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:a0ffe3d95ad9be4b6b6a1c8f74d3cb24ba2064f376eb66ea3bbfe2eb9c72163a
+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:d59dac9434e4ebf756114005a95cdd2a4ad30d23af08165fc78bae05b307c40d
+size 180607738

checkpoint-60000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55340929ca7b251b6f353cc8a92619876fe581aa5dc5ca385367eef5cdbef9be
+size 14244

checkpoint-60000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf6bd37a0b6ce40122f150a97821e5e540ac2c58f691b7be91594627015644e
+size 988

checkpoint-60000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d95f22ef94dd372e735b26eab455dd178f90f051da1fae18b470424eb140d39
+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": 1.4862889841214795,
+  "eval_steps": 10000,
+  "global_step": 60000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.477148306869132e-05,
+      "grad_norm": 5.107126712799072,
+      "learning_rate": 0.0,
+      "loss": 4.1291,
+      "step": 1
+    },
+    {
+      "epoch": 0.24771483068691322,
+      "grad_norm": 2.9285268783569336,
+      "learning_rate": 6.191166270313119e-06,
+      "loss": 3.116,
+      "step": 10000
+    },
+    {
+      "epoch": 0.24771483068691322,
+      "eval_cosine_accuracy": 0.9546271562576294,
+      "eval_loss": 0.7354477047920227,
+      "eval_runtime": 26.0737,
+      "eval_samples_per_second": 362.626,
+      "eval_steps_per_second": 0.729,
+      "step": 10000
+    },
+    {
+      "epoch": 0.49542966137382644,
+      "grad_norm": 2.5684168338775635,
+      "learning_rate": 1.2381713238208483e-05,
+      "loss": 2.4876,
+      "step": 20000
+    },
+    {
+      "epoch": 0.49542966137382644,
+      "eval_cosine_accuracy": 0.9588577747344971,
+      "eval_loss": 0.6964159607887268,
+      "eval_runtime": 26.9741,
+      "eval_samples_per_second": 350.521,
+      "eval_steps_per_second": 0.704,
+      "step": 20000
+    },
+    {
+      "epoch": 0.7431444920607396,
+      "grad_norm": 2.7329394817352295,
+      "learning_rate": 1.8571640903686088e-05,
+      "loss": 2.2784,
+      "step": 30000
+    },
+    {
+      "epoch": 0.7431444920607396,
+      "eval_cosine_accuracy": 0.9610788226127625,
+      "eval_loss": 0.6882680058479309,
+      "eval_runtime": 27.116,
+      "eval_samples_per_second": 348.687,
+      "eval_steps_per_second": 0.701,
+      "step": 30000
+    },
+    {
+      "epoch": 0.9908593227476529,
+      "grad_norm": 2.0247957706451416,
+      "learning_rate": 2.4761568569163697e-05,
+      "loss": 2.1763,
+      "step": 40000
+    },
+    {
+      "epoch": 0.9908593227476529,
+      "eval_cosine_accuracy": 0.9565309286117554,
+      "eval_loss": 0.7003008723258972,
+      "eval_runtime": 26.7473,
+      "eval_samples_per_second": 353.493,
+      "eval_steps_per_second": 0.71,
+      "step": 40000
+    },
+    {
+      "epoch": 1.2385741534345662,
+      "grad_norm": 2.110393762588501,
+      "learning_rate": 3.0952734839476816e-05,
+      "loss": 2.1013,
+      "step": 50000
+    },
+    {
+      "epoch": 1.2385741534345662,
+      "eval_cosine_accuracy": 0.9638286828994751,
+      "eval_loss": 0.6568410992622375,
+      "eval_runtime": 27.7548,
+      "eval_samples_per_second": 340.661,
+      "eval_steps_per_second": 0.685,
+      "step": 50000
+    },
+    {
+      "epoch": 1.4862889841214795,
+      "grad_norm": 1.90959894657135,
+      "learning_rate": 3.7142662504954425e-05,
+      "loss": 2.0239,
+      "step": 60000
+    },
+    {
+      "epoch": 1.4862889841214795,
+      "eval_cosine_accuracy": 0.964040219783783,
+      "eval_loss": 0.627728283405304,
+      "eval_runtime": 27.4598,
+      "eval_samples_per_second": 344.321,
+      "eval_steps_per_second": 0.692,
+      "step": 60000
+    }
+  ],
+  "logging_steps": 10000,
+  "max_steps": 161476,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 30000,
+  "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 sha256:9fb298a9aecd230533dd4ba4cfcb9a181b81a9d75b55968e96b0570f2ee4969a
+size 5624

checkpoint-60000/training_metrics.json

@@ -0,0 +1,42 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.24771483068691322,
+      "global_step": 10000,
+      "eval_loss": 0.7354477047920227,
+      "eval_cosine_accuracy": 0.9546271562576294
+    },
+    {
+      "epoch": 0.49542966137382644,
+      "global_step": 20000,
+      "eval_loss": 0.6964159607887268,
+      "eval_cosine_accuracy": 0.9588577747344971
+    },
+    {
+      "epoch": 0.7431444920607396,
+      "global_step": 30000,
+      "eval_loss": 0.6882680058479309,
+      "eval_cosine_accuracy": 0.9610788226127625
+    },
+    {
+      "epoch": 0.9908593227476529,
+      "global_step": 40000,
+      "eval_loss": 0.7003008723258972,
+      "eval_cosine_accuracy": 0.9565309286117554
+    },
+    {
+      "epoch": 1.2385741534345662,
+      "global_step": 50000,
+      "eval_loss": 0.6568410992622375,
+      "eval_cosine_accuracy": 0.9638286828994751
+    },
+    {
+      "epoch": 1.4862889841214795,
+      "global_step": 60000,
+      "eval_loss": 0.627728283405304,
+      "eval_cosine_accuracy": 0.964040219783783
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 60000
+}