a3642aa9ba8c8067699334b10da62ccf74ac84885d7c7aecd0b8bbb683
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a07f86b5e6b9a8e9e28b1a380cc79b873a2cbfbfffbb4b2f2beac31c3225e5
+oid sha256:3528e6a3642aa9ba8c8067699334b10da62ccf74ac84885d7c7aecd0b8bbb683
 size 4664