Training checkpoint - Epoch 3, Step 39040

checkpoint-39040/1_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-39040/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-39040/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-39040/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2568389936c2617abaa79d5fad1ba3fb470452ef1e3f0b0cffa61c7d4408d23b
+size 90864192

checkpoint-39040/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-39040/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fceabb742d98ef9a26801529dd16953ece0e6f1379f7f53bcd2eb22692ccb25c
+size 180607738

checkpoint-39040/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c4b14d22e6f82ac35b47b217d24eaab7705e46a8f70872ab15f3189e519d8e
+size 14244

checkpoint-39040/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace30a4b53f1e5216edfed42e21a1b7cedd2d8c8c90d32ffe001bc9f36c0cce4
+size 988

checkpoint-39040/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8aca7ceb92ecbeae372ec012e97dd8aa68478a0ca32d25bc32db202d124280
+size 1064

checkpoint-39040/sentence_bert_config.json

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

checkpoint-39040/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-39040/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-39040/trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9983619983619985,
+  "eval_steps": 4000,
+  "global_step": 39040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00010245901639344262,
+      "grad_norm": 6.315417766571045,
+      "learning_rate": 0.0,
+      "loss": 4.1362,
+      "step": 1
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 4.62825345993042,
+      "learning_rate": 1.536501024590164e-05,
+      "loss": 3.1603,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "eval_cosine_accuracy": 0.953901469707489,
+      "eval_loss": 1.0815402269363403,
+      "eval_runtime": 24.8505,
+      "eval_samples_per_second": 380.595,
+      "eval_steps_per_second": 1.489,
+      "step": 4000
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 4.6219048500061035,
+      "learning_rate": 2.999728935936485e-05,
+      "loss": 2.7017,
+      "step": 8000
+    },
+    {
+      "epoch": 0.819672131147541,
+      "eval_cosine_accuracy": 0.9081200957298279,
+      "eval_loss": 1.3302178382873535,
+      "eval_runtime": 22.5389,
+      "eval_samples_per_second": 419.629,
+      "eval_steps_per_second": 1.642,
+      "step": 8000
+    },
+    {
+      "epoch": 1.2295081967213115,
+      "grad_norm": 4.111813068389893,
+      "learning_rate": 2.868919465032591e-05,
+      "loss": 2.4584,
+      "step": 12000
+    },
+    {
+      "epoch": 1.2295081967213115,
+      "eval_cosine_accuracy": 0.957390546798706,
+      "eval_loss": 0.9852072596549988,
+      "eval_runtime": 25.1342,
+      "eval_samples_per_second": 376.3,
+      "eval_steps_per_second": 1.472,
+      "step": 12000
+    },
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 3.6833724975585938,
+      "learning_rate": 2.51957420925816e-05,
+      "loss": 2.2777,
+      "step": 16000
+    },
+    {
+      "epoch": 1.639344262295082,
+      "eval_cosine_accuracy": 0.9606682062149048,
+      "eval_loss": 0.9453343749046326,
+      "eval_runtime": 22.7137,
+      "eval_samples_per_second": 416.401,
+      "eval_steps_per_second": 1.629,
+      "step": 16000
+    },
+    {
+      "epoch": 2.0491400491400493,
+      "grad_norm": 7.341921329498291,
+      "learning_rate": 2.0076071378946667e-05,
+      "loss": 2.1676,
+      "step": 20000
+    },
+    {
+      "epoch": 2.0491400491400493,
+      "eval_cosine_accuracy": 0.961091160774231,
+      "eval_loss": 0.9533414840698242,
+      "eval_runtime": 22.8729,
+      "eval_samples_per_second": 413.502,
+      "eval_steps_per_second": 1.618,
+      "step": 20000
+    },
+    {
+      "epoch": 2.458640458640459,
+      "grad_norm": 4.12435245513916,
+      "learning_rate": 1.4144955104259103e-05,
+      "loss": 2.067,
+      "step": 24000
+    },
+    {
+      "epoch": 2.458640458640459,
+      "eval_cosine_accuracy": 0.9617255330085754,
+      "eval_loss": 0.9420561790466309,
+      "eval_runtime": 22.7914,
+      "eval_samples_per_second": 414.981,
+      "eval_steps_per_second": 1.623,
+      "step": 24000
+    },
+    {
+      "epoch": 2.868140868140868,
+      "grad_norm": 3.720942497253418,
+      "learning_rate": 8.351689838906174e-06,
+      "loss": 2.0149,
+      "step": 28000
+    },
+    {
+      "epoch": 2.868140868140868,
+      "eval_cosine_accuracy": 0.9643687605857849,
+      "eval_loss": 0.926335871219635,
+      "eval_runtime": 22.8686,
+      "eval_samples_per_second": 413.58,
+      "eval_steps_per_second": 1.618,
+      "step": 28000
+    },
+    {
+      "epoch": 3.2776412776412776,
+      "grad_norm": 3.9042465686798096,
+      "learning_rate": 3.618247724624548e-06,
+      "loss": 1.9927,
+      "step": 32000
+    },
+    {
+      "epoch": 3.2776412776412776,
+      "eval_cosine_accuracy": 0.9641573429107666,
+      "eval_loss": 0.945164680480957,
+      "eval_runtime": 22.9055,
+      "eval_samples_per_second": 412.914,
+      "eval_steps_per_second": 1.615,
+      "step": 32000
+    },
+    {
+      "epoch": 3.687141687141687,
+      "grad_norm": 4.156418800354004,
+      "learning_rate": 7.022332589674108e-07,
+      "loss": 1.9635,
+      "step": 36000
+    },
+    {
+      "epoch": 3.687141687141687,
+      "eval_cosine_accuracy": 0.9652146100997925,
+      "eval_loss": 0.9383304119110107,
+      "eval_runtime": 22.8196,
+      "eval_samples_per_second": 414.468,
+      "eval_steps_per_second": 1.621,
+      "step": 36000
+    }
+  ],
+  "logging_steps": 4000,
+  "max_steps": 39040,
+  "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-39040/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec23f19d0cff0c28e00004981af4156b2e8279702f263e1ed82f3627125ee63
+size 5624

checkpoint-39040/training_metrics.json

@@ -0,0 +1,48 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 1.2295081967213115,
+      "global_step": 12000,
+      "eval_loss": 0.9852072596549988,
+      "eval_cosine_accuracy": 0.957390546798706
+    },
+    {
+      "epoch": 1.639344262295082,
+      "global_step": 16000,
+      "eval_loss": 0.9453343749046326,
+      "eval_cosine_accuracy": 0.9606682062149048
+    },
+    {
+      "epoch": 2.0491400491400493,
+      "global_step": 20000,
+      "eval_loss": 0.9533414840698242,
+      "eval_cosine_accuracy": 0.961091160774231
+    },
+    {
+      "epoch": 2.458640458640459,
+      "global_step": 24000,
+      "eval_loss": 0.9420561790466309,
+      "eval_cosine_accuracy": 0.9617255330085754
+    },
+    {
+      "epoch": 2.868140868140868,
+      "global_step": 28000,
+      "eval_loss": 0.926335871219635,
+      "eval_cosine_accuracy": 0.9643687605857849
+    },
+    {
+      "epoch": 3.2776412776412776,
+      "global_step": 32000,
+      "eval_loss": 0.945164680480957,
+      "eval_cosine_accuracy": 0.9641573429107666
+    },
+    {
+      "epoch": 3.687141687141687,
+      "global_step": 36000,
+      "eval_loss": 0.9383304119110107,
+      "eval_cosine_accuracy": 0.9652146100997925
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 39040
+}