Training checkpoint - Epoch 5, Step 28494

checkpoint-28494/1_Pooling/config.json

@@ -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
+}

checkpoint-28494/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-28494/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.53.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-28494/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef64eb279bd1143813054d3a1c19b0c3ee03c635e278ac83a31c243832e56161
+size 133462128

checkpoint-28494/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"
+  }
+]

checkpoint-28494/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160ce039d4d9e0c72a32c520f11e9299acda3e10e0c702df874084581f7bec11
+size 265862074

checkpoint-28494/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94280ea6a40633f11f1d4cfbc067f04f76df31000c3711ddf55b2f9e3483ba6
+size 14244

checkpoint-28494/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079e98317a0bafa89e69868dfd90a63dc2e8575f1b29f30ca7aa2068bc25659d
+size 988

checkpoint-28494/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728d34c4b1b8245fbd587855093c11992d5ec092cdd6adc456438cd2e920c12
+size 1064

checkpoint-28494/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 128,
+    "do_lower_case": false
+}

checkpoint-28494/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-28494/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

checkpoint-28494/trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.995896896370331,
+  "eval_steps": 2000,
+  "global_step": 28494,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00021059281878487945,
+      "grad_norm": 6.283910751342773,
+      "learning_rate": 0.0,
+      "loss": 2.9659,
+      "step": 1
+    },
+    {
+      "epoch": 0.42118563756975885,
+      "grad_norm": 3.459829092025757,
+      "learning_rate": 6.308972198820557e-06,
+      "loss": 2.3382,
+      "step": 2000
+    },
+    {
+      "epoch": 0.42118563756975885,
+      "eval_cosine_accuracy": 0.940467357635498,
+      "eval_loss": 0.7114619016647339,
+      "eval_runtime": 39.4223,
+      "eval_samples_per_second": 239.889,
+      "eval_steps_per_second": 0.939,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "grad_norm": 3.597459077835083,
+      "learning_rate": 1.262742207245156e-05,
+      "loss": 1.5917,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "eval_cosine_accuracy": 0.94924396276474,
+      "eval_loss": 0.6677370667457581,
+      "eval_runtime": 38.4447,
+      "eval_samples_per_second": 245.99,
+      "eval_steps_per_second": 0.962,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "grad_norm": 3.2468101978302,
+      "learning_rate": 1.894271272114575e-05,
+      "loss": 1.2489,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "eval_cosine_accuracy": 0.9509358406066895,
+      "eval_loss": 0.6355894207954407,
+      "eval_runtime": 38.9493,
+      "eval_samples_per_second": 242.803,
+      "eval_steps_per_second": 0.95,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "grad_norm": 2.8085293769836426,
+      "learning_rate": 2.5261162594776748e-05,
+      "loss": 1.0529,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "eval_cosine_accuracy": 0.9561171531677246,
+      "eval_loss": 0.6007522940635681,
+      "eval_runtime": 38.6218,
+      "eval_samples_per_second": 244.862,
+      "eval_steps_per_second": 0.958,
+      "step": 8000
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "grad_norm": 2.866631031036377,
+      "learning_rate": 2.9948961266100144e-05,
+      "loss": 0.9333,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "eval_cosine_accuracy": 0.9581262469291687,
+      "eval_loss": 0.5822440385818481,
+      "eval_runtime": 38.2791,
+      "eval_samples_per_second": 247.054,
+      "eval_steps_per_second": 0.967,
+      "step": 10000
+    },
+    {
+      "epoch": 2.525618095739085,
+      "grad_norm": 2.5513157844543457,
+      "learning_rate": 2.8737333981264332e-05,
+      "loss": 0.8338,
+      "step": 12000
+    },
+    {
+      "epoch": 2.525618095739085,
+      "eval_cosine_accuracy": 0.9619329571723938,
+      "eval_loss": 0.5283726453781128,
+      "eval_runtime": 38.3146,
+      "eval_samples_per_second": 246.825,
+      "eval_steps_per_second": 0.966,
+      "step": 12000
+    },
+    {
+      "epoch": 2.946449237243556,
+      "grad_norm": 2.3156800270080566,
+      "learning_rate": 2.6038422479079082e-05,
+      "loss": 0.7775,
+      "step": 14000
+    },
+    {
+      "epoch": 2.946449237243556,
+      "eval_cosine_accuracy": 0.9632018804550171,
+      "eval_loss": 0.5352063775062561,
+      "eval_runtime": 38.4524,
+      "eval_samples_per_second": 245.94,
+      "eval_steps_per_second": 0.962,
+      "step": 14000
+    },
+    {
+      "epoch": 3.367175170962651,
+      "grad_norm": 2.613723039627075,
+      "learning_rate": 2.214208112730914e-05,
+      "loss": 0.7191,
+      "step": 16000
+    },
+    {
+      "epoch": 3.367175170962651,
+      "eval_cosine_accuracy": 0.9644707441329956,
+      "eval_loss": 0.5300219058990479,
+      "eval_runtime": 38.4919,
+      "eval_samples_per_second": 245.688,
+      "eval_steps_per_second": 0.961,
+      "step": 16000
+    },
+    {
+      "epoch": 3.7880063124671226,
+      "grad_norm": 2.4794392585754395,
+      "learning_rate": 1.747162298904552e-05,
+      "loss": 0.6904,
+      "step": 18000
+    },
+    {
+      "epoch": 3.7880063124671226,
+      "eval_cosine_accuracy": 0.9654224514961243,
+      "eval_loss": 0.5290876626968384,
+      "eval_runtime": 38.7123,
+      "eval_samples_per_second": 244.289,
+      "eval_steps_per_second": 0.956,
+      "step": 18000
+    },
+    {
+      "epoch": 4.2087322461862176,
+      "grad_norm": 2.228278398513794,
+      "learning_rate": 1.2533270267732734e-05,
+      "loss": 0.6632,
+      "step": 20000
+    },
+    {
+      "epoch": 4.2087322461862176,
+      "eval_cosine_accuracy": 0.9654224514961243,
+      "eval_loss": 0.5150468945503235,
+      "eval_runtime": 38.2521,
+      "eval_samples_per_second": 247.228,
+      "eval_steps_per_second": 0.967,
+      "step": 20000
+    },
+    {
+      "epoch": 4.629563387690689,
+      "grad_norm": 2.236833333969116,
+      "learning_rate": 7.866645425121001e-06,
+      "loss": 0.6361,
+      "step": 22000
+    },
+    {
+      "epoch": 4.629563387690689,
+      "eval_cosine_accuracy": 0.9681717157363892,
+      "eval_loss": 0.508901834487915,
+      "eval_runtime": 38.4653,
+      "eval_samples_per_second": 245.858,
+      "eval_steps_per_second": 0.962,
+      "step": 22000
+    },
+    {
+      "epoch": 5.050289321409784,
+      "grad_norm": 2.372911214828491,
+      "learning_rate": 3.968297987748927e-06,
+      "loss": 0.6282,
+      "step": 24000
+    },
+    {
+      "epoch": 5.050289321409784,
+      "eval_cosine_accuracy": 0.9665855765342712,
+      "eval_loss": 0.5077974200248718,
+      "eval_runtime": 38.4543,
+      "eval_samples_per_second": 245.929,
+      "eval_steps_per_second": 0.962,
+      "step": 24000
+    },
+    {
+      "epoch": 5.471120462914255,
+      "grad_norm": 2.0694260597229004,
+      "learning_rate": 1.266653483605697e-06,
+      "loss": 0.6182,
+      "step": 26000
+    },
+    {
+      "epoch": 5.471120462914255,
+      "eval_cosine_accuracy": 0.9678544998168945,
+      "eval_loss": 0.5082845687866211,
+      "eval_runtime": 38.4237,
+      "eval_samples_per_second": 246.124,
+      "eval_steps_per_second": 0.963,
+      "step": 26000
+    },
+    {
+      "epoch": 5.891951604418727,
+      "grad_norm": 2.4205498695373535,
+      "learning_rate": 5.206608348125475e-08,
+      "loss": 0.6099,
+      "step": 28000
+    },
+    {
+      "epoch": 5.891951604418727,
+      "eval_cosine_accuracy": 0.9674315452575684,
+      "eval_loss": 0.5089024305343628,
+      "eval_runtime": 38.5858,
+      "eval_samples_per_second": 245.09,
+      "eval_steps_per_second": 0.959,
+      "step": 28000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 28494,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-28494/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a2639051e7edc25c6524995dcff4f20d605413da34fc2896e35672135e9956
+size 5624

checkpoint-28494/training_metrics.json

@@ -0,0 +1,90 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.42118563756975885,
+      "global_step": 2000,
+      "eval_loss": 0.7114619016647339,
+      "eval_cosine_accuracy": 0.940467357635498
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "global_step": 4000,
+      "eval_loss": 0.6677370667457581,
+      "eval_cosine_accuracy": 0.94924396276474
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "global_step": 6000,
+      "eval_loss": 0.6355894207954407,
+      "eval_cosine_accuracy": 0.9509358406066895
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "global_step": 8000,
+      "eval_loss": 0.6007522940635681,
+      "eval_cosine_accuracy": 0.9561171531677246
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "global_step": 10000,
+      "eval_loss": 0.5822440385818481,
+      "eval_cosine_accuracy": 0.9581262469291687
+    },
+    {
+      "epoch": 2.525618095739085,
+      "global_step": 12000,
+      "eval_loss": 0.5283726453781128,
+      "eval_cosine_accuracy": 0.9619329571723938
+    },
+    {
+      "epoch": 2.946449237243556,
+      "global_step": 14000,
+      "eval_loss": 0.5352063775062561,
+      "eval_cosine_accuracy": 0.9632018804550171
+    },
+    {
+      "epoch": 3.367175170962651,
+      "global_step": 16000,
+      "eval_loss": 0.5300219058990479,
+      "eval_cosine_accuracy": 0.9644707441329956
+    },
+    {
+      "epoch": 3.7880063124671226,
+      "global_step": 18000,
+      "eval_loss": 0.5290876626968384,
+      "eval_cosine_accuracy": 0.9654224514961243
+    },
+    {
+      "epoch": 4.2087322461862176,
+      "global_step": 20000,
+      "eval_loss": 0.5150468945503235,
+      "eval_cosine_accuracy": 0.9654224514961243
+    },
+    {
+      "epoch": 4.629563387690689,
+      "global_step": 22000,
+      "eval_loss": 0.508901834487915,
+      "eval_cosine_accuracy": 0.9681717157363892
+    },
+    {
+      "epoch": 5.050289321409784,
+      "global_step": 24000,
+      "eval_loss": 0.5077974200248718,
+      "eval_cosine_accuracy": 0.9665855765342712
+    },
+    {
+      "epoch": 5.471120462914255,
+      "global_step": 26000,
+      "eval_loss": 0.5082845687866211,
+      "eval_cosine_accuracy": 0.9678544998168945
+    },
+    {
+      "epoch": 5.891951604418727,
+      "global_step": 28000,
+      "eval_loss": 0.5089024305343628,
+      "eval_cosine_accuracy": 0.9674315452575684
+    }
+  ],
+  "current_epoch": 5,
+  "global_step": 28494
+}