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:fe5ab96126640029986268f1a67892e5a323acbb0c96d80f3f2e7bcb1124b23f
+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:fe7b2b377193403841a3372d65ab550259c78f948969e9ab7aeff40a70184e07
+size 180607738

checkpoint-16056/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6888d6149604d75397d98ead0fe5d34e8c9ee1be97f01518babb7fb052e469
+size 14244

checkpoint-16056/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79efab9dbccac94bd2b27d8f5b7ee2d8836a93330cda9396b1a7ea0e186afa6e
+size 988

checkpoint-16056/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b50ecdbc39df689c625324b5414f8ae692cfeb17917353db6adf07a5176e95
+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": 7.590192794799805,
+      "learning_rate": 0.0,
+      "loss": 2.3884,
+      "step": 1
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "grad_norm": 3.019765615463257,
+      "learning_rate": 1.1207250981125022e-05,
+      "loss": 1.785,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37369207772795215,
+      "eval_cosine_accuracy": 0.9499841332435608,
+      "eval_loss": 0.5602969527244568,
+      "eval_runtime": 26.6864,
+      "eval_samples_per_second": 354.375,
+      "eval_steps_per_second": 1.386,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "grad_norm": 2.5413217544555664,
+      "learning_rate": 2.242010839095496e-05,
+      "loss": 1.1108,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "eval_cosine_accuracy": 0.9589722156524658,
+      "eval_loss": 0.5159783363342285,
+      "eval_runtime": 25.5224,
+      "eval_samples_per_second": 370.537,
+      "eval_steps_per_second": 1.45,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "grad_norm": 2.387631893157959,
+      "learning_rate": 2.9730417899789746e-05,
+      "loss": 0.8076,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "eval_cosine_accuracy": 0.9627788662910461,
+      "eval_loss": 0.4667944014072418,
+      "eval_runtime": 24.8171,
+      "eval_samples_per_second": 381.068,
+      "eval_steps_per_second": 1.491,
+      "step": 6000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "grad_norm": 3.606900930404663,
+      "learning_rate": 2.570034218588925e-05,
+      "loss": 0.6523,
+      "step": 8000
+    },
+    {
+      "epoch": 1.494214259051885,
+      "eval_cosine_accuracy": 0.9653167128562927,
+      "eval_loss": 0.43460702896118164,
+      "eval_runtime": 24.7987,
+      "eval_samples_per_second": 381.351,
+      "eval_steps_per_second": 1.492,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "grad_norm": 3.4747698307037354,
+      "learning_rate": 1.8087809898718502e-05,
+      "loss": 0.5738,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "eval_cosine_accuracy": 0.9685946702957153,
+      "eval_loss": 0.4207793176174164,
+      "eval_runtime": 26.0835,
+      "eval_samples_per_second": 362.566,
+      "eval_steps_per_second": 1.419,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "grad_norm": 2.458117723464966,
+      "learning_rate": 9.44172361789971e-06,
+      "loss": 0.5108,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "eval_cosine_accuracy": 0.9683831930160522,
+      "eval_loss": 0.4035998284816742,
+      "eval_runtime": 24.8029,
+      "eval_samples_per_second": 381.285,
+      "eval_steps_per_second": 1.492,
+      "step": 12000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "grad_norm": 2.087043523788452,
+      "learning_rate": 2.6611118385980525e-06,
+      "loss": 0.4865,
+      "step": 14000
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "eval_cosine_accuracy": 0.9688061475753784,
+      "eval_loss": 0.4007338583469391,
+      "eval_runtime": 24.621,
+      "eval_samples_per_second": 384.103,
+      "eval_steps_per_second": 1.503,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "grad_norm": 2.813512086868286,
+      "learning_rate": 2.40345357287175e-09,
+      "loss": 0.4823,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "eval_cosine_accuracy": 0.9685946702957153,
+      "eval_loss": 0.40074479579925537,
+      "eval_runtime": 24.7903,
+      "eval_samples_per_second": 381.48,
+      "eval_steps_per_second": 1.493,
+      "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 sha256:18e060478d7049f408792af1b540d4c07725191dc3e7b034272925db79e6321c
+size 5624

checkpoint-16056/training_metrics.json

@@ -0,0 +1,54 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.37369207772795215,
+      "global_step": 2000,
+      "eval_loss": 0.5602969527244568,
+      "eval_cosine_accuracy": 0.9499841332435608
+    },
+    {
+      "epoch": 0.7473841554559043,
+      "global_step": 4000,
+      "eval_loss": 0.5159783363342285,
+      "eval_cosine_accuracy": 0.9589722156524658
+    },
+    {
+      "epoch": 1.1209406494960805,
+      "global_step": 6000,
+      "eval_loss": 0.4667944014072418,
+      "eval_cosine_accuracy": 0.9627788662910461
+    },
+    {
+      "epoch": 1.494214259051885,
+      "global_step": 8000,
+      "eval_loss": 0.43460702896118164,
+      "eval_cosine_accuracy": 0.9653167128562927
+    },
+    {
+      "epoch": 1.8674878686076894,
+      "global_step": 10000,
+      "eval_loss": 0.4207793176174164,
+      "eval_cosine_accuracy": 0.9685946702957153
+    },
+    {
+      "epoch": 2.2407614781634937,
+      "global_step": 12000,
+      "eval_loss": 0.4035998284816742,
+      "eval_cosine_accuracy": 0.9683831930160522
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "global_step": 14000,
+      "eval_loss": 0.4007338583469391,
+      "eval_cosine_accuracy": 0.9688061475753784
+    },
+    {
+      "epoch": 2.9873086972751026,
+      "global_step": 16000,
+      "eval_loss": 0.40074479579925537,
+      "eval_cosine_accuracy": 0.9685946702957153
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 16056
+}