Training checkpoint - Epoch 2, Step 22112

checkpoint-22112/1_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-22112/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-22112/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-22112/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c00adf65aa9411563e506526d9a6de38bfc9ad196019b7f0bd6d8edb1a5c2cf
+size 90864192

checkpoint-22112/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-22112/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885e7cc3a51b08a9d36d45e21b940453d2f1e6b551934bacab69d6c903574198
+size 180607738

checkpoint-22112/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af9909d45c5789599a530a1b36c08469289030356e183964196551019a0200c
+size 14244

checkpoint-22112/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdf4d0e668af8554609d8abed34798eaab3af07487d7524cc8d3e78373cd1d1
+size 988

checkpoint-22112/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b183fdffff75809af3b729cb7da147e7efe529e9be4b08d01d8153303dd28eaf
+size 1064

checkpoint-22112/sentence_bert_config.json

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

checkpoint-22112/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-22112/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-22112/trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 2000,
+  "global_step": 22112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 9.048136083966703e-05,
+      "grad_norm": 6.883802890777588,
+      "learning_rate": 0.0,
+      "loss": 3.6871,
+      "step": 1
+    },
+    {
+      "epoch": 0.18096272167933405,
+      "grad_norm": 4.156403064727783,
+      "learning_rate": 5.426658220975478e-06,
+      "loss": 3.6171,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18096272167933405,
+      "eval_cosine_accuracy": 0.9458659291267395,
+      "eval_loss": 1.19174063205719,
+      "eval_runtime": 24.1437,
+      "eval_samples_per_second": 391.738,
+      "eval_steps_per_second": 1.532,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3619254433586681,
+      "grad_norm": 4.531202793121338,
+      "learning_rate": 1.085603112840467e-05,
+      "loss": 2.9866,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3619254433586681,
+      "eval_cosine_accuracy": 0.9442799687385559,
+      "eval_loss": 1.1735926866531372,
+      "eval_runtime": 25.7204,
+      "eval_samples_per_second": 367.723,
+      "eval_steps_per_second": 1.439,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5428881650380022,
+      "grad_norm": 4.661669731140137,
+      "learning_rate": 1.6282689349380148e-05,
+      "loss": 2.6071,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5428881650380022,
+      "eval_cosine_accuracy": 0.9467117786407471,
+      "eval_loss": 1.1516979932785034,
+      "eval_runtime": 25.8461,
+      "eval_samples_per_second": 365.935,
+      "eval_steps_per_second": 1.432,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7238508867173362,
+      "grad_norm": 4.64531135559082,
+      "learning_rate": 2.1709347570355623e-05,
+      "loss": 2.3272,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7238508867173362,
+      "eval_cosine_accuracy": 0.9510467052459717,
+      "eval_loss": 1.1301954984664917,
+      "eval_runtime": 26.5489,
+      "eval_samples_per_second": 356.248,
+      "eval_steps_per_second": 1.394,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9048136083966702,
+      "grad_norm": 4.573121070861816,
+      "learning_rate": 2.71360057913311e-05,
+      "loss": 2.1236,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9048136083966702,
+      "eval_cosine_accuracy": 0.9563332796096802,
+      "eval_loss": 1.0893216133117676,
+      "eval_runtime": 25.6992,
+      "eval_samples_per_second": 368.027,
+      "eval_steps_per_second": 1.44,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 4.530196666717529,
+      "learning_rate": 2.9940039535626347e-05,
+      "loss": 2.0434,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "eval_cosine_accuracy": 0.954641580581665,
+      "eval_loss": 1.0764466524124146,
+      "eval_runtime": 25.4391,
+      "eval_samples_per_second": 371.79,
+      "eval_steps_per_second": 1.454,
+      "step": 12000
+    },
+    {
+      "epoch": 1.2665461121157324,
+      "grad_norm": 4.325132369995117,
+      "learning_rate": 2.9420604401266522e-05,
+      "loss": 1.8618,
+      "step": 14000
+    },
+    {
+      "epoch": 1.2665461121157324,
+      "eval_cosine_accuracy": 0.9577077627182007,
+      "eval_loss": 1.0421515703201294,
+      "eval_runtime": 25.53,
+      "eval_samples_per_second": 370.466,
+      "eval_steps_per_second": 1.449,
+      "step": 14000
+    },
+    {
+      "epoch": 1.447377938517179,
+      "grad_norm": 4.479296684265137,
+      "learning_rate": 2.8385395034797537e-05,
+      "loss": 1.7865,
+      "step": 16000
+    },
+    {
+      "epoch": 1.447377938517179,
+      "eval_cosine_accuracy": 0.9604567289352417,
+      "eval_loss": 1.029998779296875,
+      "eval_runtime": 26.1797,
+      "eval_samples_per_second": 361.273,
+      "eval_steps_per_second": 1.413,
+      "step": 16000
+    },
+    {
+      "epoch": 1.6282097649186258,
+      "grad_norm": 4.179690361022949,
+      "learning_rate": 2.6872305921528123e-05,
+      "loss": 1.7094,
+      "step": 18000
+    },
+    {
+      "epoch": 1.6282097649186258,
+      "eval_cosine_accuracy": 0.9583421349525452,
+      "eval_loss": 1.0228686332702637,
+      "eval_runtime": 26.1715,
+      "eval_samples_per_second": 361.385,
+      "eval_steps_per_second": 1.414,
+      "step": 18000
+    },
+    {
+      "epoch": 1.8090415913200724,
+      "grad_norm": 4.186921119689941,
+      "learning_rate": 2.4932879923820447e-05,
+      "loss": 1.6576,
+      "step": 20000
+    },
+    {
+      "epoch": 1.8090415913200724,
+      "eval_cosine_accuracy": 0.9603510499000549,
+      "eval_loss": 0.9981576800346375,
+      "eval_runtime": 26.1781,
+      "eval_samples_per_second": 361.294,
+      "eval_steps_per_second": 1.413,
+      "step": 20000
+    },
+    {
+      "epoch": 1.989873417721519,
+      "grad_norm": 4.027351379394531,
+      "learning_rate": 2.2637835327220155e-05,
+      "loss": 1.6159,
+      "step": 22000
+    },
+    {
+      "epoch": 1.989873417721519,
+      "eval_cosine_accuracy": 0.9623599052429199,
+      "eval_loss": 0.9824916124343872,
+      "eval_runtime": 25.2661,
+      "eval_samples_per_second": 374.336,
+      "eval_steps_per_second": 1.464,
+      "step": 22000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 44208,
+  "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-22112/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7540012bdd071accb15b1b179cb138d8156ad2667e83b26ce9cb1620af865060
+size 5624

checkpoint-22112/training_metrics.json

@@ -0,0 +1,72 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.18096272167933405,
+      "global_step": 2000,
+      "eval_loss": 1.19174063205719,
+      "eval_cosine_accuracy": 0.9458659291267395
+    },
+    {
+      "epoch": 0.3619254433586681,
+      "global_step": 4000,
+      "eval_loss": 1.1735926866531372,
+      "eval_cosine_accuracy": 0.9442799687385559
+    },
+    {
+      "epoch": 0.5428881650380022,
+      "global_step": 6000,
+      "eval_loss": 1.1516979932785034,
+      "eval_cosine_accuracy": 0.9467117786407471
+    },
+    {
+      "epoch": 0.7238508867173362,
+      "global_step": 8000,
+      "eval_loss": 1.1301954984664917,
+      "eval_cosine_accuracy": 0.9510467052459717
+    },
+    {
+      "epoch": 0.9048136083966702,
+      "global_step": 10000,
+      "eval_loss": 1.0893216133117676,
+      "eval_cosine_accuracy": 0.9563332796096802
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "global_step": 12000,
+      "eval_loss": 1.0764466524124146,
+      "eval_cosine_accuracy": 0.954641580581665
+    },
+    {
+      "epoch": 1.2665461121157324,
+      "global_step": 14000,
+      "eval_loss": 1.0421515703201294,
+      "eval_cosine_accuracy": 0.9577077627182007
+    },
+    {
+      "epoch": 1.447377938517179,
+      "global_step": 16000,
+      "eval_loss": 1.029998779296875,
+      "eval_cosine_accuracy": 0.9604567289352417
+    },
+    {
+      "epoch": 1.6282097649186258,
+      "global_step": 18000,
+      "eval_loss": 1.0228686332702637,
+      "eval_cosine_accuracy": 0.9583421349525452
+    },
+    {
+      "epoch": 1.8090415913200724,
+      "global_step": 20000,
+      "eval_loss": 0.9981576800346375,
+      "eval_cosine_accuracy": 0.9603510499000549
+    },
+    {
+      "epoch": 1.989873417721519,
+      "global_step": 22000,
+      "eval_loss": 0.9824916124343872,
+      "eval_cosine_accuracy": 0.9623599052429199
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 22112
+}