Training checkpoint - Epoch 2, Step 9764

checkpoint-9764/1_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-9764/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-9764/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-9764/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:512123f7deef5dac68ebf796863efa407221d501c5886cb6dbab9c41d5f3739f
+size 90864192

checkpoint-9764/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-9764/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e301da66ffd1d5e04836838cd980f7a056a3165858c58eb1d96b50a4d0a3091
+size 180607738

checkpoint-9764/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d30775b84819d5d2c98513ebd41eb258b1606bcaf4be45e6b48190797a6f034b
+size 14244

checkpoint-9764/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a09f4dac06c949424fb572cc4f23054c2cfe3448fbf1b774ee33f7a5e985e7f
+size 988

checkpoint-9764/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff834f274e1b605203ac33fb2bb8a0292ddea5195a120a74606152ccb84e4745
+size 1064

checkpoint-9764/sentence_bert_config.json

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

checkpoint-9764/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-9764/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-9764/trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 2000,
+  "global_step": 9764,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00020491803278688525,
+      "grad_norm": 7.146026134490967,
+      "learning_rate": 0.0,
+      "loss": 5.3596,
+      "step": 1
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 3.285043954849243,
+      "learning_rate": 1.2291453166632506e-05,
+      "loss": 3.8653,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "eval_cosine_accuracy": 0.9486149549484253,
+      "eval_loss": 1.1072193384170532,
+      "eval_runtime": 23.3961,
+      "eval_samples_per_second": 404.255,
+      "eval_steps_per_second": 1.581,
+      "step": 2000
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 3.012749671936035,
+      "learning_rate": 2.4589055134248825e-05,
+      "loss": 3.0105,
+      "step": 4000
+    },
+    {
+      "epoch": 0.819672131147541,
+      "eval_cosine_accuracy": 0.9498836994171143,
+      "eval_loss": 1.038019061088562,
+      "eval_runtime": 22.8225,
+      "eval_samples_per_second": 414.416,
+      "eval_steps_per_second": 1.621,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2293202293202294,
+      "grad_norm": 3.132009267807007,
+      "learning_rate": 2.9569679354976812e-05,
+      "loss": 2.6189,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2293202293202294,
+      "eval_cosine_accuracy": 0.955910325050354,
+      "eval_loss": 1.0144742727279663,
+      "eval_runtime": 22.4633,
+      "eval_samples_per_second": 421.042,
+      "eval_steps_per_second": 1.647,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6388206388206388,
+      "grad_norm": 2.9897189140319824,
+      "learning_rate": 2.6766216489460155e-05,
+      "loss": 2.4043,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6388206388206388,
+      "eval_cosine_accuracy": 0.9584478735923767,
+      "eval_loss": 0.9785193204879761,
+      "eval_runtime": 22.6802,
+      "eval_samples_per_second": 417.016,
+      "eval_steps_per_second": 1.631,
+      "step": 8000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 19520,
+  "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-9764/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c9f181965c573b2a16fc09e1e0732b4685ed3b8c188e7dc1504cce8e661888
+size 5624

checkpoint-9764/training_metrics.json

@@ -0,0 +1,30 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.4098360655737705,
+      "global_step": 2000,
+      "eval_loss": 1.1072193384170532,
+      "eval_cosine_accuracy": 0.9486149549484253
+    },
+    {
+      "epoch": 0.819672131147541,
+      "global_step": 4000,
+      "eval_loss": 1.038019061088562,
+      "eval_cosine_accuracy": 0.9498836994171143
+    },
+    {
+      "epoch": 1.2293202293202294,
+      "global_step": 6000,
+      "eval_loss": 1.0144742727279663,
+      "eval_cosine_accuracy": 0.955910325050354
+    },
+    {
+      "epoch": 1.6388206388206388,
+      "global_step": 8000,
+      "eval_loss": 0.9785193204879761,
+      "eval_cosine_accuracy": 0.9584478735923767
+    }
+  ],
+  "current_epoch": 2,
+  "global_step": 9764
+}