Training checkpoint - Epoch 1, Step 60000

checkpoint-60000/1_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-60000/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-60000/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-60000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4993a9ce84d09ec766d16bd1fd8b57a18cee6df1b4097bcfb71c4c24b9fc8f
+size 90864192

checkpoint-60000/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-60000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a1a081dd10e1416b8c7617b7bb6ed1916f499cf8785d5f09e289c3d9cca03b
+size 180607738

checkpoint-60000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb2834ec163d2416200ed6e9a85adab6d4a78b031d86270fb89d5295f2542fd
+size 14244

checkpoint-60000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8dae4393c167bd70d32b16d8177fd63b4e64aff7df734eda7e1fde5cf1c852
+size 988

checkpoint-60000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d3f24dfc8d1f77746f4b538fc8d67d8d07c35c6447da1b8d610a77e75575c9
+size 1064

checkpoint-60000/sentence_bert_config.json

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

checkpoint-60000/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-60000/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-60000/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2219959266802445,
+  "eval_steps": 10000,
+  "global_step": 60000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0366598778004072e-05,
+      "grad_norm": 5.12221622467041,
+      "learning_rate": 0.0,
+      "loss": 3.9041,
+      "step": 1
+    },
+    {
+      "epoch": 0.20366598778004075,
+      "grad_norm": 3.2589175701141357,
+      "learning_rate": 3.0538300169046214e-06,
+      "loss": 3.1019,
+      "step": 10000
+    },
+    {
+      "epoch": 0.20366598778004075,
+      "eval_cosine_accuracy": 0.9558963775634766,
+      "eval_loss": 0.7072300314903259,
+      "eval_runtime": 26.2631,
+      "eval_samples_per_second": 360.011,
+      "eval_steps_per_second": 0.723,
+      "step": 10000
+    },
+    {
+      "epoch": 0.4073319755600815,
+      "grad_norm": 3.009838104248047,
+      "learning_rate": 6.107965539013015e-06,
+      "loss": 2.4816,
+      "step": 20000
+    },
+    {
+      "epoch": 0.4073319755600815,
+      "eval_cosine_accuracy": 0.9631940722465515,
+      "eval_loss": 0.6796981692314148,
+      "eval_runtime": 27.0569,
+      "eval_samples_per_second": 349.448,
+      "eval_steps_per_second": 0.702,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6109979633401222,
+      "grad_norm": 2.8665454387664795,
+      "learning_rate": 9.161490050713865e-06,
+      "loss": 2.2429,
+      "step": 30000
+    },
+    {
+      "epoch": 0.6109979633401222,
+      "eval_cosine_accuracy": 0.9656266570091248,
+      "eval_loss": 0.6776911020278931,
+      "eval_runtime": 27.1462,
+      "eval_samples_per_second": 348.299,
+      "eval_steps_per_second": 0.7,
+      "step": 30000
+    },
+    {
+      "epoch": 0.814663951120163,
+      "grad_norm": 2.6346378326416016,
+      "learning_rate": 1.2215625572822259e-05,
+      "loss": 2.0977,
+      "step": 40000
+    },
+    {
+      "epoch": 0.814663951120163,
+      "eval_cosine_accuracy": 0.9663670063018799,
+      "eval_loss": 0.6755352020263672,
+      "eval_runtime": 27.1553,
+      "eval_samples_per_second": 348.183,
+      "eval_steps_per_second": 0.7,
+      "step": 40000
+    },
+    {
+      "epoch": 1.0183299389002036,
+      "grad_norm": 2.571259021759033,
+      "learning_rate": 1.5269150084523106e-05,
+      "loss": 2.0487,
+      "step": 50000
+    },
+    {
+      "epoch": 1.0183299389002036,
+      "eval_cosine_accuracy": 0.9670015573501587,
+      "eval_loss": 0.658900797367096,
+      "eval_runtime": 34.6686,
+      "eval_samples_per_second": 272.725,
+      "eval_steps_per_second": 0.548,
+      "step": 50000
+    },
+    {
+      "epoch": 1.2219959266802445,
+      "grad_norm": 2.607664108276367,
+      "learning_rate": 1.832298010142773e-05,
+      "loss": 1.9234,
+      "step": 60000
+    },
+    {
+      "epoch": 1.2219959266802445,
+      "eval_cosine_accuracy": 0.9677419066429138,
+      "eval_loss": 0.6515311598777771,
+      "eval_runtime": 30.1727,
+      "eval_samples_per_second": 313.362,
+      "eval_steps_per_second": 0.63,
+      "step": 60000
+    }
+  ],
+  "logging_steps": 10000,
+  "max_steps": 196400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 20000,
+  "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": 512,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-60000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6823f202b89703fc0dac1ef1c30cc8d7b673d418ad1ed2e22c35ee3119a77a9
+size 5624

checkpoint-60000/training_metrics.json

@@ -0,0 +1,42 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.20366598778004075,
+      "global_step": 10000,
+      "eval_loss": 0.7072300314903259,
+      "eval_cosine_accuracy": 0.9558963775634766
+    },
+    {
+      "epoch": 0.4073319755600815,
+      "global_step": 20000,
+      "eval_loss": 0.6796981692314148,
+      "eval_cosine_accuracy": 0.9631940722465515
+    },
+    {
+      "epoch": 0.6109979633401222,
+      "global_step": 30000,
+      "eval_loss": 0.6776911020278931,
+      "eval_cosine_accuracy": 0.9656266570091248
+    },
+    {
+      "epoch": 0.814663951120163,
+      "global_step": 40000,
+      "eval_loss": 0.6755352020263672,
+      "eval_cosine_accuracy": 0.9663670063018799
+    },
+    {
+      "epoch": 1.0183299389002036,
+      "global_step": 50000,
+      "eval_loss": 0.658900797367096,
+      "eval_cosine_accuracy": 0.9670015573501587
+    },
+    {
+      "epoch": 1.2219959266802445,
+      "global_step": 60000,
+      "eval_loss": 0.6515311598777771,
+      "eval_cosine_accuracy": 0.9677419066429138
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 60000
+}