Training in progress, epoch 1

logs/events.out.tfevents.1709743617.d65e8524b0f6.5185.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd3edecd4b34bf433593b8db9a0701e415dc1c7d6588e8abc9715387483cd6d
-size 5997
+oid sha256:0a22a8506befe2b5418e69dc19a020aaa01cbae5562e10c407acf9c005c458d9
+size 9766

logs/events.out.tfevents.1709744396.d65e8524b0f6.5185.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca551e81a998c9c0286c4fd5e81f6ae29a3c1b1224e11717a7c556d0fece8b8
+size 5313

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57db14253ca1fd241e823b6c203cf94037878d1575b293d3aae91cf1bfa2f479
+oid sha256:51a935794de403f21bd54072fc625be3ef950ae5022098e29b1e547e13cbe384
 size 17549312

run-10/checkpoint-64/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-64/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a935794de403f21bd54072fc625be3ef950ae5022098e29b1e547e13cbe384
+size 17549312

run-10/checkpoint-64/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363db406b381045f5f9b4481326206add3058e28b1c3d6ee0d72ba29bc0af253
+size 35122746

run-10/checkpoint-64/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81e0709cee2e0cbd7f20f3b37b5237db97916e48290254907ac493726d5be56
+size 14054

run-10/checkpoint-64/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40fb077b778692a6bb6014df36a6ac930274c6ec3bcee6d1bf632ac4c9b720f0
+size 1064

run-10/checkpoint-64/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-64/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-64/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.773972602739726,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-64",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 64,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.969868183135986,
+      "learning_rate": 0.0006324213595544264,
+      "loss": 0.5787,
+      "step": 64
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.773972602739726,
+      "eval_f1": 0.8070175438596492,
+      "eval_loss": 0.48913490772247314,
+      "eval_precision": 0.7040816326530612,
+      "eval_recall": 0.9452054794520548,
+      "eval_runtime": 27.7283,
+      "eval_samples_per_second": 36.858,
+      "eval_steps_per_second": 1.154,
+      "step": 64
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9990297556295253,
+    "learning_rate": 0.000790526699443033,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 48,
+    "temperature": 30
+  }
+}

run-10/checkpoint-64/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10318ca028e91ec5668eb2cb6ad3dd869bdfca116061dca662c8b2df479ddbc
+size 4920

run-9/checkpoint-486/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-9/checkpoint-486/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5da3e053d21edc60eba1201b82f0691fc93d3628123c63e464f1fe30d07a931
+size 17549312

run-9/checkpoint-486/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d5db002f29ad2a38211e907b6850d9cd6f7564f327bce78576d5e61f67a46f
+size 35122746

run-9/checkpoint-486/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c3673de8a74b585e61908dcf9f2cd648f988d9cb931bd93ef977a62b7245ce
+size 14054

run-9/checkpoint-486/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9f073abb271405e6f8322f9edd75c2b089ab0e00c90a314f15e686bca9b1f9
+size 1064

run-9/checkpoint-486/special_tokens_map.json

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

run-9/checkpoint-486/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-9/checkpoint-486/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.8160469667318982,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-405",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 486,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9513042569160461,
+      "learning_rate": 0.0005954099159667608,
+      "loss": 0.499,
+      "step": 81
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6829745596868885,
+      "eval_f1": 0.6067961165048544,
+      "eval_loss": 0.4608267843723297,
+      "eval_precision": 0.7987220447284346,
+      "eval_recall": 0.4892367906066536,
+      "eval_runtime": 28.3141,
+      "eval_samples_per_second": 36.095,
+      "eval_steps_per_second": 1.13,
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7321057319641113,
+      "learning_rate": 0.0004961749299723006,
+      "loss": 0.4578,
+      "step": 162
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7827788649706457,
+      "eval_f1": 0.798913043478261,
+      "eval_loss": 0.42703160643577576,
+      "eval_precision": 0.7436762225969646,
+      "eval_recall": 0.863013698630137,
+      "eval_runtime": 28.5611,
+      "eval_samples_per_second": 35.783,
+      "eval_steps_per_second": 1.12,
+      "step": 162
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.0545783042907715,
+      "learning_rate": 0.00039693994397784046,
+      "loss": 0.4299,
+      "step": 243
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7954990215264188,
+      "eval_f1": 0.8168273444347064,
+      "eval_loss": 0.4317159950733185,
+      "eval_precision": 0.7396825396825397,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 28.0555,
+      "eval_samples_per_second": 36.428,
+      "eval_steps_per_second": 1.141,
+      "step": 243
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1239681243896484,
+      "learning_rate": 0.0002977049579833804,
+      "loss": 0.4141,
+      "step": 324
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8052837573385518,
+      "eval_f1": 0.7995971802618329,
+      "eval_loss": 0.41590413451194763,
+      "eval_precision": 0.8236514522821576,
+      "eval_recall": 0.776908023483366,
+      "eval_runtime": 28.4853,
+      "eval_samples_per_second": 35.878,
+      "eval_steps_per_second": 1.123,
+      "step": 324
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.6590023040771484,
+      "learning_rate": 0.00019846997198892023,
+      "loss": 0.4038,
+      "step": 405
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8160469667318982,
+      "eval_f1": 0.8256029684601114,
+      "eval_loss": 0.40745633840560913,
+      "eval_precision": 0.7848324514991182,
+      "eval_recall": 0.8708414872798435,
+      "eval_runtime": 28.3469,
+      "eval_samples_per_second": 36.053,
+      "eval_steps_per_second": 1.129,
+      "step": 405
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.6547752618789673,
+      "learning_rate": 9.923498599446012e-05,
+      "loss": 0.3966,
+      "step": 486
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8111545988258317,
+      "eval_f1": 0.8259693417493238,
+      "eval_loss": 0.40955477952957153,
+      "eval_precision": 0.7658862876254181,
+      "eval_recall": 0.8962818003913894,
+      "eval_runtime": 27.9254,
+      "eval_samples_per_second": 36.598,
+      "eval_steps_per_second": 1.146,
+      "step": 486
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 567,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1414171183680.0,
+  "train_batch_size": 38,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7591558093291033,
+    "learning_rate": 0.0006946449019612209,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 38,
+    "temperature": 16
+  }
+}

run-9/checkpoint-486/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fad448e04565949ea4efea7c003869a9eee3ec99659d009b28c258bd8f5483
+size 4920

run-9/checkpoint-567/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-9/checkpoint-567/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceeb5958cee6b128e8a78d58410343ce34693e93e1193bb7f84e13ff72a35764
+size 17549312

run-9/checkpoint-567/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126cb59e2aef56c9d1a87cc429638842df54e49eee5a25789f036ffc57cc7812
+size 35122746

run-9/checkpoint-567/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e4f9e302afb3c2b76a73bf918a3e6f210099a9d0460887c8d02169bdcd7139
+size 14054

run-9/checkpoint-567/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666dabf8c3e78327a9272c42611f37d641d40e4183325279625b3f7f315de73d
+size 1064

run-9/checkpoint-567/special_tokens_map.json

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

run-9/checkpoint-567/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-9/checkpoint-567/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.8228962818003914,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-567",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 567,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9513042569160461,
+      "learning_rate": 0.0005954099159667608,
+      "loss": 0.499,
+      "step": 81
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6829745596868885,
+      "eval_f1": 0.6067961165048544,
+      "eval_loss": 0.4608267843723297,
+      "eval_precision": 0.7987220447284346,
+      "eval_recall": 0.4892367906066536,
+      "eval_runtime": 28.3141,
+      "eval_samples_per_second": 36.095,
+      "eval_steps_per_second": 1.13,
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7321057319641113,
+      "learning_rate": 0.0004961749299723006,
+      "loss": 0.4578,
+      "step": 162
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7827788649706457,
+      "eval_f1": 0.798913043478261,
+      "eval_loss": 0.42703160643577576,
+      "eval_precision": 0.7436762225969646,
+      "eval_recall": 0.863013698630137,
+      "eval_runtime": 28.5611,
+      "eval_samples_per_second": 35.783,
+      "eval_steps_per_second": 1.12,
+      "step": 162
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.0545783042907715,
+      "learning_rate": 0.00039693994397784046,
+      "loss": 0.4299,
+      "step": 243
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7954990215264188,
+      "eval_f1": 0.8168273444347064,
+      "eval_loss": 0.4317159950733185,
+      "eval_precision": 0.7396825396825397,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 28.0555,
+      "eval_samples_per_second": 36.428,
+      "eval_steps_per_second": 1.141,
+      "step": 243
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1239681243896484,
+      "learning_rate": 0.0002977049579833804,
+      "loss": 0.4141,
+      "step": 324
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8052837573385518,
+      "eval_f1": 0.7995971802618329,
+      "eval_loss": 0.41590413451194763,
+      "eval_precision": 0.8236514522821576,
+      "eval_recall": 0.776908023483366,
+      "eval_runtime": 28.4853,
+      "eval_samples_per_second": 35.878,
+      "eval_steps_per_second": 1.123,
+      "step": 324
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.6590023040771484,
+      "learning_rate": 0.00019846997198892023,
+      "loss": 0.4038,
+      "step": 405
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8160469667318982,
+      "eval_f1": 0.8256029684601114,
+      "eval_loss": 0.40745633840560913,
+      "eval_precision": 0.7848324514991182,
+      "eval_recall": 0.8708414872798435,
+      "eval_runtime": 28.3469,
+      "eval_samples_per_second": 36.053,
+      "eval_steps_per_second": 1.129,
+      "step": 405
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.6547752618789673,
+      "learning_rate": 9.923498599446012e-05,
+      "loss": 0.3966,
+      "step": 486
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8111545988258317,
+      "eval_f1": 0.8259693417493238,
+      "eval_loss": 0.40955477952957153,
+      "eval_precision": 0.7658862876254181,
+      "eval_recall": 0.8962818003913894,
+      "eval_runtime": 27.9254,
+      "eval_samples_per_second": 36.598,
+      "eval_steps_per_second": 1.146,
+      "step": 486
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.1821346282958984,
+      "learning_rate": 0.0,
+      "loss": 0.3931,
+      "step": 567
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8271251193887298,
+      "eval_loss": 0.40074673295021057,
+      "eval_precision": 0.8078358208955224,
+      "eval_recall": 0.8473581213307241,
+      "eval_runtime": 27.6176,
+      "eval_samples_per_second": 37.005,
+      "eval_steps_per_second": 1.159,
+      "step": 567
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 567,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1649866380960.0,
+  "train_batch_size": 38,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7591558093291033,
+    "learning_rate": 0.0006946449019612209,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 38,
+    "temperature": 16
+  }
+}

run-9/checkpoint-567/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fad448e04565949ea4efea7c003869a9eee3ec99659d009b28c258bd8f5483
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1777509d483b05de90fbacc92d98f5cf027460114d71f11ec490e4a5ee41350
+oid sha256:f10318ca028e91ec5668eb2cb6ad3dd869bdfca116061dca662c8b2df479ddbc
 size 4920