Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-multilingual-reranker-base",
+  "architectures": [
+    "NewForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614613583e9b342ce815f07a147543961ad777fd0c65abce44d186b3ddab7f04
+size 611934706

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64b175d67ecd8c9eb34e4c8f299b2e0017a03bfbb425586e62ee79a8653cded
+size 17082832

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 7466,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1339405304045004,
+      "grad_norm": 9.218611717224121,
+      "learning_rate": 1.878641737807314e-05,
+      "loss": 0.5203,
+      "step": 500
+    },
+    {
+      "epoch": 0.2678810608090008,
+      "grad_norm": 6.3912835121154785,
+      "learning_rate": 1.9249888376246466e-05,
+      "loss": 0.4005,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4018215912135012,
+      "grad_norm": 9.956713676452637,
+      "learning_rate": 1.776157166244977e-05,
+      "loss": 0.3351,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5357621216180016,
+      "grad_norm": 7.163393974304199,
+      "learning_rate": 1.6273254948653075e-05,
+      "loss": 0.3351,
+      "step": 2000
+    },
+    {
+      "epoch": 0.669702652022502,
+      "grad_norm": 9.230996131896973,
+      "learning_rate": 1.4784938234856378e-05,
+      "loss": 0.3012,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8036431824270024,
+      "grad_norm": 5.652143955230713,
+      "learning_rate": 1.3296621521059683e-05,
+      "loss": 0.3005,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9375837128315028,
+      "grad_norm": 5.993182182312012,
+      "learning_rate": 1.1808304807262986e-05,
+      "loss": 0.2899,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0715242432360033,
+      "grad_norm": 7.842578411102295,
+      "learning_rate": 1.0319988093466291e-05,
+      "loss": 0.2625,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2054647736405035,
+      "grad_norm": 8.451859474182129,
+      "learning_rate": 8.834648013097187e-06,
+      "loss": 0.2381,
+      "step": 4500
+    },
+    {
+      "epoch": 1.339405304045004,
+      "grad_norm": 5.78533935546875,
+      "learning_rate": 7.346331299300492e-06,
+      "loss": 0.2359,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4733458344495043,
+      "grad_norm": 3.672053098678589,
+      "learning_rate": 5.8609912189313885e-06,
+      "loss": 0.224,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6072863648540048,
+      "grad_norm": 7.369091987609863,
+      "learning_rate": 4.372674505134693e-06,
+      "loss": 0.2324,
+      "step": 6000
+    },
+    {
+      "epoch": 1.7412268952585053,
+      "grad_norm": 5.801908016204834,
+      "learning_rate": 2.890311058193184e-06,
+      "loss": 0.2193,
+      "step": 6500
+    },
+    {
+      "epoch": 1.8751674256630055,
+      "grad_norm": 7.236237525939941,
+      "learning_rate": 1.4019943443964876e-06,
+      "loss": 0.2281,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7466,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819a41c48213cda2585e5b4c6be90c74aa7350c8881ce010e842d5ce9f28a109
+size 7224