Training checkpoint - Epoch 1, Step 6148

checkpoint-6148/1_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-6148/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-6148/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.53.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-6148/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4f81b5d0d40fc7449c7f741b286bd712e91837b614352661dbdff87cb50c19
+size 90864192

checkpoint-6148/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-6148/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920b54c0ee09b3df3da97eac9d5ed7bc422ca5308754bcf20df92ce415005a8e
+size 180607738

checkpoint-6148/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cee4ae00f83b6bb6b05e5b7b11209552d98455abfffc9a910e5869adb04e29
+size 14244

checkpoint-6148/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1115e318e1d2ef529101ce8b3c30504645d8d7586a43b3a74ceaa3e447c21205
+size 988

checkpoint-6148/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bce4989ac0397d5123abe9a3343cbcd9671de10b8d6fc792e1f26d7b550ab64
+size 1064

checkpoint-6148/sentence_bert_config.json

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

checkpoint-6148/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-6148/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-6148/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 6148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00016265452179570593,
+      "grad_norm": 6.156601428985596,
+      "learning_rate": 0.0,
+      "loss": 3.8933,
+      "step": 1
+    },
+    {
+      "epoch": 0.16265452179570591,
+      "grad_norm": 4.289596080780029,
+      "learning_rate": 1.015450294775361e-05,
+      "loss": 3.2074,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16265452179570591,
+      "eval_cosine_accuracy": 0.9418973326683044,
+      "eval_loss": 1.027454137802124,
+      "eval_runtime": 39.0658,
+      "eval_samples_per_second": 242.309,
+      "eval_steps_per_second": 0.947,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32530904359141183,
+      "grad_norm": 4.5890212059021,
+      "learning_rate": 2.0319170563122585e-05,
+      "loss": 2.4803,
+      "step": 2000
+    },
+    {
+      "epoch": 0.32530904359141183,
+      "eval_cosine_accuracy": 0.9498203992843628,
+      "eval_loss": 0.9803651571273804,
+      "eval_runtime": 31.9174,
+      "eval_samples_per_second": 296.578,
+      "eval_steps_per_second": 1.159,
+      "step": 2000
+    },
+    {
+      "epoch": 0.48796356538711777,
+      "grad_norm": 4.498090744018555,
+      "learning_rate": 3.0483838178491565e-05,
+      "loss": 2.3204,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48796356538711777,
+      "eval_cosine_accuracy": 0.9540460705757141,
+      "eval_loss": 0.9327970147132874,
+      "eval_runtime": 31.8807,
+      "eval_samples_per_second": 296.919,
+      "eval_steps_per_second": 1.161,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6506180871828237,
+      "grad_norm": 4.331326484680176,
+      "learning_rate": 4.0648505793860545e-05,
+      "loss": 2.5228,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6506180871828237,
+      "eval_cosine_accuracy": 0.9547855257987976,
+      "eval_loss": 0.9004496932029724,
+      "eval_runtime": 32.3273,
+      "eval_samples_per_second": 292.818,
+      "eval_steps_per_second": 1.145,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8132726089785296,
+      "grad_norm": 3.2787270545959473,
+      "learning_rate": 4.9799217201240286e-05,
+      "loss": 3.0266,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8132726089785296,
+      "eval_cosine_accuracy": 0.9421085715293884,
+      "eval_loss": 0.8936010003089905,
+      "eval_runtime": 31.9692,
+      "eval_samples_per_second": 296.098,
+      "eval_steps_per_second": 1.157,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9759271307742355,
+      "grad_norm": 2.9815802574157715,
+      "learning_rate": 4.7260204340974945e-05,
+      "loss": 3.3448,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9759271307742355,
+      "eval_cosine_accuracy": 0.9148531556129456,
+      "eval_loss": 0.965604305267334,
+      "eval_runtime": 31.9786,
+      "eval_samples_per_second": 296.011,
+      "eval_steps_per_second": 1.157,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 24592,
+  "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": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6148/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08359a2e253fade1dea7241b671c2d8b98a9dcaa096d3051decfd5ff500b3305
+size 5624