Training checkpoint - Epoch 2, 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:fe227df3b804f497f349d5ac202f717b8d6017342596410c9d5e3c88e933ad98
+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 sha256:56757de30b20e057b32a573580905e6d26e9afc2c21b50c59e53b9022e67f539
+size 180607738

checkpoint-150000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc615bafcdac64b1bdfa7f0d8d2a342d5ae9f23289c4d4038ac51a8f8c6bee3
+size 14244

checkpoint-150000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5611658daaf26989087362ce5b2cc81c9dee72520345a42abe591b284a34bce9
+size 988

checkpoint-150000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5afa334224ea1384ee819f8bbfe1ce419e7186bc40ed1efbd95f6750912557
+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": 2.949620482164628,
+  "eval_steps": 10000,
+  "global_step": 150000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.9664136547764188e-05,
+      "grad_norm": 5.198209762573242,
+      "learning_rate": 0.0,
+      "loss": 4.3979,
+      "step": 1
+    },
+    {
+      "epoch": 0.19664136547764188,
+      "grad_norm": 3.0463807582855225,
+      "learning_rate": 2.948793581499617e-06,
+      "loss": 3.3508,
+      "step": 10000
+    },
+    {
+      "epoch": 0.19664136547764188,
+      "eval_cosine_accuracy": 0.9498677849769592,
+      "eval_loss": 0.7947401404380798,
+      "eval_runtime": 30.8185,
+      "eval_samples_per_second": 306.797,
+      "eval_steps_per_second": 0.617,
+      "step": 10000
+    },
+    {
+      "epoch": 0.39328273095528377,
+      "grad_norm": 2.7137584686279297,
+      "learning_rate": 5.897292195150729e-06,
+      "loss": 2.709,
+      "step": 20000
+    },
+    {
+      "epoch": 0.39328273095528377,
+      "eval_cosine_accuracy": 0.9549444913864136,
+      "eval_loss": 0.743651270866394,
+      "eval_runtime": 32.9031,
+      "eval_samples_per_second": 287.359,
+      "eval_steps_per_second": 0.577,
+      "step": 20000
+    },
+    {
+      "epoch": 0.5899240964329256,
+      "grad_norm": 2.5484485626220703,
+      "learning_rate": 8.845790808801841e-06,
+      "loss": 2.4959,
+      "step": 30000
+    },
+    {
+      "epoch": 0.5899240964329256,
+      "eval_cosine_accuracy": 0.9576943516731262,
+      "eval_loss": 0.7173787951469421,
+      "eval_runtime": 31.7928,
+      "eval_samples_per_second": 297.394,
+      "eval_steps_per_second": 0.598,
+      "step": 30000
+    },
+    {
+      "epoch": 0.7865654619105675,
+      "grad_norm": 2.6198248863220215,
+      "learning_rate": 1.1794289422452952e-05,
+      "loss": 2.3685,
+      "step": 40000
+    },
+    {
+      "epoch": 0.7865654619105675,
+      "eval_cosine_accuracy": 0.9585404396057129,
+      "eval_loss": 0.6878712773323059,
+      "eval_runtime": 31.9522,
+      "eval_samples_per_second": 295.91,
+      "eval_steps_per_second": 0.595,
+      "step": 40000
+    },
+    {
+      "epoch": 0.9832068273882094,
+      "grad_norm": 2.5395779609680176,
+      "learning_rate": 1.474249306825556e-05,
+      "loss": 2.2836,
+      "step": 50000
+    },
+    {
+      "epoch": 0.9832068273882094,
+      "eval_cosine_accuracy": 0.9613960981369019,
+      "eval_loss": 0.6971630454063416,
+      "eval_runtime": 30.62,
+      "eval_samples_per_second": 308.785,
+      "eval_steps_per_second": 0.621,
+      "step": 50000
+    },
+    {
+      "epoch": 1.1798481928658513,
+      "grad_norm": 2.367072343826294,
+      "learning_rate": 1.7690991681906672e-05,
+      "loss": 2.2663,
+      "step": 60000
+    },
+    {
+      "epoch": 1.1798481928658513,
+      "eval_cosine_accuracy": 0.9620306491851807,
+      "eval_loss": 0.686095118522644,
+      "eval_runtime": 32.588,
+      "eval_samples_per_second": 290.138,
+      "eval_steps_per_second": 0.583,
+      "step": 60000
+    },
+    {
+      "epoch": 1.376489558343493,
+      "grad_norm": 2.1865155696868896,
+      "learning_rate": 2.0639490295557785e-05,
+      "loss": 2.1727,
+      "step": 70000
+    },
+    {
+      "epoch": 1.376489558343493,
+      "eval_cosine_accuracy": 0.9620306491851807,
+      "eval_loss": 0.6829742193222046,
+      "eval_runtime": 25.9819,
+      "eval_samples_per_second": 363.907,
+      "eval_steps_per_second": 0.731,
+      "step": 70000
+    },
+    {
+      "epoch": 1.573130923821135,
+      "grad_norm": 2.05108642578125,
+      "learning_rate": 2.358739897351189e-05,
+      "loss": 2.1365,
+      "step": 80000
+    },
+    {
+      "epoch": 1.573130923821135,
+      "eval_cosine_accuracy": 0.9628767967224121,
+      "eval_loss": 0.6505528688430786,
+      "eval_runtime": 27.2795,
+      "eval_samples_per_second": 346.597,
+      "eval_steps_per_second": 0.696,
+      "step": 80000
+    },
+    {
+      "epoch": 1.769772289298777,
+      "grad_norm": 2.038926124572754,
+      "learning_rate": 2.6536192555011505e-05,
+      "loss": 2.1067,
+      "step": 90000
+    },
+    {
+      "epoch": 1.769772289298777,
+      "eval_cosine_accuracy": 0.964040219783783,
+      "eval_loss": 0.645112931728363,
+      "eval_runtime": 27.7341,
+      "eval_samples_per_second": 340.915,
+      "eval_steps_per_second": 0.685,
+      "step": 90000
+    },
+    {
+      "epoch": 1.9664136547764186,
+      "grad_norm": 1.8988077640533447,
+      "learning_rate": 2.9484691168662618e-05,
+      "loss": 2.0809,
+      "step": 100000
+    },
+    {
+      "epoch": 1.9664136547764186,
+      "eval_cosine_accuracy": 0.9636171460151672,
+      "eval_loss": 0.6595451235771179,
+      "eval_runtime": 27.9534,
+      "eval_samples_per_second": 338.242,
+      "eval_steps_per_second": 0.68,
+      "step": 100000
+    },
+    {
+      "epoch": 2.0368899201636057,
+      "grad_norm": 1.775089144706726,
+      "learning_rate": 2.9516082547994732e-05,
+      "loss": 1.3347,
+      "step": 110000
+    },
+    {
+      "epoch": 2.0368899201636057,
+      "eval_cosine_accuracy": 0.9627709984779358,
+      "eval_loss": 0.6458898186683655,
+      "eval_runtime": 29.3282,
+      "eval_samples_per_second": 322.386,
+      "eval_steps_per_second": 0.648,
+      "step": 110000
+    },
+    {
+      "epoch": 2.2335312856412477,
+      "grad_norm": 1.702778935432434,
+      "learning_rate": 2.7680238096077758e-05,
+      "loss": 2.0499,
+      "step": 120000
+    },
+    {
+      "epoch": 2.2335312856412477,
+      "eval_cosine_accuracy": 0.9645690321922302,
+      "eval_loss": 0.644099771976471,
+      "eval_runtime": 27.3025,
+      "eval_samples_per_second": 346.305,
+      "eval_steps_per_second": 0.696,
+      "step": 120000
+    },
+    {
+      "epoch": 2.5563377512093446,
+      "grad_norm": 1.955954670906067,
+      "learning_rate": 2.4645638868401546e-05,
+      "loss": 2.0301,
+      "step": 130000
+    },
+    {
+      "epoch": 2.5563377512093446,
+      "eval_cosine_accuracy": 0.9654151201248169,
+      "eval_loss": 0.636643648147583,
+      "eval_runtime": 26.1277,
+      "eval_samples_per_second": 361.876,
+      "eval_steps_per_second": 0.727,
+      "step": 130000
+    },
+    {
+      "epoch": 2.752979116686986,
+      "grad_norm": 1.8052382469177246,
+      "learning_rate": 2.069838365907062e-05,
+      "loss": 2.0156,
+      "step": 140000
+    },
+    {
+      "epoch": 2.752979116686986,
+      "eval_cosine_accuracy": 0.9653093814849854,
+      "eval_loss": 0.6524764895439148,
+      "eval_runtime": 27.4521,
+      "eval_samples_per_second": 344.419,
+      "eval_steps_per_second": 0.692,
+      "step": 140000
+    },
+    {
+      "epoch": 2.949620482164628,
+      "grad_norm": 1.7682826519012451,
+      "learning_rate": 1.6213487492820253e-05,
+      "loss": 2.0053,
+      "step": 150000
+    },
+    {
+      "epoch": 2.949620482164628,
+      "eval_cosine_accuracy": 0.9673188924789429,
+      "eval_loss": 0.6424700617790222,
+      "eval_runtime": 27.5466,
+      "eval_samples_per_second": 343.236,
+      "eval_steps_per_second": 0.69,
+      "step": 150000
+    }
+  ],
+  "logging_steps": 10000,
+  "max_steps": 203416,
+  "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 sha256:6ce8872a78c17886a45b7a8d05946ba348b6206e06c0ad177cfc58155fd16ae6
+size 5624

checkpoint-150000/training_metrics.json

@@ -0,0 +1,24 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 2.5563377512093446,
+      "global_step": 130000,
+      "eval_loss": 0.636643648147583,
+      "eval_cosine_accuracy": 0.9654151201248169
+    },
+    {
+      "epoch": 2.752979116686986,
+      "global_step": 140000,
+      "eval_loss": 0.6524764895439148,
+      "eval_cosine_accuracy": 0.9653093814849854
+    },
+    {
+      "epoch": 2.949620482164628,
+      "global_step": 150000,
+      "eval_loss": 0.6424700617790222,
+      "eval_cosine_accuracy": 0.9673188924789429
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 150000
+}