Training checkpoint - Epoch 3, Step 21408

checkpoint-21408/1_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-21408/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-21408/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-21408/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789391264f4dd781ee17071d7ec1eec2ef54e8f66172dc4f9bc21e8c0b10c26b
+size 90864192

checkpoint-21408/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-21408/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d7bf4cf60f1f368ea2f1609c3ad040cfc52b6d514b41341dab4742718fe1836
+size 180607738

checkpoint-21408/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7b3274ab9a42a40a075a3379139c4dcae86277ec7b988e4bb3ebdf11a11b2e
+size 14244

checkpoint-21408/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecfc341065bfc244a95e3db13a5c960f7f4970a1b153b7afc9778b3715a3ba2
+size 988

checkpoint-21408/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa71666415d0f6e167939e263fd72c01f431e5a971fb1a37fde175338e6a85b
+size 1064

checkpoint-21408/sentence_bert_config.json

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

checkpoint-21408/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-21408/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-21408/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.996640537513998,
+  "eval_steps": 2000,
+  "global_step": 21408,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001868460388639761,
+      "grad_norm": 4.329383373260498,
+      "learning_rate": 0.0,
+      "loss": 2.3475,
+      "step": 1
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "grad_norm": 1.3929723501205444,
+      "learning_rate": 4.6683792620270904e-05,
+      "loss": 1.4174,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "eval_cosine_accuracy": 0.9179443717002869,
+      "eval_loss": 0.44630110263824463,
+      "eval_runtime": 28.0643,
+      "eval_samples_per_second": 336.976,
+      "eval_steps_per_second": 1.318,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "grad_norm": 1.1317882537841797,
+      "learning_rate": 4.886145894517875e-05,
+      "loss": 0.7274,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "eval_cosine_accuracy": 0.9551655054092407,
+      "eval_loss": 0.38517987728118896,
+      "eval_runtime": 27.0397,
+      "eval_samples_per_second": 349.745,
+      "eval_steps_per_second": 1.368,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "grad_norm": 0.9535921812057495,
+      "learning_rate": 4.521439737687342e-05,
+      "loss": 0.5395,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "eval_cosine_accuracy": 0.9591836929321289,
+      "eval_loss": 0.35122039914131165,
+      "eval_runtime": 27.55,
+      "eval_samples_per_second": 343.266,
+      "eval_steps_per_second": 1.343,
+      "step": 6000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "grad_norm": 1.612464427947998,
+      "learning_rate": 3.94365487916572e-05,
+      "loss": 0.4559,
+      "step": 8000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "eval_cosine_accuracy": 0.9590779542922974,
+      "eval_loss": 0.3402463495731354,
+      "eval_runtime": 27.2192,
+      "eval_samples_per_second": 347.439,
+      "eval_steps_per_second": 1.359,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "grad_norm": 1.5486053228378296,
+      "learning_rate": 3.214085926202344e-05,
+      "loss": 0.4172,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "eval_cosine_accuracy": 0.9661626219749451,
+      "eval_loss": 0.3279242217540741,
+      "eval_runtime": 27.4211,
+      "eval_samples_per_second": 344.88,
+      "eval_steps_per_second": 1.349,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "grad_norm": 1.1644288301467896,
+      "learning_rate": 2.4093202063327968e-05,
+      "loss": 0.371,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "eval_cosine_accuracy": 0.9637305736541748,
+      "eval_loss": 0.3213804364204407,
+      "eval_runtime": 27.6554,
+      "eval_samples_per_second": 341.958,
+      "eval_steps_per_second": 1.338,
+      "step": 12000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "grad_norm": 1.0064548254013062,
+      "learning_rate": 1.6141035155888573e-05,
+      "loss": 0.3539,
+      "step": 14000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "eval_cosine_accuracy": 0.9640477895736694,
+      "eval_loss": 0.3214086592197418,
+      "eval_runtime": 27.4392,
+      "eval_samples_per_second": 344.653,
+      "eval_steps_per_second": 1.348,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "grad_norm": 1.2689568996429443,
+      "learning_rate": 9.121760901796114e-06,
+      "loss": 0.3476,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "eval_cosine_accuracy": 0.9684889316558838,
+      "eval_loss": 0.32107028365135193,
+      "eval_runtime": 27.4942,
+      "eval_samples_per_second": 343.963,
+      "eval_steps_per_second": 1.346,
+      "step": 16000
+    },
+    {
+      "epoch": 3.360582306830907,
+      "grad_norm": 0.8944636583328247,
+      "learning_rate": 3.7745434696297987e-06,
+      "loss": 0.3258,
+      "step": 18000
+    },
+    {
+      "epoch": 3.360582306830907,
+      "eval_cosine_accuracy": 0.9685946702957153,
+      "eval_loss": 0.3215343952178955,
+      "eval_runtime": 27.4763,
+      "eval_samples_per_second": 344.188,
+      "eval_steps_per_second": 1.347,
+      "step": 18000
+    },
+    {
+      "epoch": 3.7338559163867115,
+      "grad_norm": 0.8781867027282715,
+      "learning_rate": 6.624712050480375e-07,
+      "loss": 0.3261,
+      "step": 20000
+    },
+    {
+      "epoch": 3.7338559163867115,
+      "eval_cosine_accuracy": 0.9687004089355469,
+      "eval_loss": 0.3220231533050537,
+      "eval_runtime": 27.4299,
+      "eval_samples_per_second": 344.77,
+      "eval_steps_per_second": 1.349,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 21408,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-21408/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c363c35f36f73a15e3e1fcc2e6851bc6b14b09d730a7daedc89b32fd15181f2
+size 5624

checkpoint-21408/training_metrics.json

@@ -0,0 +1,66 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.37369207772795215,
+      "global_step": 2000,
+      "eval_loss": 0.44630110263824463,
+      "eval_cosine_accuracy": 0.9179443717002869
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "global_step": 4000,
+      "eval_loss": 0.38517987728118896,
+      "eval_cosine_accuracy": 0.9551655054092407
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "global_step": 6000,
+      "eval_loss": 0.35122039914131165,
+      "eval_cosine_accuracy": 0.9591836929321289
+    },
+    {
+      "epoch": 1.494214259051885,
+      "global_step": 8000,
+      "eval_loss": 0.3402463495731354,
+      "eval_cosine_accuracy": 0.9590779542922974
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "global_step": 10000,
+      "eval_loss": 0.3279242217540741,
+      "eval_cosine_accuracy": 0.9661626219749451
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "global_step": 12000,
+      "eval_loss": 0.3213804364204407,
+      "eval_cosine_accuracy": 0.9637305736541748
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "global_step": 14000,
+      "eval_loss": 0.3214086592197418,
+      "eval_cosine_accuracy": 0.9640477895736694
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "global_step": 16000,
+      "eval_loss": 0.32107028365135193,
+      "eval_cosine_accuracy": 0.9684889316558838
+    },
+    {
+      "epoch": 3.360582306830907,
+      "global_step": 18000,
+      "eval_loss": 0.3215343952178955,
+      "eval_cosine_accuracy": 0.9685946702957153
+    },
+    {
+      "epoch": 3.7338559163867115,
+      "global_step": 20000,
+      "eval_loss": 0.3220231533050537,
+      "eval_cosine_accuracy": 0.9687004089355469
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 21408
+}