Training checkpoint - Epoch 3, Step 19520

checkpoint-19520/1_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-19520/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-19520/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-19520/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff1eb1cd3c724dd4ddc7afd35045a62fef4027ace56c431a39f41f989bcbcc7
+size 90864192

checkpoint-19520/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-19520/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89aac319e4198d4a5639e78451a4a723ea92d903ffd0f416c2bcbdc31db86bac
+size 180607738

checkpoint-19520/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f5fec805b08e95f4d1e09291c07ab74489c340c99b2609dba71a214dae5551
+size 14244

checkpoint-19520/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdc49560e553164b1dbfae34d183bfef60709f4ef9b5eab12b9bd606d05fc67
+size 988

checkpoint-19520/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ed8821d8febf06e28e941b45d85b92aff76633b36e7ff3afa45759194a733e
+size 1064

checkpoint-19520/sentence_bert_config.json

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

checkpoint-19520/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-19520/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-19520/trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9975429975429977,
+  "eval_steps": 2000,
+  "global_step": 19520,
+  "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
+    },
+    {
+      "epoch": 2.048321048321048,
+      "grad_norm": 2.879348039627075,
+      "learning_rate": 2.1833792815950103e-05,
+      "loss": 2.2687,
+      "step": 10000
+    },
+    {
+      "epoch": 2.048321048321048,
+      "eval_cosine_accuracy": 0.9582363963127136,
+      "eval_loss": 0.9782044887542725,
+      "eval_runtime": 22.63,
+      "eval_samples_per_second": 417.941,
+      "eval_steps_per_second": 1.635,
+      "step": 10000
+    },
+    {
+      "epoch": 2.4578214578214577,
+      "grad_norm": 3.2528302669525146,
+      "learning_rate": 1.5657997618453395e-05,
+      "loss": 2.1783,
+      "step": 12000
+    },
+    {
+      "epoch": 2.4578214578214577,
+      "eval_cosine_accuracy": 0.9606682062149048,
+      "eval_loss": 0.9658162593841553,
+      "eval_runtime": 22.5541,
+      "eval_samples_per_second": 419.348,
+      "eval_steps_per_second": 1.641,
+      "step": 12000
+    },
+    {
+      "epoch": 2.8673218673218672,
+      "grad_norm": 4.912777423858643,
+      "learning_rate": 9.368833553773793e-06,
+      "loss": 2.1255,
+      "step": 14000
+    },
+    {
+      "epoch": 2.8673218673218672,
+      "eval_cosine_accuracy": 0.9623599052429199,
+      "eval_loss": 0.9558193683624268,
+      "eval_runtime": 22.5573,
+      "eval_samples_per_second": 419.288,
+      "eval_steps_per_second": 1.64,
+      "step": 14000
+    },
+    {
+      "epoch": 3.276822276822277,
+      "grad_norm": 2.9567198753356934,
+      "learning_rate": 4.094509579831635e-06,
+      "loss": 2.1017,
+      "step": 16000
+    },
+    {
+      "epoch": 3.276822276822277,
+      "eval_cosine_accuracy": 0.9614083170890808,
+      "eval_loss": 0.9604467749595642,
+      "eval_runtime": 23.1493,
+      "eval_samples_per_second": 408.565,
+      "eval_steps_per_second": 1.598,
+      "step": 16000
+    },
+    {
+      "epoch": 3.6863226863226863,
+      "grad_norm": 3.0146830081939697,
+      "learning_rate": 7.990468087462394e-07,
+      "loss": 2.0732,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6863226863226863,
+      "eval_cosine_accuracy": 0.9623599052429199,
+      "eval_loss": 0.9567595720291138,
+      "eval_runtime": 22.8988,
+      "eval_samples_per_second": 413.035,
+      "eval_steps_per_second": 1.616,
+      "step": 18000
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-19520/training_args.bin

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

checkpoint-19520/training_metrics.json

@@ -0,0 +1,60 @@
+{
+  "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
+    },
+    {
+      "epoch": 2.048321048321048,
+      "global_step": 10000,
+      "eval_loss": 0.9782044887542725,
+      "eval_cosine_accuracy": 0.9582363963127136
+    },
+    {
+      "epoch": 2.4578214578214577,
+      "global_step": 12000,
+      "eval_loss": 0.9658162593841553,
+      "eval_cosine_accuracy": 0.9606682062149048
+    },
+    {
+      "epoch": 2.8673218673218672,
+      "global_step": 14000,
+      "eval_loss": 0.9558193683624268,
+      "eval_cosine_accuracy": 0.9623599052429199
+    },
+    {
+      "epoch": 3.276822276822277,
+      "global_step": 16000,
+      "eval_loss": 0.9604467749595642,
+      "eval_cosine_accuracy": 0.9614083170890808
+    },
+    {
+      "epoch": 3.6863226863226863,
+      "global_step": 18000,
+      "eval_loss": 0.9567595720291138,
+      "eval_cosine_accuracy": 0.9623599052429199
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 19520
+}