Upload trained model from Colab

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "HypencoderDualEncoder"
+  ],
+  "dtype": "float32",
+  "loss_kwargs": [
+    {
+      "only_use_first_item": false,
+      "use_in_batch_negatives": true
+    }
+  ],
+  "loss_type": [
+    "cross_entropy"
+  ],
+  "pad_token_id": 0,
+  "passage_encoder_kwargs": {
+    "freeze_transformer": false,
+    "model_name_or_path": "google-bert/bert-base-uncased",
+    "pooling_type": "cls"
+  },
+  "passage_encoder_type": "",
+  "query_encoder_kwargs": {
+    "base_encoder_output_dim": 768,
+    "converter_kwargs": {
+      "activation_type": "relu",
+      "do_residual_on_last": false,
+      "vector_dimensions": [
+        768,
+        768,
+        768,
+        1
+      ]
+    },
+    "embedding_representation": null,
+    "freeze_transformer": false,
+    "model_name_or_path": "google-bert/bert-base-uncased"
+  },
+  "query_encoder_type": "",
+  "shared_encoder": true,
+  "transformers_version": "4.57.3"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71d4bbf0dbb8f96cd50ab8c98d8a9de5caf033f1d4a7720237c78ece90ba065
+size 961117643

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56c184e7d449ed330439af0f02c281d18dc6d7065390df19e86cbc7d7f5bba3
+size 482938527

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd534f6ebbb516b62333aa923a6934154ccbd07e54bd5104919568028957c3b
+size 14709

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ff8f998cb067e02aae6670b9b368c2b6a0fe01a7b5c433931769c0c086f0b4
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2af4c3dc11ee541ea87d3376c9625bf95ce64e9940fe29e7007984168b8c90
+size 1465

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.125,
+      "grad_norm": 4.301389694213867,
+      "learning_rate": 2e-05,
+      "loss": 0.4434,
+      "step": 10
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.2016409635543823,
+      "learning_rate": 2e-05,
+      "loss": 0.1615,
+      "step": 20
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 7.786351203918457,
+      "learning_rate": 2e-05,
+      "loss": 0.3108,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.272088050842285,
+      "learning_rate": 2e-05,
+      "loss": 0.265,
+      "step": 40
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 8.268477439880371,
+      "learning_rate": 2e-05,
+      "loss": 0.1791,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.466449737548828,
+      "learning_rate": 2e-05,
+      "loss": 0.1371,
+      "step": 60
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.038673318922519684,
+      "learning_rate": 2e-05,
+      "loss": 0.0898,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.542387008666992,
+      "learning_rate": 2e-05,
+      "loss": 0.0904,
+      "step": 80
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 80,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c38f4f879882c53b94e9c46072be848b78e99012375d1e73243c9d92dc8ec4
+size 5905