Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314fca40dce046335f6f2e1b99d6bd581da6efddc8ada3abf60ab9fb65036c14
+oid sha256:dd3baf215415fc6919c9269fc718ad45584786020e74cab6835b5db373b298de
 size 1340618660

run-10/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-10/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389863f55590d75da37b5b0808d4b8ab90a8f4d20e242729e80295788e961d96
+size 1340618660

run-10/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c110de866f9809697812b32e2fa5a25c29f86c51dc4066567849f391822be1f8
+size 2681472237

run-10/checkpoint-1000/rng_state.pth

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

run-10/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c88585b1a11261eb1d1ed11e9f36a7a745e73ffe409a912539bfa311998a84
+size 1064

run-10/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-10/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-10/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": 0.7418705821037292,
+      "eval_loss": 0.4915386140346527,
+      "eval_runtime": 9.0118,
+      "eval_samples_per_second": 331.011,
+      "eval_steps_per_second": 20.751,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7596379518508911,
+      "eval_loss": 0.5060486197471619,
+      "eval_runtime": 9.006,
+      "eval_samples_per_second": 331.224,
+      "eval_steps_per_second": 20.764,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.023440837860107,
+      "learning_rate": 1.743940882471145e-05,
+      "loss": 0.4047,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7616493701934814,
+      "eval_loss": 0.623109757900238,
+      "eval_runtime": 8.9301,
+      "eval_samples_per_second": 334.037,
+      "eval_steps_per_second": 20.94,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.9390846490859985,
+      "eval_runtime": 8.9745,
+      "eval_samples_per_second": 332.388,
+      "eval_steps_per_second": 20.837,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7690244913101196,
+      "eval_loss": 0.9651883840560913,
+      "eval_runtime": 8.9946,
+      "eval_samples_per_second": 331.645,
+      "eval_steps_per_second": 20.79,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 5.892197132110596,
+      "learning_rate": 1.1074661078466395e-05,
+      "loss": 0.0891,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.211040714779136e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3804156570956505e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-10/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5dc945d20af18c94d03892d0b724309a25886ca2a3a6557699258d1d340072
+size 5048

run-10/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-10/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3baf215415fc6919c9269fc718ad45584786020e74cab6835b5db373b298de
+size 1340618660

run-10/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09786f3ed9601811d70c8c18dfbe59a0e263d1a8d0a936922a336050aa38c36a
+size 2681472237

run-10/checkpoint-1500/rng_state.pth

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

run-10/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a9504d33974a99cd9d416a907f7671011855bb883c3e3c2361b92f81b9cbd2
+size 1064

run-10/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-10/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-10/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": 0.7418705821037292,
+      "eval_loss": 0.4915386140346527,
+      "eval_runtime": 9.0118,
+      "eval_samples_per_second": 331.011,
+      "eval_steps_per_second": 20.751,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7596379518508911,
+      "eval_loss": 0.5060486197471619,
+      "eval_runtime": 9.006,
+      "eval_samples_per_second": 331.224,
+      "eval_steps_per_second": 20.764,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.023440837860107,
+      "learning_rate": 1.743940882471145e-05,
+      "loss": 0.4047,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7616493701934814,
+      "eval_loss": 0.623109757900238,
+      "eval_runtime": 8.9301,
+      "eval_samples_per_second": 334.037,
+      "eval_steps_per_second": 20.94,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.9390846490859985,
+      "eval_runtime": 8.9745,
+      "eval_samples_per_second": 332.388,
+      "eval_steps_per_second": 20.837,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7690244913101196,
+      "eval_loss": 0.9651883840560913,
+      "eval_runtime": 8.9946,
+      "eval_samples_per_second": 331.645,
+      "eval_steps_per_second": 20.79,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 5.892197132110596,
+      "learning_rate": 1.1074661078466395e-05,
+      "loss": 0.0891,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7646664381027222,
+      "eval_loss": 1.2514368295669556,
+      "eval_runtime": 8.9943,
+      "eval_samples_per_second": 331.655,
+      "eval_steps_per_second": 20.791,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7713711261749268,
+      "eval_loss": 1.320696473121643,
+      "eval_runtime": 9.0089,
+      "eval_samples_per_second": 331.118,
+      "eval_steps_per_second": 20.757,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7723767757415771,
+      "eval_loss": 1.3310731649398804,
+      "eval_runtime": 9.0256,
+      "eval_samples_per_second": 330.504,
+      "eval_steps_per_second": 20.719,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 3.7906782627105713,
+      "learning_rate": 4.709913332221341e-06,
+      "loss": 0.0243,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.7556431817986532e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3804156570956505e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-10/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5dc945d20af18c94d03892d0b724309a25886ca2a3a6557699258d1d340072
+size 5048