Upload folder using huggingface_hub

Browse files

Files changed (16) hide show

.gitattributes +1 -0
1_Pooling/config.json +10 -0
README.md +0 -0
config.json +25 -0
config_sentence_transformers.json +10 -0
model.safetensors +3 -0
modules.json +20 -0
optimizer.pt +3 -0
rng_state.pth +3 -0
scheduler.pt +3 -0
sentence_bert_config.json +4 -0
special_tokens_map.json +51 -0
tokenizer.json +3 -0
tokenizer_config.json +56 -0
trainer_state.json +509 -0
training_args.bin +3 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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

1_Pooling/config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md ADDED Viewed

The diff for this file is too large to render. See raw diff

config.json ADDED Viewed

	@@ -0,0 +1,25 @@

+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.7.1+cu128"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:11407a208a2be3cd06b48f6a28931de116570bfb7520f75ae45cd99aa60d13c1
+size 470637416

modules.json ADDED Viewed

	@@ -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"
+  }
+]

optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2c68f3ed8eaeb602a94a167d2f1cef89b9665019c918e50882f194581c2c1c48
+size 940212619

rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ca820c499203a7884efe42f8add1720c864beea265fa9eea32b7023634d03e
+size 14645

scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d682d4736c51a8bddec1240460a5cab5736031f55035e379f81f659ab4d9c0bb
+size 1465

sentence_bert_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json ADDED Viewed

	@@ -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": false,
+    "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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef04f2b385d1514f500e779207ace0f53e30895ce37563179e29f4022d28ca38
+size 17083053

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "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": false,
+      "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,509 @@

+{
+  "best_global_step": 2035,
+  "best_metric": 8.790307998657227,
+  "best_model_checkpoint": "printing_press/author-paraphrase/models/intfloat/multilingual-e5-small/checkpoint-2035",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 6.021224498748779,
+      "learning_rate": 4.9513513513513516e-05,
+      "loss": 3.1392,
+      "step": 100
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 5.465278625488281,
+      "learning_rate": 4.902211302211302e-05,
+      "loss": 2.8632,
+      "step": 200
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 6.197441577911377,
+      "learning_rate": 4.853071253071254e-05,
+      "loss": 2.6963,
+      "step": 300
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 5.761979579925537,
+      "learning_rate": 4.803931203931204e-05,
+      "loss": 2.6594,
+      "step": 400
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 6.232619285583496,
+      "learning_rate": 4.754791154791155e-05,
+      "loss": 2.584,
+      "step": 500
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 5.387997627258301,
+      "learning_rate": 4.705651105651106e-05,
+      "loss": 2.5429,
+      "step": 600
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 5.559869766235352,
+      "learning_rate": 4.656511056511057e-05,
+      "loss": 2.5105,
+      "step": 700
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 6.779473781585693,
+      "learning_rate": 4.6073710073710074e-05,
+      "loss": 2.4482,
+      "step": 800
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 5.715710639953613,
+      "learning_rate": 4.558230958230959e-05,
+      "loss": 2.442,
+      "step": 900
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 5.751602649688721,
+      "learning_rate": 4.5090909090909095e-05,
+      "loss": 2.4386,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 6.389184951782227,
+      "learning_rate": 4.45995085995086e-05,
+      "loss": 2.3912,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 5.976380825042725,
+      "learning_rate": 4.410810810810811e-05,
+      "loss": 2.3778,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 5.9267120361328125,
+      "learning_rate": 4.361670761670762e-05,
+      "loss": 2.3481,
+      "step": 1300
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 5.765600681304932,
+      "learning_rate": 4.312530712530713e-05,
+      "loss": 2.3325,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 5.1934285163879395,
+      "learning_rate": 4.263390663390663e-05,
+      "loss": 2.3082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 5.619853973388672,
+      "learning_rate": 4.2142506142506146e-05,
+      "loss": 2.2942,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 5.406186103820801,
+      "learning_rate": 4.165110565110565e-05,
+      "loss": 2.3115,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 4.95747184753418,
+      "learning_rate": 4.115970515970517e-05,
+      "loss": 2.2769,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 6.417170524597168,
+      "learning_rate": 4.066830466830467e-05,
+      "loss": 2.2402,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 6.344349384307861,
+      "learning_rate": 4.017690417690418e-05,
+      "loss": 2.2372,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_cosine_accuracy": 0.9193994404320385,
+      "eval_cosine_accuracy_threshold": 0.8741108775138855,
+      "eval_cosine_ap": 0.8367251348799856,
+      "eval_cosine_f1": 0.7428981208338088,
+      "eval_cosine_f1_threshold": 0.8662768006324768,
+      "eval_cosine_mcc": 0.6915836823172079,
+      "eval_cosine_precision": 0.7443417485874784,
+      "eval_cosine_recall": 0.741460081983213,
+      "eval_loss": 8.790307998657227,
+      "eval_runtime": 1127.8164,
+      "eval_samples_per_second": 163.527,
+      "eval_steps_per_second": 1.203,
+      "step": 2035
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 5.7056660652160645,
+      "learning_rate": 3.968550368550369e-05,
+      "loss": 2.1558,
+      "step": 2100
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 6.209120273590088,
+      "learning_rate": 3.91941031941032e-05,
+      "loss": 2.0741,
+      "step": 2200
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 6.506903648376465,
+      "learning_rate": 3.8702702702702704e-05,
+      "loss": 2.0783,
+      "step": 2300
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 5.882590293884277,
+      "learning_rate": 3.821130221130221e-05,
+      "loss": 2.0596,
+      "step": 2400
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 5.904178619384766,
+      "learning_rate": 3.7719901719901725e-05,
+      "loss": 2.0398,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 6.1165924072265625,
+      "learning_rate": 3.7228501228501226e-05,
+      "loss": 2.0504,
+      "step": 2600
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 5.996497631072998,
+      "learning_rate": 3.673710073710074e-05,
+      "loss": 2.0674,
+      "step": 2700
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 7.482200622558594,
+      "learning_rate": 3.624570024570025e-05,
+      "loss": 2.0305,
+      "step": 2800
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 5.874721527099609,
+      "learning_rate": 3.575429975429976e-05,
+      "loss": 2.0372,
+      "step": 2900
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 6.226138114929199,
+      "learning_rate": 3.526289926289926e-05,
+      "loss": 2.0271,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 6.130570411682129,
+      "learning_rate": 3.4771498771498776e-05,
+      "loss": 2.007,
+      "step": 3100
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 6.400360584259033,
+      "learning_rate": 3.428009828009828e-05,
+      "loss": 2.0074,
+      "step": 3200
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 6.5269341468811035,
+      "learning_rate": 3.378869778869779e-05,
+      "loss": 1.9978,
+      "step": 3300
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 5.755340576171875,
+      "learning_rate": 3.32972972972973e-05,
+      "loss": 1.974,
+      "step": 3400
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 6.60841178894043,
+      "learning_rate": 3.2805896805896805e-05,
+      "loss": 1.9922,
+      "step": 3500
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 7.436590194702148,
+      "learning_rate": 3.231449631449632e-05,
+      "loss": 1.9743,
+      "step": 3600
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 6.426479339599609,
+      "learning_rate": 3.182309582309582e-05,
+      "loss": 1.9536,
+      "step": 3700
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 6.678687572479248,
+      "learning_rate": 3.1331695331695334e-05,
+      "loss": 1.9717,
+      "step": 3800
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 6.789039134979248,
+      "learning_rate": 3.084029484029484e-05,
+      "loss": 1.9324,
+      "step": 3900
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 6.285867691040039,
+      "learning_rate": 3.0348894348894352e-05,
+      "loss": 1.9275,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_cosine_accuracy": 0.9200772117032121,
+      "eval_cosine_accuracy_threshold": 0.8600538969039917,
+      "eval_cosine_ap": 0.8386338276944761,
+      "eval_cosine_f1": 0.7448358673957842,
+      "eval_cosine_f1_threshold": 0.8511393070220947,
+      "eval_cosine_mcc": 0.6936559183741586,
+      "eval_cosine_precision": 0.7430153128945579,
+      "eval_cosine_recall": 0.7466653653458261,
+      "eval_loss": 9.22366714477539,
+      "eval_runtime": 1127.8509,
+      "eval_samples_per_second": 163.522,
+      "eval_steps_per_second": 1.203,
+      "step": 4070
+    },
+    {
+      "epoch": 2.0147420147420148,
+      "grad_norm": 7.566407680511475,
+      "learning_rate": 2.9857493857493856e-05,
+      "loss": 1.9059,
+      "step": 4100
+    },
+    {
+      "epoch": 2.063882063882064,
+      "grad_norm": 6.225943565368652,
+      "learning_rate": 2.9366093366093367e-05,
+      "loss": 1.7814,
+      "step": 4200
+    },
+    {
+      "epoch": 2.113022113022113,
+      "grad_norm": 6.670715808868408,
+      "learning_rate": 2.8874692874692877e-05,
+      "loss": 1.7528,
+      "step": 4300
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 8.022383689880371,
+      "learning_rate": 2.8383292383292388e-05,
+      "loss": 1.786,
+      "step": 4400
+    },
+    {
+      "epoch": 2.211302211302211,
+      "grad_norm": 7.271859169006348,
+      "learning_rate": 2.7891891891891892e-05,
+      "loss": 1.7963,
+      "step": 4500
+    },
+    {
+      "epoch": 2.2604422604422605,
+      "grad_norm": 6.646120071411133,
+      "learning_rate": 2.7400491400491403e-05,
+      "loss": 1.7744,
+      "step": 4600
+    },
+    {
+      "epoch": 2.30958230958231,
+      "grad_norm": 6.8744330406188965,
+      "learning_rate": 2.6909090909090913e-05,
+      "loss": 1.7753,
+      "step": 4700
+    },
+    {
+      "epoch": 2.3587223587223587,
+      "grad_norm": 8.4681396484375,
+      "learning_rate": 2.641769041769042e-05,
+      "loss": 1.7671,
+      "step": 4800
+    },
+    {
+      "epoch": 2.407862407862408,
+      "grad_norm": 6.876530170440674,
+      "learning_rate": 2.5926289926289924e-05,
+      "loss": 1.7832,
+      "step": 4900
+    },
+    {
+      "epoch": 2.457002457002457,
+      "grad_norm": 6.952081680297852,
+      "learning_rate": 2.5434889434889435e-05,
+      "loss": 1.7715,
+      "step": 5000
+    },
+    {
+      "epoch": 2.506142506142506,
+      "grad_norm": 7.127411365509033,
+      "learning_rate": 2.4943488943488943e-05,
+      "loss": 1.721,
+      "step": 5100
+    },
+    {
+      "epoch": 2.555282555282555,
+      "grad_norm": 7.662739276885986,
+      "learning_rate": 2.4452088452088453e-05,
+      "loss": 1.7584,
+      "step": 5200
+    },
+    {
+      "epoch": 2.6044226044226044,
+      "grad_norm": 7.068917751312256,
+      "learning_rate": 2.396068796068796e-05,
+      "loss": 1.7348,
+      "step": 5300
+    },
+    {
+      "epoch": 2.6535626535626538,
+      "grad_norm": 6.970505714416504,
+      "learning_rate": 2.346928746928747e-05,
+      "loss": 1.7331,
+      "step": 5400
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 7.2441182136535645,
+      "learning_rate": 2.297788697788698e-05,
+      "loss": 1.7274,
+      "step": 5500
+    },
+    {
+      "epoch": 2.751842751842752,
+      "grad_norm": 7.026419162750244,
+      "learning_rate": 2.248648648648649e-05,
+      "loss": 1.7587,
+      "step": 5600
+    },
+    {
+      "epoch": 2.800982800982801,
+      "grad_norm": 5.773149490356445,
+      "learning_rate": 2.1995085995085997e-05,
+      "loss": 1.7379,
+      "step": 5700
+    },
+    {
+      "epoch": 2.85012285012285,
+      "grad_norm": 6.8897809982299805,
+      "learning_rate": 2.1503685503685507e-05,
+      "loss": 1.7579,
+      "step": 5800
+    },
+    {
+      "epoch": 2.899262899262899,
+      "grad_norm": 7.6783766746521,
+      "learning_rate": 2.1012285012285015e-05,
+      "loss": 1.7573,
+      "step": 5900
+    },
+    {
+      "epoch": 2.9484029484029484,
+      "grad_norm": 6.818024158477783,
+      "learning_rate": 2.0520884520884522e-05,
+      "loss": 1.708,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9975429975429977,
+      "grad_norm": 7.6112542152404785,
+      "learning_rate": 2.002948402948403e-05,
+      "loss": 1.7159,
+      "step": 6100
+    },
+    {
+      "epoch": 3.0,
+      "eval_cosine_accuracy": 0.9208363155269265,
+      "eval_cosine_accuracy_threshold": 0.8324185609817505,
+      "eval_cosine_ap": 0.8415735890036254,
+      "eval_cosine_f1": 0.7493691493691494,
+      "eval_cosine_f1_threshold": 0.8252550363540649,
+      "eval_cosine_mcc": 0.6992932604835177,
+      "eval_cosine_precision": 0.7499918532277512,
+      "eval_cosine_recall": 0.7487474786908712,
+      "eval_loss": 9.839451789855957,
+      "eval_runtime": 1129.5778,
+      "eval_samples_per_second": 163.272,
+      "eval_steps_per_second": 1.201,
+      "step": 6105
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10175,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 136,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9c5f531debf1f74c84f519c72b0b1c02f7f63a0b81d042e6d7aff896d6f1e0
+size 6097