Training checkpoint - Epoch 1, Step 10512

checkpoint-10512/1_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-10512/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-10512/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-10512/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c434022055af09bf5c8e9108602b159528ec0790c41791540a1ca073029b01cd
+size 90864192

checkpoint-10512/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-10512/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019a9342fe2e130f52f2f5f9eeb4b2f8ba2fea908b5181ff290273a0e607029b
+size 180607738

checkpoint-10512/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156511896b370dc25cb4a9d134829c35f859bd75969b87f982ac7dcfd0541606
+size 14244

checkpoint-10512/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8001e500bb4d5328c194456b5620ed3a863a70ee3e3af3fee2b70edaae3c20d
+size 988

checkpoint-10512/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028b590ec57d9d78c476b46fa662d497b6b5d808d69076d53e363885c3dbed28
+size 1064

checkpoint-10512/sentence_bert_config.json

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

checkpoint-10512/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-10512/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-10512/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9984802431610942,
+  "eval_steps": 2000,
+  "global_step": 10512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001902587519025875,
+      "grad_norm": 6.173529624938965,
+      "learning_rate": 0.0,
+      "loss": 2.3156,
+      "step": 1
+    },
+    {
+      "epoch": 0.380517503805175,
+      "grad_norm": 4.211840629577637,
+      "learning_rate": 1.9509538417053586e-05,
+      "loss": 2.0027,
+      "step": 2000
+    },
+    {
+      "epoch": 0.380517503805175,
+      "eval_loss": 1.2400720119476318,
+      "eval_runtime": 73.7674,
+      "eval_samples_per_second": 390.769,
+      "eval_steps_per_second": 1.532,
+      "step": 2000
+    },
+    {
+      "epoch": 0.76103500761035,
+      "grad_norm": 4.12247371673584,
+      "learning_rate": 1.558121760403115e-05,
+      "loss": 2.3392,
+      "step": 4000
+    },
+    {
+      "epoch": 0.76103500761035,
+      "eval_loss": 1.0379940271377563,
+      "eval_runtime": 15.8497,
+      "eval_samples_per_second": 1818.712,
+      "eval_steps_per_second": 7.129,
+      "step": 4000
+    },
+    {
+      "epoch": 1.141337386018237,
+      "grad_norm": 3.9710476398468018,
+      "learning_rate": 9.283295746269904e-06,
+      "loss": 2.5713,
+      "step": 6000
+    },
+    {
+      "epoch": 1.141337386018237,
+      "eval_loss": 1.0637402534484863,
+      "eval_runtime": 15.3045,
+      "eval_samples_per_second": 1883.492,
+      "eval_steps_per_second": 7.383,
+      "step": 6000
+    },
+    {
+      "epoch": 1.521276595744681,
+      "grad_norm": 4.5138092041015625,
+      "learning_rate": 3.2922575064750017e-06,
+      "loss": 2.1283,
+      "step": 8000
+    },
+    {
+      "epoch": 1.521276595744681,
+      "eval_loss": 1.0629677772521973,
+      "eval_runtime": 15.2421,
+      "eval_samples_per_second": 1891.205,
+      "eval_steps_per_second": 7.414,
+      "step": 8000
+    },
+    {
+      "epoch": 1.9012158054711246,
+      "grad_norm": 4.457160472869873,
+      "learning_rate": 1.470284758432794e-07,
+      "loss": 2.1013,
+      "step": 10000
+    },
+    {
+      "epoch": 1.9012158054711246,
+      "eval_loss": 1.0634821653366089,
+      "eval_runtime": 15.115,
+      "eval_samples_per_second": 1907.115,
+      "eval_steps_per_second": 7.476,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 10512,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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-10512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6b0679c9323fef82bbf6e0549449335f7d24c3263524e193ad415e2f627e34
+size 5624

checkpoint-10512/training_metrics.json

@@ -0,0 +1,36 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.380517503805175,
+      "global_step": 2000,
+      "eval_loss": 1.2400720119476318,
+      "eval_cosine_accuracy": null
+    },
+    {
+      "epoch": 0.76103500761035,
+      "global_step": 4000,
+      "eval_loss": 1.0379940271377563,
+      "eval_cosine_accuracy": null
+    },
+    {
+      "epoch": 1.141337386018237,
+      "global_step": 6000,
+      "eval_loss": 1.0637402534484863,
+      "eval_cosine_accuracy": null
+    },
+    {
+      "epoch": 1.521276595744681,
+      "global_step": 8000,
+      "eval_loss": 1.0629677772521973,
+      "eval_cosine_accuracy": null
+    },
+    {
+      "epoch": 1.9012158054711246,
+      "global_step": 10000,
+      "eval_loss": 1.0634821653366089,
+      "eval_cosine_accuracy": null
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 10512
+}