Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d02d211e7561875298f3c001e8380357c2c211b42c673a2a036e6425844c3f
+oid sha256:cf2844bb5895c089895f3baacf143af8bdbc6a35bdbd95d693233064cf88e5a8
 size 1340618660

run-10/checkpoint-2500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-10/checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a3c899825174a21280d99040391dafd2fb4b91921cc52510d15fe1d73b7aa9
+size 1340618660

run-10/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032cadaf3856159ea2c7c4c9d156457683853961f453784a4f4299f868655ed6
+size 2681472237

run-10/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba21e6de271ea59300bf3a1775b2bf5221b252ebeca24277a3f0a7fb49d6db7
+size 14244

run-10/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea9994621aa4abe7aa10dd4f69390db580350138abc5ceefa8b5dc96b312ea6
+size 1064

run-10/checkpoint-2500/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-2500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-10/checkpoint-2500/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.702412868632708,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7502514123916626,
+      "eval_loss": 0.47628718614578247,
+      "eval_runtime": 9.4864,
+      "eval_samples_per_second": 314.449,
+      "eval_steps_per_second": 19.712,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 11.133524894714355,
+      "learning_rate": 1.3824026202690149e-05,
+      "loss": 0.5239,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.4691523015499115,
+      "eval_runtime": 9.6019,
+      "eval_samples_per_second": 310.669,
+      "eval_steps_per_second": 19.475,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 12.096076011657715,
+      "learning_rate": 1.1684084066050808e-05,
+      "loss": 0.2819,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7730472683906555,
+      "eval_loss": 0.6077698469161987,
+      "eval_runtime": 9.4502,
+      "eval_samples_per_second": 315.654,
+      "eval_steps_per_second": 19.788,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7696949243545532,
+      "eval_loss": 0.8962089419364929,
+      "eval_runtime": 9.4938,
+      "eval_samples_per_second": 314.204,
+      "eval_steps_per_second": 19.697,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.9103776216506958,
+      "learning_rate": 9.544141929411465e-06,
+      "loss": 0.1205,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7790814638137817,
+      "eval_loss": 1.138683795928955,
+      "eval_runtime": 9.5013,
+      "eval_samples_per_second": 313.959,
+      "eval_steps_per_second": 19.682,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 12.819802284240723,
+      "learning_rate": 7.4041997927721225e-06,
+      "loss": 0.0447,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 1.263724446296692,
+      "eval_runtime": 9.4719,
+      "eval_samples_per_second": 314.933,
+      "eval_steps_per_second": 19.743,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.741857647895813,
+      "learning_rate": 5.264257656132781e-06,
+      "loss": 0.0301,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.44783784953936e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.596396833932949e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-10/checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47134252dc6f773c0096a54db073ad1298ed08b2898516facd775fca78de1342
+size 5048

run-10/checkpoint-3000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-10/checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d62f12e29d3b403c36d60eb0bfe76848b0a17f2b45d5b70af1ba3a93f8d5188
+size 1340618660

run-10/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f592ad18ac9b550ffef7f1c6c9a76b7a350c1bde2f879cf46e844d935f79381c
+size 2681472237

run-10/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cc5084c28610350139001bdf2e7741e2feb5bc0126e5b3ce15926d06089ebc
+size 14244

run-10/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d53fec68fe91c4f57806ca10a8ff6a7fc06a5737b0a9e0b1708fba31471ddc
+size 1064

run-10/checkpoint-3000/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-3000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-10/checkpoint-3000/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7502514123916626,
+      "eval_loss": 0.47628718614578247,
+      "eval_runtime": 9.4864,
+      "eval_samples_per_second": 314.449,
+      "eval_steps_per_second": 19.712,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 11.133524894714355,
+      "learning_rate": 1.3824026202690149e-05,
+      "loss": 0.5239,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.4691523015499115,
+      "eval_runtime": 9.6019,
+      "eval_samples_per_second": 310.669,
+      "eval_steps_per_second": 19.475,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 12.096076011657715,
+      "learning_rate": 1.1684084066050808e-05,
+      "loss": 0.2819,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7730472683906555,
+      "eval_loss": 0.6077698469161987,
+      "eval_runtime": 9.4502,
+      "eval_samples_per_second": 315.654,
+      "eval_steps_per_second": 19.788,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7696949243545532,
+      "eval_loss": 0.8962089419364929,
+      "eval_runtime": 9.4938,
+      "eval_samples_per_second": 314.204,
+      "eval_steps_per_second": 19.697,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.9103776216506958,
+      "learning_rate": 9.544141929411465e-06,
+      "loss": 0.1205,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7790814638137817,
+      "eval_loss": 1.138683795928955,
+      "eval_runtime": 9.5013,
+      "eval_samples_per_second": 313.959,
+      "eval_steps_per_second": 19.682,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 12.819802284240723,
+      "learning_rate": 7.4041997927721225e-06,
+      "loss": 0.0447,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 1.263724446296692,
+      "eval_runtime": 9.4719,
+      "eval_samples_per_second": 314.933,
+      "eval_steps_per_second": 19.743,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.741857647895813,
+      "learning_rate": 5.264257656132781e-06,
+      "loss": 0.0301,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7790814638137817,
+      "eval_loss": 1.3301361799240112,
+      "eval_runtime": 9.4495,
+      "eval_samples_per_second": 315.677,
+      "eval_steps_per_second": 19.789,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7787462472915649,
+      "eval_loss": 1.3093613386154175,
+      "eval_runtime": 9.6096,
+      "eval_samples_per_second": 310.419,
+      "eval_steps_per_second": 19.46,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 0.6469907760620117,
+      "learning_rate": 3.124315519493439e-06,
+      "loss": 0.0153,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.7238658858210836e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.596396833932949e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-10/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47134252dc6f773c0096a54db073ad1298ed08b2898516facd775fca78de1342
+size 5048

run-10/checkpoint-3500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-10/checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c5255a0d8cc33363013b8873279f3ca0672473c04df2665df74a51751b6953
+size 1340618660

run-10/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0499678807e49f720371175d17de0a2deb3950038e8bc43f6e58c6a7a54e02be
+size 2681472237

run-10/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1d1d89dd6f7639777970d77f6c7dc074edb948b4911bac5bcd126ef93417be
+size 14244

run-10/checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6ecbb99bc8efec196358738c78caa9bc93a8209200cd1808afb6c65b705800
+size 1064

run-10/checkpoint-3500/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-3500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-10/checkpoint-3500/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.383378016085791,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7502514123916626,
+      "eval_loss": 0.47628718614578247,
+      "eval_runtime": 9.4864,
+      "eval_samples_per_second": 314.449,
+      "eval_steps_per_second": 19.712,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 11.133524894714355,
+      "learning_rate": 1.3824026202690149e-05,
+      "loss": 0.5239,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.4691523015499115,
+      "eval_runtime": 9.6019,
+      "eval_samples_per_second": 310.669,
+      "eval_steps_per_second": 19.475,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 12.096076011657715,
+      "learning_rate": 1.1684084066050808e-05,
+      "loss": 0.2819,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7730472683906555,
+      "eval_loss": 0.6077698469161987,
+      "eval_runtime": 9.4502,
+      "eval_samples_per_second": 315.654,
+      "eval_steps_per_second": 19.788,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7696949243545532,
+      "eval_loss": 0.8962089419364929,
+      "eval_runtime": 9.4938,
+      "eval_samples_per_second": 314.204,
+      "eval_steps_per_second": 19.697,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.9103776216506958,
+      "learning_rate": 9.544141929411465e-06,
+      "loss": 0.1205,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7790814638137817,
+      "eval_loss": 1.138683795928955,
+      "eval_runtime": 9.5013,
+      "eval_samples_per_second": 313.959,
+      "eval_steps_per_second": 19.682,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 12.819802284240723,
+      "learning_rate": 7.4041997927721225e-06,
+      "loss": 0.0447,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7750586867332458,
+      "eval_loss": 1.263724446296692,
+      "eval_runtime": 9.4719,
+      "eval_samples_per_second": 314.933,
+      "eval_steps_per_second": 19.743,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.741857647895813,
+      "learning_rate": 5.264257656132781e-06,
+      "loss": 0.0301,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7790814638137817,
+      "eval_loss": 1.3301361799240112,
+      "eval_runtime": 9.4495,
+      "eval_samples_per_second": 315.677,
+      "eval_steps_per_second": 19.789,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7787462472915649,
+      "eval_loss": 1.3093613386154175,
+      "eval_runtime": 9.6096,
+      "eval_samples_per_second": 310.419,
+      "eval_steps_per_second": 19.46,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 0.6469907760620117,
+      "learning_rate": 3.124315519493439e-06,
+      "loss": 0.0153,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7770700454711914,
+      "eval_loss": 1.3546313047409058,
+      "eval_runtime": 9.6011,
+      "eval_samples_per_second": 310.692,
+      "eval_steps_per_second": 19.477,
+      "step": 3357
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 4.288186550140381,
+      "learning_rate": 9.843733828540973e-07,
+      "loss": 0.0116,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2.000097781399735e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.596396833932949e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-10/checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47134252dc6f773c0096a54db073ad1298ed08b2898516facd775fca78de1342
+size 5048

run-11/checkpoint-500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2844bb5895c089895f3baacf143af8bdbc6a35bdbd95d693233064cf88e5a8
+size 1340618660

run-11/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa18cffad33eb46417878f832a3bf17cd17e7862df83dccb54ada017373d3bd
+size 2681472237

run-11/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36b07531802314760ae1506940c4c080c120d9680fd6ffed0e22965b2cace9f
+size 14244

run-11/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b4a17a23d8a46e7de6a68b97d26848c3e5df0fedc18dd36528f2f59af4cfa0
+size 1064

run-11/checkpoint-500/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-500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-500/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3404825737265416,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7582970261573792,
+      "eval_loss": 0.47316744923591614,
+      "eval_runtime": 9.4669,
+      "eval_samples_per_second": 315.098,
+      "eval_steps_per_second": 19.753,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 10.698078155517578,
+      "learning_rate": 1.3190684345219897e-05,
+      "loss": 0.5103,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2761230492754704.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5232585946647127e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-11/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea0c85a511ff99603991d94be896e3984a3c9119a97f449093b304a9f1146e6
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47134252dc6f773c0096a54db073ad1298ed08b2898516facd775fca78de1342
+oid sha256:7ea0c85a511ff99603991d94be896e3984a3c9119a97f449093b304a9f1146e6
 size 5048