Lettria/debug_finetuning_model_tuesday-morning

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.3.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eval/binary_classification_evaluation_BinaryClassifEval_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+1.0,1848,0.9985443959243085,-0.20544850826263428,0.9992716678805535,1.0,0.9985443959243085,-0.20544850826263428,1.0,0.0
+2.0,3696,0.9985443959243085,-0.1559901237487793,0.9992716678805535,1.0,0.9985443959243085,-0.1559901237487793,1.0,0.0
+3.0,5544,0.9985443959243085,-0.23389852046966553,0.9992716678805535,1.0,0.9985443959243085,-0.23389852046966553,1.0,0.0
+4.0,7392,0.9985443959243085,-0.1840038299560547,0.9992716678805535,1.0,0.9985443959243085,-0.1840038299560547,1.0,0.0
+5.0,9240,0.9985443959243085,-0.13899779319763184,0.9992716678805535,1.0,0.9985443959243085,-0.13899779319763184,1.0,0.0
+6.0,11088,0.9985443959243085,-0.2695996165275574,0.9992716678805535,1.0,0.9985443959243085,-0.2695996165275574,1.0,0.0
+7.0,12936,0.9985443959243085,-0.08752036094665527,0.9992716678805535,1.0,0.9985443959243085,-0.08752036094665527,1.0,0.0
+8.0,14784,0.9985443959243085,-0.2031029462814331,0.9992716678805535,1.0,0.9985443959243085,-0.2031029462814331,1.0,0.0
+9.0,16632,0.9985443959243085,-0.18599945306777954,0.9992716678805535,1.0,0.9985443959243085,-0.18599945306777954,1.0,0.0
+10.0,18480,0.9985443959243085,-0.1892727017402649,0.9992716678805535,1.0,0.9985443959243085,-0.1892727017402649,1.0,0.0
+10.0,18480,0.9985443959243085,-0.1892727017402649,0.9992716678805535,1.0,0.9985443959243085,-0.1892727017402649,1.0,0.0

eval/similarity_evaluation_EmbeddingSimEval_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine_pearson,cosine_spearman
+1.0,1848,nan,nan
+2.0,3696,nan,nan
+3.0,5544,nan,nan
+4.0,7392,nan,nan
+5.0,9240,nan,nan
+6.0,11088,nan,nan
+7.0,12936,nan,nan
+8.0,14784,nan,nan
+9.0,16632,nan,nan
+10.0,18480,nan,nan
+10.0,18480,nan,nan

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f90b4d6e11296c705426ec15434a5fc62ffc64b080f7bff6befb00cbbe48488
+size 437951328

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"
+  }
+]

runs/Feb25_08-42-58_algo-1/events.out.tfevents.1740472979.algo-1.62.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b06e80997548a5c44aaded1c6616ae1c4b376eae437fc2f2707793b46d1a8e
+size 145943

runs/Feb25_08-42-58_algo-1/events.out.tfevents.1740474369.algo-1.62.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c50c4f4d26a77a7ebb9ecef1360e65fb29adcba7ecce151c0184236e1d48256
+size 1198

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e87b4404cfc2e76f838eeb91aaae77e9593521c9e08369324ce5fd40bc1f22
+size 5624