Training in progress, epoch 1

logs/events.out.tfevents.1706249191.A-FVFFG2C4Q05P.18450.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd4c98722af83f9cd7065f3fd5cfcacdfcac48df3dc0e783e0ec52fb1acd051
-size 6836
+oid sha256:fdcd42daa136fe8519540756bd62979a83acbaec9a5c9fc5d8254f1e236a717f
+size 9110

logs/events.out.tfevents.1706255967.A-FVFFG2C4Q05P.18450.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a53cff59c56eccfc3140c8f042ece607e14a86f9879d2cbf9e00110325ac57
+size 4916

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45e54c68134b07329ebc8d713846f3b955a30406885d185b73d22e069d4130d
+oid sha256:b8104b43e1ff981c627302fe90303061144ca4ca2303da8a646f6b76ba1e3aa2
 size 17549312

run-18/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-18/checkpoint-4743/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f71d0ed4873b51f977b3f71c99e0060df817dbdc20e60906b715c2c5277f79a
+size 17549312

run-18/checkpoint-4743/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a267e9ef89a5b1528bcc1d8725360b2407b195cde2f3de49f1a405f6e5b1ff
+size 35122373

run-18/checkpoint-4743/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e213b9ff178552aa357195f6c9b9ab9b2dd2939ab6f17cc6cea934aabceeb6f8
+size 13617

run-18/checkpoint-4743/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f624afb3695e747210fc31ba13be424f31b85325b23ce8b6597856c329631eb
+size 627

run-18/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-18/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-18/checkpoint-4743/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": 0.8337155963302753,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/checkpoint-2108",
+  "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": 0.00014893639687145338,
+      "loss": 0.8667,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 0.8296506404876709,
+      "eval_runtime": 6.9326,
+      "eval_samples_per_second": 125.782,
+      "eval_steps_per_second": 1.01,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013031934726252174,
+      "loss": 0.4473,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.9700397849082947,
+      "eval_runtime": 7.0917,
+      "eval_samples_per_second": 122.961,
+      "eval_steps_per_second": 0.987,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00011170229765359004,
+      "loss": 0.3367,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.971959114074707,
+      "eval_runtime": 7.4513,
+      "eval_samples_per_second": 117.027,
+      "eval_steps_per_second": 0.939,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.308524804465839e-05,
+      "loss": 0.2772,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.9656078219413757,
+      "eval_runtime": 7.1382,
+      "eval_samples_per_second": 122.16,
+      "eval_steps_per_second": 0.981,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.446819843572669e-05,
+      "loss": 0.2345,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.0300672054290771,
+      "eval_runtime": 7.485,
+      "eval_samples_per_second": 116.5,
+      "eval_steps_per_second": 0.935,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 5.585114882679502e-05,
+      "loss": 0.2064,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.020656704902649,
+      "eval_runtime": 7.1445,
+      "eval_samples_per_second": 122.052,
+      "eval_steps_per_second": 0.98,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.7234099217863346e-05,
+      "loss": 0.1846,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.0487580299377441,
+      "eval_runtime": 7.1258,
+      "eval_samples_per_second": 122.372,
+      "eval_steps_per_second": 0.982,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.8617049608931673e-05,
+      "loss": 0.1712,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 1.0559272766113281,
+      "eval_runtime": 7.1081,
+      "eval_samples_per_second": 122.677,
+      "eval_steps_per_second": 0.985,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.0,
+      "loss": 0.16,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.0831522941589355,
+      "eval_runtime": 7.1677,
+      "eval_samples_per_second": 121.656,
+      "eval_steps_per_second": 0.977,
+      "step": 4743
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 72808011721980.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7585638468345914,
+    "learning_rate": 0.00016755344648038508,
+    "num_train_epochs": 9,
+    "temperature": 8
+  }
+}

run-18/checkpoint-4743/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbd4682b40d5fae102c1795c728b50c70c76c7e268fdc70a102dfd6332bccba
+size 4283

run-19/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-19/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8104b43e1ff981c627302fe90303061144ca4ca2303da8a646f6b76ba1e3aa2
+size 17549312

run-19/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9c30f81214020b331ac222dae32f587736f45b30fcaa1182f0953e61f81baa
+size 35122373

run-19/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f943a8d8f93fea7f44cad3b9bfb2d2b97d65b141eb704b9cba669cf42e776b14
+size 13617

run-19/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c488be9d46d7ca315b237e312fd8eb7a538a2299aefdb5fb8d7aa7c3518b8c0
+size 627

run-19/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-19/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-19/checkpoint-527/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.823394495412844,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-19/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": 0.0001543009451614587,
+      "loss": 0.7761,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.7534914016723633,
+      "eval_runtime": 6.3767,
+      "eval_samples_per_second": 136.747,
+      "eval_steps_per_second": 1.098,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 8069051778960.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7643956095002787,
+    "learning_rate": 0.00018516113419375044,
+    "num_train_epochs": 6,
+    "temperature": 5
+  }
+}

run-19/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03358da370598853b4d67813a0f88223247ad38cde69c687e74f501a1a601607
+size 4283

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dbd4682b40d5fae102c1795c728b50c70c76c7e268fdc70a102dfd6332bccba
+oid sha256:03358da370598853b4d67813a0f88223247ad38cde69c687e74f501a1a601607
 size 4283