Training in progress, epoch 1

logs/events.out.tfevents.1711298948.8cc2eef2edb7.2942.32

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf6e4aef381f8338e63e887500d03e859380e00c5704977bdd22912f78fcc2f
-size 8326
+oid sha256:07afdbe62c1a0195bbc0a5c3af865869df780e11b26c429d88bcf66c915cd593
+size 9410

logs/events.out.tfevents.1711299078.8cc2eef2edb7.2942.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f90a4e44192d7f910a91e801c78a4aac9dc0c5b9184fd69a8b2ddfa342506cc
+size 5407

logs/events.out.tfevents.1711299098.8cc2eef2edb7.2942.34

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30b36696d92002fc84a6360c244b8e5e073bd9d12c6aed557a5c4fcaf78dd2e
+size 5406

logs/events.out.tfevents.1711299118.8cc2eef2edb7.2942.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c201d741f3f8cd0156d9449ca7d84852e4fe2837f855dc1c8bfdcfca60dc7d7
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00922bada62aa0eb120cea58c425bddd385877fe9fa9ab352ec2dcd3e7efa4ec
+oid sha256:adcb77a661aa58bcee1882579f4f446dcd45fd555c27a4d70afe50daafe7f770
 size 17549312

run-32/checkpoint-1782/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-32/checkpoint-1782/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbea493dc91c85b0ddeddecbefed8cbfee97b74014c0e4adf5cf5e97f6a5734
+size 17549312

run-32/checkpoint-1782/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0658dd776dfe4e93eeeccec3b009bcd283b808ff95c494ed1dc2d6cd7a4a5d3
+size 35123898

run-32/checkpoint-1782/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a02d6fe58f222754d8b6c88c72e65619363bb5593417cc44e98640fe115ffbc
+size 14308

run-32/checkpoint-1782/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baae38df2f80a437881570d02c0a78f2a94c4416cb8bc9e5df8720a3ddc8d6cb
+size 1064

run-32/checkpoint-1782/special_tokens_map.json

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

run-32/checkpoint-1782/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-32/checkpoint-1782/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.689108910891089,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-1782",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1782,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.0489678382873535,
+      "learning_rate": 0.00030782109688346106,
+      "loss": 0.6591,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5366336633663367,
+      "eval_f1": 0.20945945945945946,
+      "eval_loss": 0.6587525606155396,
+      "eval_mcc": 0.12699706368366073,
+      "eval_precision": 0.7045454545454546,
+      "eval_recall": 0.12301587301587301,
+      "eval_runtime": 0.9347,
+      "eval_samples_per_second": 540.253,
+      "eval_steps_per_second": 17.117,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.570565104484558,
+      "learning_rate": 0.00024625687750676884,
+      "loss": 0.6201,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6514851485148515,
+      "eval_f1": 0.7095709570957095,
+      "eval_loss": 0.6164775490760803,
+      "eval_mcc": 0.33175059993848016,
+      "eval_precision": 0.6073446327683616,
+      "eval_recall": 0.8531746031746031,
+      "eval_runtime": 0.94,
+      "eval_samples_per_second": 537.23,
+      "eval_steps_per_second": 17.021,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.9003602266311646,
+      "learning_rate": 0.00018469265813007664,
+      "loss": 0.6,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6574257425742575,
+      "eval_f1": 0.7131011608623549,
+      "eval_loss": 0.6146110892295837,
+      "eval_mcc": 0.3427822124548935,
+      "eval_precision": 0.6125356125356125,
+      "eval_recall": 0.8531746031746031,
+      "eval_runtime": 0.9324,
+      "eval_samples_per_second": 541.638,
+      "eval_steps_per_second": 17.161,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.194995880126953,
+      "learning_rate": 0.00012312843875338442,
+      "loss": 0.5817,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6574257425742575,
+      "eval_f1": 0.7082630691399663,
+      "eval_loss": 0.598789632320404,
+      "eval_mcc": 0.3369187333704843,
+      "eval_precision": 0.6158357771260997,
+      "eval_recall": 0.8333333333333334,
+      "eval_runtime": 0.9317,
+      "eval_samples_per_second": 542.019,
+      "eval_steps_per_second": 17.173,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.605654001235962,
+      "learning_rate": 6.156421937669221e-05,
+      "loss": 0.5679,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6811881188118812,
+      "eval_f1": 0.7130124777183601,
+      "eval_loss": 0.5869699120521545,
+      "eval_mcc": 0.37225914648565367,
+      "eval_precision": 0.6472491909385113,
+      "eval_recall": 0.7936507936507936,
+      "eval_runtime": 0.9345,
+      "eval_samples_per_second": 540.401,
+      "eval_steps_per_second": 17.122,
+      "step": 1485
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.7389540672302246,
+      "learning_rate": 0.0,
+      "loss": 0.5593,
+      "step": 1782
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.689108910891089,
+      "eval_f1": 0.7140255009107468,
+      "eval_loss": 0.5873299241065979,
+      "eval_mcc": 0.3845872427583931,
+      "eval_precision": 0.6599326599326599,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 0.9332,
+      "eval_samples_per_second": 541.174,
+      "eval_steps_per_second": 17.146,
+      "step": 1782
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 4384207595880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9361124407975862,
+    "learning_rate": 0.0003693853162601533,
+    "num_train_epochs": 6,
+    "temperature": 21
+  }
+}

run-32/checkpoint-1782/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8392c48e77ef3e277bb806e38539adfe405c083ee9826264540c767c93e40b
+size 4920

run-35/checkpoint-297/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-35/checkpoint-297/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adcb77a661aa58bcee1882579f4f446dcd45fd555c27a4d70afe50daafe7f770
+size 17549312

run-35/checkpoint-297/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaae3324e30a35b982d4ddb6ba62ccbc284f4da14039753b3892613bb10357ec
+size 35123898

run-35/checkpoint-297/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
+size 14308

run-35/checkpoint-297/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef06f7649554e3cac341667c2f48750669f06fbc17f79011451535951f2bea4c
+size 1064

run-35/checkpoint-297/special_tokens_map.json

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

run-35/checkpoint-297/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-35/checkpoint-297/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.497029702970297,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-35/checkpoint-297",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 297,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.011061429977417,
+      "learning_rate": 0.0008596139358612845,
+      "loss": 0.6951,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.497029702970297,
+      "eval_f1": 0.664021164021164,
+      "eval_loss": 0.6919692158699036,
+      "eval_mcc": -0.044631832853976164,
+      "eval_precision": 0.498015873015873,
+      "eval_recall": 0.996031746031746,
+      "eval_runtime": 0.9311,
+      "eval_samples_per_second": 542.385,
+      "eval_steps_per_second": 17.184,
+      "step": 297
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 730701265980.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9987048243469214,
+    "learning_rate": 0.0009824159266986108,
+    "num_train_epochs": 8,
+    "temperature": 5
+  }
+}

run-35/checkpoint-297/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5517b196c46e47a36c72ced76e5af4b26f847ea05009b31731917e96011dcbda
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082ccacbf20ed2e5f12a8657057e2759074f79e8de35cb8d580c36b197471a5a
-size 4984
+oid sha256:5517b196c46e47a36c72ced76e5af4b26f847ea05009b31731917e96011dcbda
+size 4920