Training in progress, epoch 1

logs/events.out.tfevents.1723126587.621b935b3e3f.593.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5069d888ab15fd866d2604c63c5674f3a2cd53ee9892c8109f076ab5408af859
-size 5986
+oid sha256:44021d8bb2f38a3002920e0f4b9de51998fcc09ec3d08acab3132499e167183a
+size 7408

logs/events.out.tfevents.1723127354.621b935b3e3f.593.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b319ba7b28af00f1311d9090014a5f88fbb07e6be562fdfec9e1a1d9b4d803
+size 5452

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d70ed5f158bf8599f4b2b3cc15b4588ac9c1dea898ba5bb48036de5eecb688
+oid sha256:58a9f75f0f120bd5b6d6e19c699abb5423fcb1e644dadd5fc3d02bec80aece0d
 size 17549312

run-2/checkpoint-2108/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-2108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6a0006699e719334c593fea102724b9f93cb4f9b64587b0f671000a6b03a28
+size 17549312

run-2/checkpoint-2108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac325a84a5abb6659e3971caf5bf40d9e7f66e027e8f2f1ee779da814ea4ea1
+size 35123898

run-2/checkpoint-2108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37554b2d10e31eaeff51183dc670fea3e7982972d731e9e9b6dff48f2395e37d
+size 14308

run-2/checkpoint-2108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99601113e80d47c6dd9d6cfd0d9efe853329cb213686cb8c2b2ed3d19e58c371
+size 1064

run-2/checkpoint-2108/special_tokens_map.json

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

run-2/checkpoint-2108/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-2/checkpoint-2108/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-527",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.61258888244629,
+      "learning_rate": 0.00029723759979073097,
+      "loss": 1.527,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.6911760568618774,
+      "eval_runtime": 2.6073,
+      "eval_samples_per_second": 334.44,
+      "eval_steps_per_second": 2.685,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.284183979034424,
+      "learning_rate": 0.00019815839986048731,
+      "loss": 0.67,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.8715265989303589,
+      "eval_runtime": 2.6081,
+      "eval_samples_per_second": 334.343,
+      "eval_steps_per_second": 2.684,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 15.639009475708008,
+      "learning_rate": 9.907919993024366e-05,
+      "loss": 0.4531,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 1.803161859512329,
+      "eval_runtime": 2.5962,
+      "eval_samples_per_second": 335.871,
+      "eval_steps_per_second": 2.696,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 16.141427993774414,
+      "learning_rate": 0.0,
+      "loss": 0.3446,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 1.8865516185760498,
+      "eval_runtime": 2.6209,
+      "eval_samples_per_second": 332.708,
+      "eval_steps_per_second": 2.671,
+      "step": 2108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 32337743850420.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.22408062690203823,
+    "learning_rate": 0.00039631679972097463,
+    "num_train_epochs": 4,
+    "temperature": 30
+  }
+}

run-2/checkpoint-2108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d2d08bafd61b2b33d0c565753a1d7c509d44fc2acd3aa963e54f9b640da58c
+size 5176

run-3/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a9f75f0f120bd5b6d6e19c699abb5423fcb1e644dadd5fc3d02bec80aece0d
+size 17549312

run-3/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa19ad8a9922f7df4efb0619c0af2bcac7502f0f20263e902aad77771b2d8b94
+size 35123898

run-3/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
+size 14308

run-3/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c066c460110a9f09939ad8ae38c11aa296ff3b507960c2cccf1f6678c51790c5
+size 1064

run-3/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-3/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-3/checkpoint-527/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.7259174311926605,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/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,
+      "grad_norm": 4.747544288635254,
+      "learning_rate": 8.421921303617797e-06,
+      "loss": 1.1824,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7259174311926605,
+      "eval_loss": 1.0221459865570068,
+      "eval_runtime": 2.6361,
+      "eval_samples_per_second": 330.793,
+      "eval_steps_per_second": 2.655,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8183970243354497,
+    "learning_rate": 1.0106305564341356e-05,
+    "num_train_epochs": 6,
+    "temperature": 4
+  }
+}

run-3/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19b3d1ab98759ce4a3c2a3b1b6c08002a84c81483690b1cbe27bc016b13e374
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d2d08bafd61b2b33d0c565753a1d7c509d44fc2acd3aa963e54f9b640da58c
+oid sha256:e19b3d1ab98759ce4a3c2a3b1b6c08002a84c81483690b1cbe27bc016b13e374
 size 5176