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:c7473698cda6efac0e58d7cce1592c40c743bfd0c0448e8268382841ca3e090a
+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 sha256:5511f724db043643ab1b09f34fe8c28ba72ee6d5cc03c214f38976b7fff522f3
+size 180607738

checkpoint-16056/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1951421050bca0f7f397341055a14f5696abb3a7b36cc39cc26045851154ec
+size 14244

checkpoint-16056/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebc69ca21d5bd42a2fea16b3497d9690d67450d3b3ade35188b81396f5afa82
+size 988

checkpoint-16056/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ecc15bee8532c8f92d12ce2121251c937028a20c97b7bdf5976591133dfb054
+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": 7.283237457275391,
+      "learning_rate": 0.0,
+      "loss": 2.5638,
+      "step": 1
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "grad_norm": 3.5235743522644043,
+      "learning_rate": 1.1207250981125022e-05,
+      "loss": 1.8628,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "eval_cosine_accuracy": 0.9401501417160034,
+      "eval_loss": 0.6366472244262695,
+      "eval_runtime": 25.214,
+      "eval_samples_per_second": 375.069,
+      "eval_steps_per_second": 1.467,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "grad_norm": 2.6583433151245117,
+      "learning_rate": 2.242010839095496e-05,
+      "loss": 1.1435,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "eval_cosine_accuracy": 0.9509358406066895,
+      "eval_loss": 0.5591886043548584,
+      "eval_runtime": 24.4126,
+      "eval_samples_per_second": 387.381,
+      "eval_steps_per_second": 1.516,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "grad_norm": 2.364020824432373,
+      "learning_rate": 2.972958644109329e-05,
+      "loss": 0.8327,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "eval_cosine_accuracy": 0.961192786693573,
+      "eval_loss": 0.4972971975803375,
+      "eval_runtime": 24.4554,
+      "eval_samples_per_second": 386.705,
+      "eval_steps_per_second": 1.513,
+      "step": 6000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "grad_norm": 3.4594027996063232,
+      "learning_rate": 2.570034218588925e-05,
+      "loss": 0.6756,
+      "step": 8000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "eval_cosine_accuracy": 0.96235591173172,
+      "eval_loss": 0.46515747904777527,
+      "eval_runtime": 24.4138,
+      "eval_samples_per_second": 387.363,
+      "eval_steps_per_second": 1.516,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "grad_norm": 3.648329257965088,
+      "learning_rate": 1.8087809898718502e-05,
+      "loss": 0.5943,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "eval_cosine_accuracy": 0.965951144695282,
+      "eval_loss": 0.44677722454071045,
+      "eval_runtime": 24.6447,
+      "eval_samples_per_second": 383.734,
+      "eval_steps_per_second": 1.501,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "grad_norm": 2.807162046432495,
+      "learning_rate": 9.44581252844728e-06,
+      "loss": 0.533,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "eval_cosine_accuracy": 0.9661626219749451,
+      "eval_loss": 0.42888060212135315,
+      "eval_runtime": 24.4803,
+      "eval_samples_per_second": 386.311,
+      "eval_steps_per_second": 1.511,
+      "step": 12000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "grad_norm": 2.1939520835876465,
+      "learning_rate": 2.6611118385980525e-06,
+      "loss": 0.5074,
+      "step": 14000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "eval_cosine_accuracy": 0.9669028520584106,
+      "eval_loss": 0.4245707094669342,
+      "eval_runtime": 24.8026,
+      "eval_samples_per_second": 381.291,
+      "eval_steps_per_second": 1.492,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "grad_norm": 2.9214141368865967,
+      "learning_rate": 2.482899053539156e-09,
+      "loss": 0.5037,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "eval_cosine_accuracy": 0.9678544998168945,
+      "eval_loss": 0.42359817028045654,
+      "eval_runtime": 24.826,
+      "eval_samples_per_second": 380.931,
+      "eval_steps_per_second": 1.49,
+      "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:eb1926076e88d25a9018fb1173f526ee720af818fcd75fb8f9ab7f59f9538f7e
+size 5624

checkpoint-16056/training_metrics.json

@@ -0,0 +1,54 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.37369207772795215,
+      "global_step": 2000,
+      "eval_loss": 0.6366472244262695,
+      "eval_cosine_accuracy": 0.9401501417160034
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "global_step": 4000,
+      "eval_loss": 0.5591886043548584,
+      "eval_cosine_accuracy": 0.9509358406066895
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "global_step": 6000,
+      "eval_loss": 0.4972971975803375,
+      "eval_cosine_accuracy": 0.961192786693573
+    },
+    {
+      "epoch": 1.494214259051885,
+      "global_step": 8000,
+      "eval_loss": 0.46515747904777527,
+      "eval_cosine_accuracy": 0.96235591173172
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "global_step": 10000,
+      "eval_loss": 0.44677722454071045,
+      "eval_cosine_accuracy": 0.965951144695282
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "global_step": 12000,
+      "eval_loss": 0.42888060212135315,
+      "eval_cosine_accuracy": 0.9661626219749451
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "global_step": 14000,
+      "eval_loss": 0.4245707094669342,
+      "eval_cosine_accuracy": 0.9669028520584106
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "global_step": 16000,
+      "eval_loss": 0.42359817028045654,
+      "eval_cosine_accuracy": 0.9678544998168945
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 16056
+}