Training checkpoint - Epoch 2, Step 21736

checkpoint-21736/1_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-21736/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-21736/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-21736/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce2c55866dccc1cc5c37a8d2e20d29f59bc49f7539ff62b1defaf2229158161
+size 90864192

checkpoint-21736/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-21736/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc801c9e76a1a9c60a0bbedba1672cd162f2f0427d3c1c3e34ce217abdcca40
+size 180607738

checkpoint-21736/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6effbc02b5404d7512f7c5a1d6bc6bf64213ea83f002a367da4b4f3aff2351
+size 14244

checkpoint-21736/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91513ac992d666cc4fb655ee17c8a692c5a052627e6d63603247eb61ddf0f565
+size 988

checkpoint-21736/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bdf9a582ad9f1b76fa0c94414538ea6baae399a581ca87d9d6a8c643af08b55
+size 1064

checkpoint-21736/sentence_bert_config.json

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

checkpoint-21736/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-21736/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-21736/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 2000,
+  "global_step": 21736,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 9.204712812960235e-05,
+      "grad_norm": 13.360148429870605,
+      "learning_rate": 0.0,
+      "loss": 2.3674,
+      "step": 1
+    },
+    {
+      "epoch": 0.18409425625920472,
+      "grad_norm": 9.698494911193848,
+      "learning_rate": 5.52057442695388e-06,
+      "loss": 1.8916,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18409425625920472,
+      "eval_cosine_accuracy": 0.9443621635437012,
+      "eval_loss": 0.7301858067512512,
+      "eval_runtime": 24.6963,
+      "eval_samples_per_second": 382.81,
+      "eval_steps_per_second": 1.498,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36818851251840945,
+      "grad_norm": 4.1456756591796875,
+      "learning_rate": 1.1043910521955262e-05,
+      "loss": 1.3359,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36818851251840945,
+      "eval_cosine_accuracy": 0.9476411938667297,
+      "eval_loss": 0.7006688117980957,
+      "eval_runtime": 23.8109,
+      "eval_samples_per_second": 397.045,
+      "eval_steps_per_second": 1.554,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5522827687776142,
+      "grad_norm": 6.158293724060059,
+      "learning_rate": 1.656172328086164e-05,
+      "loss": 1.0329,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5522827687776142,
+      "eval_cosine_accuracy": 0.9529299736022949,
+      "eval_loss": 0.6458290815353394,
+      "eval_runtime": 23.7658,
+      "eval_samples_per_second": 397.799,
+      "eval_steps_per_second": 1.557,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7363770250368189,
+      "grad_norm": 3.041351556777954,
+      "learning_rate": 2.208505937586302e-05,
+      "loss": 0.8502,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7363770250368189,
+      "eval_cosine_accuracy": 0.958430290222168,
+      "eval_loss": 0.6126231551170349,
+      "eval_runtime": 23.8204,
+      "eval_samples_per_second": 396.887,
+      "eval_steps_per_second": 1.553,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9204712812960235,
+      "grad_norm": 3.5076329708099365,
+      "learning_rate": 2.7602872134769403e-05,
+      "loss": 0.7183,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9204712812960235,
+      "eval_cosine_accuracy": 0.9612862467765808,
+      "eval_loss": 0.5929833054542542,
+      "eval_runtime": 23.7689,
+      "eval_samples_per_second": 397.746,
+      "eval_steps_per_second": 1.557,
+      "step": 10000
+    },
+    {
+      "epoch": 1.1044885945548197,
+      "grad_norm": 5.993108749389648,
+      "learning_rate": 2.991079806492284e-05,
+      "loss": 0.6232,
+      "step": 12000
+    },
+    {
+      "epoch": 1.1044885945548197,
+      "eval_cosine_accuracy": 0.9625555276870728,
+      "eval_loss": 0.5854976177215576,
+      "eval_runtime": 23.6381,
+      "eval_samples_per_second": 399.947,
+      "eval_steps_per_second": 1.565,
+      "step": 12000
+    },
+    {
+      "epoch": 1.2884473877851361,
+      "grad_norm": 3.1183509826660156,
+      "learning_rate": 2.9322078021233654e-05,
+      "loss": 0.5509,
+      "step": 14000
+    },
+    {
+      "epoch": 1.2884473877851361,
+      "eval_cosine_accuracy": 0.9658345580101013,
+      "eval_loss": 0.5530505776405334,
+      "eval_runtime": 23.8535,
+      "eval_samples_per_second": 396.337,
+      "eval_steps_per_second": 1.551,
+      "step": 14000
+    },
+    {
+      "epoch": 1.4724061810154525,
+      "grad_norm": 2.6417152881622314,
+      "learning_rate": 2.8202595151679806e-05,
+      "loss": 0.5088,
+      "step": 16000
+    },
+    {
+      "epoch": 1.4724061810154525,
+      "eval_cosine_accuracy": 0.9668923020362854,
+      "eval_loss": 0.5652992725372314,
+      "eval_runtime": 23.8646,
+      "eval_samples_per_second": 396.152,
+      "eval_steps_per_second": 1.55,
+      "step": 16000
+    },
+    {
+      "epoch": 1.656364974245769,
+      "grad_norm": 2.9723057746887207,
+      "learning_rate": 2.659489882695295e-05,
+      "loss": 0.4759,
+      "step": 18000
+    },
+    {
+      "epoch": 1.656364974245769,
+      "eval_cosine_accuracy": 0.9699597954750061,
+      "eval_loss": 0.5359070301055908,
+      "eval_runtime": 24.2142,
+      "eval_samples_per_second": 390.432,
+      "eval_steps_per_second": 1.528,
+      "step": 18000
+    },
+    {
+      "epoch": 1.8403237674760855,
+      "grad_norm": 2.547870397567749,
+      "learning_rate": 2.455694759085683e-05,
+      "loss": 0.4477,
+      "step": 20000
+    },
+    {
+      "epoch": 1.8403237674760855,
+      "eval_cosine_accuracy": 0.9698540568351746,
+      "eval_loss": 0.5235444903373718,
+      "eval_runtime": 23.7486,
+      "eval_samples_per_second": 398.087,
+      "eval_steps_per_second": 1.558,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 43456,
+  "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-21736/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478e80b28b6969b356244dab5e55ca31ea07eda29bfe09042cc4750d73bdd006
+size 5624

checkpoint-21736/training_metrics.json

@@ -0,0 +1,66 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.18409425625920472,
+      "global_step": 2000,
+      "eval_loss": 0.7301858067512512,
+      "eval_cosine_accuracy": 0.9443621635437012
+    },
+    {
+      "epoch": 0.36818851251840945,
+      "global_step": 4000,
+      "eval_loss": 0.7006688117980957,
+      "eval_cosine_accuracy": 0.9476411938667297
+    },
+    {
+      "epoch": 0.5522827687776142,
+      "global_step": 6000,
+      "eval_loss": 0.6458290815353394,
+      "eval_cosine_accuracy": 0.9529299736022949
+    },
+    {
+      "epoch": 0.7363770250368189,
+      "global_step": 8000,
+      "eval_loss": 0.6126231551170349,
+      "eval_cosine_accuracy": 0.958430290222168
+    },
+    {
+      "epoch": 0.9204712812960235,
+      "global_step": 10000,
+      "eval_loss": 0.5929833054542542,
+      "eval_cosine_accuracy": 0.9612862467765808
+    },
+    {
+      "epoch": 1.1044885945548197,
+      "global_step": 12000,
+      "eval_loss": 0.5854976177215576,
+      "eval_cosine_accuracy": 0.9625555276870728
+    },
+    {
+      "epoch": 1.2884473877851361,
+      "global_step": 14000,
+      "eval_loss": 0.5530505776405334,
+      "eval_cosine_accuracy": 0.9658345580101013
+    },
+    {
+      "epoch": 1.4724061810154525,
+      "global_step": 16000,
+      "eval_loss": 0.5652992725372314,
+      "eval_cosine_accuracy": 0.9668923020362854
+    },
+    {
+      "epoch": 1.656364974245769,
+      "global_step": 18000,
+      "eval_loss": 0.5359070301055908,
+      "eval_cosine_accuracy": 0.9699597954750061
+    },
+    {
+      "epoch": 1.8403237674760855,
+      "global_step": 20000,
+      "eval_loss": 0.5235444903373718,
+      "eval_cosine_accuracy": 0.9698540568351746
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 21736
+}