Training checkpoint - Epoch 1, Step 10704

checkpoint-10704/1_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-10704/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-10704/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-10704/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d4f2740140ea3abe1f66262d03bbd785e0e69c8697fc1eefdd7ef67e9fba47
+size 90864192

checkpoint-10704/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-10704/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181576c7458c6e5c85e03e3ffd1da584164ccc162c456ea765e84a66c0ee3b71
+size 180607738

checkpoint-10704/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c772855f1aa593fac440d319e58e4093e4af19961d473f5f288132e2a782e7
+size 14244

checkpoint-10704/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c38b72cd84b0113d23d5f36f7d47e853821fcfa57b7b12a181ebb9f91a5e7e
+size 988

checkpoint-10704/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179b250829f8f48c8287b5478df2254eff6e22690d35ef096fbe94ef1b1b3b82
+size 1064

checkpoint-10704/sentence_bert_config.json

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

checkpoint-10704/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-10704/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-10704/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 2000,
+  "global_step": 10704,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 9.342301943198804e-05,
+      "grad_norm": 6.934398651123047,
+      "learning_rate": 0.0,
+      "loss": 2.7298,
+      "step": 1
+    },
+    {
+      "epoch": 0.18684603886397608,
+      "grad_norm": 3.9505438804626465,
+      "learning_rate": 5.603101934037186e-06,
+      "loss": 1.95,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18684603886397608,
+      "eval_cosine_accuracy": 0.945648729801178,
+      "eval_loss": 0.6836262345314026,
+      "eval_runtime": 25.1378,
+      "eval_samples_per_second": 376.206,
+      "eval_steps_per_second": 1.472,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "grad_norm": 3.8480846881866455,
+      "learning_rate": 1.1209006820517613e-05,
+      "loss": 1.3877,
+      "step": 4000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "eval_cosine_accuracy": 0.9498783946037292,
+      "eval_loss": 0.6531221866607666,
+      "eval_runtime": 28.1391,
+      "eval_samples_per_second": 336.081,
+      "eval_steps_per_second": 1.315,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5605381165919282,
+      "grad_norm": 3.624490976333618,
+      "learning_rate": 1.681491170699804e-05,
+      "loss": 1.0715,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5605381165919282,
+      "eval_cosine_accuracy": 0.9564343690872192,
+      "eval_loss": 0.6075382828712463,
+      "eval_runtime": 27.553,
+      "eval_samples_per_second": 343.229,
+      "eval_steps_per_second": 1.343,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "grad_norm": 2.9945709705352783,
+      "learning_rate": 2.241521068859198e-05,
+      "loss": 0.8659,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "eval_cosine_accuracy": 0.9581262469291687,
+      "eval_loss": 0.5895714163780212,
+      "eval_runtime": 27.1473,
+      "eval_samples_per_second": 348.359,
+      "eval_steps_per_second": 1.363,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9342301943198804,
+      "grad_norm": 4.797957420349121,
+      "learning_rate": 2.801831262262917e-05,
+      "loss": 0.4948,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9342301943198804,
+      "eval_cosine_accuracy": 0.9602410793304443,
+      "eval_loss": 0.5568962097167969,
+      "eval_runtime": 26.8641,
+      "eval_samples_per_second": 352.032,
+      "eval_steps_per_second": 1.377,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 21408,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10704/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a13bf630fb201f36ee45f310ed664ecd254295c7aa69f3d9e8c66a2d1466333
+size 5624

checkpoint-10704/training_metrics.json

@@ -0,0 +1,36 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.18684603886397608,
+      "global_step": 2000,
+      "eval_loss": 0.6836262345314026,
+      "eval_cosine_accuracy": 0.945648729801178
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "global_step": 4000,
+      "eval_loss": 0.6531221866607666,
+      "eval_cosine_accuracy": 0.9498783946037292
+    },
+    {
+      "epoch": 0.5605381165919282,
+      "global_step": 6000,
+      "eval_loss": 0.6075382828712463,
+      "eval_cosine_accuracy": 0.9564343690872192
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "global_step": 8000,
+      "eval_loss": 0.5895714163780212,
+      "eval_cosine_accuracy": 0.9581262469291687
+    },
+    {
+      "epoch": 0.9342301943198804,
+      "global_step": 10000,
+      "eval_loss": 0.5568962097167969,
+      "eval_cosine_accuracy": 0.9602410793304443
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 10704
+}