Training checkpoint - Epoch 1, Step 8592

checkpoint-8592/1_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-8592/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": 6,
+  "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-8592/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-8592/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a61c487beb363b9f2ba06b81ddc3e53d6b0a2c639ee23e6952bd7780510834
+size 90864192

checkpoint-8592/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-8592/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed2077cd1424a4bd6263b74c29ad763d99139dddac5cda268504b7e6a29c62a
+size 180607738

checkpoint-8592/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8957d8449ae46b38d8fe19fffa1ae3f7b3df2da18808afae432603b2da24ba
+size 14244

checkpoint-8592/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af7a0439d0c5b73969913ee5bf0dce610cfc36e12df7e585d423d497b4b4781
+size 988

checkpoint-8592/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a793324604a443d51136ef867b5388749921f4ed6b25fd241c495cebbb15b87c
+size 1064

checkpoint-8592/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "do_lower_case": false
+}

checkpoint-8592/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-8592/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": 256,
+  "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-8592/trainer_state.json

@@ -0,0 +1,313 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 8592,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00011638733705772812,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 9.4531,
+      "step": 1
+    },
+    {
+      "epoch": 0.05819366852886406,
+      "grad_norm": 6.4754815101623535,
+      "learning_rate": 1.7390292166220463e-06,
+      "loss": 6.7666,
+      "step": 500
+    },
+    {
+      "epoch": 0.05819366852886406,
+      "eval_cosine_accuracy": 0.9417916536331177,
+      "eval_loss": 4.736684322357178,
+      "eval_runtime": 26.7399,
+      "eval_samples_per_second": 354.003,
+      "eval_steps_per_second": 1.384,
+      "step": 500
+    },
+    {
+      "epoch": 0.11638733705772812,
+      "grad_norm": 5.042841911315918,
+      "learning_rate": 3.4850424863228964e-06,
+      "loss": 4.0612,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11638733705772812,
+      "eval_cosine_accuracy": 0.9421085715293884,
+      "eval_loss": 4.456507682800293,
+      "eval_runtime": 27.0721,
+      "eval_samples_per_second": 349.659,
+      "eval_steps_per_second": 1.367,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "grad_norm": 4.396075248718262,
+      "learning_rate": 5.2310557560237455e-06,
+      "loss": 3.8306,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "eval_cosine_accuracy": 0.9389393329620361,
+      "eval_loss": 4.417118072509766,
+      "eval_runtime": 29.5299,
+      "eval_samples_per_second": 320.556,
+      "eval_steps_per_second": 1.253,
+      "step": 1500
+    },
+    {
+      "epoch": 0.23277467411545624,
+      "grad_norm": 4.9983229637146,
+      "learning_rate": 6.9770690257245955e-06,
+      "loss": 3.7166,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23277467411545624,
+      "eval_cosine_accuracy": 0.9376716613769531,
+      "eval_loss": 4.384617805480957,
+      "eval_runtime": 27.1288,
+      "eval_samples_per_second": 348.928,
+      "eval_steps_per_second": 1.364,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2909683426443203,
+      "grad_norm": 5.1397552490234375,
+      "learning_rate": 8.723082295425445e-06,
+      "loss": 3.5906,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2909683426443203,
+      "eval_cosine_accuracy": 0.929537296295166,
+      "eval_loss": 4.382342338562012,
+      "eval_runtime": 27.2377,
+      "eval_samples_per_second": 347.534,
+      "eval_steps_per_second": 1.358,
+      "step": 2500
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "grad_norm": 5.401367664337158,
+      "learning_rate": 1.0469095565126295e-05,
+      "loss": 3.504,
+      "step": 3000
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "eval_cosine_accuracy": 0.9236213564872742,
+      "eval_loss": 4.398530006408691,
+      "eval_runtime": 27.2096,
+      "eval_samples_per_second": 347.891,
+      "eval_steps_per_second": 1.36,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4073556797020484,
+      "grad_norm": 5.506592273712158,
+      "learning_rate": 1.2215108834827144e-05,
+      "loss": 3.4064,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4073556797020484,
+      "eval_cosine_accuracy": 0.9207690954208374,
+      "eval_loss": 4.428633689880371,
+      "eval_runtime": 27.2549,
+      "eval_samples_per_second": 347.314,
+      "eval_steps_per_second": 1.358,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4655493482309125,
+      "grad_norm": 6.144413471221924,
+      "learning_rate": 1.3961122104527995e-05,
+      "loss": 3.3219,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4655493482309125,
+      "eval_cosine_accuracy": 0.9240439534187317,
+      "eval_loss": 4.413504600524902,
+      "eval_runtime": 27.1733,
+      "eval_samples_per_second": 348.357,
+      "eval_steps_per_second": 1.362,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5237430167597765,
+      "grad_norm": 6.7739691734313965,
+      "learning_rate": 1.570364334768944e-05,
+      "loss": 3.2308,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5237430167597765,
+      "eval_cosine_accuracy": 0.9183393120765686,
+      "eval_loss": 4.584815979003906,
+      "eval_runtime": 27.4916,
+      "eval_samples_per_second": 344.324,
+      "eval_steps_per_second": 1.346,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5819366852886406,
+      "grad_norm": 7.5280914306640625,
+      "learning_rate": 1.7449656617390294e-05,
+      "loss": 3.1167,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5819366852886406,
+      "eval_cosine_accuracy": 0.9231988191604614,
+      "eval_loss": 4.731673240661621,
+      "eval_runtime": 27.9733,
+      "eval_samples_per_second": 338.394,
+      "eval_steps_per_second": 1.323,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6401303538175046,
+      "grad_norm": 8.379385948181152,
+      "learning_rate": 1.919217786055174e-05,
+      "loss": 3.0155,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6401303538175046,
+      "eval_cosine_accuracy": 0.9202408790588379,
+      "eval_loss": 4.590743064880371,
+      "eval_runtime": 30.4387,
+      "eval_samples_per_second": 310.985,
+      "eval_steps_per_second": 1.216,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6983240223463687,
+      "grad_norm": 7.9107985496521,
+      "learning_rate": 2.093819113025259e-05,
+      "loss": 2.928,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6983240223463687,
+      "eval_cosine_accuracy": 0.9188675284385681,
+      "eval_loss": 4.662985324859619,
+      "eval_runtime": 27.6404,
+      "eval_samples_per_second": 342.469,
+      "eval_steps_per_second": 1.339,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7565176908752328,
+      "grad_norm": 8.108757972717285,
+      "learning_rate": 2.268420439995344e-05,
+      "loss": 2.8455,
+      "step": 6500
+    },
+    {
+      "epoch": 0.7565176908752328,
+      "eval_cosine_accuracy": 0.9199239611625671,
+      "eval_loss": 4.784646511077881,
+      "eval_runtime": 27.3827,
+      "eval_samples_per_second": 345.693,
+      "eval_steps_per_second": 1.351,
+      "step": 6500
+    },
+    {
+      "epoch": 0.8147113594040968,
+      "grad_norm": 8.092316627502441,
+      "learning_rate": 2.443021766965429e-05,
+      "loss": 2.7847,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8147113594040968,
+      "eval_cosine_accuracy": 0.9054510593414307,
+      "eval_loss": 4.925645351409912,
+      "eval_runtime": 27.6051,
+      "eval_samples_per_second": 342.908,
+      "eval_steps_per_second": 1.34,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8729050279329609,
+      "grad_norm": 8.676020622253418,
+      "learning_rate": 2.617623093935514e-05,
+      "loss": 2.7228,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8729050279329609,
+      "eval_cosine_accuracy": 0.9056623578071594,
+      "eval_loss": 4.843690395355225,
+      "eval_runtime": 27.3545,
+      "eval_samples_per_second": 346.049,
+      "eval_steps_per_second": 1.353,
+      "step": 7500
+    },
+    {
+      "epoch": 0.931098696461825,
+      "grad_norm": 9.083893775939941,
+      "learning_rate": 2.791875218251659e-05,
+      "loss": 2.6738,
+      "step": 8000
+    },
+    {
+      "epoch": 0.931098696461825,
+      "eval_cosine_accuracy": 0.907247006893158,
+      "eval_loss": 4.833749771118164,
+      "eval_runtime": 27.6952,
+      "eval_samples_per_second": 341.791,
+      "eval_steps_per_second": 1.336,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9892923649906891,
+      "grad_norm": 7.430295944213867,
+      "learning_rate": 2.9664765452217438e-05,
+      "loss": 2.6174,
+      "step": 8500
+    },
+    {
+      "epoch": 0.9892923649906891,
+      "eval_cosine_accuracy": 0.9006972312927246,
+      "eval_loss": 4.809013366699219,
+      "eval_runtime": 27.7002,
+      "eval_samples_per_second": 341.731,
+      "eval_steps_per_second": 1.336,
+      "step": 8500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 34368,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8592/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2efd1e792aece673d4f9c02b27251769a72b304f7949f137f2a4d2582ff9c2ea
+size 5688

checkpoint-8592/training_metrics.json

@@ -0,0 +1,108 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.05819366852886406,
+      "global_step": 500,
+      "eval_loss": 4.736684322357178,
+      "eval_cosine_accuracy": 0.9417916536331177
+    },
+    {
+      "epoch": 0.11638733705772812,
+      "global_step": 1000,
+      "eval_loss": 4.456507682800293,
+      "eval_cosine_accuracy": 0.9421085715293884
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "global_step": 1500,
+      "eval_loss": 4.417118072509766,
+      "eval_cosine_accuracy": 0.9389393329620361
+    },
+    {
+      "epoch": 0.23277467411545624,
+      "global_step": 2000,
+      "eval_loss": 4.384617805480957,
+      "eval_cosine_accuracy": 0.9376716613769531
+    },
+    {
+      "epoch": 0.2909683426443203,
+      "global_step": 2500,
+      "eval_loss": 4.382342338562012,
+      "eval_cosine_accuracy": 0.929537296295166
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "global_step": 3000,
+      "eval_loss": 4.398530006408691,
+      "eval_cosine_accuracy": 0.9236213564872742
+    },
+    {
+      "epoch": 0.4073556797020484,
+      "global_step": 3500,
+      "eval_loss": 4.428633689880371,
+      "eval_cosine_accuracy": 0.9207690954208374
+    },
+    {
+      "epoch": 0.4655493482309125,
+      "global_step": 4000,
+      "eval_loss": 4.413504600524902,
+      "eval_cosine_accuracy": 0.9240439534187317
+    },
+    {
+      "epoch": 0.5237430167597765,
+      "global_step": 4500,
+      "eval_loss": 4.584815979003906,
+      "eval_cosine_accuracy": 0.9183393120765686
+    },
+    {
+      "epoch": 0.5819366852886406,
+      "global_step": 5000,
+      "eval_loss": 4.731673240661621,
+      "eval_cosine_accuracy": 0.9231988191604614
+    },
+    {
+      "epoch": 0.6401303538175046,
+      "global_step": 5500,
+      "eval_loss": 4.590743064880371,
+      "eval_cosine_accuracy": 0.9202408790588379
+    },
+    {
+      "epoch": 0.6983240223463687,
+      "global_step": 6000,
+      "eval_loss": 4.662985324859619,
+      "eval_cosine_accuracy": 0.9188675284385681
+    },
+    {
+      "epoch": 0.7565176908752328,
+      "global_step": 6500,
+      "eval_loss": 4.784646511077881,
+      "eval_cosine_accuracy": 0.9199239611625671
+    },
+    {
+      "epoch": 0.8147113594040968,
+      "global_step": 7000,
+      "eval_loss": 4.925645351409912,
+      "eval_cosine_accuracy": 0.9054510593414307
+    },
+    {
+      "epoch": 0.8729050279329609,
+      "global_step": 7500,
+      "eval_loss": 4.843690395355225,
+      "eval_cosine_accuracy": 0.9056623578071594
+    },
+    {
+      "epoch": 0.931098696461825,
+      "global_step": 8000,
+      "eval_loss": 4.833749771118164,
+      "eval_cosine_accuracy": 0.907247006893158
+    },
+    {
+      "epoch": 0.9892923649906891,
+      "global_step": 8500,
+      "eval_loss": 4.809013366699219,
+      "eval_cosine_accuracy": 0.9006972312927246
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 8592
+}