Training in progress, step 7000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72209b9df4502711fb0a9fb259fc535f893260274e7ba5e9ba48218f87827596
+oid sha256:4aefc1e273c7b854ce79fbf89143ffaaa58dc72848293d37f97e6122859bdb79
 size 1340618660

run-19/checkpoint-4000/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-19/checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0f559f09f91876b2789941332e0a0bbf3886569d5a1dfc1e73beb7ef660215
+size 1340618660

run-19/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7ff18a8f5398a8ff2b875bbab9ee0e5b148ec37d225e9c0402eaefc9ad6660
+size 2681472237

run-19/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964f4b0fc1ae48263176e28a78d31a31267f7cb8f04acc9b199d89800cfff478
+size 14244

run-19/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb6f332dbf9964cc35b17527f063876c1eda946a2e6e032ef0f7c2dfcab5209
+size 1064

run-19/checkpoint-4000/special_tokens_map.json

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

run-19/checkpoint-4000/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-19/checkpoint-4000/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.361930294906166,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 12.96187973022461,
+      "learning_rate": 5.852478627669732e-06,
+      "loss": 0.5779,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7619845867156982,
+      "eval_loss": 0.48268476128578186,
+      "eval_runtime": 9.469,
+      "eval_samples_per_second": 315.027,
+      "eval_steps_per_second": 19.749,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 19.64900779724121,
+      "learning_rate": 5.432041944647482e-06,
+      "loss": 0.464,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.5030698180198669,
+      "eval_runtime": 9.5015,
+      "eval_samples_per_second": 313.951,
+      "eval_steps_per_second": 19.681,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 9.11796760559082,
+      "learning_rate": 5.0116052616252305e-06,
+      "loss": 0.4025,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 11.002016067504883,
+      "learning_rate": 4.59116857860298e-06,
+      "loss": 0.2688,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 0.5899690389633179,
+      "eval_runtime": 9.4806,
+      "eval_samples_per_second": 314.643,
+      "eval_steps_per_second": 19.725,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 3.2045211791992188,
+      "learning_rate": 4.170731895580729e-06,
+      "loss": 0.2182,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7673482894897461,
+      "eval_loss": 0.7394132614135742,
+      "eval_runtime": 9.6202,
+      "eval_samples_per_second": 310.077,
+      "eval_steps_per_second": 19.438,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.5618192553520203,
+      "learning_rate": 3.7502952125584775e-06,
+      "loss": 0.1644,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 19.86639976501465,
+      "learning_rate": 3.3298585295362272e-06,
+      "loss": 0.1173,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7646664381027222,
+      "eval_loss": 0.7920505404472351,
+      "eval_runtime": 9.4974,
+      "eval_samples_per_second": 314.085,
+      "eval_steps_per_second": 19.69,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 7.497531414031982,
+      "learning_rate": 2.909421846513976e-06,
+      "loss": 0.1026,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.1054878313466996e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.272915310691983e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-19/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
+size 5048

run-19/checkpoint-4500/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-19/checkpoint-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d652f8d231b8971668f5e3fb86f9ca85c822439006a926d7aa2ec2ef8c1b86e1
+size 1340618660

run-19/checkpoint-4500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f8044e48ddae671d05900c6f5fef2785741cb00d8b74d931112d530c435d3f
+size 2681472237

run-19/checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c65c81fd3021fa5a65673197784a1bfa7af04999304bdf6b50fc4ee0d7de006
+size 14244

run-19/checkpoint-4500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eaf982abcbdd4552dc43a111b6674b60294be1163d73803906351e1150045e8
+size 1064

run-19/checkpoint-4500/special_tokens_map.json

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

run-19/checkpoint-4500/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-19/checkpoint-4500/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.032171581769437,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 12.96187973022461,
+      "learning_rate": 5.852478627669732e-06,
+      "loss": 0.5779,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7619845867156982,
+      "eval_loss": 0.48268476128578186,
+      "eval_runtime": 9.469,
+      "eval_samples_per_second": 315.027,
+      "eval_steps_per_second": 19.749,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 19.64900779724121,
+      "learning_rate": 5.432041944647482e-06,
+      "loss": 0.464,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.5030698180198669,
+      "eval_runtime": 9.5015,
+      "eval_samples_per_second": 313.951,
+      "eval_steps_per_second": 19.681,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 9.11796760559082,
+      "learning_rate": 5.0116052616252305e-06,
+      "loss": 0.4025,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 11.002016067504883,
+      "learning_rate": 4.59116857860298e-06,
+      "loss": 0.2688,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 0.5899690389633179,
+      "eval_runtime": 9.4806,
+      "eval_samples_per_second": 314.643,
+      "eval_steps_per_second": 19.725,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 3.2045211791992188,
+      "learning_rate": 4.170731895580729e-06,
+      "loss": 0.2182,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7673482894897461,
+      "eval_loss": 0.7394132614135742,
+      "eval_runtime": 9.6202,
+      "eval_samples_per_second": 310.077,
+      "eval_steps_per_second": 19.438,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.5618192553520203,
+      "learning_rate": 3.7502952125584775e-06,
+      "loss": 0.1644,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 19.86639976501465,
+      "learning_rate": 3.3298585295362272e-06,
+      "loss": 0.1173,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7646664381027222,
+      "eval_loss": 0.7920505404472351,
+      "eval_runtime": 9.4974,
+      "eval_samples_per_second": 314.085,
+      "eval_steps_per_second": 19.69,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 7.497531414031982,
+      "learning_rate": 2.909421846513976e-06,
+      "loss": 0.1026,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.9123848676681519,
+      "eval_runtime": 9.4955,
+      "eval_samples_per_second": 314.147,
+      "eval_steps_per_second": 19.693,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 21.95626449584961,
+      "learning_rate": 2.488985163491725e-06,
+      "loss": 0.082,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.2362610220848e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.272915310691983e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-19/checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
+size 5048

run-19/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-19/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7072d8120c383505bffa543bbf63c1edbb6dbc90885dff5e685598df808a33ba
+size 1340618660

run-19/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aaa86f26d3e8b515f8215f889a7c69e24a60e321999a60b83e5b8aec94bbdf6
+size 2681472237

run-19/checkpoint-5000/rng_state.pth

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

run-19/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86338e9094b0919b9dac730a6eb7371c4cbc31ee8f821ad4537edcd27d946ff
+size 1064

run-19/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-19/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-19/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": 12.96187973022461,
+      "learning_rate": 5.852478627669732e-06,
+      "loss": 0.5779,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7619845867156982,
+      "eval_loss": 0.48268476128578186,
+      "eval_runtime": 9.469,
+      "eval_samples_per_second": 315.027,
+      "eval_steps_per_second": 19.749,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 19.64900779724121,
+      "learning_rate": 5.432041944647482e-06,
+      "loss": 0.464,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.5030698180198669,
+      "eval_runtime": 9.5015,
+      "eval_samples_per_second": 313.951,
+      "eval_steps_per_second": 19.681,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 9.11796760559082,
+      "learning_rate": 5.0116052616252305e-06,
+      "loss": 0.4025,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 11.002016067504883,
+      "learning_rate": 4.59116857860298e-06,
+      "loss": 0.2688,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 0.5899690389633179,
+      "eval_runtime": 9.4806,
+      "eval_samples_per_second": 314.643,
+      "eval_steps_per_second": 19.725,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 3.2045211791992188,
+      "learning_rate": 4.170731895580729e-06,
+      "loss": 0.2182,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7673482894897461,
+      "eval_loss": 0.7394132614135742,
+      "eval_runtime": 9.6202,
+      "eval_samples_per_second": 310.077,
+      "eval_steps_per_second": 19.438,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.5618192553520203,
+      "learning_rate": 3.7502952125584775e-06,
+      "loss": 0.1644,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 19.86639976501465,
+      "learning_rate": 3.3298585295362272e-06,
+      "loss": 0.1173,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7646664381027222,
+      "eval_loss": 0.7920505404472351,
+      "eval_runtime": 9.4974,
+      "eval_samples_per_second": 314.085,
+      "eval_steps_per_second": 19.69,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 7.497531414031982,
+      "learning_rate": 2.909421846513976e-06,
+      "loss": 0.1026,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.9123848676681519,
+      "eval_runtime": 9.4955,
+      "eval_samples_per_second": 314.147,
+      "eval_steps_per_second": 19.693,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 21.95626449584961,
+      "learning_rate": 2.488985163491725e-06,
+      "loss": 0.082,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.22410695254802704,
+      "learning_rate": 2.0685484804694742e-06,
+      "loss": 0.065,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.366556235578496e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.272915310691983e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-19/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
+size 5048

run-19/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-19/checkpoint-5500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8ae85a05964de0f4a2ef88835626a7a850c2e6af594e1b0e52678abdfb1a99
+size 1340618660

run-19/checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cbdf90f670dcd79e231b6dd10918a8d709bc52d6b561859c84cf0da719c71e9
+size 2681472237

run-19/checkpoint-5500/rng_state.pth

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

run-19/checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c407b012ab8de6d0ec8dc9ec2f22225726fa649291914e1cf1b72410bee98c
+size 1064

run-19/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-19/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-19/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": 12.96187973022461,
+      "learning_rate": 5.852478627669732e-06,
+      "loss": 0.5779,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7619845867156982,
+      "eval_loss": 0.48268476128578186,
+      "eval_runtime": 9.469,
+      "eval_samples_per_second": 315.027,
+      "eval_steps_per_second": 19.749,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 19.64900779724121,
+      "learning_rate": 5.432041944647482e-06,
+      "loss": 0.464,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.5030698180198669,
+      "eval_runtime": 9.5015,
+      "eval_samples_per_second": 313.951,
+      "eval_steps_per_second": 19.681,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 9.11796760559082,
+      "learning_rate": 5.0116052616252305e-06,
+      "loss": 0.4025,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 11.002016067504883,
+      "learning_rate": 4.59116857860298e-06,
+      "loss": 0.2688,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 0.5899690389633179,
+      "eval_runtime": 9.4806,
+      "eval_samples_per_second": 314.643,
+      "eval_steps_per_second": 19.725,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 3.2045211791992188,
+      "learning_rate": 4.170731895580729e-06,
+      "loss": 0.2182,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7673482894897461,
+      "eval_loss": 0.7394132614135742,
+      "eval_runtime": 9.6202,
+      "eval_samples_per_second": 310.077,
+      "eval_steps_per_second": 19.438,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 0.5618192553520203,
+      "learning_rate": 3.7502952125584775e-06,
+      "loss": 0.1644,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 19.86639976501465,
+      "learning_rate": 3.3298585295362272e-06,
+      "loss": 0.1173,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7646664381027222,
+      "eval_loss": 0.7920505404472351,
+      "eval_runtime": 9.4974,
+      "eval_samples_per_second": 314.085,
+      "eval_steps_per_second": 19.69,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 7.497531414031982,
+      "learning_rate": 2.909421846513976e-06,
+      "loss": 0.1026,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.9123848676681519,
+      "eval_runtime": 9.4955,
+      "eval_samples_per_second": 314.147,
+      "eval_steps_per_second": 19.693,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 21.95626449584961,
+      "learning_rate": 2.488985163491725e-06,
+      "loss": 0.082,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.22410695254802704,
+      "learning_rate": 2.0685484804694742e-06,
+      "loss": 0.065,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.9457674026489258,
+      "eval_runtime": 9.4723,
+      "eval_samples_per_second": 314.918,
+      "eval_steps_per_second": 19.742,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 53.26298904418945,
+      "learning_rate": 1.6481117974472235e-06,
+      "loss": 0.0629,
+      "step": 5500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4966570546711928e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.272915310691983e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-19/checkpoint-5500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
+size 5048

run-19/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-19/checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:222c337855cb5af036286792a98d51327d23a50c06898ad8974652081a61acdf
+size 1340618660

run-19/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c806ab7d1a3035af670a69dc57e95340e6779d352cf26af33ca6372f7dde2c4e
+size 2681472237

run-19/checkpoint-6000/rng_state.pth

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

run-19/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6beb9b3c5de11cfa1655c4d50cc3169e519e7e84211bc73bd03d5f87551c103
+size 1064