Training checkpoint - Epoch 3, Step 27418

checkpoint-27418/1_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-27418/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-27418/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-27418/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25958b6099674c19e29e836d28bb518a61250541c9d81824565662a411fb174
+size 90864192

checkpoint-27418/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-27418/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fddbbd2279f6c7997e1e84375fd20a277d79ec61bed3d921db47df8553c300
+size 180607738

checkpoint-27418/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924e4d57f12062bafcc138cd377f5ee03eb4a57545a9dade5de19b39bca8dacb
+size 14244

checkpoint-27418/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d80be813c44e5903ff9dbd7fc7ca7b5b7139187b70547c6ed7f3d3cdd9b7c006
+size 988

checkpoint-27418/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd66e88310b9fd98309ce782f6e2990dcf3751d83790dc720d257b860c9e962
+size 1064

checkpoint-27418/sentence_bert_config.json

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

checkpoint-27418/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-27418/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-27418/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 4000,
+  "global_step": 27418,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00010948105977665864,
+      "grad_norm": 5.878234386444092,
+      "learning_rate": 0.0,
+      "loss": 3.3696,
+      "step": 1
+    },
+    {
+      "epoch": 0.4379242391066345,
+      "grad_norm": 4.34870719909668,
+      "learning_rate": 1.0944170771756979e-05,
+      "loss": 2.7485,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4379242391066345,
+      "eval_cosine_accuracy": 0.948341429233551,
+      "eval_loss": 1.1948620080947876,
+      "eval_runtime": 24.3202,
+      "eval_samples_per_second": 389.224,
+      "eval_steps_per_second": 1.521,
+      "step": 4000
+    },
+    {
+      "epoch": 0.875848478213269,
+      "grad_norm": 6.708064079284668,
+      "learning_rate": 1.997258984476735e-05,
+      "loss": 2.6312,
+      "step": 8000
+    },
+    {
+      "epoch": 0.875848478213269,
+      "eval_cosine_accuracy": 0.8973166942596436,
+      "eval_loss": 1.4613265991210938,
+      "eval_runtime": 22.6953,
+      "eval_samples_per_second": 417.09,
+      "eval_steps_per_second": 1.63,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3134981404506672,
+      "grad_norm": 4.031854152679443,
+      "learning_rate": 1.8757613770758945e-05,
+      "loss": 2.3518,
+      "step": 12000
+    },
+    {
+      "epoch": 1.3134981404506672,
+      "eval_cosine_accuracy": 0.9525671005249023,
+      "eval_loss": 1.0801939964294434,
+      "eval_runtime": 22.887,
+      "eval_samples_per_second": 413.597,
+      "eval_steps_per_second": 1.617,
+      "step": 12000
+    },
+    {
+      "epoch": 1.7510391599212425,
+      "grad_norm": 4.038516044616699,
+      "learning_rate": 1.595100201380366e-05,
+      "loss": 2.0753,
+      "step": 16000
+    },
+    {
+      "epoch": 1.7510391599212425,
+      "eval_cosine_accuracy": 0.9567927122116089,
+      "eval_loss": 1.0488860607147217,
+      "eval_runtime": 23.2727,
+      "eval_samples_per_second": 406.743,
+      "eval_steps_per_second": 1.59,
+      "step": 16000
+    },
+    {
+      "epoch": 2.188580179391818,
+      "grad_norm": 4.980384349822998,
+      "learning_rate": 1.2061731000172012e-05,
+      "loss": 1.9719,
+      "step": 20000
+    },
+    {
+      "epoch": 2.188580179391818,
+      "eval_cosine_accuracy": 0.9575322270393372,
+      "eval_loss": 1.0590463876724243,
+      "eval_runtime": 22.8994,
+      "eval_samples_per_second": 413.374,
+      "eval_steps_per_second": 1.616,
+      "step": 20000
+    },
+    {
+      "epoch": 2.6261211988623936,
+      "grad_norm": 3.9708364009857178,
+      "learning_rate": 7.796502829807719e-06,
+      "loss": 1.9013,
+      "step": 24000
+    },
+    {
+      "epoch": 2.6261211988623936,
+      "eval_cosine_accuracy": 0.9605958461761475,
+      "eval_loss": 1.0383129119873047,
+      "eval_runtime": 23.0066,
+      "eval_samples_per_second": 411.448,
+      "eval_steps_per_second": 1.608,
+      "step": 24000
+    }
+  ],
+  "logging_steps": 4000,
+  "max_steps": 36536,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-27418/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b6360d6a202d655266754f4547c20eefb6b1b8b3bbbf820dc6c2a70f265c7d
+size 5624

checkpoint-27418/training_metrics.json

@@ -0,0 +1,42 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.4379242391066345,
+      "global_step": 4000,
+      "eval_loss": 1.1948620080947876,
+      "eval_cosine_accuracy": 0.948341429233551
+    },
+    {
+      "epoch": 0.875848478213269,
+      "global_step": 8000,
+      "eval_loss": 1.4613265991210938,
+      "eval_cosine_accuracy": 0.8973166942596436
+    },
+    {
+      "epoch": 1.3134981404506672,
+      "global_step": 12000,
+      "eval_loss": 1.0801939964294434,
+      "eval_cosine_accuracy": 0.9525671005249023
+    },
+    {
+      "epoch": 1.7510391599212425,
+      "global_step": 16000,
+      "eval_loss": 1.0488860607147217,
+      "eval_cosine_accuracy": 0.9567927122116089
+    },
+    {
+      "epoch": 2.188580179391818,
+      "global_step": 20000,
+      "eval_loss": 1.0590463876724243,
+      "eval_cosine_accuracy": 0.9575322270393372
+    },
+    {
+      "epoch": 2.6261211988623936,
+      "global_step": 24000,
+      "eval_loss": 1.0383129119873047,
+      "eval_cosine_accuracy": 0.9605958461761475
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 27418
+}