Training checkpoint - Epoch 3, Step 150000

checkpoint-150000/1_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-150000/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-150000/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-150000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a092c879c9785c5f418d5463d3977669fab10bfd496f17f811626547792f19d2
+size 90864192

checkpoint-150000/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-150000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4f8001dff995c27040a10e0c328d4d8c7099ff473f3e8e477a8cd37146da19
+size 180607738

checkpoint-150000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422ac70c219518de095766f6d26affdf1bb8031db8a472d6165f720bd2b5e73a
+size 14244

checkpoint-150000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39614ee0cdc31722b42f54ed529422a821a2d103445d67a059cf0da1767e913
+size 988

checkpoint-150000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce2a55aa464e61bbff0d9b08d518ece9f7f1982567a4a124ae903610a534846
+size 1064

checkpoint-150000/sentence_bert_config.json

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

checkpoint-150000/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-150000/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-150000/trainer_state.json

@@ -0,0 +1,281 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.401701076239576,
+  "eval_steps": 10000,
+  "global_step": 150000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.3758048038773133e-05,
+      "grad_norm": 4.939470291137695,
+      "learning_rate": 0.0,
+      "loss": 3.9948,
+      "step": 1
+    },
+    {
+      "epoch": 0.23758048038773136,
+      "grad_norm": 2.9926953315734863,
+      "learning_rate": 3.5623663578047044e-06,
+      "loss": 3.2694,
+      "step": 10000
+    },
+    {
+      "epoch": 0.23758048038773136,
+      "eval_cosine_accuracy": 0.9539926052093506,
+      "eval_loss": 0.764169454574585,
+      "eval_runtime": 26.3677,
+      "eval_samples_per_second": 358.583,
+      "eval_steps_per_second": 0.721,
+      "step": 10000
+    },
+    {
+      "epoch": 0.4751609607754627,
+      "grad_norm": 3.001824140548706,
+      "learning_rate": 7.124732715609409e-06,
+      "loss": 2.6376,
+      "step": 20000
+    },
+    {
+      "epoch": 0.4751609607754627,
+      "eval_cosine_accuracy": 0.9616076350212097,
+      "eval_loss": 0.6928738355636597,
+      "eval_runtime": 26.4682,
+      "eval_samples_per_second": 357.221,
+      "eval_steps_per_second": 0.718,
+      "step": 20000
+    },
+    {
+      "epoch": 0.712741441163194,
+      "grad_norm": 2.8817107677459717,
+      "learning_rate": 1.0687099073414113e-05,
+      "loss": 2.4101,
+      "step": 30000
+    },
+    {
+      "epoch": 0.712741441163194,
+      "eval_cosine_accuracy": 0.9626652598381042,
+      "eval_loss": 0.6757322549819946,
+      "eval_runtime": 26.9757,
+      "eval_samples_per_second": 350.5,
+      "eval_steps_per_second": 0.704,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9503219215509254,
+      "grad_norm": 2.5843374729156494,
+      "learning_rate": 1.4249465431218818e-05,
+      "loss": 2.274,
+      "step": 40000
+    },
+    {
+      "epoch": 0.9503219215509254,
+      "eval_cosine_accuracy": 0.9663670063018799,
+      "eval_loss": 0.6607074737548828,
+      "eval_runtime": 27.5896,
+      "eval_samples_per_second": 342.701,
+      "eval_steps_per_second": 0.689,
+      "step": 40000
+    },
+    {
+      "epoch": 1.1879024019386568,
+      "grad_norm": 2.4177308082580566,
+      "learning_rate": 1.7811831789023522e-05,
+      "loss": 2.2229,
+      "step": 50000
+    },
+    {
+      "epoch": 1.1879024019386568,
+      "eval_cosine_accuracy": 0.9650978446006775,
+      "eval_loss": 0.6596832871437073,
+      "eval_runtime": 28.4294,
+      "eval_samples_per_second": 332.578,
+      "eval_steps_per_second": 0.668,
+      "step": 50000
+    },
+    {
+      "epoch": 1.425482882326388,
+      "grad_norm": 2.5173802375793457,
+      "learning_rate": 2.1374198146828226e-05,
+      "loss": 2.1147,
+      "step": 60000
+    },
+    {
+      "epoch": 1.425482882326388,
+      "eval_cosine_accuracy": 0.967107355594635,
+      "eval_loss": 0.6737655997276306,
+      "eval_runtime": 28.0648,
+      "eval_samples_per_second": 336.899,
+      "eval_steps_per_second": 0.677,
+      "step": 60000
+    },
+    {
+      "epoch": 1.6630633627141194,
+      "grad_norm": 2.5599939823150635,
+      "learning_rate": 2.4935851746258018e-05,
+      "loss": 2.0603,
+      "step": 70000
+    },
+    {
+      "epoch": 1.6630633627141194,
+      "eval_cosine_accuracy": 0.9672130942344666,
+      "eval_loss": 0.6480635404586792,
+      "eval_runtime": 27.0703,
+      "eval_samples_per_second": 349.276,
+      "eval_steps_per_second": 0.702,
+      "step": 70000
+    },
+    {
+      "epoch": 1.9006438431018506,
+      "grad_norm": 2.274336099624634,
+      "learning_rate": 2.8498218104062724e-05,
+      "loss": 2.0208,
+      "step": 80000
+    },
+    {
+      "epoch": 1.9006438431018506,
+      "eval_cosine_accuracy": 0.9679534435272217,
+      "eval_loss": 0.6634311079978943,
+      "eval_runtime": 26.5714,
+      "eval_samples_per_second": 355.834,
+      "eval_steps_per_second": 0.715,
+      "step": 80000
+    },
+    {
+      "epoch": 2.138224323489582,
+      "grad_norm": 38.125125885009766,
+      "learning_rate": 2.9652644925951974e-05,
+      "loss": 1.4874,
+      "step": 90000
+    },
+    {
+      "epoch": 2.138224323489582,
+      "eval_cosine_accuracy": 0.9315705895423889,
+      "eval_loss": 0.8910566568374634,
+      "eval_runtime": 27.0766,
+      "eval_samples_per_second": 349.195,
+      "eval_steps_per_second": 0.702,
+      "step": 90000
+    },
+    {
+      "epoch": 2.21436886745385,
+      "grad_norm": 1.930785059928894,
+      "learning_rate": 2.7474065271765394e-05,
+      "loss": 1.7984,
+      "step": 100000
+    },
+    {
+      "epoch": 2.21436886745385,
+      "eval_cosine_accuracy": 0.9664727449417114,
+      "eval_loss": 0.6721837520599365,
+      "eval_runtime": 29.2032,
+      "eval_samples_per_second": 323.766,
+      "eval_steps_per_second": 0.651,
+      "step": 100000
+    },
+    {
+      "epoch": 2.4519493478415813,
+      "grad_norm": 1.9230319261550903,
+      "learning_rate": 2.3579735325035144e-05,
+      "loss": 1.9529,
+      "step": 110000
+    },
+    {
+      "epoch": 2.4519493478415813,
+      "eval_cosine_accuracy": 0.9691168665885925,
+      "eval_loss": 0.6769542694091797,
+      "eval_runtime": 26.9479,
+      "eval_samples_per_second": 350.863,
+      "eval_steps_per_second": 0.705,
+      "step": 110000
+    },
+    {
+      "epoch": 2.6895298282293125,
+      "grad_norm": 1.9773123264312744,
+      "learning_rate": 1.8505599334305437e-05,
+      "loss": 1.9337,
+      "step": 120000
+    },
+    {
+      "epoch": 2.6895298282293125,
+      "eval_cosine_accuracy": 0.9710206389427185,
+      "eval_loss": 0.6512405276298523,
+      "eval_runtime": 26.87,
+      "eval_samples_per_second": 351.879,
+      "eval_steps_per_second": 0.707,
+      "step": 120000
+    },
+    {
+      "epoch": 3.0885462450405075,
+      "grad_norm": 12.169724464416504,
+      "learning_rate": 1.2950387678813519e-05,
+      "loss": 1.6912,
+      "step": 130000
+    },
+    {
+      "epoch": 3.0885462450405075,
+      "eval_cosine_accuracy": 0.9476467370986938,
+      "eval_loss": 0.8111016750335693,
+      "eval_runtime": 26.3122,
+      "eval_samples_per_second": 359.339,
+      "eval_steps_per_second": 0.722,
+      "step": 130000
+    },
+    {
+      "epoch": 3.164120595851845,
+      "grad_norm": 1.8629993200302124,
+      "learning_rate": 7.675028535386121e-06,
+      "loss": 1.4797,
+      "step": 140000
+    },
+    {
+      "epoch": 3.164120595851845,
+      "eval_cosine_accuracy": 0.9709148406982422,
+      "eval_loss": 0.6482858061790466,
+      "eval_runtime": 29.0766,
+      "eval_samples_per_second": 325.176,
+      "eval_steps_per_second": 0.653,
+      "step": 140000
+    },
+    {
+      "epoch": 3.401701076239576,
+      "grad_norm": 1.8768196105957031,
+      "learning_rate": 3.407595832899329e-06,
+      "loss": 1.9017,
+      "step": 150000
+    },
+    {
+      "epoch": 3.401701076239576,
+      "eval_cosine_accuracy": 0.9719725251197815,
+      "eval_loss": 0.6554318070411682,
+      "eval_runtime": 27.6894,
+      "eval_samples_per_second": 341.466,
+      "eval_steps_per_second": 0.686,
+      "step": 150000
+    }
+  ],
+  "logging_steps": 10000,
+  "max_steps": 168364,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 30000,
+  "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": 512,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c64dbd85e30a29db68bdc729f8fd5df5728e408ade763e2e1bf3750362719f
+size 5624

checkpoint-150000/training_metrics.json

@@ -0,0 +1,24 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 3.0885462450405075,
+      "global_step": 130000,
+      "eval_loss": 0.8111016750335693,
+      "eval_cosine_accuracy": 0.9476467370986938
+    },
+    {
+      "epoch": 3.164120595851845,
+      "global_step": 140000,
+      "eval_loss": 0.6482858061790466,
+      "eval_cosine_accuracy": 0.9709148406982422
+    },
+    {
+      "epoch": 3.401701076239576,
+      "global_step": 150000,
+      "eval_loss": 0.6554318070411682,
+      "eval_cosine_accuracy": 0.9719725251197815
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 150000
+}