Training in progress, epoch 1

logs/events.out.tfevents.1709781087.013ec1551212.249.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5707686ff7b7fb1bc0f2e972217fb03e4d9d3cae1bfff1b60c479f199ddcb8f3
-size 10080
+oid sha256:af8d45e55b3474217f42f81db9e6c0245f4457d6a6f0e6bd3fcb00f909e577a0
+size 11117

logs/events.out.tfevents.1709797197.013ec1551212.249.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f678f97e393882b8b0486eab0fa8a6a444221bf737057894dabac936e7db1f
+size 4184

logs/events.out.tfevents.1709797404.013ec1551212.75384.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5832084823ee7a82ad090c0928c4eab358619f147483cb501dc91607ba5114
+size 11143

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2df3cb3e88190b5f69cf52719a5d9d9199d39fb58e1b1c585a3e8db156d8e2
+size 5325

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d720b0193cfa005c6365520aa52c9db6393b96538783c0a2d5b4ec14ef3af9f8
+oid sha256:9d6e809fa4ddd0b43cb54e40a5bf7be2f23fa24eeb8a9d83d1f805ad260bcaaa
 size 17549312

run-0/checkpoint-1532/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-0/checkpoint-1532/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d66723e4ad468ba0fca5ed6143edc2877df304e3a2a6591838f4bc7d8af99ca
+size 17549312

run-0/checkpoint-1532/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9fe642d5bf199a065666e80ac2eab3878b5f90c670f6e9fddf2b473d9f724f3
+size 35122746

run-0/checkpoint-1532/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16aaf318a00ee2d6780264865ac856fcd3f746d06b5d79fd7d77f53b35786488
+size 14054

run-0/checkpoint-1532/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c9185b6e29abc7b74228400a89157683875affd336c5a265b9ce3b28a560956
+size 1064

run-0/checkpoint-1532/special_tokens_map.json

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

run-0/checkpoint-1532/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-0/checkpoint-1532/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.5596868884540117,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1532",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1532,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.49913594126701355,
+      "learning_rate": 9.527255626859226e-05,
+      "loss": 0.162,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5430528375733855,
+      "eval_f1": 0.21247892074198985,
+      "eval_loss": 0.1496681571006775,
+      "eval_precision": 0.7682926829268293,
+      "eval_recall": 0.1232876712328767,
+      "eval_runtime": 132.7483,
+      "eval_samples_per_second": 7.699,
+      "eval_steps_per_second": 1.928,
+      "step": 766
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9839492440223694,
+      "learning_rate": 8.336348673501824e-05,
+      "loss": 0.1535,
+      "step": 1532
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5596868884540117,
+      "eval_f1": 0.2788461538461538,
+      "eval_loss": 0.15276561677455902,
+      "eval_precision": 0.7699115044247787,
+      "eval_recall": 0.17025440313111545,
+      "eval_runtime": 132.9511,
+      "eval_samples_per_second": 7.687,
+      "eval_steps_per_second": 1.926,
+      "step": 1532
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6894,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.18918715587656498,
+    "learning_rate": 0.0001071816258021663,
+    "num_train_epochs": 9,
+    "temperature": 30
+  }
+}

run-0/checkpoint-1532/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339050e22400caec39dad41abc311f3dacd25a4d50f4ff152ce282eb1ce6bf33
+size 4920

run-0/checkpoint-6894/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-0/checkpoint-6894/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b4b7c80c00ffc96f697c18d149d0ecb3872bf1a7050ec3c607c6f5e312bd7c
+size 17549312

run-0/checkpoint-6894/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56877d2480ece557b6eae167f561382774ebaf54923ea6ebc095000ba2fbfc14
+size 35122746

run-0/checkpoint-6894/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ffe05c05ef484b71468374c222ba2df0f72c4f9bf269c844f741792915a14f
+size 14054

run-0/checkpoint-6894/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90813b99b04602bf6d76432092a611b847e8137081beda7f00a8e0a48382efcc
+size 1064

run-0/checkpoint-6894/special_tokens_map.json

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

run-0/checkpoint-6894/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-0/checkpoint-6894/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 0.5596868884540117,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1532",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 6894,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.49913594126701355,
+      "learning_rate": 9.527255626859226e-05,
+      "loss": 0.162,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5430528375733855,
+      "eval_f1": 0.21247892074198985,
+      "eval_loss": 0.1496681571006775,
+      "eval_precision": 0.7682926829268293,
+      "eval_recall": 0.1232876712328767,
+      "eval_runtime": 132.7483,
+      "eval_samples_per_second": 7.699,
+      "eval_steps_per_second": 1.928,
+      "step": 766
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9839492440223694,
+      "learning_rate": 8.336348673501824e-05,
+      "loss": 0.1535,
+      "step": 1532
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5596868884540117,
+      "eval_f1": 0.2788461538461538,
+      "eval_loss": 0.15276561677455902,
+      "eval_precision": 0.7699115044247787,
+      "eval_recall": 0.17025440313111545,
+      "eval_runtime": 132.9511,
+      "eval_samples_per_second": 7.687,
+      "eval_steps_per_second": 1.926,
+      "step": 1532
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.20836693048477173,
+      "learning_rate": 7.145441720144419e-05,
+      "loss": 0.1517,
+      "step": 2298
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5322896281800391,
+      "eval_f1": 0.16433566433566432,
+      "eval_loss": 0.15022048354148865,
+      "eval_precision": 0.7704918032786885,
+      "eval_recall": 0.09197651663405088,
+      "eval_runtime": 133.1996,
+      "eval_samples_per_second": 7.673,
+      "eval_steps_per_second": 1.922,
+      "step": 2298
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.4116870164871216,
+      "learning_rate": 5.9545347667870174e-05,
+      "loss": 0.1508,
+      "step": 3064
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.538160469667319,
+      "eval_f1": 0.18620689655172412,
+      "eval_loss": 0.14854486286640167,
+      "eval_precision": 0.782608695652174,
+      "eval_recall": 0.10567514677103718,
+      "eval_runtime": 135.4399,
+      "eval_samples_per_second": 7.546,
+      "eval_steps_per_second": 1.89,
+      "step": 3064
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8599097728729248,
+      "learning_rate": 4.763627813429613e-05,
+      "loss": 0.1499,
+      "step": 3830
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5547945205479452,
+      "eval_f1": 0.26016260162601623,
+      "eval_loss": 0.14884987473487854,
+      "eval_precision": 0.7692307692307693,
+      "eval_recall": 0.15655577299412915,
+      "eval_runtime": 134.169,
+      "eval_samples_per_second": 7.617,
+      "eval_steps_per_second": 1.908,
+      "step": 3830
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.176220417022705,
+      "learning_rate": 3.5727208600722096e-05,
+      "loss": 0.1487,
+      "step": 4596
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5538160469667319,
+      "eval_f1": 0.25,
+      "eval_loss": 0.14816069602966309,
+      "eval_precision": 0.7835051546391752,
+      "eval_recall": 0.1487279843444227,
+      "eval_runtime": 132.3135,
+      "eval_samples_per_second": 7.724,
+      "eval_steps_per_second": 1.935,
+      "step": 4596
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7192456126213074,
+      "learning_rate": 2.3818139067148064e-05,
+      "loss": 0.1481,
+      "step": 5362
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5528375733855186,
+      "eval_f1": 0.24212271973466004,
+      "eval_loss": 0.1478748470544815,
+      "eval_precision": 0.7934782608695652,
+      "eval_recall": 0.14285714285714285,
+      "eval_runtime": 132.0993,
+      "eval_samples_per_second": 7.737,
+      "eval_steps_per_second": 1.938,
+      "step": 5362
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.8929200172424316,
+      "learning_rate": 1.1909069533574032e-05,
+      "loss": 0.1476,
+      "step": 6128
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.550880626223092,
+      "eval_f1": 0.23627287853577372,
+      "eval_loss": 0.14707620441913605,
+      "eval_precision": 0.7888888888888889,
+      "eval_recall": 0.13894324853228962,
+      "eval_runtime": 133.3296,
+      "eval_samples_per_second": 7.665,
+      "eval_steps_per_second": 1.92,
+      "step": 6128
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.470459520816803,
+      "learning_rate": 0.0,
+      "loss": 0.1471,
+      "step": 6894
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5528375733855186,
+      "eval_f1": 0.24462809917355371,
+      "eval_loss": 0.14724816381931305,
+      "eval_precision": 0.7872340425531915,
+      "eval_recall": 0.14481409001956946,
+      "eval_runtime": 133.2048,
+      "eval_samples_per_second": 7.672,
+      "eval_steps_per_second": 1.922,
+      "step": 6894
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6894,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 2121256775520.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.18918715587656498,
+    "learning_rate": 0.0001071816258021663,
+    "num_train_epochs": 9,
+    "temperature": 30
+  }
+}

run-0/checkpoint-6894/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339050e22400caec39dad41abc311f3dacd25a4d50f4ff152ce282eb1ce6bf33
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddcb84a8b259a281ddddebb164459f532ca3d12957e80f314d863045f7bf9e04
+oid sha256:799e2785af5a356d3201d75e27036f909737ef8a3cb83c11d4ab91ab8e637b4d
 size 4920