Training checkpoint - Epoch 4, Step 21740

checkpoint-21740/1_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-21740/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-21740/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-21740/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf50b22d5a414c813b6dd06d2a1a80e40569710575e9ec1844e5fcd16f3f167
+size 90864192

checkpoint-21740/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-21740/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd65c575d5acfec7b12c42bd28a445d3dc34217885419180ae3a4c19df50c624
+size 180607738

checkpoint-21740/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25acd33ee5362d9df0d245f7ddfe71bdceffb7204e5239a22d8aed89f6f27e74
+size 14244

checkpoint-21740/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cedc3e6dce1782a6fddbd70fb8f7f68fac9ec53e1bb9ce37f6ac06e937b6acd
+size 988

checkpoint-21740/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763ba24b7085ccce26b2d8b81a36dd0a0096ffd0e2ad8c8aa63460ddb4c6dec8
+size 1064

checkpoint-21740/sentence_bert_config.json

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

checkpoint-21740/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-21740/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-21740/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 2000,
+  "global_step": 21740,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001841112031667127,
+      "grad_norm": 5.350335597991943,
+      "learning_rate": 0.0,
+      "loss": 2.627,
+      "step": 1
+    },
+    {
+      "epoch": 0.3682224063334254,
+      "grad_norm": 2.9624807834625244,
+      "learning_rate": 5.5210826735407845e-06,
+      "loss": 2.1387,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3682224063334254,
+      "eval_cosine_accuracy": 0.9451025724411011,
+      "eval_loss": 1.7286653518676758,
+      "eval_runtime": 22.2155,
+      "eval_samples_per_second": 425.558,
+      "eval_steps_per_second": 1.666,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7364448126668508,
+      "grad_norm": 2.7932302951812744,
+      "learning_rate": 1.103940342478365e-05,
+      "loss": 1.4888,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7364448126668508,
+      "eval_cosine_accuracy": 0.9483816623687744,
+      "eval_loss": 1.6283537149429321,
+      "eval_runtime": 20.6499,
+      "eval_samples_per_second": 457.823,
+      "eval_steps_per_second": 1.792,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1044982062367767,
+      "grad_norm": 2.6091675758361816,
+      "learning_rate": 1.6563248020622354e-05,
+      "loss": 1.1571,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1044982062367767,
+      "eval_cosine_accuracy": 0.9550454616546631,
+      "eval_loss": 1.5601781606674194,
+      "eval_runtime": 21.0608,
+      "eval_samples_per_second": 448.89,
+      "eval_steps_per_second": 1.757,
+      "step": 6000
+    },
+    {
+      "epoch": 1.4724496366479625,
+      "grad_norm": 2.4897782802581787,
+      "learning_rate": 2.2087092616461057e-05,
+      "loss": 0.9651,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4724496366479625,
+      "eval_cosine_accuracy": 0.9601227045059204,
+      "eval_loss": 1.4905059337615967,
+      "eval_runtime": 20.8667,
+      "eval_samples_per_second": 453.067,
+      "eval_steps_per_second": 1.773,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8404010670591482,
+      "grad_norm": 2.140065908432007,
+      "learning_rate": 2.761093721229976e-05,
+      "loss": 0.8361,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8404010670591482,
+      "eval_cosine_accuracy": 0.9631901979446411,
+      "eval_loss": 1.4158258438110352,
+      "eval_runtime": 20.8732,
+      "eval_samples_per_second": 452.924,
+      "eval_steps_per_second": 1.773,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2082605096127312,
+      "grad_norm": 2.154031753540039,
+      "learning_rate": 2.9643065488021507e-05,
+      "loss": 0.7322,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2082605096127312,
+      "eval_cosine_accuracy": 0.9681616425514221,
+      "eval_loss": 1.3638396263122559,
+      "eval_runtime": 21.1656,
+      "eval_samples_per_second": 446.668,
+      "eval_steps_per_second": 1.748,
+      "step": 12000
+    },
+    {
+      "epoch": 2.5762119400239167,
+      "grad_norm": 1.8926208019256592,
+      "learning_rate": 2.7345137014023062e-05,
+      "loss": 0.6692,
+      "step": 14000
+    },
+    {
+      "epoch": 2.5762119400239167,
+      "eval_cosine_accuracy": 0.9716522097587585,
+      "eval_loss": 1.3354265689849854,
+      "eval_runtime": 21.0015,
+      "eval_samples_per_second": 450.159,
+      "eval_steps_per_second": 1.762,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9441633704351027,
+      "grad_norm": 2.0489113330841064,
+      "learning_rate": 2.323986086259067e-05,
+      "loss": 0.6248,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9441633704351027,
+      "eval_cosine_accuracy": 0.9724984169006348,
+      "eval_loss": 1.3126671314239502,
+      "eval_runtime": 21.0289,
+      "eval_samples_per_second": 449.572,
+      "eval_steps_per_second": 1.759,
+      "step": 16000
+    },
+    {
+      "epoch": 3.3120228129886855,
+      "grad_norm": 1.8383073806762695,
+      "learning_rate": 1.7924582412953385e-05,
+      "loss": 0.5823,
+      "step": 18000
+    },
+    {
+      "epoch": 3.3120228129886855,
+      "eval_cosine_accuracy": 0.9719695448875427,
+      "eval_loss": 1.300689458847046,
+      "eval_runtime": 21.1471,
+      "eval_samples_per_second": 447.059,
+      "eval_steps_per_second": 1.75,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6799742433998714,
+      "grad_norm": 1.8207274675369263,
+      "learning_rate": 1.2180419439461194e-05,
+      "loss": 0.5574,
+      "step": 20000
+    },
+    {
+      "epoch": 3.6799742433998714,
+      "eval_cosine_accuracy": 0.9722868800163269,
+      "eval_loss": 1.2883245944976807,
+      "eval_runtime": 21.1593,
+      "eval_samples_per_second": 446.802,
+      "eval_steps_per_second": 1.749,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 27160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "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": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-21740/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23a64b0609ef744d4000956f3f6b6d74ab3e71b27ca733f83ea46cce056589f
+size 5624

checkpoint-21740/training_metrics.json

@@ -0,0 +1,66 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.3682224063334254,
+      "global_step": 2000,
+      "eval_loss": 1.7286653518676758,
+      "eval_cosine_accuracy": 0.9451025724411011
+    },
+    {
+      "epoch": 0.7364448126668508,
+      "global_step": 4000,
+      "eval_loss": 1.6283537149429321,
+      "eval_cosine_accuracy": 0.9483816623687744
+    },
+    {
+      "epoch": 1.1044982062367767,
+      "global_step": 6000,
+      "eval_loss": 1.5601781606674194,
+      "eval_cosine_accuracy": 0.9550454616546631
+    },
+    {
+      "epoch": 1.4724496366479625,
+      "global_step": 8000,
+      "eval_loss": 1.4905059337615967,
+      "eval_cosine_accuracy": 0.9601227045059204
+    },
+    {
+      "epoch": 1.8404010670591482,
+      "global_step": 10000,
+      "eval_loss": 1.4158258438110352,
+      "eval_cosine_accuracy": 0.9631901979446411
+    },
+    {
+      "epoch": 2.2082605096127312,
+      "global_step": 12000,
+      "eval_loss": 1.3638396263122559,
+      "eval_cosine_accuracy": 0.9681616425514221
+    },
+    {
+      "epoch": 2.5762119400239167,
+      "global_step": 14000,
+      "eval_loss": 1.3354265689849854,
+      "eval_cosine_accuracy": 0.9716522097587585
+    },
+    {
+      "epoch": 2.9441633704351027,
+      "global_step": 16000,
+      "eval_loss": 1.3126671314239502,
+      "eval_cosine_accuracy": 0.9724984169006348
+    },
+    {
+      "epoch": 3.3120228129886855,
+      "global_step": 18000,
+      "eval_loss": 1.300689458847046,
+      "eval_cosine_accuracy": 0.9719695448875427
+    },
+    {
+      "epoch": 3.6799742433998714,
+      "global_step": 20000,
+      "eval_loss": 1.2883245944976807,
+      "eval_cosine_accuracy": 0.9722868800163269
+    }
+  ],
+  "current_epoch": 4,
+  "global_step": 21740
+}