Training checkpoint - Epoch 3, Step 22104

checkpoint-22104/1_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-22104/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-22104/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-22104/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cae35f586c222c2eb75d6578c42e4457f2514972cd3e08ee99d93e42b3d0d2
+size 90864192

checkpoint-22104/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-22104/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f55c89c2bd50f75bfd308f131daaa407676b80cb0fe4c7e3d09125bcd9f202
+size 180607738

checkpoint-22104/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1428c6a69c9cfcf36c283d5551f7ad4db6e6df3cf64812ad991955ee35b375c
+size 14244

checkpoint-22104/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6576952f94e364bb2dfeebc009b346674486e94064c12633731060acabecac81
+size 988

checkpoint-22104/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a355c8385259310eb97427bf3a36ba5de30045efd3ec1602e899e623c721ebf
+size 1064

checkpoint-22104/sentence_bert_config.json

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

checkpoint-22104/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-22104/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-22104/trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9978300180831825,
+  "eval_steps": 2000,
+  "global_step": 22104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00018096272167933406,
+      "grad_norm": 6.262313365936279,
+      "learning_rate": 0.0,
+      "loss": 4.7609,
+      "step": 1
+    },
+    {
+      "epoch": 0.3619254433586681,
+      "grad_norm": 5.3237104415893555,
+      "learning_rate": 9.045248868778281e-06,
+      "loss": 3.5043,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3619254433586681,
+      "eval_cosine_accuracy": 0.9422711133956909,
+      "eval_loss": 1.1832270622253418,
+      "eval_runtime": 23.2175,
+      "eval_samples_per_second": 407.365,
+      "eval_steps_per_second": 1.594,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7238508867173362,
+      "grad_norm": 3.3922486305236816,
+      "learning_rate": 1.8095022624434392e-05,
+      "loss": 2.7005,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7238508867173362,
+      "eval_cosine_accuracy": 0.9441742300987244,
+      "eval_loss": 1.1732771396636963,
+      "eval_runtime": 22.575,
+      "eval_samples_per_second": 418.958,
+      "eval_steps_per_second": 1.639,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 3.309782028198242,
+      "learning_rate": 2.714027149321267e-05,
+      "loss": 2.2666,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "eval_cosine_accuracy": 0.9521040320396423,
+      "eval_loss": 1.1024649143218994,
+      "eval_runtime": 22.7494,
+      "eval_samples_per_second": 415.746,
+      "eval_steps_per_second": 1.626,
+      "step": 6000
+    },
+    {
+      "epoch": 1.447377938517179,
+      "grad_norm": 3.306711196899414,
+      "learning_rate": 3.618552036199096e-05,
+      "loss": 1.9975,
+      "step": 8000
+    },
+    {
+      "epoch": 1.447377938517179,
+      "eval_cosine_accuracy": 0.9572848677635193,
+      "eval_loss": 1.061951756477356,
+      "eval_runtime": 22.7651,
+      "eval_samples_per_second": 415.461,
+      "eval_steps_per_second": 1.625,
+      "step": 8000
+    },
+    {
+      "epoch": 1.8090415913200724,
+      "grad_norm": 2.8118510246276855,
+      "learning_rate": 4.523076923076923e-05,
+      "loss": 1.8105,
+      "step": 10000
+    },
+    {
+      "epoch": 1.8090415913200724,
+      "eval_cosine_accuracy": 0.9584478735923767,
+      "eval_loss": 1.00510835647583,
+      "eval_runtime": 22.6084,
+      "eval_samples_per_second": 418.34,
+      "eval_steps_per_second": 1.637,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1707052441229657,
+      "grad_norm": 2.829033613204956,
+      "learning_rate": 4.910376404872723e-05,
+      "loss": 1.6683,
+      "step": 12000
+    },
+    {
+      "epoch": 2.1707052441229657,
+      "eval_cosine_accuracy": 0.961091160774231,
+      "eval_loss": 1.0046641826629639,
+      "eval_runtime": 22.4829,
+      "eval_samples_per_second": 420.676,
+      "eval_steps_per_second": 1.646,
+      "step": 12000
+    },
+    {
+      "epoch": 2.532368896925859,
+      "grad_norm": 2.8044281005859375,
+      "learning_rate": 4.1742692441004384e-05,
+      "loss": 1.557,
+      "step": 14000
+    },
+    {
+      "epoch": 2.532368896925859,
+      "eval_cosine_accuracy": 0.9629942774772644,
+      "eval_loss": 0.9846329689025879,
+      "eval_runtime": 22.4278,
+      "eval_samples_per_second": 421.708,
+      "eval_steps_per_second": 1.65,
+      "step": 14000
+    },
+    {
+      "epoch": 2.8940325497287525,
+      "grad_norm": 2.797903060913086,
+      "learning_rate": 2.9123348123070232e-05,
+      "loss": 1.4912,
+      "step": 16000
+    },
+    {
+      "epoch": 2.8940325497287525,
+      "eval_cosine_accuracy": 0.9613025784492493,
+      "eval_loss": 0.9678560495376587,
+      "eval_runtime": 22.3028,
+      "eval_samples_per_second": 424.072,
+      "eval_steps_per_second": 1.659,
+      "step": 16000
+    },
+    {
+      "epoch": 3.2556962025316456,
+      "grad_norm": 2.7063376903533936,
+      "learning_rate": 1.5208545080075115e-05,
+      "loss": 1.4184,
+      "step": 18000
+    },
+    {
+      "epoch": 3.2556962025316456,
+      "eval_cosine_accuracy": 0.9626771211624146,
+      "eval_loss": 0.9667168259620667,
+      "eval_runtime": 23.5141,
+      "eval_samples_per_second": 402.227,
+      "eval_steps_per_second": 1.574,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6173598553345387,
+      "grad_norm": 2.8508188724517822,
+      "learning_rate": 4.365973814649421e-06,
+      "loss": 1.3816,
+      "step": 20000
+    },
+    {
+      "epoch": 3.6173598553345387,
+      "eval_cosine_accuracy": 0.963311493396759,
+      "eval_loss": 0.9683399796485901,
+      "eval_runtime": 22.4813,
+      "eval_samples_per_second": 420.705,
+      "eval_steps_per_second": 1.646,
+      "step": 20000
+    },
+    {
+      "epoch": 3.9790235081374323,
+      "grad_norm": 2.625483989715576,
+      "learning_rate": 1.2663979938210002e-08,
+      "loss": 1.377,
+      "step": 22000
+    },
+    {
+      "epoch": 3.9790235081374323,
+      "eval_cosine_accuracy": 0.9628885388374329,
+      "eval_loss": 0.9665988087654114,
+      "eval_runtime": 22.5665,
+      "eval_samples_per_second": 419.117,
+      "eval_steps_per_second": 1.64,
+      "step": 22000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 22104,
+  "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-22104/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b34f91400e58ea9238f7a23c07c9037ed5d214f69f310dc64a3a039ab32e884
+size 5624

checkpoint-22104/training_metrics.json

@@ -0,0 +1,72 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.3619254433586681,
+      "global_step": 2000,
+      "eval_loss": 1.1832270622253418,
+      "eval_cosine_accuracy": 0.9422711133956909
+    },
+    {
+      "epoch": 0.7238508867173362,
+      "global_step": 4000,
+      "eval_loss": 1.1732771396636963,
+      "eval_cosine_accuracy": 0.9441742300987244
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "global_step": 6000,
+      "eval_loss": 1.1024649143218994,
+      "eval_cosine_accuracy": 0.9521040320396423
+    },
+    {
+      "epoch": 1.447377938517179,
+      "global_step": 8000,
+      "eval_loss": 1.061951756477356,
+      "eval_cosine_accuracy": 0.9572848677635193
+    },
+    {
+      "epoch": 1.8090415913200724,
+      "global_step": 10000,
+      "eval_loss": 1.00510835647583,
+      "eval_cosine_accuracy": 0.9584478735923767
+    },
+    {
+      "epoch": 2.1707052441229657,
+      "global_step": 12000,
+      "eval_loss": 1.0046641826629639,
+      "eval_cosine_accuracy": 0.961091160774231
+    },
+    {
+      "epoch": 2.532368896925859,
+      "global_step": 14000,
+      "eval_loss": 0.9846329689025879,
+      "eval_cosine_accuracy": 0.9629942774772644
+    },
+    {
+      "epoch": 2.8940325497287525,
+      "global_step": 16000,
+      "eval_loss": 0.9678560495376587,
+      "eval_cosine_accuracy": 0.9613025784492493
+    },
+    {
+      "epoch": 3.2556962025316456,
+      "global_step": 18000,
+      "eval_loss": 0.9667168259620667,
+      "eval_cosine_accuracy": 0.9626771211624146
+    },
+    {
+      "epoch": 3.6173598553345387,
+      "global_step": 20000,
+      "eval_loss": 0.9683399796485901,
+      "eval_cosine_accuracy": 0.963311493396759
+    },
+    {
+      "epoch": 3.9790235081374323,
+      "global_step": 22000,
+      "eval_loss": 0.9665988087654114,
+      "eval_cosine_accuracy": 0.9628885388374329
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 22104
+}