Training checkpoint - Epoch 3, Step 21728

checkpoint-21728/1_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-21728/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-21728/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-21728/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ff0e64da13d140e76c13dd0b666ed52ce85126af69d024f78ea2aae4ef1a58
+size 90864192

checkpoint-21728/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-21728/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68ce2c5ebf08aff1c04bd90d70ec31d3a1c5cd78bf0f8a4f0aace0446514ac3
+size 180607738

checkpoint-21728/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2171753dc3173844d4bf8a6758c69a4a357d3526ecb19c50c6a0830d2aa5dd35
+size 14244

checkpoint-21728/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280f3db3ae204b6eebf8dc1acd84bf326a582ff56fe112f128e1efff77b42817
+size 988

checkpoint-21728/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecae2808023e8a039ee9514467155c0aeace0fd0977eb3c89177d045db758900
+size 1064

checkpoint-21728/sentence_bert_config.json

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

checkpoint-21728/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-21728/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-21728/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.997792494481236,
+  "eval_steps": 2000,
+  "global_step": 21728,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001840942562592047,
+      "grad_norm": 8.515005111694336,
+      "learning_rate": 0.0,
+      "loss": 2.4379,
+      "step": 1
+    },
+    {
+      "epoch": 0.36818851251840945,
+      "grad_norm": 3.0452792644500732,
+      "learning_rate": 7.3614435647210465e-06,
+      "loss": 1.786,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36818851251840945,
+      "eval_cosine_accuracy": 0.9430928826332092,
+      "eval_loss": 0.7222976684570312,
+      "eval_runtime": 25.4268,
+      "eval_samples_per_second": 371.812,
+      "eval_steps_per_second": 1.455,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7363770250368189,
+      "grad_norm": 2.7073590755462646,
+      "learning_rate": 1.4726569692505985e-05,
+      "loss": 1.1648,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7363770250368189,
+      "eval_cosine_accuracy": 0.9517664313316345,
+      "eval_loss": 0.6521320939064026,
+      "eval_runtime": 24.5714,
+      "eval_samples_per_second": 384.757,
+      "eval_steps_per_second": 1.506,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1044885945548197,
+      "grad_norm": 3.628495454788208,
+      "learning_rate": 1.994032559117187e-05,
+      "loss": 0.8611,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1044885945548197,
+      "eval_cosine_accuracy": 0.9570552110671997,
+      "eval_loss": 0.6169463396072388,
+      "eval_runtime": 24.901,
+      "eval_samples_per_second": 379.663,
+      "eval_steps_per_second": 1.486,
+      "step": 6000
+    },
+    {
+      "epoch": 1.4724061810154525,
+      "grad_norm": 2.1804251670837402,
+      "learning_rate": 1.8800429301324442e-05,
+      "loss": 0.6928,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4724061810154525,
+      "eval_cosine_accuracy": 0.9599111676216125,
+      "eval_loss": 0.5976517200469971,
+      "eval_runtime": 24.8702,
+      "eval_samples_per_second": 380.133,
+      "eval_steps_per_second": 1.488,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8403237674760855,
+      "grad_norm": 2.108644962310791,
+      "learning_rate": 1.6370020611442597e-05,
+      "loss": 0.6078,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8403237674760855,
+      "eval_cosine_accuracy": 0.9647768139839172,
+      "eval_loss": 0.5683856010437012,
+      "eval_runtime": 24.8417,
+      "eval_samples_per_second": 380.57,
+      "eval_steps_per_second": 1.489,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2082413539367183,
+      "grad_norm": 2.139408826828003,
+      "learning_rate": 1.3005347127866448e-05,
+      "loss": 0.546,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2082413539367183,
+      "eval_cosine_accuracy": 0.9662576913833618,
+      "eval_loss": 0.5582627654075623,
+      "eval_runtime": 24.3443,
+      "eval_samples_per_second": 388.346,
+      "eval_steps_per_second": 1.52,
+      "step": 12000
+    },
+    {
+      "epoch": 2.576158940397351,
+      "grad_norm": 1.8657588958740234,
+      "learning_rate": 9.197970191657793e-06,
+      "loss": 0.5072,
+      "step": 14000
+    },
+    {
+      "epoch": 2.576158940397351,
+      "eval_cosine_accuracy": 0.9669981002807617,
+      "eval_loss": 0.5446808934211731,
+      "eval_runtime": 24.0677,
+      "eval_samples_per_second": 392.809,
+      "eval_steps_per_second": 1.537,
+      "step": 14000
+    },
+    {
+      "epoch": 2.944076526857984,
+      "grad_norm": 2.716663360595703,
+      "learning_rate": 5.510062329200474e-06,
+      "loss": 0.4855,
+      "step": 16000
+    },
+    {
+      "epoch": 2.944076526857984,
+      "eval_cosine_accuracy": 0.9678443074226379,
+      "eval_loss": 0.5412708520889282,
+      "eval_runtime": 24.0975,
+      "eval_samples_per_second": 392.323,
+      "eval_steps_per_second": 1.535,
+      "step": 16000
+    },
+    {
+      "epoch": 3.3119941133186166,
+      "grad_norm": 1.9097484350204468,
+      "learning_rate": 2.480675207504122e-06,
+      "loss": 0.4667,
+      "step": 18000
+    },
+    {
+      "epoch": 3.3119941133186166,
+      "eval_cosine_accuracy": 0.9691135883331299,
+      "eval_loss": 0.5352851152420044,
+      "eval_runtime": 24.1731,
+      "eval_samples_per_second": 391.096,
+      "eval_steps_per_second": 1.531,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6799116997792494,
+      "grad_norm": 2.0206735134124756,
+      "learning_rate": 5.534839992210128e-07,
+      "loss": 0.4584,
+      "step": 20000
+    },
+    {
+      "epoch": 3.6799116997792494,
+      "eval_cosine_accuracy": 0.9692193865776062,
+      "eval_loss": 0.5349018573760986,
+      "eval_runtime": 24.317,
+      "eval_samples_per_second": 388.782,
+      "eval_steps_per_second": 1.522,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 21728,
+  "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-21728/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040234326b934008f06e26385f032cf393d8651a22077bf70d86c162ad647948
+size 5624

checkpoint-21728/training_metrics.json

@@ -0,0 +1,66 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.36818851251840945,
+      "global_step": 2000,
+      "eval_loss": 0.7222976684570312,
+      "eval_cosine_accuracy": 0.9430928826332092
+    },
+    {
+      "epoch": 0.7363770250368189,
+      "global_step": 4000,
+      "eval_loss": 0.6521320939064026,
+      "eval_cosine_accuracy": 0.9517664313316345
+    },
+    {
+      "epoch": 1.1044885945548197,
+      "global_step": 6000,
+      "eval_loss": 0.6169463396072388,
+      "eval_cosine_accuracy": 0.9570552110671997
+    },
+    {
+      "epoch": 1.4724061810154525,
+      "global_step": 8000,
+      "eval_loss": 0.5976517200469971,
+      "eval_cosine_accuracy": 0.9599111676216125
+    },
+    {
+      "epoch": 1.8403237674760855,
+      "global_step": 10000,
+      "eval_loss": 0.5683856010437012,
+      "eval_cosine_accuracy": 0.9647768139839172
+    },
+    {
+      "epoch": 2.2082413539367183,
+      "global_step": 12000,
+      "eval_loss": 0.5582627654075623,
+      "eval_cosine_accuracy": 0.9662576913833618
+    },
+    {
+      "epoch": 2.576158940397351,
+      "global_step": 14000,
+      "eval_loss": 0.5446808934211731,
+      "eval_cosine_accuracy": 0.9669981002807617
+    },
+    {
+      "epoch": 2.944076526857984,
+      "global_step": 16000,
+      "eval_loss": 0.5412708520889282,
+      "eval_cosine_accuracy": 0.9678443074226379
+    },
+    {
+      "epoch": 3.3119941133186166,
+      "global_step": 18000,
+      "eval_loss": 0.5352851152420044,
+      "eval_cosine_accuracy": 0.9691135883331299
+    },
+    {
+      "epoch": 3.6799116997792494,
+      "global_step": 20000,
+      "eval_loss": 0.5349018573760986,
+      "eval_cosine_accuracy": 0.9692193865776062
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 21728
+}