Training checkpoint - Epoch 5, Step 26790

checkpoint-26790/1_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-26790/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-26790/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-26790/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35b2e8fd03d6dfa081d8712d87c5c9f5572b1ceefdf1cd1e96f4612a8e6608b
+size 90864192

checkpoint-26790/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-26790/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa87d6058890c4f3d8302343ab219dfb7b2922b1f1c8b99cea7c2731700f6ff
+size 180607738

checkpoint-26790/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425241d9f89e9cb479cee66f69dfad390ac10d52a92195577dea117f007545c8
+size 14244

checkpoint-26790/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb73d159dd3aa208394d09dc6fdfc175a04e01ab141893bbe704a5dadae61d9f
+size 988

checkpoint-26790/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f190045219aa1a21a8421657f0a0da985af7e12645cfdb81338dfbaaac28a23
+size 1064

checkpoint-26790/sentence_bert_config.json

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

checkpoint-26790/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-26790/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": 512,
+  "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-26790/trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 2000,
+  "global_step": 26790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001866368047779022,
+      "grad_norm": 8.654276847839355,
+      "learning_rate": 0.0,
+      "loss": 2.4422,
+      "step": 1
+    },
+    {
+      "epoch": 0.3732736095558044,
+      "grad_norm": 1.7478883266448975,
+      "learning_rate": 1.867875163520837e-05,
+      "loss": 1.0123,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3732736095558044,
+      "eval_cosine_accuracy": 0.9141376614570618,
+      "eval_loss": 0.37293314933776855,
+      "eval_runtime": 24.2337,
+      "eval_samples_per_second": 390.242,
+      "eval_steps_per_second": 1.527,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7465472191116088,
+      "grad_norm": 1.4524885416030884,
+      "learning_rate": 3.7348159222575224e-05,
+      "loss": 0.5247,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7465472191116088,
+      "eval_cosine_accuracy": 0.9314793348312378,
+      "eval_loss": 0.3318365514278412,
+      "eval_runtime": 24.0684,
+      "eval_samples_per_second": 392.922,
+      "eval_steps_per_second": 1.537,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1198208286674132,
+      "grad_norm": 1.3776118755340576,
+      "learning_rate": 4.992833702272636e-05,
+      "loss": 0.3817,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1198208286674132,
+      "eval_cosine_accuracy": 0.9499841332435608,
+      "eval_loss": 0.2932388484477997,
+      "eval_runtime": 24.3626,
+      "eval_samples_per_second": 388.177,
+      "eval_steps_per_second": 1.519,
+      "step": 6000
+    },
+    {
+      "epoch": 1.4930944382232176,
+      "grad_norm": 1.2868770360946655,
+      "learning_rate": 4.880674946960199e-05,
+      "loss": 0.3022,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4930944382232176,
+      "eval_cosine_accuracy": 0.958760678768158,
+      "eval_loss": 0.2577275037765503,
+      "eval_runtime": 24.5929,
+      "eval_samples_per_second": 384.542,
+      "eval_steps_per_second": 1.504,
+      "step": 8000
+    },
+    {
+      "epoch": 1.866368047779022,
+      "grad_norm": 1.0443642139434814,
+      "learning_rate": 4.638230458722983e-05,
+      "loss": 0.2632,
+      "step": 10000
+    },
+    {
+      "epoch": 1.866368047779022,
+      "eval_cosine_accuracy": 0.9621444344520569,
+      "eval_loss": 0.24511192739009857,
+      "eval_runtime": 24.372,
+      "eval_samples_per_second": 388.028,
+      "eval_steps_per_second": 1.518,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2396416573348263,
+      "grad_norm": 1.0951056480407715,
+      "learning_rate": 4.278974285033454e-05,
+      "loss": 0.2279,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2396416573348263,
+      "eval_cosine_accuracy": 0.9625673890113831,
+      "eval_loss": 0.2212185263633728,
+      "eval_runtime": 24.3041,
+      "eval_samples_per_second": 389.111,
+      "eval_steps_per_second": 1.522,
+      "step": 12000
+    },
+    {
+      "epoch": 2.6129152668906306,
+      "grad_norm": 1.830448031425476,
+      "learning_rate": 3.8224581669016425e-05,
+      "loss": 0.2079,
+      "step": 14000
+    },
+    {
+      "epoch": 2.6129152668906306,
+      "eval_cosine_accuracy": 0.9642592668533325,
+      "eval_loss": 0.22390954196453094,
+      "eval_runtime": 24.9681,
+      "eval_samples_per_second": 378.763,
+      "eval_steps_per_second": 1.482,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9861888764464353,
+      "grad_norm": 0.8651946187019348,
+      "learning_rate": 3.293640718209743e-05,
+      "loss": 0.1982,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9861888764464353,
+      "eval_cosine_accuracy": 0.9675372838973999,
+      "eval_loss": 0.20658133924007416,
+      "eval_runtime": 24.5632,
+      "eval_samples_per_second": 385.006,
+      "eval_steps_per_second": 1.506,
+      "step": 16000
+    },
+    {
+      "epoch": 3.3594624860022395,
+      "grad_norm": 0.7335544228553772,
+      "learning_rate": 2.7214334055891687e-05,
+      "loss": 0.1786,
+      "step": 18000
+    },
+    {
+      "epoch": 3.3594624860022395,
+      "eval_cosine_accuracy": 0.9678544998168945,
+      "eval_loss": 0.211293026804924,
+      "eval_runtime": 29.8065,
+      "eval_samples_per_second": 317.279,
+      "eval_steps_per_second": 1.241,
+      "step": 18000
+    },
+    {
+      "epoch": 3.732736095558044,
+      "grad_norm": 0.8901182413101196,
+      "learning_rate": 2.137119902954239e-05,
+      "loss": 0.1727,
+      "step": 20000
+    },
+    {
+      "epoch": 3.732736095558044,
+      "eval_cosine_accuracy": 0.9667970538139343,
+      "eval_loss": 0.20058989524841309,
+      "eval_runtime": 24.2231,
+      "eval_samples_per_second": 390.413,
+      "eval_steps_per_second": 1.527,
+      "step": 20000
+    },
+    {
+      "epoch": 4.106009705113848,
+      "grad_norm": 1.0788087844848633,
+      "learning_rate": 1.5726457529028778e-05,
+      "loss": 0.1646,
+      "step": 22000
+    },
+    {
+      "epoch": 4.106009705113848,
+      "eval_cosine_accuracy": 0.9681717157363892,
+      "eval_loss": 0.2036646157503128,
+      "eval_runtime": 24.6296,
+      "eval_samples_per_second": 383.97,
+      "eval_steps_per_second": 1.502,
+      "step": 22000
+    },
+    {
+      "epoch": 4.479283314669653,
+      "grad_norm": 0.796744167804718,
+      "learning_rate": 1.0588718424838651e-05,
+      "loss": 0.1564,
+      "step": 24000
+    },
+    {
+      "epoch": 4.479283314669653,
+      "eval_cosine_accuracy": 0.9673258066177368,
+      "eval_loss": 0.1985815167427063,
+      "eval_runtime": 24.3781,
+      "eval_samples_per_second": 387.929,
+      "eval_steps_per_second": 1.518,
+      "step": 24000
+    },
+    {
+      "epoch": 4.852556924225457,
+      "grad_norm": 0.9555702805519104,
+      "learning_rate": 6.2388717916832815e-06,
+      "loss": 0.1545,
+      "step": 26000
+    },
+    {
+      "epoch": 4.852556924225457,
+      "eval_cosine_accuracy": 0.9682774543762207,
+      "eval_loss": 0.1962214708328247,
+      "eval_runtime": 24.7415,
+      "eval_samples_per_second": 382.232,
+      "eval_steps_per_second": 1.495,
+      "step": 26000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 32148,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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-26790/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e270e39f4afa8063ac001167a89b656bc8b3bcf329e11d10005640282cef58
+size 5624

checkpoint-26790/training_metrics.json

@@ -0,0 +1,84 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.3732736095558044,
+      "global_step": 2000,
+      "eval_loss": 0.37293314933776855,
+      "eval_cosine_accuracy": 0.9141376614570618
+    },
+    {
+      "epoch": 0.7465472191116088,
+      "global_step": 4000,
+      "eval_loss": 0.3318365514278412,
+      "eval_cosine_accuracy": 0.9314793348312378
+    },
+    {
+      "epoch": 1.1198208286674132,
+      "global_step": 6000,
+      "eval_loss": 0.2932388484477997,
+      "eval_cosine_accuracy": 0.9499841332435608
+    },
+    {
+      "epoch": 1.4930944382232176,
+      "global_step": 8000,
+      "eval_loss": 0.2577275037765503,
+      "eval_cosine_accuracy": 0.958760678768158
+    },
+    {
+      "epoch": 1.866368047779022,
+      "global_step": 10000,
+      "eval_loss": 0.24511192739009857,
+      "eval_cosine_accuracy": 0.9621444344520569
+    },
+    {
+      "epoch": 2.2396416573348263,
+      "global_step": 12000,
+      "eval_loss": 0.2212185263633728,
+      "eval_cosine_accuracy": 0.9625673890113831
+    },
+    {
+      "epoch": 2.6129152668906306,
+      "global_step": 14000,
+      "eval_loss": 0.22390954196453094,
+      "eval_cosine_accuracy": 0.9642592668533325
+    },
+    {
+      "epoch": 2.9861888764464353,
+      "global_step": 16000,
+      "eval_loss": 0.20658133924007416,
+      "eval_cosine_accuracy": 0.9675372838973999
+    },
+    {
+      "epoch": 3.3594624860022395,
+      "global_step": 18000,
+      "eval_loss": 0.211293026804924,
+      "eval_cosine_accuracy": 0.9678544998168945
+    },
+    {
+      "epoch": 3.732736095558044,
+      "global_step": 20000,
+      "eval_loss": 0.20058989524841309,
+      "eval_cosine_accuracy": 0.9667970538139343
+    },
+    {
+      "epoch": 4.106009705113848,
+      "global_step": 22000,
+      "eval_loss": 0.2036646157503128,
+      "eval_cosine_accuracy": 0.9681717157363892
+    },
+    {
+      "epoch": 4.479283314669653,
+      "global_step": 24000,
+      "eval_loss": 0.1985815167427063,
+      "eval_cosine_accuracy": 0.9673258066177368
+    },
+    {
+      "epoch": 4.852556924225457,
+      "global_step": 26000,
+      "eval_loss": 0.1962214708328247,
+      "eval_cosine_accuracy": 0.9682774543762207
+    }
+  ],
+  "current_epoch": 5,
+  "global_step": 26790
+}