Training checkpoint - Epoch 1, Step 60000

checkpoint-60000/1_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-60000/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-60000/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-60000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1bcab656c29352e28360c3dbd405cf9e99099f535d0c560778291185f3448e
+size 90864192

checkpoint-60000/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-60000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b089e2e1aad148f048b50490a291aa98979bc8e716488a500b77b5c9a4cb54c1
+size 180607738

checkpoint-60000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52c1e45b2a6be1300b4c3f8ed9d3102eae10d423a93977c9f7f3159cb447aad
+size 14244

checkpoint-60000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca97e2ef7b4a9b2ec6c7f4a1a43c701938b26da462b3f6f5c3deffe10916cd2d
+size 988

checkpoint-60000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0ab92ee8447728eaf3de01236fb4195cf53e39483ff1607e1db07122e4ed13
+size 1064

checkpoint-60000/sentence_bert_config.json

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

checkpoint-60000/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-60000/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-60000/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4477367049512595,
+  "eval_steps": 10000,
+  "global_step": 60000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.412894508252099e-05,
+      "grad_norm": 4.8172993659973145,
+      "learning_rate": 0.0,
+      "loss": 3.8384,
+      "step": 1
+    },
+    {
+      "epoch": 0.24128945082520992,
+      "grad_norm": 2.6814990043640137,
+      "learning_rate": 3.6183432666554063e-06,
+      "loss": 2.9764,
+      "step": 10000
+    },
+    {
+      "epoch": 0.24128945082520992,
+      "eval_cosine_accuracy": 0.9525219202041626,
+      "eval_loss": 1.2816005945205688,
+      "eval_runtime": 25.5253,
+      "eval_samples_per_second": 370.495,
+      "eval_steps_per_second": 0.744,
+      "step": 10000
+    },
+    {
+      "epoch": 0.48257890165041983,
+      "grad_norm": 2.516390323638916,
+      "learning_rate": 7.235962647491736e-06,
+      "loss": 2.3257,
+      "step": 20000
+    },
+    {
+      "epoch": 0.48257890165041983,
+      "eval_cosine_accuracy": 0.9563286304473877,
+      "eval_loss": 1.2216517925262451,
+      "eval_runtime": 27.1816,
+      "eval_samples_per_second": 347.919,
+      "eval_steps_per_second": 0.699,
+      "step": 20000
+    },
+    {
+      "epoch": 0.7238683524756298,
+      "grad_norm": 2.6789209842681885,
+      "learning_rate": 1.0854305914147143e-05,
+      "loss": 2.1003,
+      "step": 30000
+    },
+    {
+      "epoch": 0.7238683524756298,
+      "eval_cosine_accuracy": 0.9602410793304443,
+      "eval_loss": 1.1404365301132202,
+      "eval_runtime": 29.5686,
+      "eval_samples_per_second": 319.833,
+      "eval_steps_per_second": 0.643,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9651578033008397,
+      "grad_norm": 2.530951499938965,
+      "learning_rate": 1.4471925294983472e-05,
+      "loss": 1.9546,
+      "step": 40000
+    },
+    {
+      "epoch": 0.9651578033008397,
+      "eval_cosine_accuracy": 0.9626731276512146,
+      "eval_loss": 1.0469619035720825,
+      "eval_runtime": 29.1732,
+      "eval_samples_per_second": 324.168,
+      "eval_steps_per_second": 0.651,
+      "step": 40000
+    },
+    {
+      "epoch": 1.2064472541260496,
+      "grad_norm": 2.358119249343872,
+      "learning_rate": 1.80895446758198e-05,
+      "loss": 1.8854,
+      "step": 50000
+    },
+    {
+      "epoch": 1.2064472541260496,
+      "eval_cosine_accuracy": 0.9646822214126587,
+      "eval_loss": 1.008235216140747,
+      "eval_runtime": 31.1627,
+      "eval_samples_per_second": 303.472,
+      "eval_steps_per_second": 0.61,
+      "step": 50000
+    },
+    {
+      "epoch": 1.4477367049512595,
+      "grad_norm": 2.3736186027526855,
+      "learning_rate": 2.1707887942475207e-05,
+      "loss": 1.7656,
+      "step": 60000
+    },
+    {
+      "epoch": 1.4477367049512595,
+      "eval_cosine_accuracy": 0.9640477895736694,
+      "eval_loss": 1.0126267671585083,
+      "eval_runtime": 27.9019,
+      "eval_samples_per_second": 338.938,
+      "eval_steps_per_second": 0.681,
+      "step": 60000
+    }
+  ],
+  "logging_steps": 10000,
+  "max_steps": 165776,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 30000,
+  "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-60000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac70e4eebe141ca6627aa63c5c2bea833caab65ec3f905c28e36ddaa6c330b99
+size 5624

checkpoint-60000/training_metrics.json

@@ -0,0 +1,42 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.24128945082520992,
+      "global_step": 10000,
+      "eval_loss": 1.2816005945205688,
+      "eval_cosine_accuracy": 0.9525219202041626
+    },
+    {
+      "epoch": 0.48257890165041983,
+      "global_step": 20000,
+      "eval_loss": 1.2216517925262451,
+      "eval_cosine_accuracy": 0.9563286304473877
+    },
+    {
+      "epoch": 0.7238683524756298,
+      "global_step": 30000,
+      "eval_loss": 1.1404365301132202,
+      "eval_cosine_accuracy": 0.9602410793304443
+    },
+    {
+      "epoch": 0.9651578033008397,
+      "global_step": 40000,
+      "eval_loss": 1.0469619035720825,
+      "eval_cosine_accuracy": 0.9626731276512146
+    },
+    {
+      "epoch": 1.2064472541260496,
+      "global_step": 50000,
+      "eval_loss": 1.008235216140747,
+      "eval_cosine_accuracy": 0.9646822214126587
+    },
+    {
+      "epoch": 1.4477367049512595,
+      "global_step": 60000,
+      "eval_loss": 1.0126267671585083,
+      "eval_cosine_accuracy": 0.9640477895736694
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 60000
+}