Training checkpoint - Epoch 4, Step 23745

checkpoint-23745/1_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-23745/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-23745/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-23745/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dee9d4bed12bf19bb5973bf04e973f044fded6caf5faf6ff742c8fdd126407
+size 90864192

checkpoint-23745/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-23745/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d46019612970dabc358dce5a33d4424ba88d6a118ebcc16f0bf1978c6dc6059
+size 180607738

checkpoint-23745/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66881fc379c78fdb64b5d81c229514bfa8990c3de3a2bfe02644d1767038b67a
+size 14244

checkpoint-23745/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba2d9861718463ff7bd6d73f6b23628ebc78b5e0f737da9d01a6bf436bebb71
+size 988

checkpoint-23745/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56059f8cf6f4a7f5f3fbcb5597777373f624910c77fff821492af2b29fd9562b
+size 1064

checkpoint-23745/sentence_bert_config.json

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

checkpoint-23745/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-23745/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-23745/trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.99673855865334,
+  "eval_steps": 2000,
+  "global_step": 23745,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00021059281878487945,
+      "grad_norm": 5.663685321807861,
+      "learning_rate": 0.0,
+      "loss": 3.071,
+      "step": 1
+    },
+    {
+      "epoch": 0.42118563756975885,
+      "grad_norm": 2.951986312866211,
+      "learning_rate": 4.210193765796125e-06,
+      "loss": 2.5694,
+      "step": 2000
+    },
+    {
+      "epoch": 0.42118563756975885,
+      "eval_cosine_accuracy": 0.9467061161994934,
+      "eval_loss": 0.70719313621521,
+      "eval_runtime": 24.761,
+      "eval_samples_per_second": 381.931,
+      "eval_steps_per_second": 1.494,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "grad_norm": 3.3405182361602783,
+      "learning_rate": 8.42038753159225e-06,
+      "loss": 1.8962,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "eval_cosine_accuracy": 0.947446346282959,
+      "eval_loss": 0.6832706928253174,
+      "eval_runtime": 23.9291,
+      "eval_samples_per_second": 395.21,
+      "eval_steps_per_second": 1.546,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "grad_norm": 3.1271069049835205,
+      "learning_rate": 1.2632687447346253e-05,
+      "loss": 1.5288,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "eval_cosine_accuracy": 0.9527333974838257,
+      "eval_loss": 0.6657891273498535,
+      "eval_runtime": 24.265,
+      "eval_samples_per_second": 389.738,
+      "eval_steps_per_second": 1.525,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "grad_norm": 2.898742914199829,
+      "learning_rate": 1.6842881213142376e-05,
+      "loss": 1.291,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "eval_cosine_accuracy": 0.9556941986083984,
+      "eval_loss": 0.6694506406784058,
+      "eval_runtime": 24.4035,
+      "eval_samples_per_second": 387.527,
+      "eval_steps_per_second": 1.516,
+      "step": 8000
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "grad_norm": 2.797808885574341,
+      "learning_rate": 1.9939298262564484e-05,
+      "loss": 1.1379,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "eval_cosine_accuracy": 0.959395170211792,
+      "eval_loss": 0.6313222646713257,
+      "eval_runtime": 24.2386,
+      "eval_samples_per_second": 390.162,
+      "eval_steps_per_second": 1.526,
+      "step": 10000
+    },
+    {
+      "epoch": 2.525618095739085,
+      "grad_norm": 2.581394910812378,
+      "learning_rate": 1.8520145973137717e-05,
+      "loss": 1.0164,
+      "step": 12000
+    },
+    {
+      "epoch": 2.525618095739085,
+      "eval_cosine_accuracy": 0.9608755707740784,
+      "eval_loss": 0.5995237827301025,
+      "eval_runtime": 24.2243,
+      "eval_samples_per_second": 390.393,
+      "eval_steps_per_second": 1.527,
+      "step": 12000
+    },
+    {
+      "epoch": 2.946449237243556,
+      "grad_norm": 2.4010143280029297,
+      "learning_rate": 1.5472589867421462e-05,
+      "loss": 0.9469,
+      "step": 14000
+    },
+    {
+      "epoch": 2.946449237243556,
+      "eval_cosine_accuracy": 0.9616157412528992,
+      "eval_loss": 0.5910899043083191,
+      "eval_runtime": 24.1507,
+      "eval_samples_per_second": 391.583,
+      "eval_steps_per_second": 1.532,
+      "step": 14000
+    },
+    {
+      "epoch": 3.367175170962651,
+      "grad_norm": 2.631092071533203,
+      "learning_rate": 1.1376907109575828e-05,
+      "loss": 0.888,
+      "step": 16000
+    },
+    {
+      "epoch": 3.367175170962651,
+      "eval_cosine_accuracy": 0.9633076190948486,
+      "eval_loss": 0.5799629092216492,
+      "eval_runtime": 24.0714,
+      "eval_samples_per_second": 392.872,
+      "eval_steps_per_second": 1.537,
+      "step": 16000
+    },
+    {
+      "epoch": 3.7880063124671226,
+      "grad_norm": 2.4939944744110107,
+      "learning_rate": 7.019909902200382e-06,
+      "loss": 0.859,
+      "step": 18000
+    },
+    {
+      "epoch": 3.7880063124671226,
+      "eval_cosine_accuracy": 0.9638363122940063,
+      "eval_loss": 0.5834744572639465,
+      "eval_runtime": 24.2033,
+      "eval_samples_per_second": 390.732,
+      "eval_steps_per_second": 1.529,
+      "step": 18000
+    },
+    {
+      "epoch": 4.2087322461862176,
+      "grad_norm": 2.450113296508789,
+      "learning_rate": 3.232479237868129e-06,
+      "loss": 0.8402,
+      "step": 20000
+    },
+    {
+      "epoch": 4.2087322461862176,
+      "eval_cosine_accuracy": 0.9642592668533325,
+      "eval_loss": 0.5751084089279175,
+      "eval_runtime": 24.1378,
+      "eval_samples_per_second": 391.791,
+      "eval_steps_per_second": 1.533,
+      "step": 20000
+    },
+    {
+      "epoch": 4.629563387690689,
+      "grad_norm": 2.3858232498168945,
+      "learning_rate": 7.376524535818352e-07,
+      "loss": 0.8222,
+      "step": 22000
+    },
+    {
+      "epoch": 4.629563387690689,
+      "eval_cosine_accuracy": 0.9646822214126587,
+      "eval_loss": 0.5725743174552917,
+      "eval_runtime": 24.1149,
+      "eval_samples_per_second": 392.164,
+      "eval_steps_per_second": 1.534,
+      "step": 22000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 23745,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-23745/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1fbdf3fe5bdbd313c5a1290321ec0a4c83807e3a4e7a1c14f9ebd7401069c2
+size 5624

checkpoint-23745/training_metrics.json

@@ -0,0 +1,72 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.42118563756975885,
+      "global_step": 2000,
+      "eval_loss": 0.70719313621521,
+      "eval_cosine_accuracy": 0.9467061161994934
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "global_step": 4000,
+      "eval_loss": 0.6832706928253174,
+      "eval_cosine_accuracy": 0.947446346282959
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "global_step": 6000,
+      "eval_loss": 0.6657891273498535,
+      "eval_cosine_accuracy": 0.9527333974838257
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "global_step": 8000,
+      "eval_loss": 0.6694506406784058,
+      "eval_cosine_accuracy": 0.9556941986083984
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "global_step": 10000,
+      "eval_loss": 0.6313222646713257,
+      "eval_cosine_accuracy": 0.959395170211792
+    },
+    {
+      "epoch": 2.525618095739085,
+      "global_step": 12000,
+      "eval_loss": 0.5995237827301025,
+      "eval_cosine_accuracy": 0.9608755707740784
+    },
+    {
+      "epoch": 2.946449237243556,
+      "global_step": 14000,
+      "eval_loss": 0.5910899043083191,
+      "eval_cosine_accuracy": 0.9616157412528992
+    },
+    {
+      "epoch": 3.367175170962651,
+      "global_step": 16000,
+      "eval_loss": 0.5799629092216492,
+      "eval_cosine_accuracy": 0.9633076190948486
+    },
+    {
+      "epoch": 3.7880063124671226,
+      "global_step": 18000,
+      "eval_loss": 0.5834744572639465,
+      "eval_cosine_accuracy": 0.9638363122940063
+    },
+    {
+      "epoch": 4.2087322461862176,
+      "global_step": 20000,
+      "eval_loss": 0.5751084089279175,
+      "eval_cosine_accuracy": 0.9642592668533325
+    },
+    {
+      "epoch": 4.629563387690689,
+      "global_step": 22000,
+      "eval_loss": 0.5725743174552917,
+      "eval_cosine_accuracy": 0.9646822214126587
+    }
+  ],
+  "current_epoch": 4,
+  "global_step": 23745
+}