Training in progress, step 6500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf085d2c69232d0fb9d03f6a146375f6cf8a762b1857195f5d8efd7d6dcd309
+oid sha256:51c962031030b93573918496db27236871fd68d7e942d34a323b0d368b1d7b78
 size 1340618660

run-4/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-4/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f21453111c442d1209b84e3d87421d510abc042e85b1b08dd1f2b00f7a5e2d6
+size 1340618660

run-4/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024fbf33b8ca098cde5238ca77f28aeb2cf09519855e9427a260000209647fb9
+size 2681472237

run-4/checkpoint-5000/rng_state.pth

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

run-4/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c20cfa058f7e33316b019755194797d0c0cd76e8ffcdceb4e845e909e1e8202
+size 1064

run-4/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-4/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-4/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": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.5234329700469971,
+      "eval_runtime": 9.4342,
+      "eval_samples_per_second": 316.19,
+      "eval_steps_per_second": 19.821,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 6.197817325592041,
+      "learning_rate": 1.0519194482965755e-05,
+      "loss": 0.3313,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 20.681987762451172,
+      "learning_rate": 9.63671172432769e-06,
+      "loss": 0.1575,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.6654106378555298,
+      "eval_runtime": 9.4207,
+      "eval_samples_per_second": 316.642,
+      "eval_steps_per_second": 19.85,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.6577324271202087,
+      "learning_rate": 8.754228965689622e-06,
+      "loss": 0.1178,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7763996124267578,
+      "eval_loss": 1.094183087348938,
+      "eval_runtime": 9.4168,
+      "eval_samples_per_second": 316.775,
+      "eval_steps_per_second": 19.858,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 5.022602558135986,
+      "learning_rate": 7.871746207051555e-06,
+      "loss": 0.0777,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 0.7826739549636841,
+      "learning_rate": 6.989263448413488e-06,
+      "loss": 0.044,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.782433807849884,
+      "eval_loss": 1.2965056896209717,
+      "eval_runtime": 9.3869,
+      "eval_samples_per_second": 317.783,
+      "eval_steps_per_second": 19.921,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7349833250045776,
+      "learning_rate": 6.106780689775422e-06,
+      "loss": 0.0345,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7861213684082031,
+      "eval_loss": 1.1750046014785767,
+      "eval_runtime": 9.4116,
+      "eval_samples_per_second": 316.949,
+      "eval_steps_per_second": 19.869,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 16.81600570678711,
+      "learning_rate": 5.224297931137354e-06,
+      "loss": 0.0227,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.004451041109859943,
+      "learning_rate": 4.341815172499288e-06,
+      "loss": 0.0164,
+      "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": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048

run-4/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-4/checkpoint-5500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ede1c60310d54b2cae23ad7b0e004acc7f8312420ac89e924064fc9a88f321b
+size 1340618660

run-4/checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589a2750c3ddea9b90eeefcd3ccf9f8f8d63832bb03796c4d2a262b97107bc1b
+size 2681472237

run-4/checkpoint-5500/rng_state.pth

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

run-4/checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5b48602e277a4937977b7051d7ed6763715c441b1c73f78ddcd3cba2ed61f4
+size 1064

run-4/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-4/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-4/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": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.5234329700469971,
+      "eval_runtime": 9.4342,
+      "eval_samples_per_second": 316.19,
+      "eval_steps_per_second": 19.821,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 6.197817325592041,
+      "learning_rate": 1.0519194482965755e-05,
+      "loss": 0.3313,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 20.681987762451172,
+      "learning_rate": 9.63671172432769e-06,
+      "loss": 0.1575,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.6654106378555298,
+      "eval_runtime": 9.4207,
+      "eval_samples_per_second": 316.642,
+      "eval_steps_per_second": 19.85,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.6577324271202087,
+      "learning_rate": 8.754228965689622e-06,
+      "loss": 0.1178,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7763996124267578,
+      "eval_loss": 1.094183087348938,
+      "eval_runtime": 9.4168,
+      "eval_samples_per_second": 316.775,
+      "eval_steps_per_second": 19.858,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 5.022602558135986,
+      "learning_rate": 7.871746207051555e-06,
+      "loss": 0.0777,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 0.7826739549636841,
+      "learning_rate": 6.989263448413488e-06,
+      "loss": 0.044,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.782433807849884,
+      "eval_loss": 1.2965056896209717,
+      "eval_runtime": 9.3869,
+      "eval_samples_per_second": 317.783,
+      "eval_steps_per_second": 19.921,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7349833250045776,
+      "learning_rate": 6.106780689775422e-06,
+      "loss": 0.0345,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7861213684082031,
+      "eval_loss": 1.1750046014785767,
+      "eval_runtime": 9.4116,
+      "eval_samples_per_second": 316.949,
+      "eval_steps_per_second": 19.869,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 16.81600570678711,
+      "learning_rate": 5.224297931137354e-06,
+      "loss": 0.0227,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.004451041109859943,
+      "learning_rate": 4.341815172499288e-06,
+      "loss": 0.0164,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7827690243721008,
+      "eval_loss": 1.4659219980239868,
+      "eval_runtime": 9.615,
+      "eval_samples_per_second": 310.243,
+      "eval_steps_per_second": 19.449,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 4.934184551239014,
+      "learning_rate": 3.4593324138612214e-06,
+      "loss": 0.0136,
+      "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": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-5500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048

run-4/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-4/checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81db1a61180c18ed6dd2ce56b0bb272e0a16df8af4b11c089aeb4ca699e8fae
+size 1340618660

run-4/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec7115aed7b117dc2e72293e6a34f42845c82d22099fceb445014348cb206e9
+size 2681472237

run-4/checkpoint-6000/rng_state.pth

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

run-4/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12643eac350e8602802a64d8770bd0e9959be8429f5cb549dc3c2908dd68c980
+size 1064

run-4/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-4/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-4/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": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.5234329700469971,
+      "eval_runtime": 9.4342,
+      "eval_samples_per_second": 316.19,
+      "eval_steps_per_second": 19.821,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 6.197817325592041,
+      "learning_rate": 1.0519194482965755e-05,
+      "loss": 0.3313,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 20.681987762451172,
+      "learning_rate": 9.63671172432769e-06,
+      "loss": 0.1575,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.6654106378555298,
+      "eval_runtime": 9.4207,
+      "eval_samples_per_second": 316.642,
+      "eval_steps_per_second": 19.85,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.6577324271202087,
+      "learning_rate": 8.754228965689622e-06,
+      "loss": 0.1178,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7763996124267578,
+      "eval_loss": 1.094183087348938,
+      "eval_runtime": 9.4168,
+      "eval_samples_per_second": 316.775,
+      "eval_steps_per_second": 19.858,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 5.022602558135986,
+      "learning_rate": 7.871746207051555e-06,
+      "loss": 0.0777,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 0.7826739549636841,
+      "learning_rate": 6.989263448413488e-06,
+      "loss": 0.044,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.782433807849884,
+      "eval_loss": 1.2965056896209717,
+      "eval_runtime": 9.3869,
+      "eval_samples_per_second": 317.783,
+      "eval_steps_per_second": 19.921,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7349833250045776,
+      "learning_rate": 6.106780689775422e-06,
+      "loss": 0.0345,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7861213684082031,
+      "eval_loss": 1.1750046014785767,
+      "eval_runtime": 9.4116,
+      "eval_samples_per_second": 316.949,
+      "eval_steps_per_second": 19.869,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 16.81600570678711,
+      "learning_rate": 5.224297931137354e-06,
+      "loss": 0.0227,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.004451041109859943,
+      "learning_rate": 4.341815172499288e-06,
+      "loss": 0.0164,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7827690243721008,
+      "eval_loss": 1.4659219980239868,
+      "eval_runtime": 9.615,
+      "eval_samples_per_second": 310.243,
+      "eval_steps_per_second": 19.449,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 4.934184551239014,
+      "learning_rate": 3.4593324138612214e-06,
+      "loss": 0.0136,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7847804427146912,
+      "eval_loss": 1.4372460842132568,
+      "eval_runtime": 9.4141,
+      "eval_samples_per_second": 316.864,
+      "eval_steps_per_second": 19.864,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 6.715782642364502,
+      "learning_rate": 2.5768496552231545e-06,
+      "loss": 0.0143,
+      "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": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048

run-4/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-4/checkpoint-6500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c962031030b93573918496db27236871fd68d7e942d34a323b0d368b1d7b78
+size 1340618660

run-4/checkpoint-6500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b47d2d40a2b01cf8df001dbce8648b9863828b3c7d7a8df38f9bbdce485631f
+size 2681472237

run-4/checkpoint-6500/rng_state.pth

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

run-4/checkpoint-6500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f3dda8cf0c883de569ec52b10b9b59e7aec93a2f6b48bd8f1289eb6d68a369
+size 1064

run-4/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-4/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-4/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": 13.804513931274414,
+      "learning_rate": 1.2284160000241888e-05,
+      "loss": 0.5698,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7532685399055481,
+      "eval_loss": 0.4876743257045746,
+      "eval_runtime": 9.5369,
+      "eval_samples_per_second": 312.785,
+      "eval_steps_per_second": 19.608,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 23.23216438293457,
+      "learning_rate": 1.1401677241603822e-05,
+      "loss": 0.4247,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.5234329700469971,
+      "eval_runtime": 9.4342,
+      "eval_samples_per_second": 316.19,
+      "eval_steps_per_second": 19.821,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 6.197817325592041,
+      "learning_rate": 1.0519194482965755e-05,
+      "loss": 0.3313,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 20.681987762451172,
+      "learning_rate": 9.63671172432769e-06,
+      "loss": 0.1575,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.6654106378555298,
+      "eval_runtime": 9.4207,
+      "eval_samples_per_second": 316.642,
+      "eval_steps_per_second": 19.85,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.6577324271202087,
+      "learning_rate": 8.754228965689622e-06,
+      "loss": 0.1178,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7763996124267578,
+      "eval_loss": 1.094183087348938,
+      "eval_runtime": 9.4168,
+      "eval_samples_per_second": 316.775,
+      "eval_steps_per_second": 19.858,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 5.022602558135986,
+      "learning_rate": 7.871746207051555e-06,
+      "loss": 0.0777,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 0.7826739549636841,
+      "learning_rate": 6.989263448413488e-06,
+      "loss": 0.044,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.782433807849884,
+      "eval_loss": 1.2965056896209717,
+      "eval_runtime": 9.3869,
+      "eval_samples_per_second": 317.783,
+      "eval_steps_per_second": 19.921,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7349833250045776,
+      "learning_rate": 6.106780689775422e-06,
+      "loss": 0.0345,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7861213684082031,
+      "eval_loss": 1.1750046014785767,
+      "eval_runtime": 9.4116,
+      "eval_samples_per_second": 316.949,
+      "eval_steps_per_second": 19.869,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 16.81600570678711,
+      "learning_rate": 5.224297931137354e-06,
+      "loss": 0.0227,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.004451041109859943,
+      "learning_rate": 4.341815172499288e-06,
+      "loss": 0.0164,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7827690243721008,
+      "eval_loss": 1.4659219980239868,
+      "eval_runtime": 9.615,
+      "eval_samples_per_second": 310.243,
+      "eval_steps_per_second": 19.449,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 4.934184551239014,
+      "learning_rate": 3.4593324138612214e-06,
+      "loss": 0.0136,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7847804427146912,
+      "eval_loss": 1.4372460842132568,
+      "eval_runtime": 9.4141,
+      "eval_samples_per_second": 316.864,
+      "eval_steps_per_second": 19.864,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 6.715782642364502,
+      "learning_rate": 2.5768496552231545e-06,
+      "loss": 0.0143,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 0.0020331561099737883,
+      "learning_rate": 1.694366896585088e-06,
+      "loss": 0.0059,
+      "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": 1.3166642758879955e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-6500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
+size 5048