Training in progress, epoch 1

logs/events.out.tfevents.1709621162.404ecd1cf399.26000.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56446eacc9914ea8457a82ce9aaf576e70f8d2071b141fef01eb6d7cd2b07f70
-size 5997
+oid sha256:7f188aab21c187430a049f0cb45d7be4ff226f7a643fb22094c1b513edbe3290
+size 7034

logs/events.out.tfevents.1709621520.404ecd1cf399.26000.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9f443ea6d1d3319ca5cfeff866cbad95d207de761827824356f08b8566c031
+size 5314

logs/events.out.tfevents.1709621638.404ecd1cf399.26000.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ce6158d6aa6340bb86067d40de8ad5bcca52a5360b90c636c54e9151f0834f
+size 5314

logs/events.out.tfevents.1709621754.404ecd1cf399.26000.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa54aa96f058cf0ad96ff3a163b9e620867a3c93faa4253808a3ee297687b65
+size 5314

logs/events.out.tfevents.1709621872.404ecd1cf399.26000.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b8ad32bb77f3edd0962f26324a60cca56b98a7ae17cd4721427aea1686a54
+size 5315

logs/events.out.tfevents.1709621988.404ecd1cf399.26000.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c864e36fa21afb69b83dc1eb0f2270c1e8b2de14744a3b41a9d2eb8269a55c9d
+size 5314

logs/events.out.tfevents.1709622105.404ecd1cf399.26000.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773319b7521f22549a7a8b17ff140feb1a90416bee36cfdf45128a017d4dbd53
+size 5315

logs/events.out.tfevents.1709622224.404ecd1cf399.26000.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d52bd5fd37dfc611b4b637516c60ecd5c7388580f62b6db2e6e20b9cb14c47d
+size 5315

logs/events.out.tfevents.1709622341.404ecd1cf399.26000.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6855da1bc56c58c69c9b9c23403d8c7d4f91347c1bf03382bd673668f5f49fbc
+size 5315

logs/events.out.tfevents.1709622459.404ecd1cf399.26000.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed4c7f97b576fe13069a4307c1886daa638f6125083ecb85516722d06c05663
+size 5311

logs/events.out.tfevents.1709622577.404ecd1cf399.26000.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5893da421a5e6fe626da3bc647153fcbc26a75d404672693f0175d8c2dd8c36d
+size 5315

logs/events.out.tfevents.1709622697.404ecd1cf399.26000.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b13c9a120729e9f5b44a32bc258f58c815c20cb691f744147e7a047aa13d7b
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8218b0b49358a4f2c91ebc8c843961cecc26366dde2821fd7b7fcdb07a6f52db
+oid sha256:0340ebc32cb2d6702dc3fa2be07246d93c8e0bf967f78c96478e03a388469de0
 size 17549312

run-10/checkpoint-288/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-10/checkpoint-288/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90544cd346f84f4589af99a78110877a58e704cb23b6f374ebdfba5b1f7654c5
+size 17549312

run-10/checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c3fc2822ded408ee92a83ac988187d1edba9601e41f58ea728289e3b9381cb
+size 35122746

run-10/checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3c2bb1d96a39a28ae1b66f234e351e3c13c700fc97347efd6308798b151790
+size 14054

run-10/checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c115d3f4c35a47d3adb59e1f87f96436fbc076b7e6a682ba8005683cfea2d74
+size 1064

run-10/checkpoint-288/special_tokens_map.json

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

run-10/checkpoint-288/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-10/checkpoint-288/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.8297455968688845,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-288",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 288,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9170680046081543,
+      "learning_rate": 0.0005212663608648181,
+      "loss": 0.5641,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.799412915851272,
+      "eval_f1": 0.8197009674582234,
+      "eval_loss": 0.47259676456451416,
+      "eval_precision": 0.744408945686901,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 30.8424,
+      "eval_samples_per_second": 33.136,
+      "eval_steps_per_second": 1.038,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.4848690032958984,
+      "learning_rate": 0.00026063318043240905,
+      "loss": 0.456,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.824853228962818,
+      "eval_f1": 0.8406055209260909,
+      "eval_loss": 0.4349122643470764,
+      "eval_precision": 0.7712418300653595,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 31.1515,
+      "eval_samples_per_second": 32.807,
+      "eval_steps_per_second": 1.027,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.3911333084106445,
+      "learning_rate": 0.0,
+      "loss": 0.4063,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8297455968688845,
+      "eval_f1": 0.8421052631578947,
+      "eval_loss": 0.42057597637176514,
+      "eval_precision": 0.7851099830795262,
+      "eval_recall": 0.9080234833659491,
+      "eval_runtime": 32.1366,
+      "eval_samples_per_second": 31.802,
+      "eval_steps_per_second": 0.996,
+      "step": 288
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 288,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9610512963031814,
+    "learning_rate": 0.0007818995412972273,
+    "num_train_epochs": 3,
+    "temperature": 24
+  }
+}

run-10/checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c48cb920a64a7322ad1d6d741321a643be4ed10af970a24a154150a0def2990
+size 4920

run-21/checkpoint-96/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-21/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0340ebc32cb2d6702dc3fa2be07246d93c8e0bf967f78c96478e03a388469de0
+size 17549312

run-21/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c513239be26577cef37b2a5c5921b280d68af12a23bbcc48e367b3d5257fef7e
+size 35122746

run-21/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
+size 14054

run-21/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c973b1c012d03414b773f9d4a120a97ecb91fe35ce74c8cc2ee1c6e41f7efae6
+size 1064

run-21/checkpoint-96/special_tokens_map.json

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

run-21/checkpoint-96/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-21/checkpoint-96/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7886497064579256,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-96",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.274248719215393,
+      "learning_rate": 0.00018849707699065689,
+      "loss": 0.5008,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7886497064579256,
+      "eval_f1": 0.807142857142857,
+      "eval_loss": 0.4340507984161377,
+      "eval_precision": 0.7422003284072249,
+      "eval_recall": 0.8845401174168297,
+      "eval_runtime": 30.5806,
+      "eval_samples_per_second": 33.42,
+      "eval_steps_per_second": 1.046,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7341174287180767,
+    "learning_rate": 0.0002356213462383211,
+    "num_train_epochs": 5,
+    "temperature": 30
+  }
+}

run-21/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda209f700b90b88269aa2223f5df9860e130b74cffee3dfa38a80b8c6373616
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c48cb920a64a7322ad1d6d741321a643be4ed10af970a24a154150a0def2990
+oid sha256:cda209f700b90b88269aa2223f5df9860e130b74cffee3dfa38a80b8c6373616
 size 4920