Training in progress, step 6500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e055789496ecfb0bd5d04cefeda4b729150af3930f01b6aff77b8aa729b719
+oid sha256:e1af72a2907f9e79c930ee7945f6c558350175849d97e1d6f8a69b012a1b1b0b
 size 1340618660

run-1/checkpoint-5000/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-1/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8854338c04553c0d9914953ad7b45ff89da0b9321b53b58e7fb906ddb37ad719
+size 1340618660

run-1/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb216a93017f8ee3b7e66037fc5d74f459f8710acd788e9141e070a68c61a227
+size 2681472237

run-1/checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6e7b4445fde26e96fc3b984ba0d561dd1184ebbc74ec417e69ac27afee388f
+size 14244

run-1/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e937db918663d18da0ec1a4d31de19a54e1f0b83288d5ac84c31c8f131c029be
+size 1064

run-1/checkpoint-5000/special_tokens_map.json

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

run-1/checkpoint-5000/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-1/checkpoint-5000/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.702412868632708,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 2.054403066635132,
+      "learning_rate": 6.75599008099931e-05,
+      "loss": 0.6856,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4924572706222534,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9909,
+      "eval_samples_per_second": 331.779,
+      "eval_steps_per_second": 20.799,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.88927161693573,
+      "learning_rate": 6.270645965984992e-05,
+      "loss": 0.7049,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5129064917564392,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0209,
+      "eval_samples_per_second": 330.678,
+      "eval_steps_per_second": 20.73,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.888950228691101,
+      "learning_rate": 5.7853018509706724e-05,
+      "loss": 0.7041,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.8515383005142212,
+      "learning_rate": 5.299957735956355e-05,
+      "loss": 0.7017,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5085484385490417,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0308,
+      "eval_samples_per_second": 330.315,
+      "eval_steps_per_second": 20.707,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.8233052492141724,
+      "learning_rate": 4.8146136209420366e-05,
+      "loss": 0.7036,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.49782097339630127,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0208,
+      "eval_samples_per_second": 330.68,
+      "eval_steps_per_second": 20.73,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.7395379543304443,
+      "learning_rate": 4.329269505927718e-05,
+      "loss": 0.7043,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.853223204612732,
+      "learning_rate": 3.8439253909134e-05,
+      "loss": 0.7023,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4968152940273285,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0187,
+      "eval_samples_per_second": 330.757,
+      "eval_steps_per_second": 20.735,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.8915830850601196,
+      "learning_rate": 3.358581275899082e-05,
+      "loss": 0.6996,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5125712156295776,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9826,
+      "eval_samples_per_second": 332.088,
+      "eval_steps_per_second": 20.818,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.8517926931381226,
+      "learning_rate": 2.8732371608847635e-05,
+      "loss": 0.699,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.761203408241272,
+      "learning_rate": 2.3878930458704453e-05,
+      "loss": 0.6999,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.303141432855536e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.241334196013627e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8b84e61f586cb20b2c4e1e6244f78e82e764d02e70b26c7984764a166fcb30
+size 5048

run-1/checkpoint-5500/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-1/checkpoint-5500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88964b1ca726bb63cc207873a3f2265d2c60bb4892a587fe8503a96645d0653
+size 1340618660

run-1/checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdbd177f683ff6a6d7a665db384e1137152c0d6bbe6bb397e7eae519a43f6b1b
+size 2681472237

run-1/checkpoint-5500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4bd4443156419aea67e93c5b42b9fa93aaa633686043f4ecd36cb3df827a6e
+size 14244

run-1/checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe10fb655a7824f44c5ac0b7f887ad249e81bd19c0ea7c6605a20f6ce70dad6
+size 1064

run-1/checkpoint-5500/special_tokens_map.json

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

run-1/checkpoint-5500/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-1/checkpoint-5500/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.372654155495979,
+  "eval_steps": 500,
+  "global_step": 5500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 2.054403066635132,
+      "learning_rate": 6.75599008099931e-05,
+      "loss": 0.6856,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4924572706222534,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9909,
+      "eval_samples_per_second": 331.779,
+      "eval_steps_per_second": 20.799,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.88927161693573,
+      "learning_rate": 6.270645965984992e-05,
+      "loss": 0.7049,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5129064917564392,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0209,
+      "eval_samples_per_second": 330.678,
+      "eval_steps_per_second": 20.73,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.888950228691101,
+      "learning_rate": 5.7853018509706724e-05,
+      "loss": 0.7041,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.8515383005142212,
+      "learning_rate": 5.299957735956355e-05,
+      "loss": 0.7017,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5085484385490417,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0308,
+      "eval_samples_per_second": 330.315,
+      "eval_steps_per_second": 20.707,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.8233052492141724,
+      "learning_rate": 4.8146136209420366e-05,
+      "loss": 0.7036,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.49782097339630127,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0208,
+      "eval_samples_per_second": 330.68,
+      "eval_steps_per_second": 20.73,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.7395379543304443,
+      "learning_rate": 4.329269505927718e-05,
+      "loss": 0.7043,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.853223204612732,
+      "learning_rate": 3.8439253909134e-05,
+      "loss": 0.7023,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4968152940273285,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0187,
+      "eval_samples_per_second": 330.757,
+      "eval_steps_per_second": 20.735,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.8915830850601196,
+      "learning_rate": 3.358581275899082e-05,
+      "loss": 0.6996,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5125712156295776,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9826,
+      "eval_samples_per_second": 332.088,
+      "eval_steps_per_second": 20.818,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.8517926931381226,
+      "learning_rate": 2.8732371608847635e-05,
+      "loss": 0.699,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.761203408241272,
+      "learning_rate": 2.3878930458704453e-05,
+      "loss": 0.6999,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5018438100814819,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9692,
+      "eval_samples_per_second": 332.582,
+      "eval_steps_per_second": 20.849,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 1.7442079782485962,
+      "learning_rate": 1.9025489308561274e-05,
+      "loss": 0.7017,
+      "step": 5500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4332422519482328e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.241334196013627e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-5500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8b84e61f586cb20b2c4e1e6244f78e82e764d02e70b26c7984764a166fcb30
+size 5048

run-1/checkpoint-6000/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-1/checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4620a03854c3ee2597eeaaf96413883cf388434d667ddd849b39804f0f4e69fb
+size 1340618660

run-1/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4cc31e83f25cbabe6536055b9d951a36126149d186707d47bf7fbe1ece57f3
+size 2681472237

run-1/checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb6c601562c14fd8f3b9d6b06f08a1bb52309eabe2bb4d684114b4d7a5fe8dc
+size 14244

run-1/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dae51ebba0cff094a3ba3c6c5a0ce73468e764a1de0d103b0317dd96c941385
+size 1064

run-1/checkpoint-6000/special_tokens_map.json

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

run-1/checkpoint-6000/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-1/checkpoint-6000/trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 2.054403066635132,
+      "learning_rate": 6.75599008099931e-05,
+      "loss": 0.6856,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4924572706222534,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9909,
+      "eval_samples_per_second": 331.779,
+      "eval_steps_per_second": 20.799,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.88927161693573,
+      "learning_rate": 6.270645965984992e-05,
+      "loss": 0.7049,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5129064917564392,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0209,
+      "eval_samples_per_second": 330.678,
+      "eval_steps_per_second": 20.73,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.888950228691101,
+      "learning_rate": 5.7853018509706724e-05,
+      "loss": 0.7041,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.8515383005142212,
+      "learning_rate": 5.299957735956355e-05,
+      "loss": 0.7017,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5085484385490417,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0308,
+      "eval_samples_per_second": 330.315,
+      "eval_steps_per_second": 20.707,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.8233052492141724,
+      "learning_rate": 4.8146136209420366e-05,
+      "loss": 0.7036,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.49782097339630127,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0208,
+      "eval_samples_per_second": 330.68,
+      "eval_steps_per_second": 20.73,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.7395379543304443,
+      "learning_rate": 4.329269505927718e-05,
+      "loss": 0.7043,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.853223204612732,
+      "learning_rate": 3.8439253909134e-05,
+      "loss": 0.7023,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4968152940273285,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0187,
+      "eval_samples_per_second": 330.757,
+      "eval_steps_per_second": 20.735,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.8915830850601196,
+      "learning_rate": 3.358581275899082e-05,
+      "loss": 0.6996,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5125712156295776,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9826,
+      "eval_samples_per_second": 332.088,
+      "eval_steps_per_second": 20.818,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.8517926931381226,
+      "learning_rate": 2.8732371608847635e-05,
+      "loss": 0.699,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.761203408241272,
+      "learning_rate": 2.3878930458704453e-05,
+      "loss": 0.6999,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5018438100814819,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9692,
+      "eval_samples_per_second": 332.582,
+      "eval_steps_per_second": 20.849,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 1.7442079782485962,
+      "learning_rate": 1.9025489308561274e-05,
+      "loss": 0.7017,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5021790266036987,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1231,
+      "eval_samples_per_second": 326.971,
+      "eval_steps_per_second": 20.497,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 2.0343399047851562,
+      "learning_rate": 1.417204815841809e-05,
+      "loss": 0.7009,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.563011071614504e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.241334196013627e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8b84e61f586cb20b2c4e1e6244f78e82e764d02e70b26c7984764a166fcb30
+size 5048

run-1/checkpoint-6500/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-1/checkpoint-6500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1af72a2907f9e79c930ee7945f6c558350175849d97e1d6f8a69b012a1b1b0b
+size 1340618660

run-1/checkpoint-6500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49b700421894ea32a62be3bca5f1a9b7d25c321cb48ac972759269043a5e396
+size 2681472237

run-1/checkpoint-6500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f6d894359f3e2243c392a48bf280d75a9d7da29d55346796c8f588e0ed80ca
+size 14244

run-1/checkpoint-6500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a799b4f1dfd085832ca7368fd1b716b8fdafffd22089ce3ea781d826b0542a31
+size 1064

run-1/checkpoint-6500/special_tokens_map.json

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

run-1/checkpoint-6500/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-1/checkpoint-6500/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.71313672922252,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 2.054403066635132,
+      "learning_rate": 6.75599008099931e-05,
+      "loss": 0.6856,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4924572706222534,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9909,
+      "eval_samples_per_second": 331.779,
+      "eval_steps_per_second": 20.799,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.88927161693573,
+      "learning_rate": 6.270645965984992e-05,
+      "loss": 0.7049,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5129064917564392,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0209,
+      "eval_samples_per_second": 330.678,
+      "eval_steps_per_second": 20.73,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.888950228691101,
+      "learning_rate": 5.7853018509706724e-05,
+      "loss": 0.7041,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.8515383005142212,
+      "learning_rate": 5.299957735956355e-05,
+      "loss": 0.7017,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5085484385490417,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0308,
+      "eval_samples_per_second": 330.315,
+      "eval_steps_per_second": 20.707,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.8233052492141724,
+      "learning_rate": 4.8146136209420366e-05,
+      "loss": 0.7036,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.49782097339630127,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0208,
+      "eval_samples_per_second": 330.68,
+      "eval_steps_per_second": 20.73,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.7395379543304443,
+      "learning_rate": 4.329269505927718e-05,
+      "loss": 0.7043,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.853223204612732,
+      "learning_rate": 3.8439253909134e-05,
+      "loss": 0.7023,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4968152940273285,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0187,
+      "eval_samples_per_second": 330.757,
+      "eval_steps_per_second": 20.735,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.8915830850601196,
+      "learning_rate": 3.358581275899082e-05,
+      "loss": 0.6996,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5125712156295776,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9826,
+      "eval_samples_per_second": 332.088,
+      "eval_steps_per_second": 20.818,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.8517926931381226,
+      "learning_rate": 2.8732371608847635e-05,
+      "loss": 0.699,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.761203408241272,
+      "learning_rate": 2.3878930458704453e-05,
+      "loss": 0.6999,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5018438100814819,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 8.9692,
+      "eval_samples_per_second": 332.582,
+      "eval_steps_per_second": 20.849,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 1.7442079782485962,
+      "learning_rate": 1.9025489308561274e-05,
+      "loss": 0.7017,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5021790266036987,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1231,
+      "eval_samples_per_second": 326.971,
+      "eval_steps_per_second": 20.497,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 2.0343399047851562,
+      "learning_rate": 1.417204815841809e-05,
+      "loss": 0.7009,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 1.8738905191421509,
+      "learning_rate": 9.318607008274909e-06,
+      "loss": 0.6991,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6928810928603216e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.241334196013627e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-6500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8b84e61f586cb20b2c4e1e6244f78e82e764d02e70b26c7984764a166fcb30
+size 5048