Training checkpoint - Epoch 3, Step 161476

checkpoint-161476/1_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-161476/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-161476/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-161476/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d49a537d5b9dae10506700e5dae3af46c8d8eef7763a1c38a09a1c64dfb27b
+size 90864192

checkpoint-161476/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-161476/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4606676ebd2d88cf6a39d69a5856217ae63c1f8e0d6119aec5347b805ea240
+size 180607738

checkpoint-161476/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dda0d6556c8f70d46ae4b692e9f5bbd487c30f456ec1ba780bc5c501c1f3dc6
+size 14244

checkpoint-161476/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d722e5289cb6d4e2411a12793092de9d6ba61de09d3eb720460659cf597857c5
+size 988

checkpoint-161476/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2730f26ced4e3505750358e3b0656ae43f83e745493c6884e0ff0dfd96366712
+size 1064

checkpoint-161476/sentence_bert_config.json

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

checkpoint-161476/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-161476/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-161476/trainer_state.json

@@ -0,0 +1,297 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.8478040080259603,
+  "eval_steps": 10000,
+  "global_step": 161476,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.477148306869132e-05,
+      "grad_norm": 5.107126712799072,
+      "learning_rate": 0.0,
+      "loss": 4.1291,
+      "step": 1
+    },
+    {
+      "epoch": 0.24771483068691322,
+      "grad_norm": 3.010230541229248,
+      "learning_rate": 2.4762187871581455e-06,
+      "loss": 3.3262,
+      "step": 10000
+    },
+    {
+      "epoch": 0.24771483068691322,
+      "eval_cosine_accuracy": 0.9515600204467773,
+      "eval_loss": 0.7596105933189392,
+      "eval_runtime": 26.0378,
+      "eval_samples_per_second": 363.127,
+      "eval_steps_per_second": 0.73,
+      "step": 10000
+    },
+    {
+      "epoch": 0.49542966137382644,
+      "grad_norm": 2.8107306957244873,
+      "learning_rate": 4.952437574316291e-06,
+      "loss": 2.689,
+      "step": 20000
+    },
+    {
+      "epoch": 0.49542966137382644,
+      "eval_cosine_accuracy": 0.9566367268562317,
+      "eval_loss": 0.7294803857803345,
+      "eval_runtime": 26.6173,
+      "eval_samples_per_second": 355.22,
+      "eval_steps_per_second": 0.714,
+      "step": 20000
+    },
+    {
+      "epoch": 0.7431444920607396,
+      "grad_norm": 3.0228993892669678,
+      "learning_rate": 7.428408640507333e-06,
+      "loss": 2.4587,
+      "step": 30000
+    },
+    {
+      "epoch": 0.7431444920607396,
+      "eval_cosine_accuracy": 0.9584347009658813,
+      "eval_loss": 0.7089734077453613,
+      "eval_runtime": 26.6791,
+      "eval_samples_per_second": 354.397,
+      "eval_steps_per_second": 0.712,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9908593227476529,
+      "grad_norm": 2.387526273727417,
+      "learning_rate": 9.904627427665479e-06,
+      "loss": 2.3372,
+      "step": 40000
+    },
+    {
+      "epoch": 0.9908593227476529,
+      "eval_cosine_accuracy": 0.9546271562576294,
+      "eval_loss": 0.7039511203765869,
+      "eval_runtime": 26.9109,
+      "eval_samples_per_second": 351.344,
+      "eval_steps_per_second": 0.706,
+      "step": 40000
+    },
+    {
+      "epoch": 1.2385741534345662,
+      "grad_norm": 2.3799750804901123,
+      "learning_rate": 1.2380846214823623e-05,
+      "loss": 2.2443,
+      "step": 50000
+    },
+    {
+      "epoch": 1.2385741534345662,
+      "eval_cosine_accuracy": 0.9624537229537964,
+      "eval_loss": 0.6768600344657898,
+      "eval_runtime": 28.1462,
+      "eval_samples_per_second": 335.925,
+      "eval_steps_per_second": 0.675,
+      "step": 50000
+    },
+    {
+      "epoch": 1.4862889841214795,
+      "grad_norm": 2.243985176086426,
+      "learning_rate": 1.4856817281014666e-05,
+      "loss": 2.152,
+      "step": 60000
+    },
+    {
+      "epoch": 1.4862889841214795,
+      "eval_cosine_accuracy": 0.9629825353622437,
+      "eval_loss": 0.6565244793891907,
+      "eval_runtime": 27.0609,
+      "eval_samples_per_second": 349.397,
+      "eval_steps_per_second": 0.702,
+      "step": 60000
+    },
+    {
+      "epoch": 1.7340038148083927,
+      "grad_norm": 2.473121404647827,
+      "learning_rate": 1.733303606817281e-05,
+      "loss": 2.0972,
+      "step": 70000
+    },
+    {
+      "epoch": 1.7340038148083927,
+      "eval_cosine_accuracy": 0.9632998704910278,
+      "eval_loss": 0.6459464430809021,
+      "eval_runtime": 26.1365,
+      "eval_samples_per_second": 361.754,
+      "eval_steps_per_second": 0.727,
+      "step": 70000
+    },
+    {
+      "epoch": 1.981718645495306,
+      "grad_norm": 2.185279130935669,
+      "learning_rate": 1.9809254855330957e-05,
+      "loss": 2.0551,
+      "step": 80000
+    },
+    {
+      "epoch": 1.981718645495306,
+      "eval_cosine_accuracy": 0.9638286828994751,
+      "eval_loss": 0.6375178694725037,
+      "eval_runtime": 27.5082,
+      "eval_samples_per_second": 343.716,
+      "eval_steps_per_second": 0.691,
+      "step": 80000
+    },
+    {
+      "epoch": 2.078079714632515,
+      "grad_norm": 2.0905165672302246,
+      "learning_rate": 1.9362954041291794e-05,
+      "loss": 1.357,
+      "step": 90000
+    },
+    {
+      "epoch": 2.078079714632515,
+      "eval_cosine_accuracy": 0.962136447429657,
+      "eval_loss": 0.6513386368751526,
+      "eval_runtime": 29.0956,
+      "eval_samples_per_second": 324.964,
+      "eval_steps_per_second": 0.653,
+      "step": 90000
+    },
+    {
+      "epoch": 2.3257945453194284,
+      "grad_norm": 2.303090810775757,
+      "learning_rate": 1.7331262229438458e-05,
+      "loss": 2.0044,
+      "step": 100000
+    },
+    {
+      "epoch": 2.3257945453194284,
+      "eval_cosine_accuracy": 0.9637228846549988,
+      "eval_loss": 0.6505403518676758,
+      "eval_runtime": 27.1804,
+      "eval_samples_per_second": 347.86,
+      "eval_steps_per_second": 0.699,
+      "step": 100000
+    },
+    {
+      "epoch": 2.5735093760063417,
+      "grad_norm": 2.1236724853515625,
+      "learning_rate": 1.4204345622420425e-05,
+      "loss": 1.9816,
+      "step": 110000
+    },
+    {
+      "epoch": 2.5735093760063417,
+      "eval_cosine_accuracy": 0.9638286828994751,
+      "eval_loss": 0.6360126733779907,
+      "eval_runtime": 27.6037,
+      "eval_samples_per_second": 342.527,
+      "eval_steps_per_second": 0.688,
+      "step": 110000
+    },
+    {
+      "epoch": 2.8212242066932545,
+      "grad_norm": 2.01153302192688,
+      "learning_rate": 1.0449259129695853e-05,
+      "loss": 1.9647,
+      "step": 120000
+    },
+    {
+      "epoch": 2.8212242066932545,
+      "eval_cosine_accuracy": 0.9639344215393066,
+      "eval_loss": 0.646002471446991,
+      "eval_runtime": 26.695,
+      "eval_samples_per_second": 354.186,
+      "eval_steps_per_second": 0.712,
+      "step": 120000
+    },
+    {
+      "epoch": 3.0680968069558325,
+      "grad_norm": 2.065314292907715,
+      "learning_rate": 6.628514213182956e-06,
+      "loss": 1.2997,
+      "step": 130000
+    },
+    {
+      "epoch": 3.0680968069558325,
+      "eval_cosine_accuracy": 0.9647805690765381,
+      "eval_loss": 0.6370704770088196,
+      "eval_runtime": 26.4596,
+      "eval_samples_per_second": 357.337,
+      "eval_steps_per_second": 0.718,
+      "step": 130000
+    },
+    {
+      "epoch": 3.315811637642746,
+      "grad_norm": 2.0722827911376953,
+      "learning_rate": 3.3090794888600374e-06,
+      "loss": 1.9444,
+      "step": 140000
+    },
+    {
+      "epoch": 3.315811637642746,
+      "eval_cosine_accuracy": 0.9648863077163696,
+      "eval_loss": 0.6383876204490662,
+      "eval_runtime": 27.6465,
+      "eval_samples_per_second": 341.996,
+      "eval_steps_per_second": 0.687,
+      "step": 140000
+    },
+    {
+      "epoch": 3.563526468329659,
+      "grad_norm": 2.045346975326538,
+      "learning_rate": 9.906007538007667e-07,
+      "loss": 1.9387,
+      "step": 150000
+    },
+    {
+      "epoch": 3.563526468329659,
+      "eval_cosine_accuracy": 0.9655208587646484,
+      "eval_loss": 0.6318914890289307,
+      "eval_runtime": 27.3467,
+      "eval_samples_per_second": 345.745,
+      "eval_steps_per_second": 0.695,
+      "step": 150000
+    },
+    {
+      "epoch": 3.8112412990165723,
+      "grad_norm": 2.1405978202819824,
+      "learning_rate": 1.7947491247399808e-08,
+      "loss": 1.9365,
+      "step": 160000
+    },
+    {
+      "epoch": 3.8112412990165723,
+      "eval_cosine_accuracy": 0.9657323956489563,
+      "eval_loss": 0.6346824169158936,
+      "eval_runtime": 27.7227,
+      "eval_samples_per_second": 341.057,
+      "eval_steps_per_second": 0.685,
+      "step": 160000
+    }
+  ],
+  "logging_steps": 10000,
+  "max_steps": 161476,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 30000,
+  "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": 512,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-161476/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921a1e58514b9aa439f909f1b000ff6ebe32e53b418fee3f07bd4da2ea654088
+size 5624

checkpoint-161476/training_metrics.json

@@ -0,0 +1,30 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 3.0680968069558325,
+      "global_step": 130000,
+      "eval_loss": 0.6370704770088196,
+      "eval_cosine_accuracy": 0.9647805690765381
+    },
+    {
+      "epoch": 3.315811637642746,
+      "global_step": 140000,
+      "eval_loss": 0.6383876204490662,
+      "eval_cosine_accuracy": 0.9648863077163696
+    },
+    {
+      "epoch": 3.563526468329659,
+      "global_step": 150000,
+      "eval_loss": 0.6318914890289307,
+      "eval_cosine_accuracy": 0.9655208587646484
+    },
+    {
+      "epoch": 3.8112412990165723,
+      "global_step": 160000,
+      "eval_loss": 0.6346824169158936,
+      "eval_cosine_accuracy": 0.9657323956489563
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 161476
+}