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 sha256:8d4ffad2098d7f1190d2ef5b03b2ec89424b4f4ff228fc3c4f690bb311a40626
+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:a12603114a1e5e4af5d5d5c8d9da394a39e30978ddc42d36befb03931b226abf
+size 180607738

checkpoint-18450/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d61e11190f77ec16c38dd9a968cd197f1759013af9253c976ba53ab98f3ed0a
+size 14244

checkpoint-18450/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eedf4b9d439132984ffccc8e4757bf30160e2258aebaa592098fad83b20ad05a
+size 988

checkpoint-18450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fc5b69c6860803ff02d4ead2796dc3d5c30bb1ac4924492d33872735bb2501
+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 +1,185 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.997401753816174,
+  "eval_steps": 2000,
+  "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": 6.329872131347656,
+      "learning_rate": 0.0,
+      "loss": 3.5897,
+      "step": 1
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 4.293406009674072,
+      "learning_rate": 1.083468834688347e-05,
+      "loss": 2.7064,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "eval_cosine_accuracy": 0.9586942791938782,
+      "eval_loss": 0.8709586262702942,
+      "eval_runtime": 27.5933,
+      "eval_samples_per_second": 343.054,
+      "eval_steps_per_second": 1.341,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 4.324254512786865,
+      "learning_rate": 1.9978379912856214e-05,
+      "loss": 2.329,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "eval_cosine_accuracy": 0.9603845477104187,
+      "eval_loss": 0.7834552526473999,
+      "eval_runtime": 28.2134,
+      "eval_samples_per_second": 335.514,
+      "eval_steps_per_second": 1.311,
+      "step": 4000
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 3.9401559829711914,
+      "learning_rate": 1.8817456178806968e-05,
+      "loss": 3.1654,
+      "step": 6000
+    },
+    {
+      "epoch": 0.975609756097561,
+      "eval_cosine_accuracy": 0.9413691163063049,
+      "eval_loss": 0.8306073546409607,
+      "eval_runtime": 28.2637,
+      "eval_samples_per_second": 334.918,
+      "eval_steps_per_second": 1.309,
+      "step": 6000
+    },
+    {
+      "epoch": 1.3004222150048717,
+      "grad_norm": 3.761338233947754,
+      "learning_rate": 1.608423651229285e-05,
+      "loss": 2.3508,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3004222150048717,
+      "eval_cosine_accuracy": 0.9673568606376648,
+      "eval_loss": 0.7369900345802307,
+      "eval_runtime": 27.3697,
+      "eval_samples_per_second": 345.856,
+      "eval_steps_per_second": 1.352,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6252029879831114,
+      "grad_norm": 3.7593600749969482,
+      "learning_rate": 1.2264025329129863e-05,
+      "loss": 2.2106,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6252029879831114,
+      "eval_cosine_accuracy": 0.9711599349975586,
+      "eval_loss": 0.7299672961235046,
+      "eval_runtime": 27.2951,
+      "eval_samples_per_second": 346.803,
+      "eval_steps_per_second": 1.356,
+      "step": 10000
+    },
+    {
+      "epoch": 1.949983760961351,
+      "grad_norm": 5.306521415710449,
+      "learning_rate": 8.041790887292732e-06,
+      "loss": 2.1061,
+      "step": 12000
+    },
+    {
+      "epoch": 1.949983760961351,
+      "eval_cosine_accuracy": 0.9721106886863708,
+      "eval_loss": 0.7211065888404846,
+      "eval_runtime": 27.2505,
+      "eval_samples_per_second": 347.37,
+      "eval_steps_per_second": 1.358,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2747645339395905,
+      "grad_norm": 6.47313117980957,
+      "learning_rate": 4.168736998257835e-06,
+      "loss": 2.1044,
+      "step": 14000
+    },
+    {
+      "epoch": 2.2747645339395905,
+      "eval_cosine_accuracy": 0.9728502035140991,
+      "eval_loss": 0.7193670868873596,
+      "eval_runtime": 27.5218,
+      "eval_samples_per_second": 343.946,
+      "eval_steps_per_second": 1.344,
+      "step": 14000
+    },
+    {
+      "epoch": 2.5995453069178307,
+      "grad_norm": 3.510392189025879,
+      "learning_rate": 1.335492200739472e-06,
+      "loss": 2.0589,
+      "step": 16000
+    },
+    {
+      "epoch": 2.5995453069178307,
+      "eval_cosine_accuracy": 0.9726389050483704,
+      "eval_loss": 0.7184897661209106,
+      "eval_runtime": 27.2647,
+      "eval_samples_per_second": 347.189,
+      "eval_steps_per_second": 1.357,
+      "step": 16000
+    },
+    {
+      "epoch": 2.92432607989607,
+      "grad_norm": 4.426162242889404,
+      "learning_rate": 4.747708438573639e-08,
+      "loss": 2.0677,
+      "step": 18000
+    },
+    {
+      "epoch": 2.92432607989607,
+      "eval_cosine_accuracy": 0.9725332856178284,
+      "eval_loss": 0.7178966403007507,
+      "eval_runtime": 27.3913,
+      "eval_samples_per_second": 345.585,
+      "eval_steps_per_second": 1.351,
+      "step": 18000
+    }
+  ],
+  "logging_steps": 2000,
+  "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 sha256:7e680f7ce3c4003c8476426ddcd3e02f02f5e3ed6c547c8ea0531777db8148d4
+size 5624

checkpoint-18450/training_metrics.json

@@ -0,0 +1,60 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.3252032520325203,
+      "global_step": 2000,
+      "eval_loss": 0.8709586262702942,
+      "eval_cosine_accuracy": 0.9586942791938782
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "global_step": 4000,
+      "eval_loss": 0.7834552526473999,
+      "eval_cosine_accuracy": 0.9603845477104187
+    },
+    {
+      "epoch": 0.975609756097561,
+      "global_step": 6000,
+      "eval_loss": 0.8306073546409607,
+      "eval_cosine_accuracy": 0.9413691163063049
+    },
+    {
+      "epoch": 1.3004222150048717,
+      "global_step": 8000,
+      "eval_loss": 0.7369900345802307,
+      "eval_cosine_accuracy": 0.9673568606376648
+    },
+    {
+      "epoch": 1.6252029879831114,
+      "global_step": 10000,
+      "eval_loss": 0.7299672961235046,
+      "eval_cosine_accuracy": 0.9711599349975586
+    },
+    {
+      "epoch": 1.949983760961351,
+      "global_step": 12000,
+      "eval_loss": 0.7211065888404846,
+      "eval_cosine_accuracy": 0.9721106886863708
+    },
+    {
+      "epoch": 2.2747645339395905,
+      "global_step": 14000,
+      "eval_loss": 0.7193670868873596,
+      "eval_cosine_accuracy": 0.9728502035140991
+    },
+    {
+      "epoch": 2.5995453069178307,
+      "global_step": 16000,
+      "eval_loss": 0.7184897661209106,
+      "eval_cosine_accuracy": 0.9726389050483704
+    },
+    {
+      "epoch": 2.92432607989607,
+      "global_step": 18000,
+      "eval_loss": 0.7178966403007507,
+      "eval_cosine_accuracy": 0.9725332856178284
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 18450
+}