Training checkpoint - Epoch 2, Step 16056

checkpoint-16056/1_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-16056/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-16056/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-16056/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18224d349204e8555dcf191fe2ffd26102b1fd5b4f8c2ca3cd0c09c66a4470f2
+size 90864192

checkpoint-16056/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-16056/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9472175adf8a140bd5bab5083e49b96f09c32445b9d693096467f4665ad899ba
+size 180607738

checkpoint-16056/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbe21e5cafd5e6937490213e2673bb69ea25c6171d1683f00fbf41f44a8c175
+size 14244

checkpoint-16056/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f8c3cd37eb45ec4443c5f6b07ddb98f561f7a1fb9ca9c8f1407da98fd20681
+size 988

checkpoint-16056/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdd9b5be22b8443a63241a7a4c3953481fb72be7d27c6ad51d3c0637c554fcc
+size 1064

checkpoint-16056/sentence_bert_config.json

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

checkpoint-16056/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-16056/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-16056/trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9977603583426653,
+  "eval_steps": 2000,
+  "global_step": 16056,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001868460388639761,
+      "grad_norm": 2.946286916732788,
+      "learning_rate": 0.0,
+      "loss": 0.5616,
+      "step": 1
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "grad_norm": 3.3281102180480957,
+      "learning_rate": 1.9698126948968045e-05,
+      "loss": 0.5375,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "eval_cosine_accuracy": 0.9698635935783386,
+      "eval_loss": 0.48747143149375916,
+      "eval_runtime": 25.5135,
+      "eval_samples_per_second": 370.666,
+      "eval_steps_per_second": 1.45,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "grad_norm": 3.038301944732666,
+      "learning_rate": 1.7910542351398434e-05,
+      "loss": 0.4819,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "eval_cosine_accuracy": 0.9700750708580017,
+      "eval_loss": 0.4655883312225342,
+      "eval_runtime": 24.3373,
+      "eval_samples_per_second": 388.58,
+      "eval_steps_per_second": 1.52,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "grad_norm": 1.8415659666061401,
+      "learning_rate": 1.479951377448688e-05,
+      "loss": 0.4464,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "eval_cosine_accuracy": 0.9712382555007935,
+      "eval_loss": 0.45520612597465515,
+      "eval_runtime": 24.1507,
+      "eval_samples_per_second": 391.583,
+      "eval_steps_per_second": 1.532,
+      "step": 6000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "grad_norm": 3.430044412612915,
+      "learning_rate": 1.0887571873386376e-05,
+      "loss": 0.4181,
+      "step": 8000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "eval_cosine_accuracy": 0.9699693322181702,
+      "eval_loss": 0.45141610503196716,
+      "eval_runtime": 24.2116,
+      "eval_samples_per_second": 390.598,
+      "eval_steps_per_second": 1.528,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "grad_norm": 3.066155195236206,
+      "learning_rate": 6.8272844001772035e-06,
+      "loss": 0.4045,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "eval_cosine_accuracy": 0.9715554714202881,
+      "eval_loss": 0.45002102851867676,
+      "eval_runtime": 24.1353,
+      "eval_samples_per_second": 391.833,
+      "eval_steps_per_second": 1.533,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "grad_norm": 2.449310064315796,
+      "learning_rate": 3.2972732064518508e-06,
+      "loss": 0.3846,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "eval_cosine_accuracy": 0.9706037640571594,
+      "eval_loss": 0.4488030970096588,
+      "eval_runtime": 24.2639,
+      "eval_samples_per_second": 389.756,
+      "eval_steps_per_second": 1.525,
+      "step": 12000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "grad_norm": 1.9049738645553589,
+      "learning_rate": 8.875316727860706e-07,
+      "loss": 0.3799,
+      "step": 14000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "eval_cosine_accuracy": 0.9712382555007935,
+      "eval_loss": 0.44579291343688965,
+      "eval_runtime": 24.8888,
+      "eval_samples_per_second": 379.969,
+      "eval_steps_per_second": 1.487,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "grad_norm": 2.465521812438965,
+      "learning_rate": 8.15336127868438e-10,
+      "loss": 0.3818,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "eval_cosine_accuracy": 0.970709502696991,
+      "eval_loss": 0.4457339942455292,
+      "eval_runtime": 24.1508,
+      "eval_samples_per_second": 391.581,
+      "eval_steps_per_second": 1.532,
+      "step": 16000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 16056,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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-16056/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379402d179378eae8fbc291b7eb1e8a2d4a88951eda8fdca0ac9c13f56fe43c5
+size 5624

checkpoint-16056/training_metrics.json

@@ -0,0 +1,54 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.37369207772795215,
+      "global_step": 2000,
+      "eval_loss": 0.48747143149375916,
+      "eval_cosine_accuracy": 0.9698635935783386
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "global_step": 4000,
+      "eval_loss": 0.4655883312225342,
+      "eval_cosine_accuracy": 0.9700750708580017
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "global_step": 6000,
+      "eval_loss": 0.45520612597465515,
+      "eval_cosine_accuracy": 0.9712382555007935
+    },
+    {
+      "epoch": 1.494214259051885,
+      "global_step": 8000,
+      "eval_loss": 0.45141610503196716,
+      "eval_cosine_accuracy": 0.9699693322181702
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "global_step": 10000,
+      "eval_loss": 0.45002102851867676,
+      "eval_cosine_accuracy": 0.9715554714202881
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "global_step": 12000,
+      "eval_loss": 0.4488030970096588,
+      "eval_cosine_accuracy": 0.9706037640571594
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "global_step": 14000,
+      "eval_loss": 0.44579291343688965,
+      "eval_cosine_accuracy": 0.9712382555007935
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "global_step": 16000,
+      "eval_loss": 0.4457339942455292,
+      "eval_cosine_accuracy": 0.970709502696991
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 16056
+}