Training in progress, epoch 1

logs/events.out.tfevents.1709802807.013ec1551212.75384.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9768cb5cd6add87c5405e9bbf14cbcae3312cd1d1711d00f8f1d33e5b85573
-size 6008
+oid sha256:d8779f97a7a71784741e575469959ead112e1aedfe4f67d56a6be05825531392
+size 10460

logs/events.out.tfevents.1709807412.013ec1551212.75384.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57fdbd7478fb746a714ac12cd90d893ee3dfe992f1a0a995f0e32a5b2759107e
+size 5325

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0a03ef494324e1bf3cf910e1f6e5d10a1941f8c42fd5ac2c1930e599076bb4
+oid sha256:bd498e2f60a35d74720eab66caaf8010cccbb4c1cbd6adc126895adc74a5e668
 size 17549312

run-1/checkpoint-6128/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-1/checkpoint-6128/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08dbb778a24de22ffb8a84fe56975a5f9fda85d1b4a2520d9c915739f6f761a7
+size 17549312

run-1/checkpoint-6128/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26e9eba1976c6b58ff05c191e9fbd76fb0ba91086300d6ff7c859512c63ff74
+size 35122746

run-1/checkpoint-6128/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff913ac2a571c0c557c7e887f2eae101e7b6642459a8431738a103e2afda185
+size 14054

run-1/checkpoint-6128/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99513428a86bccbb643c4b65bb892a0a5f5de6bc345a3d8fde2a7878206d4ef
+size 1064

run-1/checkpoint-6128/special_tokens_map.json

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

run-1/checkpoint-6128/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-1/checkpoint-6128/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.5430528375733855,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1532",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 6128,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4840396046638489,
+      "learning_rate": 3.344893789847612e-05,
+      "loss": 0.1172,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5401174168297456,
+      "eval_f1": 0.20068027210884357,
+      "eval_loss": 0.10136038810014725,
+      "eval_precision": 0.7662337662337663,
+      "eval_recall": 0.11545988258317025,
+      "eval_runtime": 133.3642,
+      "eval_samples_per_second": 7.663,
+      "eval_steps_per_second": 1.92,
+      "step": 766
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.713012456893921,
+      "learning_rate": 2.8670518198693823e-05,
+      "loss": 0.1055,
+      "step": 1532
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5430528375733855,
+      "eval_f1": 0.21247892074198985,
+      "eval_loss": 0.10160499066114426,
+      "eval_precision": 0.7682926829268293,
+      "eval_recall": 0.1232876712328767,
+      "eval_runtime": 132.4691,
+      "eval_samples_per_second": 7.715,
+      "eval_steps_per_second": 1.933,
+      "step": 1532
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.46175065636634827,
+      "learning_rate": 2.389209849891152e-05,
+      "loss": 0.1039,
+      "step": 2298
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5322896281800391,
+      "eval_f1": 0.17301038062283738,
+      "eval_loss": 0.10080397874116898,
+      "eval_precision": 0.746268656716418,
+      "eval_recall": 0.09784735812133072,
+      "eval_runtime": 133.9804,
+      "eval_samples_per_second": 7.628,
+      "eval_steps_per_second": 1.911,
+      "step": 2298
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8960716128349304,
+      "learning_rate": 1.9113678799129215e-05,
+      "loss": 0.1038,
+      "step": 3064
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5362035225048923,
+      "eval_f1": 0.18835616438356165,
+      "eval_loss": 0.10024181753396988,
+      "eval_precision": 0.7534246575342466,
+      "eval_recall": 0.10763209393346379,
+      "eval_runtime": 131.9665,
+      "eval_samples_per_second": 7.744,
+      "eval_steps_per_second": 1.94,
+      "step": 3064
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2918031215667725,
+      "learning_rate": 1.4335259099346911e-05,
+      "loss": 0.103,
+      "step": 3830
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5401174168297456,
+      "eval_f1": 0.20068027210884357,
+      "eval_loss": 0.10036557912826538,
+      "eval_precision": 0.7662337662337663,
+      "eval_recall": 0.11545988258317025,
+      "eval_runtime": 134.3935,
+      "eval_samples_per_second": 7.605,
+      "eval_steps_per_second": 1.905,
+      "step": 3830
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0010789632797241,
+      "learning_rate": 9.556839399564608e-06,
+      "loss": 0.1025,
+      "step": 4596
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5420743639921722,
+      "eval_f1": 0.2067796610169491,
+      "eval_loss": 0.10058682411909103,
+      "eval_precision": 0.7721518987341772,
+      "eval_recall": 0.11937377690802348,
+      "eval_runtime": 132.5868,
+      "eval_samples_per_second": 7.708,
+      "eval_steps_per_second": 1.931,
+      "step": 4596
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8870960474014282,
+      "learning_rate": 4.778419699782304e-06,
+      "loss": 0.1024,
+      "step": 5362
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.541095890410959,
+      "eval_f1": 0.20373514431239387,
+      "eval_loss": 0.10063320398330688,
+      "eval_precision": 0.7692307692307693,
+      "eval_recall": 0.11741682974559686,
+      "eval_runtime": 132.2356,
+      "eval_samples_per_second": 7.729,
+      "eval_steps_per_second": 1.936,
+      "step": 5362
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.9253156185150146,
+      "learning_rate": 0.0,
+      "loss": 0.1023,
+      "step": 6128
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.541095890410959,
+      "eval_f1": 0.20373514431239387,
+      "eval_loss": 0.10009610652923584,
+      "eval_precision": 0.7692307692307693,
+      "eval_recall": 0.11741682974559686,
+      "eval_runtime": 131.3578,
+      "eval_samples_per_second": 7.78,
+      "eval_steps_per_second": 1.949,
+      "step": 6128
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6128,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1885561578240.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.1218013407365569,
+    "learning_rate": 3.822735759825843e-05,
+    "num_train_epochs": 8,
+    "temperature": 6
+  }
+}

run-1/checkpoint-6128/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799e2785af5a356d3201d75e27036f909737ef8a3cb83c11d4ab91ab8e637b4d
+size 4920

run-2/checkpoint-766/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-2/checkpoint-766/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd498e2f60a35d74720eab66caaf8010cccbb4c1cbd6adc126895adc74a5e668
+size 17549312

run-2/checkpoint-766/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75a2cd69a00f5300355253e969b40c4cef619ab6d18875410700792fd6bc2b8
+size 35122746

run-2/checkpoint-766/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29b5a9fab412f426bae759e459d7d9236aab6602ae439ea13f5bd437e1b98a4
+size 14054

run-2/checkpoint-766/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7259219e3772ab584ea10997ee87866c03e8b389b5ae114a3644dbf5c8400db
+size 1064

run-2/checkpoint-766/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-766/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-766/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.5870841487279843,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-766",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 766,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.795396089553833,
+      "learning_rate": 2.0226645656833037e-05,
+      "loss": 0.3457,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5870841487279843,
+      "eval_f1": 0.352760736196319,
+      "eval_loss": 0.3146859109401703,
+      "eval_precision": 0.8156028368794326,
+      "eval_recall": 0.22504892367906065,
+      "eval_runtime": 132.813,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 1.928,
+      "step": 766
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5362,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.43980036163769065,
+    "learning_rate": 2.359775326630521e-05,
+    "num_train_epochs": 7,
+    "temperature": 17
+  }
+}

run-2/checkpoint-766/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5b12c46007d944895fac94424c52cdff3b4d51e877318f87ce441d4dd6ec61
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:799e2785af5a356d3201d75e27036f909737ef8a3cb83c11d4ab91ab8e637b4d
+oid sha256:1c5b12c46007d944895fac94424c52cdff3b4d51e877318f87ce441d4dd6ec61
 size 4920