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:f7b5403a388f7edf996315313bb4e61008b4351695f92195f4e19b777e340f56
+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:a475ca6e0b8a4cc8789e9f9cc158641a5a9c839af140ccfce9e1944e216170bf
+size 180607738

checkpoint-16056/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0feaf08881615e043958f3fc7752bf0991bd000c32b48568f67d71886347b43
+size 14244

checkpoint-16056/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267d4bf6735cf37b4b9083f87be31c1b7c2313c9b87c982f6a994ea7900c0816
+size 988

checkpoint-16056/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8541b170718ec1bd2e5cf0c49480e92f4e7497e39768fb6a64af4ccd35baef39
+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": 512,
+  "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": 8.915643692016602,
+      "learning_rate": 0.0,
+      "loss": 3.2115,
+      "step": 1
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "grad_norm": 3.4466991424560547,
+      "learning_rate": 2.994527998755732e-05,
+      "loss": 1.907,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "eval_cosine_accuracy": 0.9618272185325623,
+      "eval_loss": 0.6304187178611755,
+      "eval_runtime": 27.4998,
+      "eval_samples_per_second": 343.893,
+      "eval_steps_per_second": 1.345,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "grad_norm": 2.7122421264648438,
+      "learning_rate": 2.8015311122967933e-05,
+      "loss": 1.1209,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "eval_cosine_accuracy": 0.9697578549385071,
+      "eval_loss": 0.553921639919281,
+      "eval_runtime": 25.7506,
+      "eval_samples_per_second": 367.254,
+      "eval_steps_per_second": 1.437,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "grad_norm": 2.4806041717529297,
+      "learning_rate": 2.3665720196385667e-05,
+      "loss": 0.9041,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "eval_cosine_accuracy": 0.9741989970207214,
+      "eval_loss": 0.5072000622749329,
+      "eval_runtime": 26.0436,
+      "eval_samples_per_second": 363.122,
+      "eval_steps_per_second": 1.421,
+      "step": 6000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "grad_norm": 4.2601141929626465,
+      "learning_rate": 1.770493593475678e-05,
+      "loss": 0.7989,
+      "step": 8000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "eval_cosine_accuracy": 0.9733530879020691,
+      "eval_loss": 0.4787100553512573,
+      "eval_runtime": 26.7179,
+      "eval_samples_per_second": 353.958,
+      "eval_steps_per_second": 1.385,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "grad_norm": 4.208492279052734,
+      "learning_rate": 1.1241230432764519e-05,
+      "loss": 0.7458,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "eval_cosine_accuracy": 0.9733530879020691,
+      "eval_loss": 0.4714418947696686,
+      "eval_runtime": 26.4276,
+      "eval_samples_per_second": 357.846,
+      "eval_steps_per_second": 1.4,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "grad_norm": 3.4276180267333984,
+      "learning_rate": 5.476382537233154e-06,
+      "loss": 0.6976,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "eval_cosine_accuracy": 0.974939227104187,
+      "eval_loss": 0.4594666063785553,
+      "eval_runtime": 26.464,
+      "eval_samples_per_second": 357.354,
+      "eval_steps_per_second": 1.398,
+      "step": 12000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "grad_norm": 2.610654592514038,
+      "learning_rate": 1.4808212490710914e-06,
+      "loss": 0.6796,
+      "step": 14000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "eval_cosine_accuracy": 0.9745162129402161,
+      "eval_loss": 0.45741090178489685,
+      "eval_runtime": 27.6186,
+      "eval_samples_per_second": 342.415,
+      "eval_steps_per_second": 1.34,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "grad_norm": 3.243903875350952,
+      "learning_rate": 1.3191027301212577e-09,
+      "loss": 0.6764,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "eval_cosine_accuracy": 0.9748334288597107,
+      "eval_loss": 0.4565849006175995,
+      "eval_runtime": 27.8151,
+      "eval_samples_per_second": 339.996,
+      "eval_steps_per_second": 1.33,
+      "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 sha256:4796567dbf8f4d41f55d26a7e24bf36dcbec2b9485f2ad98ee14681eda722fda
+size 5624

checkpoint-16056/training_metrics.json

@@ -0,0 +1,54 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.37369207772795215,
+      "global_step": 2000,
+      "eval_loss": 0.6304187178611755,
+      "eval_cosine_accuracy": 0.9618272185325623
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "global_step": 4000,
+      "eval_loss": 0.553921639919281,
+      "eval_cosine_accuracy": 0.9697578549385071
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "global_step": 6000,
+      "eval_loss": 0.5072000622749329,
+      "eval_cosine_accuracy": 0.9741989970207214
+    },
+    {
+      "epoch": 1.494214259051885,
+      "global_step": 8000,
+      "eval_loss": 0.4787100553512573,
+      "eval_cosine_accuracy": 0.9733530879020691
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "global_step": 10000,
+      "eval_loss": 0.4714418947696686,
+      "eval_cosine_accuracy": 0.9733530879020691
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "global_step": 12000,
+      "eval_loss": 0.4594666063785553,
+      "eval_cosine_accuracy": 0.974939227104187
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "global_step": 14000,
+      "eval_loss": 0.45741090178489685,
+      "eval_cosine_accuracy": 0.9745162129402161
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "global_step": 16000,
+      "eval_loss": 0.4565849006175995,
+      "eval_cosine_accuracy": 0.9748334288597107
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 16056
+}