Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357d3682c1e4ede5f1a0b9d5f129558df5d851a090b2545fa90c4ef5be5903b6
+oid sha256:842fa676b513d687d5c7365813933e30a841909c1a9d95ed3881ee9900e0bd88
 size 1340618660

run-5/checkpoint-1000/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-5/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c167766518e92b195cc1327c3e1a032a8a7b9ebabfc297e55ec86d18efcc3040
+size 1340618660

run-5/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d12ee143936d380446e16bab15f36e5f87976ef302e141a1272b32de95b212
+size 2681472237

run-5/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cb1c6ec8baf8f29c8727264c553b249322f6174c882c74c77b16215314a942
+size 14244

run-5/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af5daa0b26e288e03fd64e188f7ae81947f6748a88d07de4639664ecba4ca35
+size 1064

run-5/checkpoint-1000/special_tokens_map.json

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

run-5/checkpoint-1000/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-5/checkpoint-1000/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.347593582887701,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6878980994224548,
+      "eval_loss": 0.5814566016197205,
+      "eval_runtime": 8.9565,
+      "eval_samples_per_second": 333.054,
+      "eval_steps_per_second": 20.879,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7194100022315979,
+      "eval_loss": 0.5218587517738342,
+      "eval_runtime": 9.0661,
+      "eval_samples_per_second": 329.027,
+      "eval_steps_per_second": 20.626,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 7.46340274810791,
+      "learning_rate": 1.5373335026225161e-06,
+      "loss": 0.5847,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7344954609870911,
+      "eval_loss": 0.5096723437309265,
+      "eval_runtime": 9.0234,
+      "eval_samples_per_second": 330.583,
+      "eval_steps_per_second": 20.724,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7398592233657837,
+      "eval_loss": 0.5069338083267212,
+      "eval_runtime": 9.0796,
+      "eval_samples_per_second": 328.54,
+      "eval_steps_per_second": 20.596,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7475695610046387,
+      "eval_loss": 0.5030502676963806,
+      "eval_runtime": 9.111,
+      "eval_samples_per_second": 327.405,
+      "eval_steps_per_second": 20.525,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 5.598100662231445,
+      "learning_rate": 9.762628812274372e-07,
+      "loss": 0.4789,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.0793628984109176e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.098404124017595e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-5/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a843713c73e12f359184fae200bd4db35c7e342723c6e05d613c5eed17ea8f97
+size 5048

run-5/checkpoint-1500/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-5/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842fa676b513d687d5c7365813933e30a841909c1a9d95ed3881ee9900e0bd88
+size 1340618660

run-5/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec1ad43c8fc8d0e96124678fd1299ffe021a6df470613df08e5d1834df19594
+size 2681472237

run-5/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8821fbb31177a98f39e7e6c60f816c26063b273c90b8f01350711fa76ade8048
+size 14244

run-5/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2383c2f9cfdf19706cbd04b55c15b95a717449d472cdd4326bcc01ad794f19d5
+size 1064

run-5/checkpoint-1500/special_tokens_map.json

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

run-5/checkpoint-1500/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-5/checkpoint-1500/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.02139037433155,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6878980994224548,
+      "eval_loss": 0.5814566016197205,
+      "eval_runtime": 8.9565,
+      "eval_samples_per_second": 333.054,
+      "eval_steps_per_second": 20.879,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7194100022315979,
+      "eval_loss": 0.5218587517738342,
+      "eval_runtime": 9.0661,
+      "eval_samples_per_second": 329.027,
+      "eval_steps_per_second": 20.626,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 7.46340274810791,
+      "learning_rate": 1.5373335026225161e-06,
+      "loss": 0.5847,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7344954609870911,
+      "eval_loss": 0.5096723437309265,
+      "eval_runtime": 9.0234,
+      "eval_samples_per_second": 330.583,
+      "eval_steps_per_second": 20.724,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7398592233657837,
+      "eval_loss": 0.5069338083267212,
+      "eval_runtime": 9.0796,
+      "eval_samples_per_second": 328.54,
+      "eval_steps_per_second": 20.596,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7475695610046387,
+      "eval_loss": 0.5030502676963806,
+      "eval_runtime": 9.111,
+      "eval_samples_per_second": 327.405,
+      "eval_steps_per_second": 20.525,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 5.598100662231445,
+      "learning_rate": 9.762628812274372e-07,
+      "loss": 0.4789,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7499161958694458,
+      "eval_loss": 0.5032511949539185,
+      "eval_runtime": 9.0706,
+      "eval_samples_per_second": 328.864,
+      "eval_steps_per_second": 20.616,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7512571215629578,
+      "eval_loss": 0.5065814852714539,
+      "eval_runtime": 9.1058,
+      "eval_samples_per_second": 327.593,
+      "eval_steps_per_second": 20.536,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7515923380851746,
+      "eval_loss": 0.5092657804489136,
+      "eval_runtime": 9.0837,
+      "eval_samples_per_second": 328.392,
+      "eval_steps_per_second": 20.586,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 8.30627727508545,
+      "learning_rate": 4.1519225983235836e-07,
+      "loss": 0.4364,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6202496657094632e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.098404124017595e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-5/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a843713c73e12f359184fae200bd4db35c7e342723c6e05d613c5eed17ea8f97
+size 5048