Training checkpoint - Epoch 2, Step 15394

checkpoint-15394/1_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-15394/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-15394/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-15394/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b541b17e4cdf80b1a2253644db0a5fb2aaecc85425e1da09c8663358ae9f8d63
+size 90864192

checkpoint-15394/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-15394/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31810eedd7432ee14ba86463be0f6f9d33dfed436ea927bbb89513a967cd34a
+size 180607738

checkpoint-15394/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5231ff75144da76699a015c68820ff9b3b719fbcb244dd864aee287b46fe5509
+size 14244

checkpoint-15394/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15822cd468ab0d2594ed78470ae39bfe73dc8b0885e52d93386e478ebecf58f9
+size 988

checkpoint-15394/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5e822c55a24be1dfdde4f879e7c24d03f57f46129381f2c7f84f77de1ef0bb
+size 1064

checkpoint-15394/sentence_bert_config.json

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

checkpoint-15394/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-15394/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-15394/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 2000,
+  "global_step": 15394,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00012992074834351045,
+      "grad_norm": 7.7499589920043945,
+      "learning_rate": 0.0,
+      "loss": 3.4107,
+      "step": 1
+    },
+    {
+      "epoch": 0.2598414966870209,
+      "grad_norm": 3.223598003387451,
+      "learning_rate": 7.792359667359668e-06,
+      "loss": 2.4514,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2598414966870209,
+      "eval_cosine_accuracy": 0.946060299873352,
+      "eval_loss": 0.91331946849823,
+      "eval_runtime": 25.9781,
+      "eval_samples_per_second": 363.961,
+      "eval_steps_per_second": 0.731,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5196829933740418,
+      "grad_norm": 2.9365298748016357,
+      "learning_rate": 1.5588617463617465e-05,
+      "loss": 1.6277,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5196829933740418,
+      "eval_cosine_accuracy": 0.9472236633300781,
+      "eval_loss": 0.8556821942329407,
+      "eval_runtime": 25.551,
+      "eval_samples_per_second": 370.044,
+      "eval_steps_per_second": 0.744,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7795244900610627,
+      "grad_norm": 3.0075325965881348,
+      "learning_rate": 2.338097713097713e-05,
+      "loss": 1.2469,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7795244900610627,
+      "eval_cosine_accuracy": 0.9501850605010986,
+      "eval_loss": 0.8617205619812012,
+      "eval_runtime": 25.8371,
+      "eval_samples_per_second": 365.947,
+      "eval_steps_per_second": 0.735,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0393659867480838,
+      "grad_norm": 2.5449373722076416,
+      "learning_rate": 2.9987508340635427e-05,
+      "loss": 1.2862,
+      "step": 8000
+    },
+    {
+      "epoch": 1.0393659867480838,
+      "eval_cosine_accuracy": 0.9508196711540222,
+      "eval_loss": 0.8610702157020569,
+      "eval_runtime": 25.794,
+      "eval_samples_per_second": 366.559,
+      "eval_steps_per_second": 0.737,
+      "step": 8000
+    },
+    {
+      "epoch": 1.2992074834351046,
+      "grad_norm": 2.4445102214813232,
+      "learning_rate": 2.927163819523492e-05,
+      "loss": 0.9041,
+      "step": 10000
+    },
+    {
+      "epoch": 1.2992074834351046,
+      "eval_cosine_accuracy": 0.956213653087616,
+      "eval_loss": 0.7799679636955261,
+      "eval_runtime": 25.5138,
+      "eval_samples_per_second": 370.584,
+      "eval_steps_per_second": 0.745,
+      "step": 10000
+    },
+    {
+      "epoch": 1.5590489801221254,
+      "grad_norm": 2.134432077407837,
+      "learning_rate": 2.7505671097607588e-05,
+      "loss": 0.8181,
+      "step": 12000
+    },
+    {
+      "epoch": 1.5590489801221254,
+      "eval_cosine_accuracy": 0.9569540023803711,
+      "eval_loss": 0.7651481628417969,
+      "eval_runtime": 25.6352,
+      "eval_samples_per_second": 368.829,
+      "eval_steps_per_second": 0.741,
+      "step": 12000
+    },
+    {
+      "epoch": 1.8188904768091465,
+      "grad_norm": 2.1797378063201904,
+      "learning_rate": 2.4821088211734495e-05,
+      "loss": 0.7655,
+      "step": 14000
+    },
+    {
+      "epoch": 1.8188904768091465,
+      "eval_cosine_accuracy": 0.962136447429657,
+      "eval_loss": 0.7638042569160461,
+      "eval_runtime": 25.5173,
+      "eval_samples_per_second": 370.532,
+      "eval_steps_per_second": 0.745,
+      "step": 14000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 30788,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15394/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392ca619a98a0a6b0e35608bcb5dfed8723cd1a35912710a6fdb11d8b8538075
+size 5624

checkpoint-15394/training_metrics.json

@@ -0,0 +1,48 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.2598414966870209,
+      "global_step": 2000,
+      "eval_loss": 0.91331946849823,
+      "eval_cosine_accuracy": 0.946060299873352
+    },
+    {
+      "epoch": 0.5196829933740418,
+      "global_step": 4000,
+      "eval_loss": 0.8556821942329407,
+      "eval_cosine_accuracy": 0.9472236633300781
+    },
+    {
+      "epoch": 0.7795244900610627,
+      "global_step": 6000,
+      "eval_loss": 0.8617205619812012,
+      "eval_cosine_accuracy": 0.9501850605010986
+    },
+    {
+      "epoch": 1.0393659867480838,
+      "global_step": 8000,
+      "eval_loss": 0.8610702157020569,
+      "eval_cosine_accuracy": 0.9508196711540222
+    },
+    {
+      "epoch": 1.2992074834351046,
+      "global_step": 10000,
+      "eval_loss": 0.7799679636955261,
+      "eval_cosine_accuracy": 0.956213653087616
+    },
+    {
+      "epoch": 1.5590489801221254,
+      "global_step": 12000,
+      "eval_loss": 0.7651481628417969,
+      "eval_cosine_accuracy": 0.9569540023803711
+    },
+    {
+      "epoch": 1.8188904768091465,
+      "global_step": 14000,
+      "eval_loss": 0.7638042569160461,
+      "eval_cosine_accuracy": 0.962136447429657
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 15394
+}