Upload 14 files

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 49232
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baaaa8810c4a33f6fef84e3dbac0068cab8c485249225579c25294053a5b0fa7
+size 1448710040

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a27c808015365c0c337c21dd5a281978d825428439ab348d0b7376af39dfa7
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88660ae6403d335eceaab23dcb5f9c55926c1609dac53b5c55a868e442b4d61b
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86df1b344f7a656be2e11d32a2a223715308172bccc33f58196f2fdd0c5e3989
+size 1064

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

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_config.json

@@ -0,0 +1,63 @@
+{
+  "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
+    },
+    "49231": {
+      "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 8192,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,167 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999347982004303,
+  "eval_steps": 500,
+  "global_step": 1917,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0521614396557345,
+      "grad_norm": 6.860655307769775,
+      "learning_rate": 9.895833333333334e-06,
+      "loss": 0.2352,
+      "step": 100
+    },
+    {
+      "epoch": 0.104322879311469,
+      "grad_norm": 0.910341203212738,
+      "learning_rate": 1.996521739130435e-05,
+      "loss": 0.0854,
+      "step": 200
+    },
+    {
+      "epoch": 0.1564843189672035,
+      "grad_norm": 15.565857887268066,
+      "learning_rate": 1.8817391304347828e-05,
+      "loss": 0.0579,
+      "step": 300
+    },
+    {
+      "epoch": 0.208645758622938,
+      "grad_norm": 8.692508697509766,
+      "learning_rate": 1.7657971014492754e-05,
+      "loss": 0.0662,
+      "step": 400
+    },
+    {
+      "epoch": 0.2608071982786725,
+      "grad_norm": 0.031041253358125687,
+      "learning_rate": 1.6510144927536233e-05,
+      "loss": 0.0784,
+      "step": 500
+    },
+    {
+      "epoch": 0.312968637934407,
+      "grad_norm": 3.0286190509796143,
+      "learning_rate": 1.535072463768116e-05,
+      "loss": 0.0975,
+      "step": 600
+    },
+    {
+      "epoch": 0.3651300775901415,
+      "grad_norm": 17.107019424438477,
+      "learning_rate": 1.4191304347826087e-05,
+      "loss": 0.1162,
+      "step": 700
+    },
+    {
+      "epoch": 0.417291517245876,
+      "grad_norm": 0.3376404047012329,
+      "learning_rate": 1.3031884057971015e-05,
+      "loss": 0.1132,
+      "step": 800
+    },
+    {
+      "epoch": 0.4694529569016105,
+      "grad_norm": 0.49836966395378113,
+      "learning_rate": 1.1872463768115942e-05,
+      "loss": 0.192,
+      "step": 900
+    },
+    {
+      "epoch": 0.521614396557345,
+      "grad_norm": 0.1673300564289093,
+      "learning_rate": 1.071304347826087e-05,
+      "loss": 0.1107,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5737758362130795,
+      "grad_norm": 1.4948456287384033,
+      "learning_rate": 9.553623188405798e-06,
+      "loss": 0.1355,
+      "step": 1100
+    },
+    {
+      "epoch": 0.625937275868814,
+      "grad_norm": 2.7801311016082764,
+      "learning_rate": 8.394202898550725e-06,
+      "loss": 0.1275,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6780987155245485,
+      "grad_norm": 5.762394428253174,
+      "learning_rate": 7.234782608695653e-06,
+      "loss": 0.1514,
+      "step": 1300
+    },
+    {
+      "epoch": 0.730260155180283,
+      "grad_norm": 3.5544540882110596,
+      "learning_rate": 6.07536231884058e-06,
+      "loss": 0.165,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7824215948360175,
+      "grad_norm": 15.184954643249512,
+      "learning_rate": 4.915942028985508e-06,
+      "loss": 0.1568,
+      "step": 1500
+    },
+    {
+      "epoch": 0.834583034491752,
+      "grad_norm": 0.3603503108024597,
+      "learning_rate": 3.7565217391304347e-06,
+      "loss": 0.2338,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8867444741474865,
+      "grad_norm": 21.175050735473633,
+      "learning_rate": 2.5971014492753625e-06,
+      "loss": 0.2064,
+      "step": 1700
+    },
+    {
+      "epoch": 0.938905913803221,
+      "grad_norm": 4.581367015838623,
+      "learning_rate": 1.4376811594202899e-06,
+      "loss": 0.3337,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9910673534589555,
+      "grad_norm": 627.7379760742188,
+      "learning_rate": 2.7826086956521744e-07,
+      "loss": 0.6769,
+      "step": 1900
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1917,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0af54f1d867662205005dca9657ece93833d39cc5b2f2626e4b1d0728b36f3
+size 5624