Training checkpoint - Epoch 1, Step 10863

checkpoint-10863/1_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-10863/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-10863/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-10863/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2ddc9667a8bf4a914be010c567a710da104d5335ca054c20187f6a164da495
+size 90864192

checkpoint-10863/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-10863/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fb69fe66020e7833809340e776f5e5f1963e898c29b98892b53b0b4a421e70
+size 180607738

checkpoint-10863/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59abaa5acb9293da469ab6ead290ce882fb37e2f8b81890cf9360d65be30e746
+size 14244

checkpoint-10863/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e9d575106eef6c431a4015dd62fe11ad94d9a9c789fd60966c6617f121d9d6
+size 988

checkpoint-10863/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd963f5049ba984eaacfb40c49b1d2cb3ff9bf2e89f440bc5f525b5b77ac2758
+size 1064

checkpoint-10863/sentence_bert_config.json

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

checkpoint-10863/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-10863/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-10863/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 2000,
+  "global_step": 10863,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 9.205560158335634e-05,
+      "grad_norm": 7.180713176727295,
+      "learning_rate": 0.0,
+      "loss": 2.5727,
+      "step": 1
+    },
+    {
+      "epoch": 0.1841112031667127,
+      "grad_norm": 4.364831447601318,
+      "learning_rate": 5.5210826735407845e-06,
+      "loss": 2.2003,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1841112031667127,
+      "eval_cosine_accuracy": 0.9447852969169617,
+      "eval_loss": 1.741607666015625,
+      "eval_runtime": 20.9736,
+      "eval_samples_per_second": 450.758,
+      "eval_steps_per_second": 1.764,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3682224063334254,
+      "grad_norm": 4.162062644958496,
+      "learning_rate": 1.1042165347081569e-05,
+      "loss": 1.6012,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3682224063334254,
+      "eval_cosine_accuracy": 0.9465834498405457,
+      "eval_loss": 1.685057520866394,
+      "eval_runtime": 25.0673,
+      "eval_samples_per_second": 377.145,
+      "eval_steps_per_second": 1.476,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5523336095001381,
+      "grad_norm": 3.561060905456543,
+      "learning_rate": 1.6563248020622354e-05,
+      "loss": 1.2787,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5523336095001381,
+      "eval_cosine_accuracy": 0.9530357718467712,
+      "eval_loss": 1.589287519454956,
+      "eval_runtime": 23.3994,
+      "eval_samples_per_second": 404.028,
+      "eval_steps_per_second": 1.581,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7364448126668508,
+      "grad_norm": 3.908196449279785,
+      "learning_rate": 2.2084330694163138e-05,
+      "loss": 1.0753,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7364448126668508,
+      "eval_cosine_accuracy": 0.9574783444404602,
+      "eval_loss": 1.5174190998077393,
+      "eval_runtime": 23.6702,
+      "eval_samples_per_second": 399.405,
+      "eval_steps_per_second": 1.563,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9205560158335635,
+      "grad_norm": 3.514824628829956,
+      "learning_rate": 2.760817529000184e-05,
+      "loss": 0.9386,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9205560158335635,
+      "eval_cosine_accuracy": 0.9603342413902283,
+      "eval_loss": 1.4767882823944092,
+      "eval_runtime": 23.3417,
+      "eval_samples_per_second": 405.026,
+      "eval_steps_per_second": 1.585,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 21726,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10863/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8489ce002b532044cb5778386594077030ccd605395b8a3dc36971c8c9c644e
+size 5624

checkpoint-10863/training_metrics.json

@@ -0,0 +1,36 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.1841112031667127,
+      "global_step": 2000,
+      "eval_loss": 1.741607666015625,
+      "eval_cosine_accuracy": 0.9447852969169617
+    },
+    {
+      "epoch": 0.3682224063334254,
+      "global_step": 4000,
+      "eval_loss": 1.685057520866394,
+      "eval_cosine_accuracy": 0.9465834498405457
+    },
+    {
+      "epoch": 0.5523336095001381,
+      "global_step": 6000,
+      "eval_loss": 1.589287519454956,
+      "eval_cosine_accuracy": 0.9530357718467712
+    },
+    {
+      "epoch": 0.7364448126668508,
+      "global_step": 8000,
+      "eval_loss": 1.5174190998077393,
+      "eval_cosine_accuracy": 0.9574783444404602
+    },
+    {
+      "epoch": 0.9205560158335635,
+      "global_step": 10000,
+      "eval_loss": 1.4767882823944092,
+      "eval_cosine_accuracy": 0.9603342413902283
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 10863
+}