Training checkpoint - Epoch 2, Step 18450

checkpoint-18450/1_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-18450/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-18450/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.53.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-18450/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b550a75c40e4c12d776f41857e0e59b6d55157e11bea36db30d80a1dc9621d9
+size 90864192

checkpoint-18450/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-18450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d67a1576a431a6be6b19de0ba914f3d93776a343a7d6ede01efdb9f1b42daad
+size 180607738

checkpoint-18450/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba71b00d974be91f4a589fe77ba46c3a96dfbc452a82dea3181acc752f8a2d48
+size 14244

checkpoint-18450/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927f1e4b076f7a036a511ebe68310b2f821c9cdc64e65a9eea2aa3c1f130349f
+size 988

checkpoint-18450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79b67187d98e1f3bad9cab74ea23006e01df5f7ac43156101361d70a5fe270c
+size 1064

checkpoint-18450/sentence_bert_config.json

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

checkpoint-18450/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-18450/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-18450/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.997401753816174,
+  "eval_steps": 3000,
+  "global_step": 18450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00016260162601626016,
+      "grad_norm": 6.182025909423828,
+      "learning_rate": 0.0,
+      "loss": 3.6915,
+      "step": 1
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 4.05953311920166,
+      "learning_rate": 4.062330623306233e-05,
+      "loss": 2.5598,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "eval_cosine_accuracy": 0.9593281149864197,
+      "eval_loss": 0.8499817848205566,
+      "eval_runtime": 33.8697,
+      "eval_samples_per_second": 279.483,
+      "eval_steps_per_second": 1.092,
+      "step": 3000
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 5.307164192199707,
+      "learning_rate": 4.7043640447017424e-05,
+      "loss": 2.8278,
+      "step": 6000
+    },
+    {
+      "epoch": 0.975609756097561,
+      "eval_cosine_accuracy": 0.9243608713150024,
+      "eval_loss": 1.0148402452468872,
+      "eval_runtime": 32.3667,
+      "eval_samples_per_second": 292.461,
+      "eval_steps_per_second": 1.143,
+      "step": 6000
+    },
+    {
+      "epoch": 1.4628126014939915,
+      "grad_norm": 3.3574845790863037,
+      "learning_rate": 3.5681060055393986e-05,
+      "loss": 2.2241,
+      "step": 9000
+    },
+    {
+      "epoch": 1.4628126014939915,
+      "eval_cosine_accuracy": 0.9696809649467468,
+      "eval_loss": 0.8382735848426819,
+      "eval_runtime": 33.055,
+      "eval_samples_per_second": 286.371,
+      "eval_steps_per_second": 1.119,
+      "step": 9000
+    },
+    {
+      "epoch": 1.949983760961351,
+      "grad_norm": 4.487156867980957,
+      "learning_rate": 2.0104477218231833e-05,
+      "loss": 2.0654,
+      "step": 12000
+    },
+    {
+      "epoch": 1.949983760961351,
+      "eval_cosine_accuracy": 0.9695753455162048,
+      "eval_loss": 0.8272649049758911,
+      "eval_runtime": 32.399,
+      "eval_samples_per_second": 292.17,
+      "eval_steps_per_second": 1.142,
+      "step": 12000
+    },
+    {
+      "epoch": 2.4371549204287106,
+      "grad_norm": 3.555506467819214,
+      "learning_rate": 6.460596057366469e-06,
+      "loss": 1.9899,
+      "step": 15000
+    },
+    {
+      "epoch": 2.4371549204287106,
+      "eval_cosine_accuracy": 0.9711599349975586,
+      "eval_loss": 0.8097038865089417,
+      "eval_runtime": 32.7253,
+      "eval_samples_per_second": 289.256,
+      "eval_steps_per_second": 1.131,
+      "step": 15000
+    },
+    {
+      "epoch": 2.92432607989607,
+      "grad_norm": 3.7528107166290283,
+      "learning_rate": 1.1817537630555986e-07,
+      "loss": 1.9582,
+      "step": 18000
+    },
+    {
+      "epoch": 2.92432607989607,
+      "eval_cosine_accuracy": 0.9709486365318298,
+      "eval_loss": 0.8140485882759094,
+      "eval_runtime": 32.629,
+      "eval_samples_per_second": 290.11,
+      "eval_steps_per_second": 1.134,
+      "step": 18000
+    }
+  ],
+  "logging_steps": 3000,
+  "max_steps": 18450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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-18450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9c99efc975f2b2da871acc48af93a13158085f714ae724d586f9ab26abc970
+size 5624

checkpoint-18450/training_metrics.json

@@ -0,0 +1,42 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.4878048780487805,
+      "global_step": 3000,
+      "eval_loss": 0.8499817848205566,
+      "eval_cosine_accuracy": 0.9593281149864197
+    },
+    {
+      "epoch": 0.975609756097561,
+      "global_step": 6000,
+      "eval_loss": 1.0148402452468872,
+      "eval_cosine_accuracy": 0.9243608713150024
+    },
+    {
+      "epoch": 1.4628126014939915,
+      "global_step": 9000,
+      "eval_loss": 0.8382735848426819,
+      "eval_cosine_accuracy": 0.9696809649467468
+    },
+    {
+      "epoch": 1.949983760961351,
+      "global_step": 12000,
+      "eval_loss": 0.8272649049758911,
+      "eval_cosine_accuracy": 0.9695753455162048
+    },
+    {
+      "epoch": 2.4371549204287106,
+      "global_step": 15000,
+      "eval_loss": 0.8097038865089417,
+      "eval_cosine_accuracy": 0.9711599349975586
+    },
+    {
+      "epoch": 2.92432607989607,
+      "global_step": 18000,
+      "eval_loss": 0.8140485882759094,
+      "eval_cosine_accuracy": 0.9709486365318298
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 18450
+}