Training checkpoint - Epoch 2, Step 10710

checkpoint-10710/1_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-10710/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-10710/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-10710/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c32998641052263a0cb2a45eb3196f8014d5450997f6f7dd077789ad980548
+size 90864192

checkpoint-10710/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-10710/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1051704dcb53a927abcd9739995e053d72fe9593b4660c8e5ec3944e5dcfce9
+size 180607738

checkpoint-10710/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4427b85e2145462326010bac47043b16297253972f703dd947a69246a2c7ac
+size 14244

checkpoint-10710/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0cac195d0cc2ca1bcbb4f6eea998f8369cc362d392d823c034405bde50ef1c
+size 988

checkpoint-10710/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd25832e38dd4288d85b75386950ca3aa11b64d38cf6d3efead29cb335fbacc3
+size 1064

checkpoint-10710/sentence_bert_config.json

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

checkpoint-10710/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-10710/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-10710/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 2000,
+  "global_step": 10710,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001868460388639761,
+      "grad_norm": 8.692222595214844,
+      "learning_rate": 0.0,
+      "loss": 2.3163,
+      "step": 1
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "grad_norm": 5.377971172332764,
+      "learning_rate": 7.46776303494674e-06,
+      "loss": 1.7964,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "eval_cosine_accuracy": 0.9531564116477966,
+      "eval_loss": 0.7834969162940979,
+      "eval_runtime": 24.5425,
+      "eval_samples_per_second": 385.332,
+      "eval_steps_per_second": 1.508,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "grad_norm": 4.06288480758667,
+      "learning_rate": 1.4943001308166699e-05,
+      "loss": 1.1503,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "eval_cosine_accuracy": 0.9590779542922974,
+      "eval_loss": 0.7469472885131836,
+      "eval_runtime": 24.2666,
+      "eval_samples_per_second": 389.712,
+      "eval_steps_per_second": 1.525,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "grad_norm": 2.527675151824951,
+      "learning_rate": 1.9820278599859833e-05,
+      "loss": 0.8568,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "eval_cosine_accuracy": 0.9657396674156189,
+      "eval_loss": 0.6957386136054993,
+      "eval_runtime": 24.2697,
+      "eval_samples_per_second": 389.662,
+      "eval_steps_per_second": 1.525,
+      "step": 6000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "grad_norm": 4.718974590301514,
+      "learning_rate": 1.7133561457259503e-05,
+      "loss": 0.6922,
+      "step": 8000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "eval_cosine_accuracy": 0.9674315452575684,
+      "eval_loss": 0.6658662557601929,
+      "eval_runtime": 24.1832,
+      "eval_samples_per_second": 391.057,
+      "eval_steps_per_second": 1.53,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "grad_norm": 4.274268627166748,
+      "learning_rate": 1.2061411687112223e-05,
+      "loss": 0.6074,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "eval_cosine_accuracy": 0.9702865481376648,
+      "eval_loss": 0.6324575543403625,
+      "eval_runtime": 24.354,
+      "eval_samples_per_second": 388.315,
+      "eval_steps_per_second": 1.519,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 16056,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10710/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd58ab224311e761cbbce95c6605755997ff4c6e71361886b48c69ff66a3b28
+size 5624

checkpoint-10710/training_metrics.json

@@ -0,0 +1,36 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.37369207772795215,
+      "global_step": 2000,
+      "eval_loss": 0.7834969162940979,
+      "eval_cosine_accuracy": 0.9531564116477966
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "global_step": 4000,
+      "eval_loss": 0.7469472885131836,
+      "eval_cosine_accuracy": 0.9590779542922974
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "global_step": 6000,
+      "eval_loss": 0.6957386136054993,
+      "eval_cosine_accuracy": 0.9657396674156189
+    },
+    {
+      "epoch": 1.494214259051885,
+      "global_step": 8000,
+      "eval_loss": 0.6658662557601929,
+      "eval_cosine_accuracy": 0.9674315452575684
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "global_step": 10000,
+      "eval_loss": 0.6324575543403625,
+      "eval_cosine_accuracy": 0.9702865481376648
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 10710
+}