Training in progress, epoch 1

logs/events.out.tfevents.1711298025.8cc2eef2edb7.2942.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e135f564bfe5361558eda1a54e02747357b3662444d10b36dbdaace1f71f194
-size 6137
+oid sha256:a7276f3aeca711b03c7d2938b880c16f10366e767f7aed91d61c0a46df288cd1
+size 9411

logs/events.out.tfevents.1711298142.8cc2eef2edb7.2942.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb456eea9ebcc9ff490aa7e829a056d4bd8258c888577a196943ac81ad98b30
+size 5406

logs/events.out.tfevents.1711298162.8cc2eef2edb7.2942.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74257a401d4539b51f15033eed98e7b6cda86bae04bd1342dfe627cce5293a45
+size 5407

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f44df878d28abc84112bb60946d51999835ba4c8390b93448ebdfea2803581c
+oid sha256:b00146d689576308ddb1157deb4455691b3ce09e0f3db31e7ecc56ae7215dfd6
 size 17549312

run-16/checkpoint-1188/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-16/checkpoint-1188/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ca29e9fafb08024ed4d97930ec863c8f89bfe3080abd675b9aa6e09233bee6
+size 17549312

run-16/checkpoint-1188/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a93e9bbd2fabf07bc19f1590e3736d6541ffbc968e86ba49d36eb73c0eb8ec
+size 35123898

run-16/checkpoint-1188/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a05bef4801db254faeaae411c6646dc08c36b663ea365ca6cd58d95d1762f2
+size 14308

run-16/checkpoint-1188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27911299405f7876305f8deee9f323893d2b70be6cf8fc44d8c3556af207aac4
+size 1064

run-16/checkpoint-1188/special_tokens_map.json

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

run-16/checkpoint-1188/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-16/checkpoint-1188/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6633663366336634,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-1188",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1188,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6842290163040161,
+      "learning_rate": 0.00013702102722124262,
+      "loss": 0.6194,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5069306930693069,
+      "eval_f1": 0.023529411764705882,
+      "eval_loss": 0.6244187951087952,
+      "eval_mcc": 0.07745844229442526,
+      "eval_precision": 1.0,
+      "eval_recall": 0.011904761904761904,
+      "eval_runtime": 0.9461,
+      "eval_samples_per_second": 533.75,
+      "eval_steps_per_second": 16.911,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.26532781124115,
+      "learning_rate": 0.0001096168217769941,
+      "loss": 0.6076,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6,
+      "eval_f1": 0.6366906474820144,
+      "eval_loss": 0.6058114767074585,
+      "eval_mcc": 0.20470740045924352,
+      "eval_precision": 0.5822368421052632,
+      "eval_recall": 0.7023809523809523,
+      "eval_runtime": 0.946,
+      "eval_samples_per_second": 533.844,
+      "eval_steps_per_second": 16.914,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.4105544090270996,
+      "learning_rate": 8.221261633274557e-05,
+      "loss": 0.5931,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6138613861386139,
+      "eval_f1": 0.6859903381642513,
+      "eval_loss": 0.5950631499290466,
+      "eval_mcc": 0.25770627027550275,
+      "eval_precision": 0.5772357723577236,
+      "eval_recall": 0.8452380952380952,
+      "eval_runtime": 0.9327,
+      "eval_samples_per_second": 541.416,
+      "eval_steps_per_second": 17.154,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.0386664867401123,
+      "learning_rate": 5.480841088849705e-05,
+      "loss": 0.5675,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6633663366336634,
+      "eval_f1": 0.6953405017921147,
+      "eval_loss": 0.5774483680725098,
+      "eval_mcc": 0.3347533105713868,
+      "eval_precision": 0.6339869281045751,
+      "eval_recall": 0.7698412698412699,
+      "eval_runtime": 0.9362,
+      "eval_samples_per_second": 539.398,
+      "eval_steps_per_second": 17.09,
+      "step": 1188
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 2922805063920.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8675008492554994,
+    "learning_rate": 0.00016442523266549115,
+    "num_train_epochs": 6,
+    "temperature": 44
+  }
+}

run-16/checkpoint-1188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a760801f195b6d23ef8a34d598b151e1a6b3508f20799769efbe955042d9987a
+size 4920

run-16/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-16/checkpoint-1782/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c7f294a757eb8bf5aeab5b9691afdeb5cacf12a1b133d54d39b3327a1ff398
+size 17549312

run-16/checkpoint-1782/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3dc977073a6934e75e68bbfcdc5c453af220b60245f651f61973a7ec910e614
+size 35123898

run-16/checkpoint-1782/rng_state.pth

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

run-16/checkpoint-1782/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68a7fac444803a0a3e662fb38153e0c94973b048177237efa58161fd72b5807
+size 1064

run-16/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-16/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-16/checkpoint-1782/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.6633663366336634,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-1188",
+  "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": 1.6842290163040161,
+      "learning_rate": 0.00013702102722124262,
+      "loss": 0.6194,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5069306930693069,
+      "eval_f1": 0.023529411764705882,
+      "eval_loss": 0.6244187951087952,
+      "eval_mcc": 0.07745844229442526,
+      "eval_precision": 1.0,
+      "eval_recall": 0.011904761904761904,
+      "eval_runtime": 0.9461,
+      "eval_samples_per_second": 533.75,
+      "eval_steps_per_second": 16.911,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.26532781124115,
+      "learning_rate": 0.0001096168217769941,
+      "loss": 0.6076,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6,
+      "eval_f1": 0.6366906474820144,
+      "eval_loss": 0.6058114767074585,
+      "eval_mcc": 0.20470740045924352,
+      "eval_precision": 0.5822368421052632,
+      "eval_recall": 0.7023809523809523,
+      "eval_runtime": 0.946,
+      "eval_samples_per_second": 533.844,
+      "eval_steps_per_second": 16.914,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.4105544090270996,
+      "learning_rate": 8.221261633274557e-05,
+      "loss": 0.5931,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6138613861386139,
+      "eval_f1": 0.6859903381642513,
+      "eval_loss": 0.5950631499290466,
+      "eval_mcc": 0.25770627027550275,
+      "eval_precision": 0.5772357723577236,
+      "eval_recall": 0.8452380952380952,
+      "eval_runtime": 0.9327,
+      "eval_samples_per_second": 541.416,
+      "eval_steps_per_second": 17.154,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.0386664867401123,
+      "learning_rate": 5.480841088849705e-05,
+      "loss": 0.5675,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6633663366336634,
+      "eval_f1": 0.6953405017921147,
+      "eval_loss": 0.5774483680725098,
+      "eval_mcc": 0.3347533105713868,
+      "eval_precision": 0.6339869281045751,
+      "eval_recall": 0.7698412698412699,
+      "eval_runtime": 0.9362,
+      "eval_samples_per_second": 539.398,
+      "eval_steps_per_second": 17.09,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.236018180847168,
+      "learning_rate": 2.7404205444248525e-05,
+      "loss": 0.557,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6613861386138614,
+      "eval_f1": 0.6984126984126985,
+      "eval_loss": 0.576128363609314,
+      "eval_mcc": 0.3336455858078349,
+      "eval_precision": 0.6285714285714286,
+      "eval_recall": 0.7857142857142857,
+      "eval_runtime": 0.9461,
+      "eval_samples_per_second": 533.775,
+      "eval_steps_per_second": 16.912,
+      "step": 1485
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.6593701839447021,
+      "learning_rate": 0.0,
+      "loss": 0.5524,
+      "step": 1782
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6495049504950495,
+      "eval_f1": 0.6752293577981651,
+      "eval_loss": 0.5702252388000488,
+      "eval_mcc": 0.3032544177266147,
+      "eval_precision": 0.6279863481228669,
+      "eval_recall": 0.7301587301587301,
+      "eval_runtime": 0.9409,
+      "eval_samples_per_second": 536.729,
+      "eval_steps_per_second": 17.005,
+      "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": 0.8675008492554994,
+    "learning_rate": 0.00016442523266549115,
+    "num_train_epochs": 6,
+    "temperature": 44
+  }
+}

run-16/checkpoint-1782/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a760801f195b6d23ef8a34d598b151e1a6b3508f20799769efbe955042d9987a
+size 4920

run-18/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-18/checkpoint-297/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00146d689576308ddb1157deb4455691b3ce09e0f3db31e7ecc56ae7215dfd6
+size 17549312

run-18/checkpoint-297/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb2db184d36ba577d015362fa0543af808156082e7bd70246174d3d506987e4
+size 35123898

run-18/checkpoint-297/rng_state.pth

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

run-18/checkpoint-297/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8647ff68aa1f6840661bcc3b84f1c46cfbe4cf93809a1c2b1e819edb88818319
+size 1064

run-18/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-18/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-18/checkpoint-297/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5287128712871287,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/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": 1.6970789432525635,
+      "learning_rate": 0.0001678982407816263,
+      "loss": 0.6448,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5287128712871287,
+      "eval_f1": 0.22222222222222224,
+      "eval_loss": 0.6524360179901123,
+      "eval_mcc": 0.09039579598072835,
+      "eval_precision": 0.6296296296296297,
+      "eval_recall": 0.1349206349206349,
+      "eval_runtime": 0.9373,
+      "eval_samples_per_second": 538.78,
+      "eval_steps_per_second": 17.07,
+      "step": 297
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2079,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 730701265980.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9135980547715112,
+    "learning_rate": 0.00019588128091189738,
+    "num_train_epochs": 7,
+    "temperature": 19
+  }
+}

run-18/checkpoint-297/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be51b8bea9f36c48824e7746075aabaa63845e60abf2a29043e4a3f5e851715
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a760801f195b6d23ef8a34d598b151e1a6b3508f20799769efbe955042d9987a
+oid sha256:0be51b8bea9f36c48824e7746075aabaa63845e60abf2a29043e4a3f5e851715
 size 4920