Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee2a2f79e4db555ff39f348159a76ec37cf57dfde6ccde182981e670a0c5166
+oid sha256:06b139261e238ab62a904d642d77045bd52b72cb41a920f8faedf2668778a311
 size 1340618660

run-11/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-11/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1cdb94f2fbf5baa0f5c33b1f8b5113d761e418c4d1bb81fdb780ae0792a2d4
+size 1340618660

run-11/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359faa124b464a7cd991c684e77b936292b1de030c5a80a61b6821d532b1d29c
+size 2681472237

run-11/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2cdfcea7c19f545a5c3968413dcd70b32c860d464dd9abffbe95cff448fb946
+size 14244

run-11/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fa8681bccfea067da420b5d1a580094c846eaa191f86a64f50ab236305ea7c
+size 1064

run-11/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-11/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-11/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": 0.7442172169685364,
+      "eval_loss": 0.49692073464393616,
+      "eval_runtime": 8.8409,
+      "eval_samples_per_second": 337.409,
+      "eval_steps_per_second": 21.152,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7606436610221863,
+      "eval_loss": 0.513149082660675,
+      "eval_runtime": 8.9936,
+      "eval_samples_per_second": 331.679,
+      "eval_steps_per_second": 20.792,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.438678741455078,
+      "learning_rate": 1.6734897456112568e-05,
+      "loss": 0.3861,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7656721472740173,
+      "eval_loss": 0.6351237893104553,
+      "eval_runtime": 8.9057,
+      "eval_samples_per_second": 334.954,
+      "eval_steps_per_second": 20.998,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.763660728931427,
+      "eval_loss": 0.8534680008888245,
+      "eval_runtime": 8.9937,
+      "eval_samples_per_second": 331.677,
+      "eval_steps_per_second": 20.792,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 1.0246423482894897,
+      "eval_runtime": 8.9711,
+      "eval_samples_per_second": 332.511,
+      "eval_steps_per_second": 20.845,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 4.004021644592285,
+      "learning_rate": 1.062727064731236e-05,
+      "loss": 0.084,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.0895504027404356e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2842524264912772e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-11/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752e2b1de4ef6590ab15353edd43d492d68f23094e8b6b6a922d5d42c5f7bd77
+size 5048

run-11/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-11/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b139261e238ab62a904d642d77045bd52b72cb41a920f8faedf2668778a311
+size 1340618660

run-11/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5709ff85824d84c222c423c446f3b4ff5b72cec558ef4509182e69f5eee783e
+size 2681472237

run-11/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff9554be5662c81dc5324c0ba82c1e4075d9a58be3ecf2692e8a0f7f508c509
+size 14244

run-11/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8d29c4331b74a3e23178294e7a16685e0b1ade006480be1315eecc80604fb7
+size 1064

run-11/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-11/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-11/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": 0.7442172169685364,
+      "eval_loss": 0.49692073464393616,
+      "eval_runtime": 8.8409,
+      "eval_samples_per_second": 337.409,
+      "eval_steps_per_second": 21.152,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7606436610221863,
+      "eval_loss": 0.513149082660675,
+      "eval_runtime": 8.9936,
+      "eval_samples_per_second": 331.679,
+      "eval_steps_per_second": 20.792,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.438678741455078,
+      "learning_rate": 1.6734897456112568e-05,
+      "loss": 0.3861,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7656721472740173,
+      "eval_loss": 0.6351237893104553,
+      "eval_runtime": 8.9057,
+      "eval_samples_per_second": 334.954,
+      "eval_steps_per_second": 20.998,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.763660728931427,
+      "eval_loss": 0.8534680008888245,
+      "eval_runtime": 8.9937,
+      "eval_samples_per_second": 331.677,
+      "eval_steps_per_second": 20.792,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 1.0246423482894897,
+      "eval_runtime": 8.9711,
+      "eval_samples_per_second": 332.511,
+      "eval_steps_per_second": 20.845,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 4.004021644592285,
+      "learning_rate": 1.062727064731236e-05,
+      "loss": 0.084,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.765001654624939,
+      "eval_loss": 1.1328651905059814,
+      "eval_runtime": 8.9776,
+      "eval_samples_per_second": 332.272,
+      "eval_steps_per_second": 20.83,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.765001654624939,
+      "eval_loss": 1.1839755773544312,
+      "eval_runtime": 8.9889,
+      "eval_samples_per_second": 331.853,
+      "eval_steps_per_second": 20.803,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7666778564453125,
+      "eval_loss": 1.2200679779052734,
+      "eval_runtime": 8.9877,
+      "eval_samples_per_second": 331.9,
+      "eval_steps_per_second": 20.806,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 0.6088434457778931,
+      "learning_rate": 4.519643838512153e-06,
+      "loss": 0.0256,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6341528697599528e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2842524264912772e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-11/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752e2b1de4ef6590ab15353edd43d492d68f23094e8b6b6a922d5d42c5f7bd77
+size 5048