Training in progress, epoch 1

logs/events.out.tfevents.1713587703.1376c752d37a.9760.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ee3976d5e0bd81820b27e7535795b535b15d9f8f89a4f21961891fffee2f61
-size 6213
+oid sha256:9709c57c97b5c1d8d6104bc11007b51f94fe7f6f9a5206a325e9c5284453c812
+size 10217

logs/events.out.tfevents.1713587822.1376c752d37a.9760.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7336b3e9ad06d0cf754317a6f5329b7990c8e5d8eae8d7f33bdca1d99dc4df91
+size 5483

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5e7a82abd03878f588793986eb244c51243c6303cea3a5259a4b4d9971fd43
+oid sha256:c760849f54d8a559a8f33f29f760851e9e74f38ca6a86904333d9d7911caabcb
 size 17549312

run-10/checkpoint-214/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-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c760849f54d8a559a8f33f29f760851e9e74f38ca6a86904333d9d7911caabcb
+size 17549312

run-10/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235bd4c9fa60419081711c10b3d4893ee4f1be9a9eb8f1f8e3c44a163f038965
+size 35123898

run-10/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
+size 14308

run-10/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688c6e3ae9afeaaa8ed33b66f9de3acbdd8dc58548e2e3b2128fa50f04e555d5
+size 1064

run-10/checkpoint-214/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-214/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-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6654950205038078,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0974807739257812,
+      "learning_rate": 0.0004326089412215258,
+      "loss": 0.1568,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6654950205038078,
+      "eval_f1": 0.02393162393162393,
+      "eval_loss": 0.14753811061382294,
+      "eval_mcc": 0.021494295311278402,
+      "eval_precision": 0.4375,
+      "eval_recall": 0.012302284710017574,
+      "eval_runtime": 3.1372,
+      "eval_samples_per_second": 544.118,
+      "eval_steps_per_second": 17.213,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.22222976837593644,
+    "learning_rate": 0.0004806766013572509,
+    "num_train_epochs": 10,
+    "temperature": 30
+  }
+}

run-10/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1e2c15e1a8520a4fcd42f95a999b7b5dccad7eb96455bf4a3b6fdb073ddf90
+size 5048

run-9/checkpoint-1284/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-9/checkpoint-1284/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843b2e11c4777b9825d382bb7837706be6b271674a5e651bab5dd0b8f055d77c
+size 17549312

run-9/checkpoint-1284/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f5cdac2c9ed0f5edd495d2c5551c09325beb8ec20d58aad8c19c475b0fa54c
+size 35123898

run-9/checkpoint-1284/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa74fb48b8739c352726086ee20186281632dbf682ba20839e3522db3e3b091
+size 14308

run-9/checkpoint-1284/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32e15270b9441b6f7d657c5f51387098dee66f8c9b32098242fa3ecf6e2dd68
+size 1064

run-9/checkpoint-1284/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-1284/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-1284/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.7533684827182191,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-1284",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1284,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.803707122802734,
+      "learning_rate": 0.00012883203919617986,
+      "loss": 0.5857,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7106033977738723,
+      "eval_f1": 0.4665226781857451,
+      "eval_loss": 0.5316944122314453,
+      "eval_mcc": 0.2963991807057883,
+      "eval_precision": 0.6050420168067226,
+      "eval_recall": 0.37961335676625657,
+      "eval_runtime": 3.1407,
+      "eval_samples_per_second": 543.517,
+      "eval_steps_per_second": 17.194,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.514796733856201,
+      "learning_rate": 0.00010736003266348323,
+      "loss": 0.5209,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7375512595196251,
+      "eval_f1": 0.5343035343035344,
+      "eval_loss": 0.5052611827850342,
+      "eval_mcc": 0.37194852790942917,
+      "eval_precision": 0.6539440203562341,
+      "eval_recall": 0.45166959578207383,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 543.345,
+      "eval_steps_per_second": 17.188,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.8996012210845947,
+      "learning_rate": 8.588802613078658e-05,
+      "loss": 0.4988,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7510251903925015,
+      "eval_f1": 0.5464247598719317,
+      "eval_loss": 0.4990246295928955,
+      "eval_mcc": 0.40293110575869034,
+      "eval_precision": 0.6956521739130435,
+      "eval_recall": 0.44991212653778556,
+      "eval_runtime": 3.1538,
+      "eval_samples_per_second": 541.253,
+      "eval_steps_per_second": 17.122,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.772945404052734,
+      "learning_rate": 6.441601959808993e-05,
+      "loss": 0.4877,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7504393673110721,
+      "eval_f1": 0.5468085106382979,
+      "eval_loss": 0.4924391210079193,
+      "eval_mcc": 0.4017490048024081,
+      "eval_precision": 0.692722371967655,
+      "eval_recall": 0.45166959578207383,
+      "eval_runtime": 3.1361,
+      "eval_samples_per_second": 544.315,
+      "eval_steps_per_second": 17.219,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.012472152709961,
+      "learning_rate": 4.294401306539329e-05,
+      "loss": 0.4777,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7480960749853545,
+      "eval_f1": 0.5865384615384616,
+      "eval_loss": 0.49057498574256897,
+      "eval_mcc": 0.41147957570448196,
+      "eval_precision": 0.6475583864118896,
+      "eval_recall": 0.5360281195079086,
+      "eval_runtime": 3.1355,
+      "eval_samples_per_second": 544.41,
+      "eval_steps_per_second": 17.222,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.066332817077637,
+      "learning_rate": 2.1472006532696646e-05,
+      "loss": 0.473,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7533684827182191,
+      "eval_f1": 0.5768844221105528,
+      "eval_loss": 0.4869697391986847,
+      "eval_mcc": 0.4163848262303271,
+      "eval_precision": 0.6737089201877934,
+      "eval_recall": 0.5043936731107206,
+      "eval_runtime": 3.1259,
+      "eval_samples_per_second": 546.088,
+      "eval_steps_per_second": 17.275,
+      "step": 1284
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 3148653986640.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9569611105058125,
+    "learning_rate": 0.00015030404572887653,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-9/checkpoint-1284/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fea319273d6fad4c679e9197d2d5d7068b8b820132928c6cc3b76d4197ed182
+size 5048

run-9/checkpoint-1498/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-9/checkpoint-1498/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a826654879d40774c5b70abfd02f0724d88b5de6aecad15599069bddd81eca4a
+size 17549312

run-9/checkpoint-1498/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c109c7495b63e6e60479419094e66ace79379acbf77b8af5a8865811b240f930
+size 35123898

run-9/checkpoint-1498/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec7baa77763623ab6f5c0a3afb24b20f15950a2841a41419e9c31b1269a80a7
+size 14308

run-9/checkpoint-1498/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6505da9d8754486fd273539943850641bf00b8f420f977e2992e131ef255bfe5
+size 1064

run-9/checkpoint-1498/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-1498/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-1498/trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 0.7533684827182191,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-1284",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1498,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.803707122802734,
+      "learning_rate": 0.00012883203919617986,
+      "loss": 0.5857,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7106033977738723,
+      "eval_f1": 0.4665226781857451,
+      "eval_loss": 0.5316944122314453,
+      "eval_mcc": 0.2963991807057883,
+      "eval_precision": 0.6050420168067226,
+      "eval_recall": 0.37961335676625657,
+      "eval_runtime": 3.1407,
+      "eval_samples_per_second": 543.517,
+      "eval_steps_per_second": 17.194,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.514796733856201,
+      "learning_rate": 0.00010736003266348323,
+      "loss": 0.5209,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7375512595196251,
+      "eval_f1": 0.5343035343035344,
+      "eval_loss": 0.5052611827850342,
+      "eval_mcc": 0.37194852790942917,
+      "eval_precision": 0.6539440203562341,
+      "eval_recall": 0.45166959578207383,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 543.345,
+      "eval_steps_per_second": 17.188,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.8996012210845947,
+      "learning_rate": 8.588802613078658e-05,
+      "loss": 0.4988,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7510251903925015,
+      "eval_f1": 0.5464247598719317,
+      "eval_loss": 0.4990246295928955,
+      "eval_mcc": 0.40293110575869034,
+      "eval_precision": 0.6956521739130435,
+      "eval_recall": 0.44991212653778556,
+      "eval_runtime": 3.1538,
+      "eval_samples_per_second": 541.253,
+      "eval_steps_per_second": 17.122,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.772945404052734,
+      "learning_rate": 6.441601959808993e-05,
+      "loss": 0.4877,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7504393673110721,
+      "eval_f1": 0.5468085106382979,
+      "eval_loss": 0.4924391210079193,
+      "eval_mcc": 0.4017490048024081,
+      "eval_precision": 0.692722371967655,
+      "eval_recall": 0.45166959578207383,
+      "eval_runtime": 3.1361,
+      "eval_samples_per_second": 544.315,
+      "eval_steps_per_second": 17.219,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.012472152709961,
+      "learning_rate": 4.294401306539329e-05,
+      "loss": 0.4777,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7480960749853545,
+      "eval_f1": 0.5865384615384616,
+      "eval_loss": 0.49057498574256897,
+      "eval_mcc": 0.41147957570448196,
+      "eval_precision": 0.6475583864118896,
+      "eval_recall": 0.5360281195079086,
+      "eval_runtime": 3.1355,
+      "eval_samples_per_second": 544.41,
+      "eval_steps_per_second": 17.222,
+      "step": 1070
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.066332817077637,
+      "learning_rate": 2.1472006532696646e-05,
+      "loss": 0.473,
+      "step": 1284
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7533684827182191,
+      "eval_f1": 0.5768844221105528,
+      "eval_loss": 0.4869697391986847,
+      "eval_mcc": 0.4163848262303271,
+      "eval_precision": 0.6737089201877934,
+      "eval_recall": 0.5043936731107206,
+      "eval_runtime": 3.1259,
+      "eval_samples_per_second": 546.088,
+      "eval_steps_per_second": 17.275,
+      "step": 1284
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 7.029488563537598,
+      "learning_rate": 0.0,
+      "loss": 0.4681,
+      "step": 1498
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7533684827182191,
+      "eval_f1": 0.5852216748768473,
+      "eval_loss": 0.48801371455192566,
+      "eval_mcc": 0.41958508363357955,
+      "eval_precision": 0.6659192825112108,
+      "eval_recall": 0.5219683655536028,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 543.356,
+      "eval_steps_per_second": 17.189,
+      "step": 1498
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 3673429651080.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9569611105058125,
+    "learning_rate": 0.00015030404572887653,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-9/checkpoint-1498/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fea319273d6fad4c679e9197d2d5d7068b8b820132928c6cc3b76d4197ed182
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fea319273d6fad4c679e9197d2d5d7068b8b820132928c6cc3b76d4197ed182
+oid sha256:ce1e2c15e1a8520a4fcd42f95a999b7b5dccad7eb96455bf4a3b6fdb073ddf90
 size 5048