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 sha256:6d1a4111577ef4d291e80e5292f0f3c219b62e62ef9abecf13ac1d65f8f5dc4f
+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 sha256:7a100d193183d7e7b094edbc47b60e62ce79dd9f643b10003c192501c3c5c5b4
+size 180607738

checkpoint-8592/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2590fb0ec9cda487c083dd0ef28aca961dbe4136bc2c4ee0e715bcfbe0d3e7
+size 14244

checkpoint-8592/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b53a8e07ee4daabf485fd62b89cf48e6127315454b1d158f92cddba68d6165d
+size 988

checkpoint-8592/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22a0371420d37f26bb457170020470f80c985620cede98e6725eac95d9b56d3
+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": 8.116299629211426,
+      "learning_rate": 0.0,
+      "loss": 2.7266,
+      "step": 1
+    },
+    {
+      "epoch": 0.05819366852886406,
+      "grad_norm": 57.76313781738281,
+      "learning_rate": 1.732045163543243e-06,
+      "loss": 3.7373,
+      "step": 500
+    },
+    {
+      "epoch": 0.05819366852886406,
+      "eval_cosine_accuracy": 0.9404736757278442,
+      "eval_loss": 2.536726713180542,
+      "eval_runtime": 23.2615,
+      "eval_samples_per_second": 406.594,
+      "eval_steps_per_second": 1.591,
+      "step": 500
+    },
+    {
+      "epoch": 0.11638733705772812,
+      "grad_norm": 5.569820880889893,
+      "learning_rate": 3.4780584332440925e-06,
+      "loss": 2.8655,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11638733705772812,
+      "eval_cosine_accuracy": 0.9364559054374695,
+      "eval_loss": 2.6046745777130127,
+      "eval_runtime": 23.4136,
+      "eval_samples_per_second": 403.953,
+      "eval_steps_per_second": 1.58,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "grad_norm": 5.892590045928955,
+      "learning_rate": 5.224071702944943e-06,
+      "loss": 2.3859,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "eval_cosine_accuracy": 0.9412137866020203,
+      "eval_loss": 2.540637969970703,
+      "eval_runtime": 23.458,
+      "eval_samples_per_second": 403.189,
+      "eval_steps_per_second": 1.577,
+      "step": 1500
+    },
+    {
+      "epoch": 0.23277467411545624,
+      "grad_norm": 41.33493423461914,
+      "learning_rate": 6.970084972645793e-06,
+      "loss": 2.1884,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23277467411545624,
+      "eval_cosine_accuracy": 0.9451258182525635,
+      "eval_loss": 2.5318424701690674,
+      "eval_runtime": 23.2789,
+      "eval_samples_per_second": 406.29,
+      "eval_steps_per_second": 1.589,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2909683426443203,
+      "grad_norm": 15.76939582824707,
+      "learning_rate": 8.71260621580724e-06,
+      "loss": 1.9576,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2909683426443203,
+      "eval_cosine_accuracy": 0.9467117786407471,
+      "eval_loss": 2.474266767501831,
+      "eval_runtime": 23.3675,
+      "eval_samples_per_second": 404.75,
+      "eval_steps_per_second": 1.583,
+      "step": 2500
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "grad_norm": 7.4116950035095215,
+      "learning_rate": 1.045861948550809e-05,
+      "loss": 1.8211,
+      "step": 3000
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "eval_cosine_accuracy": 0.9435398578643799,
+      "eval_loss": 2.547072649002075,
+      "eval_runtime": 23.3771,
+      "eval_samples_per_second": 404.583,
+      "eval_steps_per_second": 1.583,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4073556797020484,
+      "grad_norm": 25.99747657775879,
+      "learning_rate": 1.2204632755208939e-05,
+      "loss": 1.6603,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4073556797020484,
+      "eval_cosine_accuracy": 0.9489321112632751,
+      "eval_loss": 2.472174644470215,
+      "eval_runtime": 23.4652,
+      "eval_samples_per_second": 403.065,
+      "eval_steps_per_second": 1.577,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4655493482309125,
+      "grad_norm": 5.763104438781738,
+      "learning_rate": 1.395064602490979e-05,
+      "loss": 1.596,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4655493482309125,
+      "eval_cosine_accuracy": 0.9438570737838745,
+      "eval_loss": 2.5426251888275146,
+      "eval_runtime": 23.3963,
+      "eval_samples_per_second": 404.252,
+      "eval_steps_per_second": 1.581,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5237430167597765,
+      "grad_norm": 4.893315315246582,
+      "learning_rate": 1.5693167268071237e-05,
+      "loss": 1.5379,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5237430167597765,
+      "eval_cosine_accuracy": 0.9473461508750916,
+      "eval_loss": 2.4768149852752686,
+      "eval_runtime": 23.5926,
+      "eval_samples_per_second": 400.888,
+      "eval_steps_per_second": 1.568,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5819366852886406,
+      "grad_norm": 43.368614196777344,
+      "learning_rate": 1.7439180537772086e-05,
+      "loss": 1.5397,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5819366852886406,
+      "eval_cosine_accuracy": 0.9487206339836121,
+      "eval_loss": 2.4771170616149902,
+      "eval_runtime": 23.566,
+      "eval_samples_per_second": 401.341,
+      "eval_steps_per_second": 1.57,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6401303538175046,
+      "grad_norm": 0.21546457707881927,
+      "learning_rate": 1.9185193807472936e-05,
+      "loss": 1.381,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6401303538175046,
+      "eval_cosine_accuracy": 0.9412137866020203,
+      "eval_loss": 2.6126925945281982,
+      "eval_runtime": 23.871,
+      "eval_samples_per_second": 396.213,
+      "eval_steps_per_second": 1.55,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6983240223463687,
+      "grad_norm": 27.70214080810547,
+      "learning_rate": 2.0931207077173788e-05,
+      "loss": 1.4407,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6983240223463687,
+      "eval_cosine_accuracy": 0.9492493271827698,
+      "eval_loss": 2.457711935043335,
+      "eval_runtime": 23.5818,
+      "eval_samples_per_second": 401.072,
+      "eval_steps_per_second": 1.569,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7565176908752328,
+      "grad_norm": 0.6600456237792969,
+      "learning_rate": 2.2677220346874637e-05,
+      "loss": 1.3692,
+      "step": 6500
+    },
+    {
+      "epoch": 0.7565176908752328,
+      "eval_cosine_accuracy": 0.9438570737838745,
+      "eval_loss": 2.48168683052063,
+      "eval_runtime": 23.5688,
+      "eval_samples_per_second": 401.294,
+      "eval_steps_per_second": 1.57,
+      "step": 6500
+    },
+    {
+      "epoch": 0.8147113594040968,
+      "grad_norm": 15.486236572265625,
+      "learning_rate": 2.4419741590036085e-05,
+      "loss": 1.2731,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8147113594040968,
+      "eval_cosine_accuracy": 0.943751335144043,
+      "eval_loss": 2.5139832496643066,
+      "eval_runtime": 23.6217,
+      "eval_samples_per_second": 400.394,
+      "eval_steps_per_second": 1.566,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8729050279329609,
+      "grad_norm": 13.570350646972656,
+      "learning_rate": 2.6165754859736934e-05,
+      "loss": 1.223,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8729050279329609,
+      "eval_cosine_accuracy": 0.9494607448577881,
+      "eval_loss": 2.4431588649749756,
+      "eval_runtime": 23.5387,
+      "eval_samples_per_second": 401.807,
+      "eval_steps_per_second": 1.572,
+      "step": 7500
+    },
+    {
+      "epoch": 0.931098696461825,
+      "grad_norm": 4.8542633056640625,
+      "learning_rate": 2.7911768129437783e-05,
+      "loss": 1.1982,
+      "step": 8000
+    },
+    {
+      "epoch": 0.931098696461825,
+      "eval_cosine_accuracy": 0.9420596361160278,
+      "eval_loss": 2.5187907218933105,
+      "eval_runtime": 23.6462,
+      "eval_samples_per_second": 399.98,
+      "eval_steps_per_second": 1.565,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9892923649906891,
+      "grad_norm": 36.649906158447266,
+      "learning_rate": 2.9657781399138632e-05,
+      "loss": 1.1693,
+      "step": 8500
+    },
+    {
+      "epoch": 0.9892923649906891,
+      "eval_cosine_accuracy": 0.9469232559204102,
+      "eval_loss": 2.4668424129486084,
+      "eval_runtime": 23.9878,
+      "eval_samples_per_second": 394.284,
+      "eval_steps_per_second": 1.542,
+      "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:e4d75a4b36857a175cdfda60f40427b0ec82ca5e37197466aed6d4cb12e0e9a8
+size 5688

checkpoint-8592/training_metrics.json

@@ -0,0 +1,108 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.05819366852886406,
+      "global_step": 500,
+      "eval_loss": 2.536726713180542,
+      "eval_cosine_accuracy": 0.9404736757278442
+    },
+    {
+      "epoch": 0.11638733705772812,
+      "global_step": 1000,
+      "eval_loss": 2.6046745777130127,
+      "eval_cosine_accuracy": 0.9364559054374695
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "global_step": 1500,
+      "eval_loss": 2.540637969970703,
+      "eval_cosine_accuracy": 0.9412137866020203
+    },
+    {
+      "epoch": 0.23277467411545624,
+      "global_step": 2000,
+      "eval_loss": 2.5318424701690674,
+      "eval_cosine_accuracy": 0.9451258182525635
+    },
+    {
+      "epoch": 0.2909683426443203,
+      "global_step": 2500,
+      "eval_loss": 2.474266767501831,
+      "eval_cosine_accuracy": 0.9467117786407471
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "global_step": 3000,
+      "eval_loss": 2.547072649002075,
+      "eval_cosine_accuracy": 0.9435398578643799
+    },
+    {
+      "epoch": 0.4073556797020484,
+      "global_step": 3500,
+      "eval_loss": 2.472174644470215,
+      "eval_cosine_accuracy": 0.9489321112632751
+    },
+    {
+      "epoch": 0.4655493482309125,
+      "global_step": 4000,
+      "eval_loss": 2.5426251888275146,
+      "eval_cosine_accuracy": 0.9438570737838745
+    },
+    {
+      "epoch": 0.5237430167597765,
+      "global_step": 4500,
+      "eval_loss": 2.4768149852752686,
+      "eval_cosine_accuracy": 0.9473461508750916
+    },
+    {
+      "epoch": 0.5819366852886406,
+      "global_step": 5000,
+      "eval_loss": 2.4771170616149902,
+      "eval_cosine_accuracy": 0.9487206339836121
+    },
+    {
+      "epoch": 0.6401303538175046,
+      "global_step": 5500,
+      "eval_loss": 2.6126925945281982,
+      "eval_cosine_accuracy": 0.9412137866020203
+    },
+    {
+      "epoch": 0.6983240223463687,
+      "global_step": 6000,
+      "eval_loss": 2.457711935043335,
+      "eval_cosine_accuracy": 0.9492493271827698
+    },
+    {
+      "epoch": 0.7565176908752328,
+      "global_step": 6500,
+      "eval_loss": 2.48168683052063,
+      "eval_cosine_accuracy": 0.9438570737838745
+    },
+    {
+      "epoch": 0.8147113594040968,
+      "global_step": 7000,
+      "eval_loss": 2.5139832496643066,
+      "eval_cosine_accuracy": 0.943751335144043
+    },
+    {
+      "epoch": 0.8729050279329609,
+      "global_step": 7500,
+      "eval_loss": 2.4431588649749756,
+      "eval_cosine_accuracy": 0.9494607448577881
+    },
+    {
+      "epoch": 0.931098696461825,
+      "global_step": 8000,
+      "eval_loss": 2.5187907218933105,
+      "eval_cosine_accuracy": 0.9420596361160278
+    },
+    {
+      "epoch": 0.9892923649906891,
+      "global_step": 8500,
+      "eval_loss": 2.4668424129486084,
+      "eval_cosine_accuracy": 0.9469232559204102
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 8592
+}