Training checkpoint - Epoch 3, Step 14255

checkpoint-14255/1_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-14255/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-14255/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-14255/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970c4a46dc423c7a4b481277c133fcfb4c93a0acde64694189013c6fa393871d
+size 90864192

checkpoint-14255/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-14255/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7badfade03bbea5151707e3dda56786469352ad1ec0d246b43a4cc82d5ceaf14
+size 180607738

checkpoint-14255/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8ef8075a22e7eef5de43a0c5c42ab8c96b152b7fadd7d50ffb715724fb5fb3
+size 14244

checkpoint-14255/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30f74ab8cecad219d6a7ff7631715b690abbfc7b96627895df5c8ab542347e3
+size 988

checkpoint-14255/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e1e356a1c11d3b7c4ba3f532c84361d115ba7124664a0bba8502f0176209ef
+size 1064

checkpoint-14255/sentence_bert_config.json

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

checkpoint-14255/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-14255/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-14255/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 2000,
+  "global_step": 14255,
+  "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": 3.0695738792419434,
+      "learning_rate": 1.2630581297388374e-05,
+      "loss": 2.308,
+      "step": 2000
+    },
+    {
+      "epoch": 0.42118563756975885,
+      "eval_cosine_accuracy": 0.9454372525215149,
+      "eval_loss": 0.6986740827560425,
+      "eval_runtime": 27.458,
+      "eval_samples_per_second": 344.417,
+      "eval_steps_per_second": 1.348,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "grad_norm": 3.1511430740356445,
+      "learning_rate": 2.5261162594776748e-05,
+      "loss": 1.522,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "eval_cosine_accuracy": 0.95579993724823,
+      "eval_loss": 0.6609594821929932,
+      "eval_runtime": 24.6873,
+      "eval_samples_per_second": 383.071,
+      "eval_steps_per_second": 1.499,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "grad_norm": 2.732968807220459,
+      "learning_rate": 2.943386210681441e-05,
+      "loss": 1.1721,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "eval_cosine_accuracy": 0.9589722156524658,
+      "eval_loss": 0.6233465671539307,
+      "eval_runtime": 25.2523,
+      "eval_samples_per_second": 374.5,
+      "eval_steps_per_second": 1.465,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "grad_norm": 2.4099602699279785,
+      "learning_rate": 2.6310608286843795e-05,
+      "loss": 0.9996,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "eval_cosine_accuracy": 0.9600296020507812,
+      "eval_loss": 0.6062663197517395,
+      "eval_runtime": 24.7031,
+      "eval_samples_per_second": 382.827,
+      "eval_steps_per_second": 1.498,
+      "step": 8000
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "grad_norm": 2.451180934906006,
+      "learning_rate": 2.1026228420758655e-05,
+      "loss": 0.9141,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "eval_cosine_accuracy": 0.9625673890113831,
+      "eval_loss": 0.5867218375205994,
+      "eval_runtime": 25.2151,
+      "eval_samples_per_second": 375.054,
+      "eval_steps_per_second": 1.467,
+      "step": 10000
+    },
+    {
+      "epoch": 2.525618095739085,
+      "grad_norm": 2.2834866046905518,
+      "learning_rate": 1.4589933019587175e-05,
+      "loss": 0.8452,
+      "step": 12000
+    },
+    {
+      "epoch": 2.525618095739085,
+      "eval_cosine_accuracy": 0.9654224514961243,
+      "eval_loss": 0.5581304430961609,
+      "eval_runtime": 24.5477,
+      "eval_samples_per_second": 385.249,
+      "eval_steps_per_second": 1.507,
+      "step": 12000
+    },
+    {
+      "epoch": 2.946449237243556,
+      "grad_norm": 2.1983766555786133,
+      "learning_rate": 8.229070615242187e-06,
+      "loss": 0.8155,
+      "step": 14000
+    },
+    {
+      "epoch": 2.946449237243556,
+      "eval_cosine_accuracy": 0.965951144695282,
+      "eval_loss": 0.5614117980003357,
+      "eval_runtime": 24.671,
+      "eval_samples_per_second": 383.325,
+      "eval_steps_per_second": 1.5,
+      "step": 14000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 18996,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-14255/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec21ce91e3df3ade500b048372527c4d77189c63423f4d0e2c7da9e882272d5
+size 5624

checkpoint-14255/training_metrics.json

@@ -0,0 +1,48 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.42118563756975885,
+      "global_step": 2000,
+      "eval_loss": 0.6986740827560425,
+      "eval_cosine_accuracy": 0.9454372525215149
+    },
+    {
+      "epoch": 0.8423712751395177,
+      "global_step": 4000,
+      "eval_loss": 0.6609594821929932,
+      "eval_cosine_accuracy": 0.95579993724823
+    },
+    {
+      "epoch": 1.2632298790110468,
+      "global_step": 6000,
+      "eval_loss": 0.6233465671539307,
+      "eval_cosine_accuracy": 0.9589722156524658
+    },
+    {
+      "epoch": 1.6840610205155182,
+      "global_step": 8000,
+      "eval_loss": 0.6062663197517395,
+      "eval_cosine_accuracy": 0.9600296020507812
+    },
+    {
+      "epoch": 2.1047869542346134,
+      "global_step": 10000,
+      "eval_loss": 0.5867218375205994,
+      "eval_cosine_accuracy": 0.9625673890113831
+    },
+    {
+      "epoch": 2.525618095739085,
+      "global_step": 12000,
+      "eval_loss": 0.5581304430961609,
+      "eval_cosine_accuracy": 0.9654224514961243
+    },
+    {
+      "epoch": 2.946449237243556,
+      "global_step": 14000,
+      "eval_loss": 0.5614117980003357,
+      "eval_cosine_accuracy": 0.965951144695282
+    }
+  ],
+  "current_epoch": 3,
+  "global_step": 14255
+}