Training in progress, epoch 11

logs/events.out.tfevents.1713594488.1376c752d37a.9760.61

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc5b96ad90f9cf6cd886e6b93d7de539016da13e2e6306c9fd1c4b8ef2a8652
+size 13868

logs/events.out.tfevents.1713594692.1376c752d37a.9760.62

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782ca5e02b94ae48a11188bfd1e28b8e70438d6be4f432ab9d73903756b3c188
+size 6212

logs/events.out.tfevents.1713594726.1376c752d37a.9760.63

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45ea4c8e1247616d8b3c1fd3a0d27f6f605bc126d3c67fbca41c3251ca40c2d
+size 12407

logs/events.out.tfevents.1713594894.1376c752d37a.9760.64

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6ae96e6638c4754accfdca50acacba2f61c00ed2311939b60c75ec54cba47a
+size 13138

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4040c6ca96a2c15bdf2ff74f1b239c6f9435742bf73587eba68d44b6a1ab734e
+oid sha256:f7c8455ed7ddb848b491c3f9183148962c793cf1f02086a98ba43b722f6ae4ce
 size 17549312

run-10/checkpoint-1926/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-10/checkpoint-1926/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb9a5154989158cf03e472860816198c094c18bb24799b3b85cc21f47f99a48
+size 17549312

run-10/checkpoint-1926/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85796ba438a7256c9ccbed492c0ca5214d3bf77d81c312f005f119519df8fc1
+size 35123898

run-10/checkpoint-1926/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2411fdfdbcf5b48d15f394158baa93e72fe1dc9a2034dc7fa2b11b876e3bf2a
+size 14308

run-10/checkpoint-1926/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee42ddf5c91d5af3ddabab385bf851359111fc42b1823c3d2a49a383fb36195d
+size 1064

run-10/checkpoint-1926/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-1926/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-1926/trainer_state.json

@@ -0,0 +1,206 @@
+{
+  "best_metric": 0.7709431751611013,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-1926",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 1926,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.383261680603027,
+      "learning_rate": 0.00019166625457051745,
+      "loss": 0.5952,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7076742823667252,
+      "eval_f1": 0.3907203907203907,
+      "eval_loss": 0.5565764307975769,
+      "eval_mcc": 0.2694716353370074,
+      "eval_precision": 0.64,
+      "eval_recall": 0.281195079086116,
+      "eval_runtime": 3.1354,
+      "eval_samples_per_second": 544.427,
+      "eval_steps_per_second": 17.223,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.881709575653076,
+      "learning_rate": 0.00017037000406268217,
+      "loss": 0.531,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7246631517281781,
+      "eval_f1": 0.520408163265306,
+      "eval_loss": 0.5205469727516174,
+      "eval_mcc": 0.3429768856541182,
+      "eval_precision": 0.6204379562043796,
+      "eval_recall": 0.44815465729349735,
+      "eval_runtime": 3.9179,
+      "eval_samples_per_second": 435.687,
+      "eval_steps_per_second": 13.783,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.652766227722168,
+      "learning_rate": 0.00014907375355484689,
+      "loss": 0.5039,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7492677211482133,
+      "eval_f1": 0.5169300225733634,
+      "eval_loss": 0.5036008358001709,
+      "eval_mcc": 0.3941392583108005,
+      "eval_precision": 0.722397476340694,
+      "eval_recall": 0.4024604569420035,
+      "eval_runtime": 3.1479,
+      "eval_samples_per_second": 542.261,
+      "eval_steps_per_second": 17.154,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.058462619781494,
+      "learning_rate": 0.0001277775030470116,
+      "loss": 0.4923,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7521968365553603,
+      "eval_f1": 0.5209513023782559,
+      "eval_loss": 0.49394065141677856,
+      "eval_mcc": 0.40200593502267246,
+      "eval_precision": 0.732484076433121,
+      "eval_recall": 0.40421792618629176,
+      "eval_runtime": 3.2248,
+      "eval_samples_per_second": 529.338,
+      "eval_steps_per_second": 16.745,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.336209297180176,
+      "learning_rate": 0.00010648125253917635,
+      "loss": 0.4809,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.760398359695372,
+      "eval_f1": 0.5490628445424476,
+      "eval_loss": 0.48668524622917175,
+      "eval_mcc": 0.42515592515592515,
+      "eval_precision": 0.7366863905325444,
+      "eval_recall": 0.437609841827768,
+      "eval_runtime": 3.1454,
+      "eval_samples_per_second": 542.701,
+      "eval_steps_per_second": 17.168,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.197123050689697,
+      "learning_rate": 8.518500203134108e-05,
+      "loss": 0.4741,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7598125366139425,
+      "eval_f1": 0.5883534136546184,
+      "eval_loss": 0.48185786604881287,
+      "eval_mcc": 0.4323191909966307,
+      "eval_precision": 0.6861826697892272,
+      "eval_recall": 0.5149384885764499,
+      "eval_runtime": 3.2476,
+      "eval_samples_per_second": 525.615,
+      "eval_steps_per_second": 16.628,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.824602127075195,
+      "learning_rate": 6.38887515235058e-05,
+      "loss": 0.4642,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7697715289982425,
+      "eval_f1": 0.5814696485623003,
+      "eval_loss": 0.47905731201171875,
+      "eval_mcc": 0.45140334971229035,
+      "eval_precision": 0.7378378378378379,
+      "eval_recall": 0.4797891036906854,
+      "eval_runtime": 3.1541,
+      "eval_samples_per_second": 541.195,
+      "eval_steps_per_second": 17.12,
+      "step": 1498
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.0699849128723145,
+      "learning_rate": 4.259250101567054e-05,
+      "loss": 0.4534,
+      "step": 1712
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7639132981839485,
+      "eval_f1": 0.5780104712041885,
+      "eval_loss": 0.4776459038257599,
+      "eval_mcc": 0.4376855515817711,
+      "eval_precision": 0.7150259067357513,
+      "eval_recall": 0.4850615114235501,
+      "eval_runtime": 3.3925,
+      "eval_samples_per_second": 503.169,
+      "eval_steps_per_second": 15.917,
+      "step": 1712
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.322149753570557,
+      "learning_rate": 2.129625050783527e-05,
+      "loss": 0.454,
+      "step": 1926
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7709431751611013,
+      "eval_f1": 0.606243705941591,
+      "eval_loss": 0.4749068319797516,
+      "eval_mcc": 0.4592236637293635,
+      "eval_precision": 0.7099056603773585,
+      "eval_recall": 0.5289982425307557,
+      "eval_runtime": 3.1452,
+      "eval_samples_per_second": 542.727,
+      "eval_steps_per_second": 17.169,
+      "step": 1926
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4722980979960.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9841007089206046,
+    "learning_rate": 0.0002129625050783527,
+    "num_train_epochs": 10,
+    "temperature": 10
+  }
+}

run-10/checkpoint-1926/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24840125a320a441e6b4f08ad7598cad2e386fff76bf035b05deefa181d478fd
+size 5048

run-10/checkpoint-2140/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-10/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3006deece588ef686aa90f5af22489aca82aee502d3c4598dc499f034de2bfd
+size 17549312

run-10/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c886181e07b34fd24d094ebae7a32850a195417c279cd9a5c780873dea0da3ea
+size 35123898

run-10/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb16c48b271d0534b9a61cb30864d6f8bb1c10a35f7fb5f704c529b2ed28df1
+size 14308

run-10/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f175a0e283d494021b65f38a7b3f3e0db70db73bf0e51bde635775ce89835d
+size 1064

run-10/checkpoint-2140/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-2140/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-2140/trainer_state.json

@@ -0,0 +1,226 @@
+{
+  "best_metric": 0.7709431751611013,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-1926",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.383261680603027,
+      "learning_rate": 0.00019166625457051745,
+      "loss": 0.5952,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7076742823667252,
+      "eval_f1": 0.3907203907203907,
+      "eval_loss": 0.5565764307975769,
+      "eval_mcc": 0.2694716353370074,
+      "eval_precision": 0.64,
+      "eval_recall": 0.281195079086116,
+      "eval_runtime": 3.1354,
+      "eval_samples_per_second": 544.427,
+      "eval_steps_per_second": 17.223,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.881709575653076,
+      "learning_rate": 0.00017037000406268217,
+      "loss": 0.531,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7246631517281781,
+      "eval_f1": 0.520408163265306,
+      "eval_loss": 0.5205469727516174,
+      "eval_mcc": 0.3429768856541182,
+      "eval_precision": 0.6204379562043796,
+      "eval_recall": 0.44815465729349735,
+      "eval_runtime": 3.9179,
+      "eval_samples_per_second": 435.687,
+      "eval_steps_per_second": 13.783,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.652766227722168,
+      "learning_rate": 0.00014907375355484689,
+      "loss": 0.5039,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7492677211482133,
+      "eval_f1": 0.5169300225733634,
+      "eval_loss": 0.5036008358001709,
+      "eval_mcc": 0.3941392583108005,
+      "eval_precision": 0.722397476340694,
+      "eval_recall": 0.4024604569420035,
+      "eval_runtime": 3.1479,
+      "eval_samples_per_second": 542.261,
+      "eval_steps_per_second": 17.154,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.058462619781494,
+      "learning_rate": 0.0001277775030470116,
+      "loss": 0.4923,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7521968365553603,
+      "eval_f1": 0.5209513023782559,
+      "eval_loss": 0.49394065141677856,
+      "eval_mcc": 0.40200593502267246,
+      "eval_precision": 0.732484076433121,
+      "eval_recall": 0.40421792618629176,
+      "eval_runtime": 3.2248,
+      "eval_samples_per_second": 529.338,
+      "eval_steps_per_second": 16.745,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.336209297180176,
+      "learning_rate": 0.00010648125253917635,
+      "loss": 0.4809,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.760398359695372,
+      "eval_f1": 0.5490628445424476,
+      "eval_loss": 0.48668524622917175,
+      "eval_mcc": 0.42515592515592515,
+      "eval_precision": 0.7366863905325444,
+      "eval_recall": 0.437609841827768,
+      "eval_runtime": 3.1454,
+      "eval_samples_per_second": 542.701,
+      "eval_steps_per_second": 17.168,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.197123050689697,
+      "learning_rate": 8.518500203134108e-05,
+      "loss": 0.4741,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7598125366139425,
+      "eval_f1": 0.5883534136546184,
+      "eval_loss": 0.48185786604881287,
+      "eval_mcc": 0.4323191909966307,
+      "eval_precision": 0.6861826697892272,
+      "eval_recall": 0.5149384885764499,
+      "eval_runtime": 3.2476,
+      "eval_samples_per_second": 525.615,
+      "eval_steps_per_second": 16.628,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.824602127075195,
+      "learning_rate": 6.38887515235058e-05,
+      "loss": 0.4642,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7697715289982425,
+      "eval_f1": 0.5814696485623003,
+      "eval_loss": 0.47905731201171875,
+      "eval_mcc": 0.45140334971229035,
+      "eval_precision": 0.7378378378378379,
+      "eval_recall": 0.4797891036906854,
+      "eval_runtime": 3.1541,
+      "eval_samples_per_second": 541.195,
+      "eval_steps_per_second": 17.12,
+      "step": 1498
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.0699849128723145,
+      "learning_rate": 4.259250101567054e-05,
+      "loss": 0.4534,
+      "step": 1712
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7639132981839485,
+      "eval_f1": 0.5780104712041885,
+      "eval_loss": 0.4776459038257599,
+      "eval_mcc": 0.4376855515817711,
+      "eval_precision": 0.7150259067357513,
+      "eval_recall": 0.4850615114235501,
+      "eval_runtime": 3.3925,
+      "eval_samples_per_second": 503.169,
+      "eval_steps_per_second": 15.917,
+      "step": 1712
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.322149753570557,
+      "learning_rate": 2.129625050783527e-05,
+      "loss": 0.454,
+      "step": 1926
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7709431751611013,
+      "eval_f1": 0.606243705941591,
+      "eval_loss": 0.4749068319797516,
+      "eval_mcc": 0.4592236637293635,
+      "eval_precision": 0.7099056603773585,
+      "eval_recall": 0.5289982425307557,
+      "eval_runtime": 3.1452,
+      "eval_samples_per_second": 542.727,
+      "eval_steps_per_second": 17.169,
+      "step": 1926
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.512744426727295,
+      "learning_rate": 0.0,
+      "loss": 0.4483,
+      "step": 2140
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7685998828353837,
+      "eval_f1": 0.6123650637880275,
+      "eval_loss": 0.4747108519077301,
+      "eval_mcc": 0.4569275831344798,
+      "eval_precision": 0.6933333333333334,
+      "eval_recall": 0.5483304042179262,
+      "eval_runtime": 3.2975,
+      "eval_samples_per_second": 517.657,
+      "eval_steps_per_second": 16.376,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5247756644400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9841007089206046,
+    "learning_rate": 0.0002129625050783527,
+    "num_train_epochs": 10,
+    "temperature": 10
+  }
+}

run-10/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24840125a320a441e6b4f08ad7598cad2e386fff76bf035b05deefa181d478fd
+size 5048

run-11/checkpoint-2140/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:188c97ad61aff2e5b6d0a7986fbaea611e1084832a9fa87c5ace12e1c1ed44a1
+size 17549312

run-11/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9e94ee6eaea9d78249540c83f730f37eedb9391c42bd54b4ab10b399ae3456
+size 35123898

run-11/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb16c48b271d0534b9a61cb30864d6f8bb1c10a35f7fb5f704c529b2ed28df1
+size 14308

run-11/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5acf84c0165126b15e88e5bef9fa7cffbd4b5a60868b508b353f061d2639d330
+size 1064

run-11/checkpoint-2140/special_tokens_map.json

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

run-11/checkpoint-2140/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-11/checkpoint-2140/trainer_state.json

@@ -0,0 +1,226 @@
+{
+  "best_metric": 0.7750439367311072,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-2140",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.918547630310059,
+      "learning_rate": 0.00018354791279082705,
+      "loss": 0.5995,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7053309900410076,
+      "eval_f1": 0.4944723618090453,
+      "eval_loss": 0.5527746677398682,
+      "eval_mcc": 0.29864842708933803,
+      "eval_precision": 0.5774647887323944,
+      "eval_recall": 0.43233743409490333,
+      "eval_runtime": 3.1509,
+      "eval_samples_per_second": 541.75,
+      "eval_steps_per_second": 17.138,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.0788278579711914,
+      "learning_rate": 0.00016519312151174438,
+      "loss": 0.5413,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7258347978910369,
+      "eval_f1": 0.4845814977973568,
+      "eval_loss": 0.5296629071235657,
+      "eval_mcc": 0.33330907379505725,
+      "eval_precision": 0.6489675516224189,
+      "eval_recall": 0.3866432337434095,
+      "eval_runtime": 3.2724,
+      "eval_samples_per_second": 521.631,
+      "eval_steps_per_second": 16.502,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.197441339492798,
+      "learning_rate": 0.00014683833023266166,
+      "loss": 0.5154,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7258347978910369,
+      "eval_f1": 0.38421052631578945,
+      "eval_loss": 0.5396824479103088,
+      "eval_mcc": 0.32457545244467173,
+      "eval_precision": 0.7643979057591623,
+      "eval_recall": 0.2565905096660808,
+      "eval_runtime": 3.1857,
+      "eval_samples_per_second": 535.83,
+      "eval_steps_per_second": 16.951,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.9606778621673584,
+      "learning_rate": 0.00012848353895357893,
+      "loss": 0.504,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7264206209724663,
+      "eval_f1": 0.3942931258106355,
+      "eval_loss": 0.5155606269836426,
+      "eval_mcc": 0.32574276921975914,
+      "eval_precision": 0.7524752475247525,
+      "eval_recall": 0.2671353251318102,
+      "eval_runtime": 3.3181,
+      "eval_samples_per_second": 514.447,
+      "eval_steps_per_second": 16.274,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.5369954109191895,
+      "learning_rate": 0.00011012874767449624,
+      "loss": 0.4946,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7504393673110721,
+      "eval_f1": 0.5590062111801243,
+      "eval_loss": 0.5006516575813293,
+      "eval_mcc": 0.4049525635550248,
+      "eval_precision": 0.6801007556675063,
+      "eval_recall": 0.47451669595782076,
+      "eval_runtime": 3.155,
+      "eval_samples_per_second": 541.038,
+      "eval_steps_per_second": 17.115,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.3806962966918945,
+      "learning_rate": 9.177395639541353e-05,
+      "loss": 0.4829,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7586408904510837,
+      "eval_f1": 0.603082851637765,
+      "eval_loss": 0.486370325088501,
+      "eval_mcc": 0.43615024061600965,
+      "eval_precision": 0.6673773987206824,
+      "eval_recall": 0.5500878734622144,
+      "eval_runtime": 3.9493,
+      "eval_samples_per_second": 432.226,
+      "eval_steps_per_second": 13.673,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.009945392608643,
+      "learning_rate": 7.341916511633083e-05,
+      "loss": 0.4704,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7580550673696543,
+      "eval_f1": 0.5100830367734281,
+      "eval_loss": 0.4908476173877716,
+      "eval_mcc": 0.41865909968733495,
+      "eval_precision": 0.7846715328467153,
+      "eval_recall": 0.37785588752196836,
+      "eval_runtime": 3.1648,
+      "eval_samples_per_second": 539.371,
+      "eval_steps_per_second": 17.063,
+      "step": 1498
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.42345666885376,
+      "learning_rate": 5.506437383724812e-05,
+      "loss": 0.4564,
+      "step": 1712
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7662565905096661,
+      "eval_f1": 0.5973763874873865,
+      "eval_loss": 0.47338271141052246,
+      "eval_mcc": 0.4474691814812865,
+      "eval_precision": 0.7014218009478673,
+      "eval_recall": 0.5202108963093146,
+      "eval_runtime": 3.2515,
+      "eval_samples_per_second": 524.99,
+      "eval_steps_per_second": 16.608,
+      "step": 1712
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 7.744714260101318,
+      "learning_rate": 3.6709582558165414e-05,
+      "loss": 0.4528,
+      "step": 1926
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7656707674282367,
+      "eval_f1": 0.5975855130784709,
+      "eval_loss": 0.4673592448234558,
+      "eval_mcc": 0.4464084855010257,
+      "eval_precision": 0.6988235294117647,
+      "eval_recall": 0.5219683655536028,
+      "eval_runtime": 3.1615,
+      "eval_samples_per_second": 539.929,
+      "eval_steps_per_second": 17.08,
+      "step": 1926
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 5.320211887359619,
+      "learning_rate": 1.8354791279082707e-05,
+      "loss": 0.4449,
+      "step": 2140
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7750439367311072,
+      "eval_f1": 0.6335877862595419,
+      "eval_loss": 0.4649231731891632,
+      "eval_mcc": 0.47665988640122975,
+      "eval_precision": 0.6931106471816284,
+      "eval_recall": 0.5834797891036907,
+      "eval_runtime": 3.2751,
+      "eval_samples_per_second": 521.205,
+      "eval_steps_per_second": 16.488,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2354,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 11,
+  "save_steps": 500,
+  "total_flos": 5247756644400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9896635045471636,
+    "learning_rate": 0.00020190270406990977,
+    "num_train_epochs": 11,
+    "temperature": 11
+  }
+}

run-11/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b75acdfed96024e41f75d5f04d6bad8799c334ee9a4d3bf53ad9d0b94d6df4
+size 5048

run-11/checkpoint-2354/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-2354/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c8455ed7ddb848b491c3f9183148962c793cf1f02086a98ba43b722f6ae4ce
+size 17549312

run-11/checkpoint-2354/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c69c8a47d60a8229114b1a6e5765c5614534f2029777cdee4ab3dba9a2dc8f7
+size 35123898

run-11/checkpoint-2354/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86a1cc2be603ae8ad6d0dcc0791ff88331c7f3e5759ecb7af57b72362de36ff
+size 14308

run-11/checkpoint-2354/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b387f82045ee791432b3c7c6543dcba918e556c042dd019b2b69165ac772b8
+size 1064

run-11/checkpoint-2354/special_tokens_map.json

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

run-11/checkpoint-2354/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-11/checkpoint-2354/trainer_state.json

@@ -0,0 +1,246 @@
+{
+  "best_metric": 0.7750439367311072,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-2140",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 2354,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.918547630310059,
+      "learning_rate": 0.00018354791279082705,
+      "loss": 0.5995,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7053309900410076,
+      "eval_f1": 0.4944723618090453,
+      "eval_loss": 0.5527746677398682,
+      "eval_mcc": 0.29864842708933803,
+      "eval_precision": 0.5774647887323944,
+      "eval_recall": 0.43233743409490333,
+      "eval_runtime": 3.1509,
+      "eval_samples_per_second": 541.75,
+      "eval_steps_per_second": 17.138,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.0788278579711914,
+      "learning_rate": 0.00016519312151174438,
+      "loss": 0.5413,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7258347978910369,
+      "eval_f1": 0.4845814977973568,
+      "eval_loss": 0.5296629071235657,
+      "eval_mcc": 0.33330907379505725,
+      "eval_precision": 0.6489675516224189,
+      "eval_recall": 0.3866432337434095,
+      "eval_runtime": 3.2724,
+      "eval_samples_per_second": 521.631,
+      "eval_steps_per_second": 16.502,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.197441339492798,
+      "learning_rate": 0.00014683833023266166,
+      "loss": 0.5154,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7258347978910369,
+      "eval_f1": 0.38421052631578945,
+      "eval_loss": 0.5396824479103088,
+      "eval_mcc": 0.32457545244467173,
+      "eval_precision": 0.7643979057591623,
+      "eval_recall": 0.2565905096660808,
+      "eval_runtime": 3.1857,
+      "eval_samples_per_second": 535.83,
+      "eval_steps_per_second": 16.951,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.9606778621673584,
+      "learning_rate": 0.00012848353895357893,
+      "loss": 0.504,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7264206209724663,
+      "eval_f1": 0.3942931258106355,
+      "eval_loss": 0.5155606269836426,
+      "eval_mcc": 0.32574276921975914,
+      "eval_precision": 0.7524752475247525,
+      "eval_recall": 0.2671353251318102,
+      "eval_runtime": 3.3181,
+      "eval_samples_per_second": 514.447,
+      "eval_steps_per_second": 16.274,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.5369954109191895,
+      "learning_rate": 0.00011012874767449624,
+      "loss": 0.4946,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7504393673110721,
+      "eval_f1": 0.5590062111801243,
+      "eval_loss": 0.5006516575813293,
+      "eval_mcc": 0.4049525635550248,
+      "eval_precision": 0.6801007556675063,
+      "eval_recall": 0.47451669595782076,
+      "eval_runtime": 3.155,
+      "eval_samples_per_second": 541.038,
+      "eval_steps_per_second": 17.115,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.3806962966918945,
+      "learning_rate": 9.177395639541353e-05,
+      "loss": 0.4829,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7586408904510837,
+      "eval_f1": 0.603082851637765,
+      "eval_loss": 0.486370325088501,
+      "eval_mcc": 0.43615024061600965,
+      "eval_precision": 0.6673773987206824,
+      "eval_recall": 0.5500878734622144,
+      "eval_runtime": 3.9493,
+      "eval_samples_per_second": 432.226,
+      "eval_steps_per_second": 13.673,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.009945392608643,
+      "learning_rate": 7.341916511633083e-05,
+      "loss": 0.4704,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7580550673696543,
+      "eval_f1": 0.5100830367734281,
+      "eval_loss": 0.4908476173877716,
+      "eval_mcc": 0.41865909968733495,
+      "eval_precision": 0.7846715328467153,
+      "eval_recall": 0.37785588752196836,
+      "eval_runtime": 3.1648,
+      "eval_samples_per_second": 539.371,
+      "eval_steps_per_second": 17.063,
+      "step": 1498
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.42345666885376,
+      "learning_rate": 5.506437383724812e-05,
+      "loss": 0.4564,
+      "step": 1712
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7662565905096661,
+      "eval_f1": 0.5973763874873865,
+      "eval_loss": 0.47338271141052246,
+      "eval_mcc": 0.4474691814812865,
+      "eval_precision": 0.7014218009478673,
+      "eval_recall": 0.5202108963093146,
+      "eval_runtime": 3.2515,
+      "eval_samples_per_second": 524.99,
+      "eval_steps_per_second": 16.608,
+      "step": 1712
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 7.744714260101318,
+      "learning_rate": 3.6709582558165414e-05,
+      "loss": 0.4528,
+      "step": 1926
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7656707674282367,
+      "eval_f1": 0.5975855130784709,
+      "eval_loss": 0.4673592448234558,
+      "eval_mcc": 0.4464084855010257,
+      "eval_precision": 0.6988235294117647,
+      "eval_recall": 0.5219683655536028,
+      "eval_runtime": 3.1615,
+      "eval_samples_per_second": 539.929,
+      "eval_steps_per_second": 17.08,
+      "step": 1926
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 5.320211887359619,
+      "learning_rate": 1.8354791279082707e-05,
+      "loss": 0.4449,
+      "step": 2140
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7750439367311072,
+      "eval_f1": 0.6335877862595419,
+      "eval_loss": 0.4649231731891632,
+      "eval_mcc": 0.47665988640122975,
+      "eval_precision": 0.6931106471816284,
+      "eval_recall": 0.5834797891036907,
+      "eval_runtime": 3.2751,
+      "eval_samples_per_second": 521.205,
+      "eval_steps_per_second": 16.488,
+      "step": 2140
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 5.221016883850098,
+      "learning_rate": 0.0,
+      "loss": 0.4371,
+      "step": 2354
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7738722905682484,
+      "eval_f1": 0.6405959031657356,
+      "eval_loss": 0.46391916275024414,
+      "eval_mcc": 0.4782970414232871,
+      "eval_precision": 0.6811881188118812,
+      "eval_recall": 0.6045694200351494,
+      "eval_runtime": 3.1542,
+      "eval_samples_per_second": 541.178,
+      "eval_steps_per_second": 17.12,
+      "step": 2354
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2354,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 11,
+  "save_steps": 500,
+  "total_flos": 5772532308840.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9896635045471636,
+    "learning_rate": 0.00020190270406990977,
+    "num_train_epochs": 11,
+    "temperature": 11
+  }
+}

run-11/checkpoint-2354/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b75acdfed96024e41f75d5f04d6bad8799c334ee9a4d3bf53ad9d0b94d6df4
+size 5048

run-8/checkpoint-2140/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}