Upload training checkpoints: RuModernBERT-base_bs64_lr_2e-05

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "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
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/config.json

@@ -0,0 +1,81 @@
+{
+  "activation_function": "gelu",
+  "allow_embedding_resizing": true,
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_layer": "rope",
+  "attention_probs_dropout_prob": 0.0,
+  "attn_out_bias": false,
+  "attn_out_dropout_prob": 0.1,
+  "attn_qkv_bias": false,
+  "bert_layer": "prenorm",
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "compile_model": true,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embed_dropout_prob": 0.0,
+  "embed_norm": true,
+  "embedding_dropout": 0.0,
+  "embedding_layer": "sans_pos",
+  "eos_token_id": 50282,
+  "final_norm": true,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "head_pred_act": "gelu",
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "init_method": "full_megatron",
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "local_attention": 128,
+  "local_attn_rotary_emb_base": 10000.0,
+  "local_rope_theta": 10000.0,
+  "loss_function": "fa_cross_entropy",
+  "loss_kwargs": {
+    "reduction": "mean"
+  },
+  "masked_prediction": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "mlp_dropout_prob": 0.0,
+  "mlp_in_bias": false,
+  "mlp_layer": "glu",
+  "mlp_out_bias": false,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "norm_kwargs": {
+    "bias": false,
+    "eps": 1e-05
+  },
+  "normalization": "layernorm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "padding": "unpadded",
+  "repad_logits_with_grad": false,
+  "rotary_emb_base": 160000.0,
+  "rotary_emb_dim": null,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "sep_token_id": 50282,
+  "skip_first_prenorm": true,
+  "sliding_window": 128,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "unpad_embeddings": true,
+  "vocab_size": 50368
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.52.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6ad3944b158a6c2d9cb2102375034c7cb108c800cf2fe00f660bc79c6ae93b
+size 596070136

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feff5a7965048e49b0061cca36c1e37eb732ef85a3419ba60782ff1173b0dc14
+size 1192227066

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e343b73b06a45201065a722c79e442474d0f13ff859fc2ea36e1dba47f0bcc
+size 14244

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08279a26896d430ef7860ac16b79b517f35867ddd6806157bee25500c5bf8ecd
+size 988

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcc0b0b64212157cf8f5c452da035fdf065ca43ee1b42daf1b6d468678af651
+size 1064

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 8192,
+    "do_lower_case": false
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[PAD]",
+    "[MASK]"
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "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
+  }
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/tokenizer_config.json

@@ -0,0 +1,961 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[PAD]",
+    "[MASK]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 8192,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/trainer_state.json

@@ -0,0 +1,1598 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.16590695663590196,
+  "eval_steps": 2000,
+  "global_step": 12400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013379615653815824,
+      "grad_norm": 1593.7158203125,
+      "learning_rate": 1.1907150979998663e-07,
+      "loss": 272.0406,
+      "step": 100
+    },
+    {
+      "epoch": 0.002675923130763165,
+      "grad_norm": 830.271484375,
+      "learning_rate": 2.5018395879323036e-07,
+      "loss": 259.1632,
+      "step": 200
+    },
+    {
+      "epoch": 0.004013884696144747,
+      "grad_norm": 957.25537109375,
+      "learning_rate": 3.839721720516423e-07,
+      "loss": 235.0577,
+      "step": 300
+    },
+    {
+      "epoch": 0.00535184626152633,
+      "grad_norm": 446.388916015625,
+      "learning_rate": 5.177603853100542e-07,
+      "loss": 229.0209,
+      "step": 400
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "grad_norm": 900.2640991210938,
+      "learning_rate": 6.515485985684662e-07,
+      "loss": 229.5855,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_codesearchnet_loss": 11.501143455505371,
+      "eval_codesearchnet_runtime": 861.5274,
+      "eval_codesearchnet_samples_per_second": 34.822,
+      "eval_codesearchnet_steps_per_second": 2.176,
+      "eval_cosine_accuracy@1": 0.18823333333333334,
+      "eval_cosine_accuracy@10": 0.30396666666666666,
+      "eval_cosine_accuracy@3": 0.24886666666666668,
+      "eval_cosine_accuracy@5": 0.2738,
+      "eval_cosine_map@100": 0.22870242076259673,
+      "eval_cosine_mrr@10": 0.22479973544973395,
+      "eval_cosine_ndcg@10": 0.24378814726804346,
+      "eval_cosine_precision@1": 0.18823333333333334,
+      "eval_cosine_precision@10": 0.03039666666666667,
+      "eval_cosine_precision@3": 0.08295555555555555,
+      "eval_cosine_precision@5": 0.054759999999999996,
+      "eval_cosine_recall@1": 0.18823333333333334,
+      "eval_cosine_recall@10": 0.30396666666666666,
+      "eval_cosine_recall@3": 0.24886666666666668,
+      "eval_cosine_recall@5": 0.2738,
+      "eval_sequential_score": 0.2087706265726278,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_codesearchnet_en_loss": 10.62355899810791,
+      "eval_codesearchnet_en_runtime": 525.6255,
+      "eval_codesearchnet_en_samples_per_second": 57.075,
+      "eval_codesearchnet_en_steps_per_second": 3.567,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 217.4482,
+      "eval_codesearchnet_pairs_samples_per_second": 137.964,
+      "eval_codesearchnet_pairs_steps_per_second": 8.623,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_solyanka_qa_loss": 10.61404800415039,
+      "eval_solyanka_qa_runtime": 30.6194,
+      "eval_solyanka_qa_samples_per_second": 163.295,
+      "eval_solyanka_qa_steps_per_second": 10.222,
+      "step": 500
+    },
+    {
+      "epoch": 0.008027769392289495,
+      "grad_norm": 862.380859375,
+      "learning_rate": 7.85336811826878e-07,
+      "loss": 222.2825,
+      "step": 600
+    },
+    {
+      "epoch": 0.009365730957671077,
+      "grad_norm": 686.0302124023438,
+      "learning_rate": 9.191250250852901e-07,
+      "loss": 224.0132,
+      "step": 700
+    },
+    {
+      "epoch": 0.01070369252305266,
+      "grad_norm": 382.3077392578125,
+      "learning_rate": 1.052913238343702e-06,
+      "loss": 220.4923,
+      "step": 800
+    },
+    {
+      "epoch": 0.012041654088434241,
+      "grad_norm": 534.106201171875,
+      "learning_rate": 1.186701451602114e-06,
+      "loss": 221.8868,
+      "step": 900
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "grad_norm": 544.294921875,
+      "learning_rate": 1.3204896648605259e-06,
+      "loss": 217.3524,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_codesearchnet_loss": 11.611088752746582,
+      "eval_codesearchnet_runtime": 868.6178,
+      "eval_codesearchnet_samples_per_second": 34.538,
+      "eval_codesearchnet_steps_per_second": 2.159,
+      "eval_cosine_accuracy@1": 0.21566666666666667,
+      "eval_cosine_accuracy@10": 0.3415666666666667,
+      "eval_cosine_accuracy@3": 0.28136666666666665,
+      "eval_cosine_accuracy@5": 0.30943333333333334,
+      "eval_cosine_map@100": 0.25975150872269276,
+      "eval_cosine_mrr@10": 0.2554449603174578,
+      "eval_cosine_ndcg@10": 0.276100097940374,
+      "eval_cosine_precision@1": 0.21566666666666667,
+      "eval_cosine_precision@10": 0.03415666666666667,
+      "eval_cosine_precision@3": 0.09378888888888888,
+      "eval_cosine_precision@5": 0.061886666666666666,
+      "eval_cosine_recall@1": 0.21566666666666667,
+      "eval_cosine_recall@10": 0.3415666666666667,
+      "eval_cosine_recall@3": 0.28136666666666665,
+      "eval_cosine_recall@5": 0.30943333333333334,
+      "eval_sequential_score": 0.22303526950392608,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_codesearchnet_en_loss": 10.429346084594727,
+      "eval_codesearchnet_en_runtime": 530.1187,
+      "eval_codesearchnet_en_samples_per_second": 56.591,
+      "eval_codesearchnet_en_steps_per_second": 3.537,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 218.5444,
+      "eval_codesearchnet_pairs_samples_per_second": 137.272,
+      "eval_codesearchnet_pairs_steps_per_second": 8.579,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_solyanka_qa_loss": 10.338957786560059,
+      "eval_solyanka_qa_runtime": 31.4753,
+      "eval_solyanka_qa_samples_per_second": 158.855,
+      "eval_solyanka_qa_steps_per_second": 9.944,
+      "step": 1000
+    },
+    {
+      "epoch": 0.014717577219197408,
+      "grad_norm": 540.063720703125,
+      "learning_rate": 1.4542778781189378e-06,
+      "loss": 206.4545,
+      "step": 1100
+    },
+    {
+      "epoch": 0.01605553878457899,
+      "grad_norm": 830.7228393554688,
+      "learning_rate": 1.5880660913773498e-06,
+      "loss": 214.426,
+      "step": 1200
+    },
+    {
+      "epoch": 0.017393500349960574,
+      "grad_norm": 597.8634643554688,
+      "learning_rate": 1.7218543046357616e-06,
+      "loss": 217.0942,
+      "step": 1300
+    },
+    {
+      "epoch": 0.018731461915342154,
+      "grad_norm": 700.58349609375,
+      "learning_rate": 1.8556425178941738e-06,
+      "loss": 212.094,
+      "step": 1400
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "grad_norm": 612.1179809570312,
+      "learning_rate": 1.9894307311525855e-06,
+      "loss": 220.9056,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_codesearchnet_loss": 11.045117378234863,
+      "eval_codesearchnet_runtime": 866.9128,
+      "eval_codesearchnet_samples_per_second": 34.606,
+      "eval_codesearchnet_steps_per_second": 2.163,
+      "eval_cosine_accuracy@1": 0.23076666666666668,
+      "eval_cosine_accuracy@10": 0.3757333333333333,
+      "eval_cosine_accuracy@3": 0.3079,
+      "eval_cosine_accuracy@5": 0.3379,
+      "eval_cosine_map@100": 0.28190035706940875,
+      "eval_cosine_mrr@10": 0.27684927248677,
+      "eval_cosine_ndcg@10": 0.3005750904599357,
+      "eval_cosine_precision@1": 0.23076666666666668,
+      "eval_cosine_precision@10": 0.037573333333333334,
+      "eval_cosine_precision@3": 0.10263333333333333,
+      "eval_cosine_precision@5": 0.06758,
+      "eval_cosine_recall@1": 0.23076666666666668,
+      "eval_cosine_recall@10": 0.3757333333333333,
+      "eval_cosine_recall@3": 0.3079,
+      "eval_cosine_recall@5": 0.3379,
+      "eval_sequential_score": 0.24193695292620615,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_codesearchnet_en_loss": 9.401904106140137,
+      "eval_codesearchnet_en_runtime": 532.7041,
+      "eval_codesearchnet_en_samples_per_second": 56.316,
+      "eval_codesearchnet_en_steps_per_second": 3.52,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 220.2554,
+      "eval_codesearchnet_pairs_samples_per_second": 136.205,
+      "eval_codesearchnet_pairs_steps_per_second": 8.513,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_solyanka_qa_loss": 9.384902000427246,
+      "eval_solyanka_qa_runtime": 32.4876,
+      "eval_solyanka_qa_samples_per_second": 153.905,
+      "eval_solyanka_qa_steps_per_second": 9.634,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02140738504610532,
+      "grad_norm": 974.6611938476562,
+      "learning_rate": 2.1232189444109977e-06,
+      "loss": 207.0585,
+      "step": 1600
+    },
+    {
+      "epoch": 0.022745346611486902,
+      "grad_norm": 738.9705810546875,
+      "learning_rate": 2.2570071576694095e-06,
+      "loss": 210.1663,
+      "step": 1700
+    },
+    {
+      "epoch": 0.024083308176868483,
+      "grad_norm": 1021.1400756835938,
+      "learning_rate": 2.3907953709278212e-06,
+      "loss": 218.8182,
+      "step": 1800
+    },
+    {
+      "epoch": 0.025421269742250067,
+      "grad_norm": 802.8325805664062,
+      "learning_rate": 2.524583584186233e-06,
+      "loss": 215.3143,
+      "step": 1900
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "grad_norm": 1093.64013671875,
+      "learning_rate": 2.6583717974446456e-06,
+      "loss": 218.6588,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_codesearchnet_loss": 9.979716300964355,
+      "eval_codesearchnet_runtime": 866.9971,
+      "eval_codesearchnet_samples_per_second": 34.602,
+      "eval_codesearchnet_steps_per_second": 2.163,
+      "eval_cosine_accuracy@1": 0.24446666666666667,
+      "eval_cosine_accuracy@10": 0.42646666666666666,
+      "eval_cosine_accuracy@3": 0.34023333333333333,
+      "eval_cosine_accuracy@5": 0.3771,
+      "eval_cosine_map@100": 0.3082119579214764,
+      "eval_cosine_mrr@10": 0.3019686111111121,
+      "eval_cosine_ndcg@10": 0.33179718595033053,
+      "eval_cosine_precision@1": 0.24446666666666667,
+      "eval_cosine_precision@10": 0.04264666666666667,
+      "eval_cosine_precision@3": 0.1134111111111111,
+      "eval_cosine_precision@5": 0.07542,
+      "eval_cosine_recall@1": 0.24446666666666667,
+      "eval_cosine_recall@10": 0.42646666666666666,
+      "eval_cosine_recall@3": 0.34023333333333333,
+      "eval_cosine_recall@5": 0.3771,
+      "eval_sequential_score": 0.26055948736028667,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_codesearchnet_en_loss": 7.814389705657959,
+      "eval_codesearchnet_en_runtime": 534.4064,
+      "eval_codesearchnet_en_samples_per_second": 56.137,
+      "eval_codesearchnet_en_steps_per_second": 3.509,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 214.7347,
+      "eval_codesearchnet_pairs_samples_per_second": 139.707,
+      "eval_codesearchnet_pairs_steps_per_second": 8.732,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_solyanka_qa_loss": 8.106107711791992,
+      "eval_solyanka_qa_runtime": 32.6063,
+      "eval_solyanka_qa_samples_per_second": 153.345,
+      "eval_solyanka_qa_steps_per_second": 9.599,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02809719287301323,
+      "grad_norm": 811.26904296875,
+      "learning_rate": 2.7921600107030574e-06,
+      "loss": 205.0786,
+      "step": 2100
+    },
+    {
+      "epoch": 0.029435154438394815,
+      "grad_norm": 1056.2335205078125,
+      "learning_rate": 2.9259482239614696e-06,
+      "loss": 204.1811,
+      "step": 2200
+    },
+    {
+      "epoch": 0.030773116003776396,
+      "grad_norm": 1020.6990356445312,
+      "learning_rate": 3.0597364372198813e-06,
+      "loss": 212.5886,
+      "step": 2300
+    },
+    {
+      "epoch": 0.03211107756915798,
+      "grad_norm": 1026.921630859375,
+      "learning_rate": 3.193524650478293e-06,
+      "loss": 206.9817,
+      "step": 2400
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "grad_norm": 731.8707275390625,
+      "learning_rate": 3.3273128637367053e-06,
+      "loss": 205.3238,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_codesearchnet_loss": 9.194226264953613,
+      "eval_codesearchnet_runtime": 870.7103,
+      "eval_codesearchnet_samples_per_second": 34.455,
+      "eval_codesearchnet_steps_per_second": 2.153,
+      "eval_cosine_accuracy@1": 0.3000333333333333,
+      "eval_cosine_accuracy@10": 0.49573333333333336,
+      "eval_cosine_accuracy@3": 0.4056,
+      "eval_cosine_accuracy@5": 0.4457333333333333,
+      "eval_cosine_map@100": 0.3686168427553011,
+      "eval_cosine_mrr@10": 0.36286292328043074,
+      "eval_cosine_ndcg@10": 0.3947834611601081,
+      "eval_cosine_precision@1": 0.3000333333333333,
+      "eval_cosine_precision@10": 0.04957333333333334,
+      "eval_cosine_precision@3": 0.1352,
+      "eval_cosine_precision@5": 0.08914666666666665,
+      "eval_cosine_recall@1": 0.3000333333333333,
+      "eval_cosine_recall@10": 0.49573333333333336,
+      "eval_cosine_recall@3": 0.4056,
+      "eval_cosine_recall@5": 0.4457333333333333,
+      "eval_sequential_score": 0.3197606115350484,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_codesearchnet_en_loss": 6.940033435821533,
+      "eval_codesearchnet_en_runtime": 530.0387,
+      "eval_codesearchnet_en_samples_per_second": 56.6,
+      "eval_codesearchnet_en_steps_per_second": 3.537,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 222.2001,
+      "eval_codesearchnet_pairs_samples_per_second": 135.013,
+      "eval_codesearchnet_pairs_steps_per_second": 8.438,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_solyanka_qa_loss": 6.828629493713379,
+      "eval_solyanka_qa_runtime": 32.3285,
+      "eval_solyanka_qa_samples_per_second": 154.662,
+      "eval_solyanka_qa_steps_per_second": 9.682,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03478700069992115,
+      "grad_norm": 937.7930908203125,
+      "learning_rate": 3.461101076995117e-06,
+      "loss": 206.5246,
+      "step": 2600
+    },
+    {
+      "epoch": 0.03612496226530273,
+      "grad_norm": 4948.39794921875,
+      "learning_rate": 3.594889290253529e-06,
+      "loss": 207.9754,
+      "step": 2700
+    },
+    {
+      "epoch": 0.03746292383068431,
+      "grad_norm": 831.9579467773438,
+      "learning_rate": 3.728677503511941e-06,
+      "loss": 202.3154,
+      "step": 2800
+    },
+    {
+      "epoch": 0.03880088539606589,
+      "grad_norm": 1097.06640625,
+      "learning_rate": 3.862465716770352e-06,
+      "loss": 193.8885,
+      "step": 2900
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "grad_norm": 897.6323852539062,
+      "learning_rate": 3.996253930028765e-06,
+      "loss": 210.3421,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_codesearchnet_loss": 6.052410125732422,
+      "eval_codesearchnet_runtime": 870.4612,
+      "eval_codesearchnet_samples_per_second": 34.464,
+      "eval_codesearchnet_steps_per_second": 2.154,
+      "eval_cosine_accuracy@1": 0.5397333333333333,
+      "eval_cosine_accuracy@10": 0.7488333333333334,
+      "eval_cosine_accuracy@3": 0.6638,
+      "eval_cosine_accuracy@5": 0.7044666666666667,
+      "eval_cosine_map@100": 0.6148666000208418,
+      "eval_cosine_mrr@10": 0.6105341666666715,
+      "eval_cosine_ndcg@10": 0.6440482320852767,
+      "eval_cosine_precision@1": 0.5397333333333333,
+      "eval_cosine_precision@10": 0.07488333333333333,
+      "eval_cosine_precision@3": 0.22126666666666664,
+      "eval_cosine_precision@5": 0.14089333333333331,
+      "eval_cosine_recall@1": 0.5397333333333333,
+      "eval_cosine_recall@10": 0.7488333333333334,
+      "eval_cosine_recall@3": 0.6638,
+      "eval_cosine_recall@5": 0.7044666666666667,
+      "eval_sequential_score": 0.5582850083065141,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_codesearchnet_en_loss": 4.175703048706055,
+      "eval_codesearchnet_en_runtime": 533.1214,
+      "eval_codesearchnet_en_samples_per_second": 56.272,
+      "eval_codesearchnet_en_steps_per_second": 3.517,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 218.5646,
+      "eval_codesearchnet_pairs_samples_per_second": 137.259,
+      "eval_codesearchnet_pairs_steps_per_second": 8.579,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_solyanka_qa_loss": 4.920586585998535,
+      "eval_solyanka_qa_runtime": 32.539,
+      "eval_solyanka_qa_samples_per_second": 153.662,
+      "eval_solyanka_qa_steps_per_second": 9.619,
+      "step": 3000
+    },
+    {
+      "epoch": 0.041476808526829057,
+      "grad_norm": 1480.8231201171875,
+      "learning_rate": 4.130042143287177e-06,
+      "loss": 198.6064,
+      "step": 3100
+    },
+    {
+      "epoch": 0.04281477009221064,
+      "grad_norm": 1052.9395751953125,
+      "learning_rate": 4.2638303565455885e-06,
+      "loss": 202.1395,
+      "step": 3200
+    },
+    {
+      "epoch": 0.044152731657592224,
+      "grad_norm": 1055.3389892578125,
+      "learning_rate": 4.397618569804001e-06,
+      "loss": 200.4315,
+      "step": 3300
+    },
+    {
+      "epoch": 0.045490693222973805,
+      "grad_norm": 1264.2374267578125,
+      "learning_rate": 4.531406783062413e-06,
+      "loss": 190.5145,
+      "step": 3400
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "grad_norm": 1371.5516357421875,
+      "learning_rate": 4.665194996320825e-06,
+      "loss": 195.653,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_codesearchnet_loss": 6.666440963745117,
+      "eval_codesearchnet_runtime": 868.1141,
+      "eval_codesearchnet_samples_per_second": 34.558,
+      "eval_codesearchnet_steps_per_second": 2.16,
+      "eval_cosine_accuracy@1": 0.4233,
+      "eval_cosine_accuracy@10": 0.6468333333333334,
+      "eval_cosine_accuracy@3": 0.5530333333333334,
+      "eval_cosine_accuracy@5": 0.5977,
+      "eval_cosine_map@100": 0.5032596816876523,
+      "eval_cosine_mrr@10": 0.4980684126984272,
+      "eval_cosine_ndcg@10": 0.5340651234341146,
+      "eval_cosine_precision@1": 0.4233,
+      "eval_cosine_precision@10": 0.06468333333333333,
+      "eval_cosine_precision@3": 0.18434444444444442,
+      "eval_cosine_precision@5": 0.11954,
+      "eval_cosine_recall@1": 0.4233,
+      "eval_cosine_recall@10": 0.6468333333333334,
+      "eval_cosine_recall@3": 0.5530333333333334,
+      "eval_cosine_recall@5": 0.5977,
+      "eval_sequential_score": 0.45468531483126856,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_codesearchnet_en_loss": 4.728166580200195,
+      "eval_codesearchnet_en_runtime": 533.0589,
+      "eval_codesearchnet_en_samples_per_second": 56.279,
+      "eval_codesearchnet_en_steps_per_second": 3.517,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 222.014,
+      "eval_codesearchnet_pairs_samples_per_second": 135.127,
+      "eval_codesearchnet_pairs_steps_per_second": 8.445,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_solyanka_qa_loss": 4.346282005310059,
+      "eval_solyanka_qa_runtime": 32.5056,
+      "eval_solyanka_qa_samples_per_second": 153.82,
+      "eval_solyanka_qa_steps_per_second": 9.629,
+      "step": 3500
+    },
+    {
+      "epoch": 0.048166616353736966,
+      "grad_norm": 832.6646728515625,
+      "learning_rate": 4.798983209579236e-06,
+      "loss": 200.2459,
+      "step": 3600
+    },
+    {
+      "epoch": 0.04950457791911855,
+      "grad_norm": 1429.9462890625,
+      "learning_rate": 4.932771422837648e-06,
+      "loss": 189.7009,
+      "step": 3700
+    },
+    {
+      "epoch": 0.050842539484500134,
+      "grad_norm": 1101.5008544921875,
+      "learning_rate": 5.06655963609606e-06,
+      "loss": 189.3891,
+      "step": 3800
+    },
+    {
+      "epoch": 0.052180501049881714,
+      "grad_norm": 1311.8643798828125,
+      "learning_rate": 5.2003478493544725e-06,
+      "loss": 197.5025,
+      "step": 3900
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "grad_norm": 1112.9697265625,
+      "learning_rate": 5.334136062612884e-06,
+      "loss": 191.8113,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_codesearchnet_loss": 6.12751579284668,
+      "eval_codesearchnet_runtime": 789.24,
+      "eval_codesearchnet_samples_per_second": 38.011,
+      "eval_codesearchnet_steps_per_second": 2.376,
+      "eval_cosine_accuracy@1": 0.4841,
+      "eval_cosine_accuracy@10": 0.6953333333333334,
+      "eval_cosine_accuracy@3": 0.6093,
+      "eval_cosine_accuracy@5": 0.6484333333333333,
+      "eval_cosine_map@100": 0.5600661539369967,
+      "eval_cosine_mrr@10": 0.55571821428573,
+      "eval_cosine_ndcg@10": 0.5895257290681525,
+      "eval_cosine_precision@1": 0.4841,
+      "eval_cosine_precision@10": 0.06953333333333334,
+      "eval_cosine_precision@3": 0.2031,
+      "eval_cosine_precision@5": 0.12968666666666667,
+      "eval_cosine_recall@1": 0.4841,
+      "eval_cosine_recall@10": 0.6953333333333334,
+      "eval_cosine_recall@3": 0.6093,
+      "eval_cosine_recall@5": 0.6484333333333333,
+      "eval_sequential_score": 0.5141830504398937,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_codesearchnet_en_loss": 4.2443318367004395,
+      "eval_codesearchnet_en_runtime": 480.3149,
+      "eval_codesearchnet_en_samples_per_second": 62.459,
+      "eval_codesearchnet_en_steps_per_second": 3.904,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 183.8739,
+      "eval_codesearchnet_pairs_samples_per_second": 163.155,
+      "eval_codesearchnet_pairs_steps_per_second": 10.197,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_solyanka_qa_loss": 4.089145183563232,
+      "eval_solyanka_qa_runtime": 25.3337,
+      "eval_solyanka_qa_samples_per_second": 197.366,
+      "eval_solyanka_qa_steps_per_second": 12.355,
+      "step": 4000
+    },
+    {
+      "epoch": 0.05485642418064488,
+      "grad_norm": 1041.763916015625,
+      "learning_rate": 5.467924275871296e-06,
+      "loss": 181.2907,
+      "step": 4100
+    },
+    {
+      "epoch": 0.05619438574602646,
+      "grad_norm": 1189.8985595703125,
+      "learning_rate": 5.601712489129708e-06,
+      "loss": 193.7115,
+      "step": 4200
+    },
+    {
+      "epoch": 0.05753234731140804,
+      "grad_norm": 1995.246826171875,
+      "learning_rate": 5.7355007023881204e-06,
+      "loss": 187.6769,
+      "step": 4300
+    },
+    {
+      "epoch": 0.05887030887678963,
+      "grad_norm": 962.8026123046875,
+      "learning_rate": 5.869288915646531e-06,
+      "loss": 186.3607,
+      "step": 4400
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "grad_norm": 1693.328369140625,
+      "learning_rate": 6.00173924677236e-06,
+      "loss": 191.9243,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_codesearchnet_loss": 5.4969258308410645,
+      "eval_codesearchnet_runtime": 798.8982,
+      "eval_codesearchnet_samples_per_second": 37.552,
+      "eval_codesearchnet_steps_per_second": 2.347,
+      "eval_cosine_accuracy@1": 0.5401333333333334,
+      "eval_cosine_accuracy@10": 0.7383333333333333,
+      "eval_cosine_accuracy@3": 0.6606666666666666,
+      "eval_cosine_accuracy@5": 0.6969,
+      "eval_cosine_map@100": 0.6123297048019136,
+      "eval_cosine_mrr@10": 0.6082852777777863,
+      "eval_cosine_ndcg@10": 0.6398697969385133,
+      "eval_cosine_precision@1": 0.5401333333333334,
+      "eval_cosine_precision@10": 0.07383333333333333,
+      "eval_cosine_precision@3": 0.2202222222222222,
+      "eval_cosine_precision@5": 0.13937999999999998,
+      "eval_cosine_recall@1": 0.5401333333333334,
+      "eval_cosine_recall@10": 0.7383333333333333,
+      "eval_cosine_recall@3": 0.6606666666666666,
+      "eval_cosine_recall@5": 0.6969,
+      "eval_sequential_score": 0.5623610573754854,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_codesearchnet_en_loss": 3.7932770252227783,
+      "eval_codesearchnet_en_runtime": 486.7262,
+      "eval_codesearchnet_en_samples_per_second": 61.636,
+      "eval_codesearchnet_en_steps_per_second": 3.852,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 189.9044,
+      "eval_codesearchnet_pairs_samples_per_second": 157.974,
+      "eval_codesearchnet_pairs_steps_per_second": 9.873,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_solyanka_qa_loss": 4.172121047973633,
+      "eval_solyanka_qa_runtime": 26.9517,
+      "eval_solyanka_qa_samples_per_second": 185.517,
+      "eval_solyanka_qa_steps_per_second": 11.613,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06154623200755279,
+      "grad_norm": 1067.1920166015625,
+      "learning_rate": 6.135527460030771e-06,
+      "loss": 189.8334,
+      "step": 4600
+    },
+    {
+      "epoch": 0.06288419357293437,
+      "grad_norm": 4186.00439453125,
+      "learning_rate": 6.269315673289184e-06,
+      "loss": 186.4033,
+      "step": 4700
+    },
+    {
+      "epoch": 0.06422215513831596,
+      "grad_norm": 1410.729736328125,
+      "learning_rate": 6.4031038865475954e-06,
+      "loss": 184.225,
+      "step": 4800
+    },
+    {
+      "epoch": 0.06556011670369755,
+      "grad_norm": 1268.47265625,
+      "learning_rate": 6.536892099806008e-06,
+      "loss": 188.3992,
+      "step": 4900
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "grad_norm": 1120.933837890625,
+      "learning_rate": 6.670680313064419e-06,
+      "loss": 183.9708,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_codesearchnet_loss": 4.910182476043701,
+      "eval_codesearchnet_runtime": 793.2722,
+      "eval_codesearchnet_samples_per_second": 37.818,
+      "eval_codesearchnet_steps_per_second": 2.364,
+      "eval_cosine_accuracy@1": 0.5617666666666666,
+      "eval_cosine_accuracy@10": 0.7616,
+      "eval_cosine_accuracy@3": 0.6858666666666666,
+      "eval_cosine_accuracy@5": 0.7219333333333333,
+      "eval_cosine_map@100": 0.6352974693863399,
+      "eval_cosine_mrr@10": 0.6315028703703756,
+      "eval_cosine_ndcg@10": 0.6631716590320138,
+      "eval_cosine_precision@1": 0.5617666666666666,
+      "eval_cosine_precision@10": 0.07615999999999999,
+      "eval_cosine_precision@3": 0.2286222222222222,
+      "eval_cosine_precision@5": 0.1443866666666667,
+      "eval_cosine_recall@1": 0.5617666666666666,
+      "eval_cosine_recall@10": 0.7616,
+      "eval_cosine_recall@3": 0.6858666666666666,
+      "eval_cosine_recall@5": 0.7219333333333333,
+      "eval_sequential_score": 0.588823994072985,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_codesearchnet_en_loss": 3.2918059825897217,
+      "eval_codesearchnet_en_runtime": 482.3681,
+      "eval_codesearchnet_en_samples_per_second": 62.193,
+      "eval_codesearchnet_en_steps_per_second": 3.887,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 187.4741,
+      "eval_codesearchnet_pairs_samples_per_second": 160.022,
+      "eval_codesearchnet_pairs_steps_per_second": 10.001,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_solyanka_qa_loss": 3.8115358352661133,
+      "eval_solyanka_qa_runtime": 25.8592,
+      "eval_solyanka_qa_samples_per_second": 193.354,
+      "eval_solyanka_qa_steps_per_second": 12.104,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06823603983446071,
+      "grad_norm": 931.2894287109375,
+      "learning_rate": 6.8044685263228316e-06,
+      "loss": 193.8627,
+      "step": 5100
+    },
+    {
+      "epoch": 0.0695740013998423,
+      "grad_norm": 1761.0831298828125,
+      "learning_rate": 6.938256739581244e-06,
+      "loss": 186.6093,
+      "step": 5200
+    },
+    {
+      "epoch": 0.07091196296522387,
+      "grad_norm": 1396.5413818359375,
+      "learning_rate": 7.072044952839655e-06,
+      "loss": 178.5979,
+      "step": 5300
+    },
+    {
+      "epoch": 0.07224992453060546,
+      "grad_norm": 1139.1634521484375,
+      "learning_rate": 7.205833166098068e-06,
+      "loss": 187.7019,
+      "step": 5400
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "grad_norm": 1028.661376953125,
+      "learning_rate": 7.3396213793564795e-06,
+      "loss": 182.9072,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_codesearchnet_loss": 5.771347999572754,
+      "eval_codesearchnet_runtime": 791.0446,
+      "eval_codesearchnet_samples_per_second": 37.925,
+      "eval_codesearchnet_steps_per_second": 2.37,
+      "eval_cosine_accuracy@1": 0.5377,
+      "eval_cosine_accuracy@10": 0.7404333333333334,
+      "eval_cosine_accuracy@3": 0.6615333333333333,
+      "eval_cosine_accuracy@5": 0.6998666666666666,
+      "eval_cosine_map@100": 0.6115645028851873,
+      "eval_cosine_mrr@10": 0.6076140476190545,
+      "eval_cosine_ndcg@10": 0.639898364994289,
+      "eval_cosine_precision@1": 0.5377,
+      "eval_cosine_precision@10": 0.07404333333333334,
+      "eval_cosine_precision@3": 0.2205111111111111,
+      "eval_cosine_precision@5": 0.13997333333333334,
+      "eval_cosine_recall@1": 0.5377,
+      "eval_cosine_recall@10": 0.7404333333333334,
+      "eval_cosine_recall@3": 0.6615333333333333,
+      "eval_cosine_recall@5": 0.6998666666666666,
+      "eval_sequential_score": 0.5537658861174344,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_codesearchnet_en_loss": 4.075521945953369,
+      "eval_codesearchnet_en_runtime": 480.6923,
+      "eval_codesearchnet_en_samples_per_second": 62.41,
+      "eval_codesearchnet_en_steps_per_second": 3.901,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 185.6337,
+      "eval_codesearchnet_pairs_samples_per_second": 161.609,
+      "eval_codesearchnet_pairs_steps_per_second": 10.101,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_solyanka_qa_loss": 4.20865535736084,
+      "eval_solyanka_qa_runtime": 25.9517,
+      "eval_solyanka_qa_samples_per_second": 192.665,
+      "eval_solyanka_qa_steps_per_second": 12.061,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07492584766136862,
+      "grad_norm": 1251.1859130859375,
+      "learning_rate": 7.473409592614891e-06,
+      "loss": 186.9648,
+      "step": 5600
+    },
+    {
+      "epoch": 0.0762638092267502,
+      "grad_norm": 1243.02099609375,
+      "learning_rate": 7.607197805873303e-06,
+      "loss": 182.2779,
+      "step": 5700
+    },
+    {
+      "epoch": 0.07760177079213178,
+      "grad_norm": 1062.451171875,
+      "learning_rate": 7.740986019131716e-06,
+      "loss": 179.2852,
+      "step": 5800
+    },
+    {
+      "epoch": 0.07893973235751336,
+      "grad_norm": 1121.85009765625,
+      "learning_rate": 7.874774232390127e-06,
+      "loss": 170.5596,
+      "step": 5900
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "grad_norm": 1335.1585693359375,
+      "learning_rate": 8.008562445648539e-06,
+      "loss": 182.9913,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_codesearchnet_loss": 4.416569232940674,
+      "eval_codesearchnet_runtime": 827.7981,
+      "eval_codesearchnet_samples_per_second": 36.241,
+      "eval_codesearchnet_steps_per_second": 2.265,
+      "eval_cosine_accuracy@1": 0.5953,
+      "eval_cosine_accuracy@10": 0.7925,
+      "eval_cosine_accuracy@3": 0.7213333333333334,
+      "eval_cosine_accuracy@5": 0.7560333333333333,
+      "eval_cosine_map@100": 0.6682719879085095,
+      "eval_cosine_mrr@10": 0.6647914021164015,
+      "eval_cosine_ndcg@10": 0.6959528934005342,
+      "eval_cosine_precision@1": 0.5953,
+      "eval_cosine_precision@10": 0.07925,
+      "eval_cosine_precision@3": 0.24044444444444443,
+      "eval_cosine_precision@5": 0.15120666666666666,
+      "eval_cosine_recall@1": 0.5953,
+      "eval_cosine_recall@10": 0.7925,
+      "eval_cosine_recall@3": 0.7213333333333334,
+      "eval_cosine_recall@5": 0.7560333333333333,
+      "eval_sequential_score": 0.625740827587927,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_codesearchnet_en_loss": 3.067141056060791,
+      "eval_codesearchnet_en_runtime": 531.0437,
+      "eval_codesearchnet_en_samples_per_second": 56.493,
+      "eval_codesearchnet_en_steps_per_second": 3.531,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 231.1077,
+      "eval_codesearchnet_pairs_samples_per_second": 129.81,
+      "eval_codesearchnet_pairs_steps_per_second": 8.113,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_solyanka_qa_loss": 3.54522967338562,
+      "eval_solyanka_qa_runtime": 35.3187,
+      "eval_solyanka_qa_samples_per_second": 141.568,
+      "eval_solyanka_qa_steps_per_second": 8.862,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08161565548827653,
+      "grad_norm": 1462.4613037109375,
+      "learning_rate": 8.142350658906952e-06,
+      "loss": 180.0925,
+      "step": 6100
+    },
+    {
+      "epoch": 0.08295361705365811,
+      "grad_norm": 1306.346435546875,
+      "learning_rate": 8.276138872165363e-06,
+      "loss": 177.6538,
+      "step": 6200
+    },
+    {
+      "epoch": 0.0842915786190397,
+      "grad_norm": 795.7644653320312,
+      "learning_rate": 8.409927085423775e-06,
+      "loss": 176.7865,
+      "step": 6300
+    },
+    {
+      "epoch": 0.08562954018442127,
+      "grad_norm": 1051.8511962890625,
+      "learning_rate": 8.543715298682186e-06,
+      "loss": 177.2024,
+      "step": 6400
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "grad_norm": 1394.38818359375,
+      "learning_rate": 8.677503511940599e-06,
+      "loss": 183.0437,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_codesearchnet_loss": 4.107079029083252,
+      "eval_codesearchnet_runtime": 933.9902,
+      "eval_codesearchnet_samples_per_second": 32.12,
+      "eval_codesearchnet_steps_per_second": 2.008,
+      "eval_cosine_accuracy@1": 0.5766666666666667,
+      "eval_cosine_accuracy@10": 0.7799333333333334,
+      "eval_cosine_accuracy@3": 0.7028333333333333,
+      "eval_cosine_accuracy@5": 0.7409333333333333,
+      "eval_cosine_map@100": 0.6514269801326987,
+      "eval_cosine_mrr@10": 0.6477988095238115,
+      "eval_cosine_ndcg@10": 0.6799886507436855,
+      "eval_cosine_precision@1": 0.5766666666666667,
+      "eval_cosine_precision@10": 0.07799333333333335,
+      "eval_cosine_precision@3": 0.23427777777777772,
+      "eval_cosine_precision@5": 0.1481866666666667,
+      "eval_cosine_recall@1": 0.5766666666666667,
+      "eval_cosine_recall@10": 0.7799333333333334,
+      "eval_cosine_recall@3": 0.7028333333333333,
+      "eval_cosine_recall@5": 0.7409333333333333,
+      "eval_sequential_score": 0.6109291855288735,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_codesearchnet_en_loss": 2.8989362716674805,
+      "eval_codesearchnet_en_runtime": 548.5847,
+      "eval_codesearchnet_en_samples_per_second": 54.686,
+      "eval_codesearchnet_en_steps_per_second": 3.418,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 251.9769,
+      "eval_codesearchnet_pairs_samples_per_second": 119.059,
+      "eval_codesearchnet_pairs_steps_per_second": 7.441,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_solyanka_qa_loss": 3.395298719406128,
+      "eval_solyanka_qa_runtime": 42.1787,
+      "eval_solyanka_qa_samples_per_second": 118.543,
+      "eval_solyanka_qa_steps_per_second": 7.421,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08830546331518445,
+      "grad_norm": 953.8713989257812,
+      "learning_rate": 8.81129172519901e-06,
+      "loss": 174.4866,
+      "step": 6600
+    },
+    {
+      "epoch": 0.08964342488056602,
+      "grad_norm": 1037.1529541015625,
+      "learning_rate": 8.945079938457422e-06,
+      "loss": 180.6098,
+      "step": 6700
+    },
+    {
+      "epoch": 0.09098138644594761,
+      "grad_norm": 2274.166748046875,
+      "learning_rate": 9.078868151715835e-06,
+      "loss": 175.4703,
+      "step": 6800
+    },
+    {
+      "epoch": 0.09231934801132918,
+      "grad_norm": 1078.928466796875,
+      "learning_rate": 9.212656364974246e-06,
+      "loss": 183.6586,
+      "step": 6900
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "grad_norm": 1381.9674072265625,
+      "learning_rate": 9.345106696100075e-06,
+      "loss": 171.7979,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_codesearchnet_loss": 5.207095146179199,
+      "eval_codesearchnet_runtime": 907.058,
+      "eval_codesearchnet_samples_per_second": 33.074,
+      "eval_codesearchnet_steps_per_second": 2.067,
+      "eval_cosine_accuracy@1": 0.5449333333333334,
+      "eval_cosine_accuracy@10": 0.7414333333333334,
+      "eval_cosine_accuracy@3": 0.6638333333333334,
+      "eval_cosine_accuracy@5": 0.7017666666666666,
+      "eval_cosine_map@100": 0.6164075899784531,
+      "eval_cosine_mrr@10": 0.6126674338624413,
+      "eval_cosine_ndcg@10": 0.6439444961382464,
+      "eval_cosine_precision@1": 0.5449333333333334,
+      "eval_cosine_precision@10": 0.07414333333333334,
+      "eval_cosine_precision@3": 0.22127777777777777,
+      "eval_cosine_precision@5": 0.1403533333333333,
+      "eval_cosine_recall@1": 0.5449333333333334,
+      "eval_cosine_recall@10": 0.7414333333333334,
+      "eval_cosine_recall@3": 0.6638333333333334,
+      "eval_cosine_recall@5": 0.7017666666666666,
+      "eval_sequential_score": 0.5749765917991857,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_codesearchnet_en_loss": 3.596595287322998,
+      "eval_codesearchnet_en_runtime": 536.7682,
+      "eval_codesearchnet_en_samples_per_second": 55.89,
+      "eval_codesearchnet_en_steps_per_second": 3.493,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 240.2488,
+      "eval_codesearchnet_pairs_samples_per_second": 124.871,
+      "eval_codesearchnet_pairs_steps_per_second": 7.804,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_solyanka_qa_loss": 4.301774024963379,
+      "eval_solyanka_qa_runtime": 36.632,
+      "eval_solyanka_qa_samples_per_second": 136.493,
+      "eval_solyanka_qa_steps_per_second": 8.544,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09499527114209236,
+      "grad_norm": 1252.0892333984375,
+      "learning_rate": 9.478894909358486e-06,
+      "loss": 173.3894,
+      "step": 7100
+    },
+    {
+      "epoch": 0.09633323270747393,
+      "grad_norm": 1923.31201171875,
+      "learning_rate": 9.612683122616898e-06,
+      "loss": 174.4687,
+      "step": 7200
+    },
+    {
+      "epoch": 0.09767119427285552,
+      "grad_norm": 1374.7725830078125,
+      "learning_rate": 9.74647133587531e-06,
+      "loss": 174.5152,
+      "step": 7300
+    },
+    {
+      "epoch": 0.0990091558382371,
+      "grad_norm": 1235.3150634765625,
+      "learning_rate": 9.880259549133722e-06,
+      "loss": 179.1588,
+      "step": 7400
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "grad_norm": 5407.0478515625,
+      "learning_rate": 1.0014047762392134e-05,
+      "loss": 179.4099,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_codesearchnet_loss": 4.5956878662109375,
+      "eval_codesearchnet_runtime": 896.509,
+      "eval_codesearchnet_samples_per_second": 33.463,
+      "eval_codesearchnet_steps_per_second": 2.091,
+      "eval_cosine_accuracy@1": 0.5804333333333334,
+      "eval_cosine_accuracy@10": 0.7716333333333333,
+      "eval_cosine_accuracy@3": 0.7015666666666667,
+      "eval_cosine_accuracy@5": 0.7351,
+      "eval_cosine_map@100": 0.6513085394657405,
+      "eval_cosine_mrr@10": 0.6478177248677272,
+      "eval_cosine_ndcg@10": 0.6780089383245728,
+      "eval_cosine_precision@1": 0.5804333333333334,
+      "eval_cosine_precision@10": 0.07716333333333333,
+      "eval_cosine_precision@3": 0.23385555555555554,
+      "eval_cosine_precision@5": 0.14702,
+      "eval_cosine_recall@1": 0.5804333333333334,
+      "eval_cosine_recall@10": 0.7716333333333333,
+      "eval_cosine_recall@3": 0.7015666666666667,
+      "eval_cosine_recall@5": 0.7351,
+      "eval_sequential_score": 0.6085904680593567,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_codesearchnet_en_loss": 3.176692485809326,
+      "eval_codesearchnet_en_runtime": 537.5798,
+      "eval_codesearchnet_en_samples_per_second": 55.806,
+      "eval_codesearchnet_en_steps_per_second": 3.488,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 233.6133,
+      "eval_codesearchnet_pairs_samples_per_second": 128.417,
+      "eval_codesearchnet_pairs_steps_per_second": 8.026,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_solyanka_qa_loss": 3.3527519702911377,
+      "eval_solyanka_qa_runtime": 35.6484,
+      "eval_solyanka_qa_samples_per_second": 140.259,
+      "eval_solyanka_qa_steps_per_second": 8.78,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10168507896900027,
+      "grad_norm": 1189.1429443359375,
+      "learning_rate": 1.0146498093517963e-05,
+      "loss": 173.8489,
+      "step": 7600
+    },
+    {
+      "epoch": 0.10436082756129317,
+      "grad_norm": 524.2390747070312,
+      "learning_rate": 1.0414074520034785e-05,
+      "loss": 57.8803,
+      "step": 7800
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "grad_norm": 364.2381896972656,
+      "learning_rate": 1.068165094655161e-05,
+      "loss": 50.8973,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_codesearchnet_loss": 0.5108523368835449,
+      "eval_codesearchnet_runtime": 850.8936,
+      "eval_codesearchnet_samples_per_second": 35.257,
+      "eval_codesearchnet_steps_per_second": 4.407,
+      "eval_cosine_accuracy@1": 0.7804666666666666,
+      "eval_cosine_accuracy@10": 0.9267,
+      "eval_cosine_accuracy@3": 0.8845,
+      "eval_cosine_accuracy@5": 0.9065,
+      "eval_cosine_map@100": 0.8373038141979917,
+      "eval_cosine_mrr@10": 0.8357315740740681,
+      "eval_cosine_ndcg@10": 0.8582006830716409,
+      "eval_cosine_precision@1": 0.7804666666666666,
+      "eval_cosine_precision@10": 0.09267000000000002,
+      "eval_cosine_precision@3": 0.29483333333333334,
+      "eval_cosine_precision@5": 0.18130000000000002,
+      "eval_cosine_recall@1": 0.7804666666666666,
+      "eval_cosine_recall@10": 0.9267,
+      "eval_cosine_recall@3": 0.8845,
+      "eval_cosine_recall@5": 0.9065,
+      "eval_sequential_score": 0.8191610196783502,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_codesearchnet_en_loss": 0.3525207042694092,
+      "eval_codesearchnet_en_runtime": 471.0461,
+      "eval_codesearchnet_en_samples_per_second": 63.688,
+      "eval_codesearchnet_en_steps_per_second": 7.961,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 321.2179,
+      "eval_codesearchnet_pairs_samples_per_second": 93.395,
+      "eval_codesearchnet_pairs_steps_per_second": 11.674,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_solyanka_qa_loss": 0.6166790723800659,
+      "eval_solyanka_qa_runtime": 59.2988,
+      "eval_solyanka_qa_samples_per_second": 84.319,
+      "eval_solyanka_qa_steps_per_second": 10.54,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10971266487212872,
+      "grad_norm": 539.6712646484375,
+      "learning_rate": 1.0949227373068434e-05,
+      "loss": 52.6686,
+      "step": 8200
+    },
+    {
+      "epoch": 0.11238858352754649,
+      "grad_norm": 285.00408935546875,
+      "learning_rate": 1.1216803799585259e-05,
+      "loss": 50.568,
+      "step": 8400
+    },
+    {
+      "epoch": 0.11506450218296427,
+      "grad_norm": 407.73565673828125,
+      "learning_rate": 1.148438022610208e-05,
+      "loss": 49.3516,
+      "step": 8600
+    },
+    {
+      "epoch": 0.11774042083838204,
+      "grad_norm": 322.4379577636719,
+      "learning_rate": 1.1751956652618906e-05,
+      "loss": 48.8846,
+      "step": 8800
+    },
+    {
+      "epoch": 0.12041633949379982,
+      "grad_norm": 267.22564697265625,
+      "learning_rate": 1.201953307913573e-05,
+      "loss": 49.1422,
+      "step": 9000
+    },
+    {
+      "epoch": 0.12309225814921759,
+      "grad_norm": 373.3161926269531,
+      "learning_rate": 1.2287109505652553e-05,
+      "loss": 51.4819,
+      "step": 9200
+    },
+    {
+      "epoch": 0.12576817680463537,
+      "grad_norm": 370.7853698730469,
+      "learning_rate": 1.2554685932169377e-05,
+      "loss": 45.9136,
+      "step": 9400
+    },
+    {
+      "epoch": 0.12844409546005314,
+      "grad_norm": 473.8594970703125,
+      "learning_rate": 1.2822262358686202e-05,
+      "loss": 46.4492,
+      "step": 9600
+    },
+    {
+      "epoch": 0.13112001411547092,
+      "grad_norm": 392.2969970703125,
+      "learning_rate": 1.3089838785203024e-05,
+      "loss": 49.4392,
+      "step": 9800
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "grad_norm": 392.4254455566406,
+      "learning_rate": 1.3357415211719849e-05,
+      "loss": 49.5231,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_codesearchnet_loss": 0.21050667762756348,
+      "eval_codesearchnet_runtime": 845.1488,
+      "eval_codesearchnet_samples_per_second": 35.497,
+      "eval_codesearchnet_steps_per_second": 4.437,
+      "eval_cosine_accuracy@1": 0.8419333333333333,
+      "eval_cosine_accuracy@10": 0.9506,
+      "eval_cosine_accuracy@3": 0.9236666666666666,
+      "eval_cosine_accuracy@5": 0.9386333333333333,
+      "eval_cosine_map@100": 0.8858101455522462,
+      "eval_cosine_mrr@10": 0.8847410185185097,
+      "eval_cosine_ndcg@10": 0.9011276163882171,
+      "eval_cosine_precision@1": 0.8419333333333333,
+      "eval_cosine_precision@10": 0.09506000000000002,
+      "eval_cosine_precision@3": 0.3078888888888889,
+      "eval_cosine_precision@5": 0.1877266666666667,
+      "eval_cosine_recall@1": 0.8419333333333333,
+      "eval_cosine_recall@10": 0.9506,
+      "eval_cosine_recall@3": 0.9236666666666666,
+      "eval_cosine_recall@5": 0.9386333333333333,
+      "eval_sequential_score": 0.8844637138667995,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_codesearchnet_en_loss": 0.1648031771183014,
+      "eval_codesearchnet_en_runtime": 477.1262,
+      "eval_codesearchnet_en_samples_per_second": 62.876,
+      "eval_codesearchnet_en_steps_per_second": 7.86,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 317.6118,
+      "eval_codesearchnet_pairs_samples_per_second": 94.455,
+      "eval_codesearchnet_pairs_steps_per_second": 11.807,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_solyanka_qa_loss": 0.48000234365463257,
+      "eval_solyanka_qa_runtime": 58.4343,
+      "eval_solyanka_qa_samples_per_second": 85.566,
+      "eval_solyanka_qa_steps_per_second": 10.696,
+      "step": 10000
+    },
+    {
+      "epoch": 0.13647185142630647,
+      "grad_norm": 302.9349060058594,
+      "learning_rate": 1.3624991638236672e-05,
+      "loss": 44.8227,
+      "step": 10200
+    },
+    {
+      "epoch": 0.13914777008172421,
+      "grad_norm": 280.627685546875,
+      "learning_rate": 1.3892568064753496e-05,
+      "loss": 47.4191,
+      "step": 10400
+    },
+    {
+      "epoch": 0.141823688737142,
+      "grad_norm": 396.9530944824219,
+      "learning_rate": 1.416014449127032e-05,
+      "loss": 48.4208,
+      "step": 10600
+    },
+    {
+      "epoch": 0.14449960739255976,
+      "grad_norm": 567.6721801757812,
+      "learning_rate": 1.4427720917787145e-05,
+      "loss": 47.0498,
+      "step": 10800
+    },
+    {
+      "epoch": 0.14717552604797754,
+      "grad_norm": 399.8636779785156,
+      "learning_rate": 1.4695297344303966e-05,
+      "loss": 47.332,
+      "step": 11000
+    },
+    {
+      "epoch": 0.14985144470339531,
+      "grad_norm": 365.3705139160156,
+      "learning_rate": 1.4962873770820792e-05,
+      "loss": 46.6691,
+      "step": 11200
+    },
+    {
+      "epoch": 0.1525273633588131,
+      "grad_norm": 329.9962463378906,
+      "learning_rate": 1.5230450197337617e-05,
+      "loss": 48.4622,
+      "step": 11400
+    },
+    {
+      "epoch": 0.15520328201423086,
+      "grad_norm": 305.3818054199219,
+      "learning_rate": 1.549802662385444e-05,
+      "loss": 47.3353,
+      "step": 11600
+    },
+    {
+      "epoch": 0.15787920066964864,
+      "grad_norm": 353.5430908203125,
+      "learning_rate": 1.5765603050371262e-05,
+      "loss": 47.3603,
+      "step": 11800
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "grad_norm": 208.02548217773438,
+      "learning_rate": 1.6033179476888088e-05,
+      "loss": 47.0726,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_codesearchnet_loss": 0.17985302209854126,
+      "eval_codesearchnet_runtime": 849.7401,
+      "eval_codesearchnet_samples_per_second": 35.305,
+      "eval_codesearchnet_steps_per_second": 4.413,
+      "eval_cosine_accuracy@1": 0.8403,
+      "eval_cosine_accuracy@10": 0.9529666666666666,
+      "eval_cosine_accuracy@3": 0.9246666666666666,
+      "eval_cosine_accuracy@5": 0.9399333333333333,
+      "eval_cosine_map@100": 0.8856879053068674,
+      "eval_cosine_mrr@10": 0.8846578571428485,
+      "eval_cosine_ndcg@10": 0.9016476260382669,
+      "eval_cosine_precision@1": 0.8403,
+      "eval_cosine_precision@10": 0.09529666666666668,
+      "eval_cosine_precision@3": 0.3082222222222222,
+      "eval_cosine_precision@5": 0.1879866666666667,
+      "eval_cosine_recall@1": 0.8403,
+      "eval_cosine_recall@10": 0.9529666666666666,
+      "eval_cosine_recall@3": 0.9246666666666666,
+      "eval_cosine_recall@5": 0.9399333333333333,
+      "eval_sequential_score": 0.8855350929516275,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_codesearchnet_en_loss": 0.14139343798160553,
+      "eval_codesearchnet_en_runtime": 478.2988,
+      "eval_codesearchnet_en_samples_per_second": 62.722,
+      "eval_codesearchnet_en_steps_per_second": 7.84,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 321.6238,
+      "eval_codesearchnet_pairs_samples_per_second": 93.277,
+      "eval_codesearchnet_pairs_steps_per_second": 11.66,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_solyanka_qa_loss": 0.4072943925857544,
+      "eval_solyanka_qa_runtime": 58.462,
+      "eval_solyanka_qa_samples_per_second": 85.526,
+      "eval_solyanka_qa_steps_per_second": 10.691,
+      "step": 12000
+    },
+    {
+      "epoch": 0.1632310379804842,
+      "grad_norm": 227.58837890625,
+      "learning_rate": 1.6300755903404913e-05,
+      "loss": 45.9733,
+      "step": 12200
+    },
+    {
+      "epoch": 0.16590695663590196,
+      "grad_norm": 364.53564453125,
+      "learning_rate": 1.6568332329921735e-05,
+      "loss": 44.1369,
+      "step": 12400
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 149482,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-12400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074a30aa700ef5929b1667220187d3885dc033bf3c587cd5cadf78f867884f08
+size 5688

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "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
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/config.json

@@ -0,0 +1,81 @@
+{
+  "activation_function": "gelu",
+  "allow_embedding_resizing": true,
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_layer": "rope",
+  "attention_probs_dropout_prob": 0.0,
+  "attn_out_bias": false,
+  "attn_out_dropout_prob": 0.1,
+  "attn_qkv_bias": false,
+  "bert_layer": "prenorm",
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "compile_model": true,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embed_dropout_prob": 0.0,
+  "embed_norm": true,
+  "embedding_dropout": 0.0,
+  "embedding_layer": "sans_pos",
+  "eos_token_id": 50282,
+  "final_norm": true,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "head_pred_act": "gelu",
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "init_method": "full_megatron",
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "local_attention": 128,
+  "local_attn_rotary_emb_base": 10000.0,
+  "local_rope_theta": 10000.0,
+  "loss_function": "fa_cross_entropy",
+  "loss_kwargs": {
+    "reduction": "mean"
+  },
+  "masked_prediction": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "mlp_dropout_prob": 0.0,
+  "mlp_in_bias": false,
+  "mlp_layer": "glu",
+  "mlp_out_bias": false,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "norm_kwargs": {
+    "bias": false,
+    "eps": 1e-05
+  },
+  "normalization": "layernorm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "padding": "unpadded",
+  "repad_logits_with_grad": false,
+  "rotary_emb_base": 160000.0,
+  "rotary_emb_dim": null,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "sep_token_id": 50282,
+  "skip_first_prenorm": true,
+  "sliding_window": 128,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "unpad_embeddings": true,
+  "vocab_size": 50368
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.52.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061f000e2c238fe4d1281907d9dead569f7e7b5e9ad4496b03954250eed2d077
+size 596070136

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72d1f947239f2519751ea98bdad8acd917633ce37550d2eb2bb51ded5eb53c4
+size 1192227066

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515fefabaf92fff68a809d35349b9cd0a7e27bd2fab1be63fbe5f9f9ed0d6b6d
+size 14244

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8508e27ca3a2950455f57602557fde79c7eff7fd1a07ed120775a8931b8cd5ca
+size 988

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706e82cab5b49194d96a03b40f2017fe3a3b553747360f3ae1b395ed310b96da
+size 1064

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 8192,
+    "do_lower_case": false
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[PAD]",
+    "[MASK]"
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "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
+  }
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/tokenizer_config.json

@@ -0,0 +1,961 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[PAD]",
+    "[MASK]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 8192,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/trainer_state.json

@@ -0,0 +1,2820 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.44955433411018597,
+  "eval_steps": 2000,
+  "global_step": 33600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013379615653815824,
+      "grad_norm": 1593.7158203125,
+      "learning_rate": 1.1907150979998663e-07,
+      "loss": 272.0406,
+      "step": 100
+    },
+    {
+      "epoch": 0.002675923130763165,
+      "grad_norm": 830.271484375,
+      "learning_rate": 2.5018395879323036e-07,
+      "loss": 259.1632,
+      "step": 200
+    },
+    {
+      "epoch": 0.004013884696144747,
+      "grad_norm": 957.25537109375,
+      "learning_rate": 3.839721720516423e-07,
+      "loss": 235.0577,
+      "step": 300
+    },
+    {
+      "epoch": 0.00535184626152633,
+      "grad_norm": 446.388916015625,
+      "learning_rate": 5.177603853100542e-07,
+      "loss": 229.0209,
+      "step": 400
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "grad_norm": 900.2640991210938,
+      "learning_rate": 6.515485985684662e-07,
+      "loss": 229.5855,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_codesearchnet_loss": 11.501143455505371,
+      "eval_codesearchnet_runtime": 861.5274,
+      "eval_codesearchnet_samples_per_second": 34.822,
+      "eval_codesearchnet_steps_per_second": 2.176,
+      "eval_cosine_accuracy@1": 0.18823333333333334,
+      "eval_cosine_accuracy@10": 0.30396666666666666,
+      "eval_cosine_accuracy@3": 0.24886666666666668,
+      "eval_cosine_accuracy@5": 0.2738,
+      "eval_cosine_map@100": 0.22870242076259673,
+      "eval_cosine_mrr@10": 0.22479973544973395,
+      "eval_cosine_ndcg@10": 0.24378814726804346,
+      "eval_cosine_precision@1": 0.18823333333333334,
+      "eval_cosine_precision@10": 0.03039666666666667,
+      "eval_cosine_precision@3": 0.08295555555555555,
+      "eval_cosine_precision@5": 0.054759999999999996,
+      "eval_cosine_recall@1": 0.18823333333333334,
+      "eval_cosine_recall@10": 0.30396666666666666,
+      "eval_cosine_recall@3": 0.24886666666666668,
+      "eval_cosine_recall@5": 0.2738,
+      "eval_sequential_score": 0.2087706265726278,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_codesearchnet_en_loss": 10.62355899810791,
+      "eval_codesearchnet_en_runtime": 525.6255,
+      "eval_codesearchnet_en_samples_per_second": 57.075,
+      "eval_codesearchnet_en_steps_per_second": 3.567,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 217.4482,
+      "eval_codesearchnet_pairs_samples_per_second": 137.964,
+      "eval_codesearchnet_pairs_steps_per_second": 8.623,
+      "step": 500
+    },
+    {
+      "epoch": 0.006689807826907913,
+      "eval_solyanka_qa_loss": 10.61404800415039,
+      "eval_solyanka_qa_runtime": 30.6194,
+      "eval_solyanka_qa_samples_per_second": 163.295,
+      "eval_solyanka_qa_steps_per_second": 10.222,
+      "step": 500
+    },
+    {
+      "epoch": 0.008027769392289495,
+      "grad_norm": 862.380859375,
+      "learning_rate": 7.85336811826878e-07,
+      "loss": 222.2825,
+      "step": 600
+    },
+    {
+      "epoch": 0.009365730957671077,
+      "grad_norm": 686.0302124023438,
+      "learning_rate": 9.191250250852901e-07,
+      "loss": 224.0132,
+      "step": 700
+    },
+    {
+      "epoch": 0.01070369252305266,
+      "grad_norm": 382.3077392578125,
+      "learning_rate": 1.052913238343702e-06,
+      "loss": 220.4923,
+      "step": 800
+    },
+    {
+      "epoch": 0.012041654088434241,
+      "grad_norm": 534.106201171875,
+      "learning_rate": 1.186701451602114e-06,
+      "loss": 221.8868,
+      "step": 900
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "grad_norm": 544.294921875,
+      "learning_rate": 1.3204896648605259e-06,
+      "loss": 217.3524,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_codesearchnet_loss": 11.611088752746582,
+      "eval_codesearchnet_runtime": 868.6178,
+      "eval_codesearchnet_samples_per_second": 34.538,
+      "eval_codesearchnet_steps_per_second": 2.159,
+      "eval_cosine_accuracy@1": 0.21566666666666667,
+      "eval_cosine_accuracy@10": 0.3415666666666667,
+      "eval_cosine_accuracy@3": 0.28136666666666665,
+      "eval_cosine_accuracy@5": 0.30943333333333334,
+      "eval_cosine_map@100": 0.25975150872269276,
+      "eval_cosine_mrr@10": 0.2554449603174578,
+      "eval_cosine_ndcg@10": 0.276100097940374,
+      "eval_cosine_precision@1": 0.21566666666666667,
+      "eval_cosine_precision@10": 0.03415666666666667,
+      "eval_cosine_precision@3": 0.09378888888888888,
+      "eval_cosine_precision@5": 0.061886666666666666,
+      "eval_cosine_recall@1": 0.21566666666666667,
+      "eval_cosine_recall@10": 0.3415666666666667,
+      "eval_cosine_recall@3": 0.28136666666666665,
+      "eval_cosine_recall@5": 0.30943333333333334,
+      "eval_sequential_score": 0.22303526950392608,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_codesearchnet_en_loss": 10.429346084594727,
+      "eval_codesearchnet_en_runtime": 530.1187,
+      "eval_codesearchnet_en_samples_per_second": 56.591,
+      "eval_codesearchnet_en_steps_per_second": 3.537,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 218.5444,
+      "eval_codesearchnet_pairs_samples_per_second": 137.272,
+      "eval_codesearchnet_pairs_steps_per_second": 8.579,
+      "step": 1000
+    },
+    {
+      "epoch": 0.013379615653815825,
+      "eval_solyanka_qa_loss": 10.338957786560059,
+      "eval_solyanka_qa_runtime": 31.4753,
+      "eval_solyanka_qa_samples_per_second": 158.855,
+      "eval_solyanka_qa_steps_per_second": 9.944,
+      "step": 1000
+    },
+    {
+      "epoch": 0.014717577219197408,
+      "grad_norm": 540.063720703125,
+      "learning_rate": 1.4542778781189378e-06,
+      "loss": 206.4545,
+      "step": 1100
+    },
+    {
+      "epoch": 0.01605553878457899,
+      "grad_norm": 830.7228393554688,
+      "learning_rate": 1.5880660913773498e-06,
+      "loss": 214.426,
+      "step": 1200
+    },
+    {
+      "epoch": 0.017393500349960574,
+      "grad_norm": 597.8634643554688,
+      "learning_rate": 1.7218543046357616e-06,
+      "loss": 217.0942,
+      "step": 1300
+    },
+    {
+      "epoch": 0.018731461915342154,
+      "grad_norm": 700.58349609375,
+      "learning_rate": 1.8556425178941738e-06,
+      "loss": 212.094,
+      "step": 1400
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "grad_norm": 612.1179809570312,
+      "learning_rate": 1.9894307311525855e-06,
+      "loss": 220.9056,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_codesearchnet_loss": 11.045117378234863,
+      "eval_codesearchnet_runtime": 866.9128,
+      "eval_codesearchnet_samples_per_second": 34.606,
+      "eval_codesearchnet_steps_per_second": 2.163,
+      "eval_cosine_accuracy@1": 0.23076666666666668,
+      "eval_cosine_accuracy@10": 0.3757333333333333,
+      "eval_cosine_accuracy@3": 0.3079,
+      "eval_cosine_accuracy@5": 0.3379,
+      "eval_cosine_map@100": 0.28190035706940875,
+      "eval_cosine_mrr@10": 0.27684927248677,
+      "eval_cosine_ndcg@10": 0.3005750904599357,
+      "eval_cosine_precision@1": 0.23076666666666668,
+      "eval_cosine_precision@10": 0.037573333333333334,
+      "eval_cosine_precision@3": 0.10263333333333333,
+      "eval_cosine_precision@5": 0.06758,
+      "eval_cosine_recall@1": 0.23076666666666668,
+      "eval_cosine_recall@10": 0.3757333333333333,
+      "eval_cosine_recall@3": 0.3079,
+      "eval_cosine_recall@5": 0.3379,
+      "eval_sequential_score": 0.24193695292620615,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_codesearchnet_en_loss": 9.401904106140137,
+      "eval_codesearchnet_en_runtime": 532.7041,
+      "eval_codesearchnet_en_samples_per_second": 56.316,
+      "eval_codesearchnet_en_steps_per_second": 3.52,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 220.2554,
+      "eval_codesearchnet_pairs_samples_per_second": 136.205,
+      "eval_codesearchnet_pairs_steps_per_second": 8.513,
+      "step": 1500
+    },
+    {
+      "epoch": 0.020069423480723738,
+      "eval_solyanka_qa_loss": 9.384902000427246,
+      "eval_solyanka_qa_runtime": 32.4876,
+      "eval_solyanka_qa_samples_per_second": 153.905,
+      "eval_solyanka_qa_steps_per_second": 9.634,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02140738504610532,
+      "grad_norm": 974.6611938476562,
+      "learning_rate": 2.1232189444109977e-06,
+      "loss": 207.0585,
+      "step": 1600
+    },
+    {
+      "epoch": 0.022745346611486902,
+      "grad_norm": 738.9705810546875,
+      "learning_rate": 2.2570071576694095e-06,
+      "loss": 210.1663,
+      "step": 1700
+    },
+    {
+      "epoch": 0.024083308176868483,
+      "grad_norm": 1021.1400756835938,
+      "learning_rate": 2.3907953709278212e-06,
+      "loss": 218.8182,
+      "step": 1800
+    },
+    {
+      "epoch": 0.025421269742250067,
+      "grad_norm": 802.8325805664062,
+      "learning_rate": 2.524583584186233e-06,
+      "loss": 215.3143,
+      "step": 1900
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "grad_norm": 1093.64013671875,
+      "learning_rate": 2.6583717974446456e-06,
+      "loss": 218.6588,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_codesearchnet_loss": 9.979716300964355,
+      "eval_codesearchnet_runtime": 866.9971,
+      "eval_codesearchnet_samples_per_second": 34.602,
+      "eval_codesearchnet_steps_per_second": 2.163,
+      "eval_cosine_accuracy@1": 0.24446666666666667,
+      "eval_cosine_accuracy@10": 0.42646666666666666,
+      "eval_cosine_accuracy@3": 0.34023333333333333,
+      "eval_cosine_accuracy@5": 0.3771,
+      "eval_cosine_map@100": 0.3082119579214764,
+      "eval_cosine_mrr@10": 0.3019686111111121,
+      "eval_cosine_ndcg@10": 0.33179718595033053,
+      "eval_cosine_precision@1": 0.24446666666666667,
+      "eval_cosine_precision@10": 0.04264666666666667,
+      "eval_cosine_precision@3": 0.1134111111111111,
+      "eval_cosine_precision@5": 0.07542,
+      "eval_cosine_recall@1": 0.24446666666666667,
+      "eval_cosine_recall@10": 0.42646666666666666,
+      "eval_cosine_recall@3": 0.34023333333333333,
+      "eval_cosine_recall@5": 0.3771,
+      "eval_sequential_score": 0.26055948736028667,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_codesearchnet_en_loss": 7.814389705657959,
+      "eval_codesearchnet_en_runtime": 534.4064,
+      "eval_codesearchnet_en_samples_per_second": 56.137,
+      "eval_codesearchnet_en_steps_per_second": 3.509,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 214.7347,
+      "eval_codesearchnet_pairs_samples_per_second": 139.707,
+      "eval_codesearchnet_pairs_steps_per_second": 8.732,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02675923130763165,
+      "eval_solyanka_qa_loss": 8.106107711791992,
+      "eval_solyanka_qa_runtime": 32.6063,
+      "eval_solyanka_qa_samples_per_second": 153.345,
+      "eval_solyanka_qa_steps_per_second": 9.599,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02809719287301323,
+      "grad_norm": 811.26904296875,
+      "learning_rate": 2.7921600107030574e-06,
+      "loss": 205.0786,
+      "step": 2100
+    },
+    {
+      "epoch": 0.029435154438394815,
+      "grad_norm": 1056.2335205078125,
+      "learning_rate": 2.9259482239614696e-06,
+      "loss": 204.1811,
+      "step": 2200
+    },
+    {
+      "epoch": 0.030773116003776396,
+      "grad_norm": 1020.6990356445312,
+      "learning_rate": 3.0597364372198813e-06,
+      "loss": 212.5886,
+      "step": 2300
+    },
+    {
+      "epoch": 0.03211107756915798,
+      "grad_norm": 1026.921630859375,
+      "learning_rate": 3.193524650478293e-06,
+      "loss": 206.9817,
+      "step": 2400
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "grad_norm": 731.8707275390625,
+      "learning_rate": 3.3273128637367053e-06,
+      "loss": 205.3238,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_codesearchnet_loss": 9.194226264953613,
+      "eval_codesearchnet_runtime": 870.7103,
+      "eval_codesearchnet_samples_per_second": 34.455,
+      "eval_codesearchnet_steps_per_second": 2.153,
+      "eval_cosine_accuracy@1": 0.3000333333333333,
+      "eval_cosine_accuracy@10": 0.49573333333333336,
+      "eval_cosine_accuracy@3": 0.4056,
+      "eval_cosine_accuracy@5": 0.4457333333333333,
+      "eval_cosine_map@100": 0.3686168427553011,
+      "eval_cosine_mrr@10": 0.36286292328043074,
+      "eval_cosine_ndcg@10": 0.3947834611601081,
+      "eval_cosine_precision@1": 0.3000333333333333,
+      "eval_cosine_precision@10": 0.04957333333333334,
+      "eval_cosine_precision@3": 0.1352,
+      "eval_cosine_precision@5": 0.08914666666666665,
+      "eval_cosine_recall@1": 0.3000333333333333,
+      "eval_cosine_recall@10": 0.49573333333333336,
+      "eval_cosine_recall@3": 0.4056,
+      "eval_cosine_recall@5": 0.4457333333333333,
+      "eval_sequential_score": 0.3197606115350484,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_codesearchnet_en_loss": 6.940033435821533,
+      "eval_codesearchnet_en_runtime": 530.0387,
+      "eval_codesearchnet_en_samples_per_second": 56.6,
+      "eval_codesearchnet_en_steps_per_second": 3.537,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 222.2001,
+      "eval_codesearchnet_pairs_samples_per_second": 135.013,
+      "eval_codesearchnet_pairs_steps_per_second": 8.438,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03344903913453956,
+      "eval_solyanka_qa_loss": 6.828629493713379,
+      "eval_solyanka_qa_runtime": 32.3285,
+      "eval_solyanka_qa_samples_per_second": 154.662,
+      "eval_solyanka_qa_steps_per_second": 9.682,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03478700069992115,
+      "grad_norm": 937.7930908203125,
+      "learning_rate": 3.461101076995117e-06,
+      "loss": 206.5246,
+      "step": 2600
+    },
+    {
+      "epoch": 0.03612496226530273,
+      "grad_norm": 4948.39794921875,
+      "learning_rate": 3.594889290253529e-06,
+      "loss": 207.9754,
+      "step": 2700
+    },
+    {
+      "epoch": 0.03746292383068431,
+      "grad_norm": 831.9579467773438,
+      "learning_rate": 3.728677503511941e-06,
+      "loss": 202.3154,
+      "step": 2800
+    },
+    {
+      "epoch": 0.03880088539606589,
+      "grad_norm": 1097.06640625,
+      "learning_rate": 3.862465716770352e-06,
+      "loss": 193.8885,
+      "step": 2900
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "grad_norm": 897.6323852539062,
+      "learning_rate": 3.996253930028765e-06,
+      "loss": 210.3421,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_codesearchnet_loss": 6.052410125732422,
+      "eval_codesearchnet_runtime": 870.4612,
+      "eval_codesearchnet_samples_per_second": 34.464,
+      "eval_codesearchnet_steps_per_second": 2.154,
+      "eval_cosine_accuracy@1": 0.5397333333333333,
+      "eval_cosine_accuracy@10": 0.7488333333333334,
+      "eval_cosine_accuracy@3": 0.6638,
+      "eval_cosine_accuracy@5": 0.7044666666666667,
+      "eval_cosine_map@100": 0.6148666000208418,
+      "eval_cosine_mrr@10": 0.6105341666666715,
+      "eval_cosine_ndcg@10": 0.6440482320852767,
+      "eval_cosine_precision@1": 0.5397333333333333,
+      "eval_cosine_precision@10": 0.07488333333333333,
+      "eval_cosine_precision@3": 0.22126666666666664,
+      "eval_cosine_precision@5": 0.14089333333333331,
+      "eval_cosine_recall@1": 0.5397333333333333,
+      "eval_cosine_recall@10": 0.7488333333333334,
+      "eval_cosine_recall@3": 0.6638,
+      "eval_cosine_recall@5": 0.7044666666666667,
+      "eval_sequential_score": 0.5582850083065141,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_codesearchnet_en_loss": 4.175703048706055,
+      "eval_codesearchnet_en_runtime": 533.1214,
+      "eval_codesearchnet_en_samples_per_second": 56.272,
+      "eval_codesearchnet_en_steps_per_second": 3.517,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 218.5646,
+      "eval_codesearchnet_pairs_samples_per_second": 137.259,
+      "eval_codesearchnet_pairs_steps_per_second": 8.579,
+      "step": 3000
+    },
+    {
+      "epoch": 0.040138846961447476,
+      "eval_solyanka_qa_loss": 4.920586585998535,
+      "eval_solyanka_qa_runtime": 32.539,
+      "eval_solyanka_qa_samples_per_second": 153.662,
+      "eval_solyanka_qa_steps_per_second": 9.619,
+      "step": 3000
+    },
+    {
+      "epoch": 0.041476808526829057,
+      "grad_norm": 1480.8231201171875,
+      "learning_rate": 4.130042143287177e-06,
+      "loss": 198.6064,
+      "step": 3100
+    },
+    {
+      "epoch": 0.04281477009221064,
+      "grad_norm": 1052.9395751953125,
+      "learning_rate": 4.2638303565455885e-06,
+      "loss": 202.1395,
+      "step": 3200
+    },
+    {
+      "epoch": 0.044152731657592224,
+      "grad_norm": 1055.3389892578125,
+      "learning_rate": 4.397618569804001e-06,
+      "loss": 200.4315,
+      "step": 3300
+    },
+    {
+      "epoch": 0.045490693222973805,
+      "grad_norm": 1264.2374267578125,
+      "learning_rate": 4.531406783062413e-06,
+      "loss": 190.5145,
+      "step": 3400
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "grad_norm": 1371.5516357421875,
+      "learning_rate": 4.665194996320825e-06,
+      "loss": 195.653,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_codesearchnet_loss": 6.666440963745117,
+      "eval_codesearchnet_runtime": 868.1141,
+      "eval_codesearchnet_samples_per_second": 34.558,
+      "eval_codesearchnet_steps_per_second": 2.16,
+      "eval_cosine_accuracy@1": 0.4233,
+      "eval_cosine_accuracy@10": 0.6468333333333334,
+      "eval_cosine_accuracy@3": 0.5530333333333334,
+      "eval_cosine_accuracy@5": 0.5977,
+      "eval_cosine_map@100": 0.5032596816876523,
+      "eval_cosine_mrr@10": 0.4980684126984272,
+      "eval_cosine_ndcg@10": 0.5340651234341146,
+      "eval_cosine_precision@1": 0.4233,
+      "eval_cosine_precision@10": 0.06468333333333333,
+      "eval_cosine_precision@3": 0.18434444444444442,
+      "eval_cosine_precision@5": 0.11954,
+      "eval_cosine_recall@1": 0.4233,
+      "eval_cosine_recall@10": 0.6468333333333334,
+      "eval_cosine_recall@3": 0.5530333333333334,
+      "eval_cosine_recall@5": 0.5977,
+      "eval_sequential_score": 0.45468531483126856,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_codesearchnet_en_loss": 4.728166580200195,
+      "eval_codesearchnet_en_runtime": 533.0589,
+      "eval_codesearchnet_en_samples_per_second": 56.279,
+      "eval_codesearchnet_en_steps_per_second": 3.517,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 222.014,
+      "eval_codesearchnet_pairs_samples_per_second": 135.127,
+      "eval_codesearchnet_pairs_steps_per_second": 8.445,
+      "step": 3500
+    },
+    {
+      "epoch": 0.046828654788355385,
+      "eval_solyanka_qa_loss": 4.346282005310059,
+      "eval_solyanka_qa_runtime": 32.5056,
+      "eval_solyanka_qa_samples_per_second": 153.82,
+      "eval_solyanka_qa_steps_per_second": 9.629,
+      "step": 3500
+    },
+    {
+      "epoch": 0.048166616353736966,
+      "grad_norm": 832.6646728515625,
+      "learning_rate": 4.798983209579236e-06,
+      "loss": 200.2459,
+      "step": 3600
+    },
+    {
+      "epoch": 0.04950457791911855,
+      "grad_norm": 1429.9462890625,
+      "learning_rate": 4.932771422837648e-06,
+      "loss": 189.7009,
+      "step": 3700
+    },
+    {
+      "epoch": 0.050842539484500134,
+      "grad_norm": 1101.5008544921875,
+      "learning_rate": 5.06655963609606e-06,
+      "loss": 189.3891,
+      "step": 3800
+    },
+    {
+      "epoch": 0.052180501049881714,
+      "grad_norm": 1311.8643798828125,
+      "learning_rate": 5.2003478493544725e-06,
+      "loss": 197.5025,
+      "step": 3900
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "grad_norm": 1112.9697265625,
+      "learning_rate": 5.334136062612884e-06,
+      "loss": 191.8113,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_codesearchnet_loss": 6.12751579284668,
+      "eval_codesearchnet_runtime": 789.24,
+      "eval_codesearchnet_samples_per_second": 38.011,
+      "eval_codesearchnet_steps_per_second": 2.376,
+      "eval_cosine_accuracy@1": 0.4841,
+      "eval_cosine_accuracy@10": 0.6953333333333334,
+      "eval_cosine_accuracy@3": 0.6093,
+      "eval_cosine_accuracy@5": 0.6484333333333333,
+      "eval_cosine_map@100": 0.5600661539369967,
+      "eval_cosine_mrr@10": 0.55571821428573,
+      "eval_cosine_ndcg@10": 0.5895257290681525,
+      "eval_cosine_precision@1": 0.4841,
+      "eval_cosine_precision@10": 0.06953333333333334,
+      "eval_cosine_precision@3": 0.2031,
+      "eval_cosine_precision@5": 0.12968666666666667,
+      "eval_cosine_recall@1": 0.4841,
+      "eval_cosine_recall@10": 0.6953333333333334,
+      "eval_cosine_recall@3": 0.6093,
+      "eval_cosine_recall@5": 0.6484333333333333,
+      "eval_sequential_score": 0.5141830504398937,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_codesearchnet_en_loss": 4.2443318367004395,
+      "eval_codesearchnet_en_runtime": 480.3149,
+      "eval_codesearchnet_en_samples_per_second": 62.459,
+      "eval_codesearchnet_en_steps_per_second": 3.904,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 183.8739,
+      "eval_codesearchnet_pairs_samples_per_second": 163.155,
+      "eval_codesearchnet_pairs_steps_per_second": 10.197,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0535184626152633,
+      "eval_solyanka_qa_loss": 4.089145183563232,
+      "eval_solyanka_qa_runtime": 25.3337,
+      "eval_solyanka_qa_samples_per_second": 197.366,
+      "eval_solyanka_qa_steps_per_second": 12.355,
+      "step": 4000
+    },
+    {
+      "epoch": 0.05485642418064488,
+      "grad_norm": 1041.763916015625,
+      "learning_rate": 5.467924275871296e-06,
+      "loss": 181.2907,
+      "step": 4100
+    },
+    {
+      "epoch": 0.05619438574602646,
+      "grad_norm": 1189.8985595703125,
+      "learning_rate": 5.601712489129708e-06,
+      "loss": 193.7115,
+      "step": 4200
+    },
+    {
+      "epoch": 0.05753234731140804,
+      "grad_norm": 1995.246826171875,
+      "learning_rate": 5.7355007023881204e-06,
+      "loss": 187.6769,
+      "step": 4300
+    },
+    {
+      "epoch": 0.05887030887678963,
+      "grad_norm": 962.8026123046875,
+      "learning_rate": 5.869288915646531e-06,
+      "loss": 186.3607,
+      "step": 4400
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "grad_norm": 1693.328369140625,
+      "learning_rate": 6.00173924677236e-06,
+      "loss": 191.9243,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_codesearchnet_loss": 5.4969258308410645,
+      "eval_codesearchnet_runtime": 798.8982,
+      "eval_codesearchnet_samples_per_second": 37.552,
+      "eval_codesearchnet_steps_per_second": 2.347,
+      "eval_cosine_accuracy@1": 0.5401333333333334,
+      "eval_cosine_accuracy@10": 0.7383333333333333,
+      "eval_cosine_accuracy@3": 0.6606666666666666,
+      "eval_cosine_accuracy@5": 0.6969,
+      "eval_cosine_map@100": 0.6123297048019136,
+      "eval_cosine_mrr@10": 0.6082852777777863,
+      "eval_cosine_ndcg@10": 0.6398697969385133,
+      "eval_cosine_precision@1": 0.5401333333333334,
+      "eval_cosine_precision@10": 0.07383333333333333,
+      "eval_cosine_precision@3": 0.2202222222222222,
+      "eval_cosine_precision@5": 0.13937999999999998,
+      "eval_cosine_recall@1": 0.5401333333333334,
+      "eval_cosine_recall@10": 0.7383333333333333,
+      "eval_cosine_recall@3": 0.6606666666666666,
+      "eval_cosine_recall@5": 0.6969,
+      "eval_sequential_score": 0.5623610573754854,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_codesearchnet_en_loss": 3.7932770252227783,
+      "eval_codesearchnet_en_runtime": 486.7262,
+      "eval_codesearchnet_en_samples_per_second": 61.636,
+      "eval_codesearchnet_en_steps_per_second": 3.852,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 189.9044,
+      "eval_codesearchnet_pairs_samples_per_second": 157.974,
+      "eval_codesearchnet_pairs_steps_per_second": 9.873,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06020827044217121,
+      "eval_solyanka_qa_loss": 4.172121047973633,
+      "eval_solyanka_qa_runtime": 26.9517,
+      "eval_solyanka_qa_samples_per_second": 185.517,
+      "eval_solyanka_qa_steps_per_second": 11.613,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06154623200755279,
+      "grad_norm": 1067.1920166015625,
+      "learning_rate": 6.135527460030771e-06,
+      "loss": 189.8334,
+      "step": 4600
+    },
+    {
+      "epoch": 0.06288419357293437,
+      "grad_norm": 4186.00439453125,
+      "learning_rate": 6.269315673289184e-06,
+      "loss": 186.4033,
+      "step": 4700
+    },
+    {
+      "epoch": 0.06422215513831596,
+      "grad_norm": 1410.729736328125,
+      "learning_rate": 6.4031038865475954e-06,
+      "loss": 184.225,
+      "step": 4800
+    },
+    {
+      "epoch": 0.06556011670369755,
+      "grad_norm": 1268.47265625,
+      "learning_rate": 6.536892099806008e-06,
+      "loss": 188.3992,
+      "step": 4900
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "grad_norm": 1120.933837890625,
+      "learning_rate": 6.670680313064419e-06,
+      "loss": 183.9708,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_codesearchnet_loss": 4.910182476043701,
+      "eval_codesearchnet_runtime": 793.2722,
+      "eval_codesearchnet_samples_per_second": 37.818,
+      "eval_codesearchnet_steps_per_second": 2.364,
+      "eval_cosine_accuracy@1": 0.5617666666666666,
+      "eval_cosine_accuracy@10": 0.7616,
+      "eval_cosine_accuracy@3": 0.6858666666666666,
+      "eval_cosine_accuracy@5": 0.7219333333333333,
+      "eval_cosine_map@100": 0.6352974693863399,
+      "eval_cosine_mrr@10": 0.6315028703703756,
+      "eval_cosine_ndcg@10": 0.6631716590320138,
+      "eval_cosine_precision@1": 0.5617666666666666,
+      "eval_cosine_precision@10": 0.07615999999999999,
+      "eval_cosine_precision@3": 0.2286222222222222,
+      "eval_cosine_precision@5": 0.1443866666666667,
+      "eval_cosine_recall@1": 0.5617666666666666,
+      "eval_cosine_recall@10": 0.7616,
+      "eval_cosine_recall@3": 0.6858666666666666,
+      "eval_cosine_recall@5": 0.7219333333333333,
+      "eval_sequential_score": 0.588823994072985,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_codesearchnet_en_loss": 3.2918059825897217,
+      "eval_codesearchnet_en_runtime": 482.3681,
+      "eval_codesearchnet_en_samples_per_second": 62.193,
+      "eval_codesearchnet_en_steps_per_second": 3.887,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 187.4741,
+      "eval_codesearchnet_pairs_samples_per_second": 160.022,
+      "eval_codesearchnet_pairs_steps_per_second": 10.001,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06689807826907912,
+      "eval_solyanka_qa_loss": 3.8115358352661133,
+      "eval_solyanka_qa_runtime": 25.8592,
+      "eval_solyanka_qa_samples_per_second": 193.354,
+      "eval_solyanka_qa_steps_per_second": 12.104,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06823603983446071,
+      "grad_norm": 931.2894287109375,
+      "learning_rate": 6.8044685263228316e-06,
+      "loss": 193.8627,
+      "step": 5100
+    },
+    {
+      "epoch": 0.0695740013998423,
+      "grad_norm": 1761.0831298828125,
+      "learning_rate": 6.938256739581244e-06,
+      "loss": 186.6093,
+      "step": 5200
+    },
+    {
+      "epoch": 0.07091196296522387,
+      "grad_norm": 1396.5413818359375,
+      "learning_rate": 7.072044952839655e-06,
+      "loss": 178.5979,
+      "step": 5300
+    },
+    {
+      "epoch": 0.07224992453060546,
+      "grad_norm": 1139.1634521484375,
+      "learning_rate": 7.205833166098068e-06,
+      "loss": 187.7019,
+      "step": 5400
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "grad_norm": 1028.661376953125,
+      "learning_rate": 7.3396213793564795e-06,
+      "loss": 182.9072,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_codesearchnet_loss": 5.771347999572754,
+      "eval_codesearchnet_runtime": 791.0446,
+      "eval_codesearchnet_samples_per_second": 37.925,
+      "eval_codesearchnet_steps_per_second": 2.37,
+      "eval_cosine_accuracy@1": 0.5377,
+      "eval_cosine_accuracy@10": 0.7404333333333334,
+      "eval_cosine_accuracy@3": 0.6615333333333333,
+      "eval_cosine_accuracy@5": 0.6998666666666666,
+      "eval_cosine_map@100": 0.6115645028851873,
+      "eval_cosine_mrr@10": 0.6076140476190545,
+      "eval_cosine_ndcg@10": 0.639898364994289,
+      "eval_cosine_precision@1": 0.5377,
+      "eval_cosine_precision@10": 0.07404333333333334,
+      "eval_cosine_precision@3": 0.2205111111111111,
+      "eval_cosine_precision@5": 0.13997333333333334,
+      "eval_cosine_recall@1": 0.5377,
+      "eval_cosine_recall@10": 0.7404333333333334,
+      "eval_cosine_recall@3": 0.6615333333333333,
+      "eval_cosine_recall@5": 0.6998666666666666,
+      "eval_sequential_score": 0.5537658861174344,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_codesearchnet_en_loss": 4.075521945953369,
+      "eval_codesearchnet_en_runtime": 480.6923,
+      "eval_codesearchnet_en_samples_per_second": 62.41,
+      "eval_codesearchnet_en_steps_per_second": 3.901,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 185.6337,
+      "eval_codesearchnet_pairs_samples_per_second": 161.609,
+      "eval_codesearchnet_pairs_steps_per_second": 10.101,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07358788609598703,
+      "eval_solyanka_qa_loss": 4.20865535736084,
+      "eval_solyanka_qa_runtime": 25.9517,
+      "eval_solyanka_qa_samples_per_second": 192.665,
+      "eval_solyanka_qa_steps_per_second": 12.061,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07492584766136862,
+      "grad_norm": 1251.1859130859375,
+      "learning_rate": 7.473409592614891e-06,
+      "loss": 186.9648,
+      "step": 5600
+    },
+    {
+      "epoch": 0.0762638092267502,
+      "grad_norm": 1243.02099609375,
+      "learning_rate": 7.607197805873303e-06,
+      "loss": 182.2779,
+      "step": 5700
+    },
+    {
+      "epoch": 0.07760177079213178,
+      "grad_norm": 1062.451171875,
+      "learning_rate": 7.740986019131716e-06,
+      "loss": 179.2852,
+      "step": 5800
+    },
+    {
+      "epoch": 0.07893973235751336,
+      "grad_norm": 1121.85009765625,
+      "learning_rate": 7.874774232390127e-06,
+      "loss": 170.5596,
+      "step": 5900
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "grad_norm": 1335.1585693359375,
+      "learning_rate": 8.008562445648539e-06,
+      "loss": 182.9913,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_codesearchnet_loss": 4.416569232940674,
+      "eval_codesearchnet_runtime": 827.7981,
+      "eval_codesearchnet_samples_per_second": 36.241,
+      "eval_codesearchnet_steps_per_second": 2.265,
+      "eval_cosine_accuracy@1": 0.5953,
+      "eval_cosine_accuracy@10": 0.7925,
+      "eval_cosine_accuracy@3": 0.7213333333333334,
+      "eval_cosine_accuracy@5": 0.7560333333333333,
+      "eval_cosine_map@100": 0.6682719879085095,
+      "eval_cosine_mrr@10": 0.6647914021164015,
+      "eval_cosine_ndcg@10": 0.6959528934005342,
+      "eval_cosine_precision@1": 0.5953,
+      "eval_cosine_precision@10": 0.07925,
+      "eval_cosine_precision@3": 0.24044444444444443,
+      "eval_cosine_precision@5": 0.15120666666666666,
+      "eval_cosine_recall@1": 0.5953,
+      "eval_cosine_recall@10": 0.7925,
+      "eval_cosine_recall@3": 0.7213333333333334,
+      "eval_cosine_recall@5": 0.7560333333333333,
+      "eval_sequential_score": 0.625740827587927,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_codesearchnet_en_loss": 3.067141056060791,
+      "eval_codesearchnet_en_runtime": 531.0437,
+      "eval_codesearchnet_en_samples_per_second": 56.493,
+      "eval_codesearchnet_en_steps_per_second": 3.531,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 231.1077,
+      "eval_codesearchnet_pairs_samples_per_second": 129.81,
+      "eval_codesearchnet_pairs_steps_per_second": 8.113,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08027769392289495,
+      "eval_solyanka_qa_loss": 3.54522967338562,
+      "eval_solyanka_qa_runtime": 35.3187,
+      "eval_solyanka_qa_samples_per_second": 141.568,
+      "eval_solyanka_qa_steps_per_second": 8.862,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08161565548827653,
+      "grad_norm": 1462.4613037109375,
+      "learning_rate": 8.142350658906952e-06,
+      "loss": 180.0925,
+      "step": 6100
+    },
+    {
+      "epoch": 0.08295361705365811,
+      "grad_norm": 1306.346435546875,
+      "learning_rate": 8.276138872165363e-06,
+      "loss": 177.6538,
+      "step": 6200
+    },
+    {
+      "epoch": 0.0842915786190397,
+      "grad_norm": 795.7644653320312,
+      "learning_rate": 8.409927085423775e-06,
+      "loss": 176.7865,
+      "step": 6300
+    },
+    {
+      "epoch": 0.08562954018442127,
+      "grad_norm": 1051.8511962890625,
+      "learning_rate": 8.543715298682186e-06,
+      "loss": 177.2024,
+      "step": 6400
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "grad_norm": 1394.38818359375,
+      "learning_rate": 8.677503511940599e-06,
+      "loss": 183.0437,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_codesearchnet_loss": 4.107079029083252,
+      "eval_codesearchnet_runtime": 933.9902,
+      "eval_codesearchnet_samples_per_second": 32.12,
+      "eval_codesearchnet_steps_per_second": 2.008,
+      "eval_cosine_accuracy@1": 0.5766666666666667,
+      "eval_cosine_accuracy@10": 0.7799333333333334,
+      "eval_cosine_accuracy@3": 0.7028333333333333,
+      "eval_cosine_accuracy@5": 0.7409333333333333,
+      "eval_cosine_map@100": 0.6514269801326987,
+      "eval_cosine_mrr@10": 0.6477988095238115,
+      "eval_cosine_ndcg@10": 0.6799886507436855,
+      "eval_cosine_precision@1": 0.5766666666666667,
+      "eval_cosine_precision@10": 0.07799333333333335,
+      "eval_cosine_precision@3": 0.23427777777777772,
+      "eval_cosine_precision@5": 0.1481866666666667,
+      "eval_cosine_recall@1": 0.5766666666666667,
+      "eval_cosine_recall@10": 0.7799333333333334,
+      "eval_cosine_recall@3": 0.7028333333333333,
+      "eval_cosine_recall@5": 0.7409333333333333,
+      "eval_sequential_score": 0.6109291855288735,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_codesearchnet_en_loss": 2.8989362716674805,
+      "eval_codesearchnet_en_runtime": 548.5847,
+      "eval_codesearchnet_en_samples_per_second": 54.686,
+      "eval_codesearchnet_en_steps_per_second": 3.418,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 251.9769,
+      "eval_codesearchnet_pairs_samples_per_second": 119.059,
+      "eval_codesearchnet_pairs_steps_per_second": 7.441,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08696750174980286,
+      "eval_solyanka_qa_loss": 3.395298719406128,
+      "eval_solyanka_qa_runtime": 42.1787,
+      "eval_solyanka_qa_samples_per_second": 118.543,
+      "eval_solyanka_qa_steps_per_second": 7.421,
+      "step": 6500
+    },
+    {
+      "epoch": 0.08830546331518445,
+      "grad_norm": 953.8713989257812,
+      "learning_rate": 8.81129172519901e-06,
+      "loss": 174.4866,
+      "step": 6600
+    },
+    {
+      "epoch": 0.08964342488056602,
+      "grad_norm": 1037.1529541015625,
+      "learning_rate": 8.945079938457422e-06,
+      "loss": 180.6098,
+      "step": 6700
+    },
+    {
+      "epoch": 0.09098138644594761,
+      "grad_norm": 2274.166748046875,
+      "learning_rate": 9.078868151715835e-06,
+      "loss": 175.4703,
+      "step": 6800
+    },
+    {
+      "epoch": 0.09231934801132918,
+      "grad_norm": 1078.928466796875,
+      "learning_rate": 9.212656364974246e-06,
+      "loss": 183.6586,
+      "step": 6900
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "grad_norm": 1381.9674072265625,
+      "learning_rate": 9.345106696100075e-06,
+      "loss": 171.7979,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_codesearchnet_loss": 5.207095146179199,
+      "eval_codesearchnet_runtime": 907.058,
+      "eval_codesearchnet_samples_per_second": 33.074,
+      "eval_codesearchnet_steps_per_second": 2.067,
+      "eval_cosine_accuracy@1": 0.5449333333333334,
+      "eval_cosine_accuracy@10": 0.7414333333333334,
+      "eval_cosine_accuracy@3": 0.6638333333333334,
+      "eval_cosine_accuracy@5": 0.7017666666666666,
+      "eval_cosine_map@100": 0.6164075899784531,
+      "eval_cosine_mrr@10": 0.6126674338624413,
+      "eval_cosine_ndcg@10": 0.6439444961382464,
+      "eval_cosine_precision@1": 0.5449333333333334,
+      "eval_cosine_precision@10": 0.07414333333333334,
+      "eval_cosine_precision@3": 0.22127777777777777,
+      "eval_cosine_precision@5": 0.1403533333333333,
+      "eval_cosine_recall@1": 0.5449333333333334,
+      "eval_cosine_recall@10": 0.7414333333333334,
+      "eval_cosine_recall@3": 0.6638333333333334,
+      "eval_cosine_recall@5": 0.7017666666666666,
+      "eval_sequential_score": 0.5749765917991857,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_codesearchnet_en_loss": 3.596595287322998,
+      "eval_codesearchnet_en_runtime": 536.7682,
+      "eval_codesearchnet_en_samples_per_second": 55.89,
+      "eval_codesearchnet_en_steps_per_second": 3.493,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 240.2488,
+      "eval_codesearchnet_pairs_samples_per_second": 124.871,
+      "eval_codesearchnet_pairs_steps_per_second": 7.804,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09365730957671077,
+      "eval_solyanka_qa_loss": 4.301774024963379,
+      "eval_solyanka_qa_runtime": 36.632,
+      "eval_solyanka_qa_samples_per_second": 136.493,
+      "eval_solyanka_qa_steps_per_second": 8.544,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09499527114209236,
+      "grad_norm": 1252.0892333984375,
+      "learning_rate": 9.478894909358486e-06,
+      "loss": 173.3894,
+      "step": 7100
+    },
+    {
+      "epoch": 0.09633323270747393,
+      "grad_norm": 1923.31201171875,
+      "learning_rate": 9.612683122616898e-06,
+      "loss": 174.4687,
+      "step": 7200
+    },
+    {
+      "epoch": 0.09767119427285552,
+      "grad_norm": 1374.7725830078125,
+      "learning_rate": 9.74647133587531e-06,
+      "loss": 174.5152,
+      "step": 7300
+    },
+    {
+      "epoch": 0.0990091558382371,
+      "grad_norm": 1235.3150634765625,
+      "learning_rate": 9.880259549133722e-06,
+      "loss": 179.1588,
+      "step": 7400
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "grad_norm": 5407.0478515625,
+      "learning_rate": 1.0014047762392134e-05,
+      "loss": 179.4099,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_codesearchnet_loss": 4.5956878662109375,
+      "eval_codesearchnet_runtime": 896.509,
+      "eval_codesearchnet_samples_per_second": 33.463,
+      "eval_codesearchnet_steps_per_second": 2.091,
+      "eval_cosine_accuracy@1": 0.5804333333333334,
+      "eval_cosine_accuracy@10": 0.7716333333333333,
+      "eval_cosine_accuracy@3": 0.7015666666666667,
+      "eval_cosine_accuracy@5": 0.7351,
+      "eval_cosine_map@100": 0.6513085394657405,
+      "eval_cosine_mrr@10": 0.6478177248677272,
+      "eval_cosine_ndcg@10": 0.6780089383245728,
+      "eval_cosine_precision@1": 0.5804333333333334,
+      "eval_cosine_precision@10": 0.07716333333333333,
+      "eval_cosine_precision@3": 0.23385555555555554,
+      "eval_cosine_precision@5": 0.14702,
+      "eval_cosine_recall@1": 0.5804333333333334,
+      "eval_cosine_recall@10": 0.7716333333333333,
+      "eval_cosine_recall@3": 0.7015666666666667,
+      "eval_cosine_recall@5": 0.7351,
+      "eval_sequential_score": 0.6085904680593567,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_codesearchnet_en_loss": 3.176692485809326,
+      "eval_codesearchnet_en_runtime": 537.5798,
+      "eval_codesearchnet_en_samples_per_second": 55.806,
+      "eval_codesearchnet_en_steps_per_second": 3.488,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 233.6133,
+      "eval_codesearchnet_pairs_samples_per_second": 128.417,
+      "eval_codesearchnet_pairs_steps_per_second": 8.026,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10034711740361868,
+      "eval_solyanka_qa_loss": 3.3527519702911377,
+      "eval_solyanka_qa_runtime": 35.6484,
+      "eval_solyanka_qa_samples_per_second": 140.259,
+      "eval_solyanka_qa_steps_per_second": 8.78,
+      "step": 7500
+    },
+    {
+      "epoch": 0.10168507896900027,
+      "grad_norm": 1189.1429443359375,
+      "learning_rate": 1.0146498093517963e-05,
+      "loss": 173.8489,
+      "step": 7600
+    },
+    {
+      "epoch": 0.10436082756129317,
+      "grad_norm": 524.2390747070312,
+      "learning_rate": 1.0414074520034785e-05,
+      "loss": 57.8803,
+      "step": 7800
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "grad_norm": 364.2381896972656,
+      "learning_rate": 1.068165094655161e-05,
+      "loss": 50.8973,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_codesearchnet_loss": 0.5108523368835449,
+      "eval_codesearchnet_runtime": 850.8936,
+      "eval_codesearchnet_samples_per_second": 35.257,
+      "eval_codesearchnet_steps_per_second": 4.407,
+      "eval_cosine_accuracy@1": 0.7804666666666666,
+      "eval_cosine_accuracy@10": 0.9267,
+      "eval_cosine_accuracy@3": 0.8845,
+      "eval_cosine_accuracy@5": 0.9065,
+      "eval_cosine_map@100": 0.8373038141979917,
+      "eval_cosine_mrr@10": 0.8357315740740681,
+      "eval_cosine_ndcg@10": 0.8582006830716409,
+      "eval_cosine_precision@1": 0.7804666666666666,
+      "eval_cosine_precision@10": 0.09267000000000002,
+      "eval_cosine_precision@3": 0.29483333333333334,
+      "eval_cosine_precision@5": 0.18130000000000002,
+      "eval_cosine_recall@1": 0.7804666666666666,
+      "eval_cosine_recall@10": 0.9267,
+      "eval_cosine_recall@3": 0.8845,
+      "eval_cosine_recall@5": 0.9065,
+      "eval_sequential_score": 0.8191610196783502,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_codesearchnet_en_loss": 0.3525207042694092,
+      "eval_codesearchnet_en_runtime": 471.0461,
+      "eval_codesearchnet_en_samples_per_second": 63.688,
+      "eval_codesearchnet_en_steps_per_second": 7.961,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 321.2179,
+      "eval_codesearchnet_pairs_samples_per_second": 93.395,
+      "eval_codesearchnet_pairs_steps_per_second": 11.674,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10703674621671094,
+      "eval_solyanka_qa_loss": 0.6166790723800659,
+      "eval_solyanka_qa_runtime": 59.2988,
+      "eval_solyanka_qa_samples_per_second": 84.319,
+      "eval_solyanka_qa_steps_per_second": 10.54,
+      "step": 8000
+    },
+    {
+      "epoch": 0.10971266487212872,
+      "grad_norm": 539.6712646484375,
+      "learning_rate": 1.0949227373068434e-05,
+      "loss": 52.6686,
+      "step": 8200
+    },
+    {
+      "epoch": 0.11238858352754649,
+      "grad_norm": 285.00408935546875,
+      "learning_rate": 1.1216803799585259e-05,
+      "loss": 50.568,
+      "step": 8400
+    },
+    {
+      "epoch": 0.11506450218296427,
+      "grad_norm": 407.73565673828125,
+      "learning_rate": 1.148438022610208e-05,
+      "loss": 49.3516,
+      "step": 8600
+    },
+    {
+      "epoch": 0.11774042083838204,
+      "grad_norm": 322.4379577636719,
+      "learning_rate": 1.1751956652618906e-05,
+      "loss": 48.8846,
+      "step": 8800
+    },
+    {
+      "epoch": 0.12041633949379982,
+      "grad_norm": 267.22564697265625,
+      "learning_rate": 1.201953307913573e-05,
+      "loss": 49.1422,
+      "step": 9000
+    },
+    {
+      "epoch": 0.12309225814921759,
+      "grad_norm": 373.3161926269531,
+      "learning_rate": 1.2287109505652553e-05,
+      "loss": 51.4819,
+      "step": 9200
+    },
+    {
+      "epoch": 0.12576817680463537,
+      "grad_norm": 370.7853698730469,
+      "learning_rate": 1.2554685932169377e-05,
+      "loss": 45.9136,
+      "step": 9400
+    },
+    {
+      "epoch": 0.12844409546005314,
+      "grad_norm": 473.8594970703125,
+      "learning_rate": 1.2822262358686202e-05,
+      "loss": 46.4492,
+      "step": 9600
+    },
+    {
+      "epoch": 0.13112001411547092,
+      "grad_norm": 392.2969970703125,
+      "learning_rate": 1.3089838785203024e-05,
+      "loss": 49.4392,
+      "step": 9800
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "grad_norm": 392.4254455566406,
+      "learning_rate": 1.3357415211719849e-05,
+      "loss": 49.5231,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_codesearchnet_loss": 0.21050667762756348,
+      "eval_codesearchnet_runtime": 845.1488,
+      "eval_codesearchnet_samples_per_second": 35.497,
+      "eval_codesearchnet_steps_per_second": 4.437,
+      "eval_cosine_accuracy@1": 0.8419333333333333,
+      "eval_cosine_accuracy@10": 0.9506,
+      "eval_cosine_accuracy@3": 0.9236666666666666,
+      "eval_cosine_accuracy@5": 0.9386333333333333,
+      "eval_cosine_map@100": 0.8858101455522462,
+      "eval_cosine_mrr@10": 0.8847410185185097,
+      "eval_cosine_ndcg@10": 0.9011276163882171,
+      "eval_cosine_precision@1": 0.8419333333333333,
+      "eval_cosine_precision@10": 0.09506000000000002,
+      "eval_cosine_precision@3": 0.3078888888888889,
+      "eval_cosine_precision@5": 0.1877266666666667,
+      "eval_cosine_recall@1": 0.8419333333333333,
+      "eval_cosine_recall@10": 0.9506,
+      "eval_cosine_recall@3": 0.9236666666666666,
+      "eval_cosine_recall@5": 0.9386333333333333,
+      "eval_sequential_score": 0.8844637138667995,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_codesearchnet_en_loss": 0.1648031771183014,
+      "eval_codesearchnet_en_runtime": 477.1262,
+      "eval_codesearchnet_en_samples_per_second": 62.876,
+      "eval_codesearchnet_en_steps_per_second": 7.86,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 317.6118,
+      "eval_codesearchnet_pairs_samples_per_second": 94.455,
+      "eval_codesearchnet_pairs_steps_per_second": 11.807,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1337959327708887,
+      "eval_solyanka_qa_loss": 0.48000234365463257,
+      "eval_solyanka_qa_runtime": 58.4343,
+      "eval_solyanka_qa_samples_per_second": 85.566,
+      "eval_solyanka_qa_steps_per_second": 10.696,
+      "step": 10000
+    },
+    {
+      "epoch": 0.13647185142630647,
+      "grad_norm": 302.9349060058594,
+      "learning_rate": 1.3624991638236672e-05,
+      "loss": 44.8227,
+      "step": 10200
+    },
+    {
+      "epoch": 0.13914777008172421,
+      "grad_norm": 280.627685546875,
+      "learning_rate": 1.3892568064753496e-05,
+      "loss": 47.4191,
+      "step": 10400
+    },
+    {
+      "epoch": 0.141823688737142,
+      "grad_norm": 396.9530944824219,
+      "learning_rate": 1.416014449127032e-05,
+      "loss": 48.4208,
+      "step": 10600
+    },
+    {
+      "epoch": 0.14449960739255976,
+      "grad_norm": 567.6721801757812,
+      "learning_rate": 1.4427720917787145e-05,
+      "loss": 47.0498,
+      "step": 10800
+    },
+    {
+      "epoch": 0.14717552604797754,
+      "grad_norm": 399.8636779785156,
+      "learning_rate": 1.4695297344303966e-05,
+      "loss": 47.332,
+      "step": 11000
+    },
+    {
+      "epoch": 0.14985144470339531,
+      "grad_norm": 365.3705139160156,
+      "learning_rate": 1.4962873770820792e-05,
+      "loss": 46.6691,
+      "step": 11200
+    },
+    {
+      "epoch": 0.1525273633588131,
+      "grad_norm": 329.9962463378906,
+      "learning_rate": 1.5230450197337617e-05,
+      "loss": 48.4622,
+      "step": 11400
+    },
+    {
+      "epoch": 0.15520328201423086,
+      "grad_norm": 305.3818054199219,
+      "learning_rate": 1.549802662385444e-05,
+      "loss": 47.3353,
+      "step": 11600
+    },
+    {
+      "epoch": 0.15787920066964864,
+      "grad_norm": 353.5430908203125,
+      "learning_rate": 1.5765603050371262e-05,
+      "loss": 47.3603,
+      "step": 11800
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "grad_norm": 208.02548217773438,
+      "learning_rate": 1.6033179476888088e-05,
+      "loss": 47.0726,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_codesearchnet_loss": 0.17985302209854126,
+      "eval_codesearchnet_runtime": 849.7401,
+      "eval_codesearchnet_samples_per_second": 35.305,
+      "eval_codesearchnet_steps_per_second": 4.413,
+      "eval_cosine_accuracy@1": 0.8403,
+      "eval_cosine_accuracy@10": 0.9529666666666666,
+      "eval_cosine_accuracy@3": 0.9246666666666666,
+      "eval_cosine_accuracy@5": 0.9399333333333333,
+      "eval_cosine_map@100": 0.8856879053068674,
+      "eval_cosine_mrr@10": 0.8846578571428485,
+      "eval_cosine_ndcg@10": 0.9016476260382669,
+      "eval_cosine_precision@1": 0.8403,
+      "eval_cosine_precision@10": 0.09529666666666668,
+      "eval_cosine_precision@3": 0.3082222222222222,
+      "eval_cosine_precision@5": 0.1879866666666667,
+      "eval_cosine_recall@1": 0.8403,
+      "eval_cosine_recall@10": 0.9529666666666666,
+      "eval_cosine_recall@3": 0.9246666666666666,
+      "eval_cosine_recall@5": 0.9399333333333333,
+      "eval_sequential_score": 0.8855350929516275,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_codesearchnet_en_loss": 0.14139343798160553,
+      "eval_codesearchnet_en_runtime": 478.2988,
+      "eval_codesearchnet_en_samples_per_second": 62.722,
+      "eval_codesearchnet_en_steps_per_second": 7.84,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 321.6238,
+      "eval_codesearchnet_pairs_samples_per_second": 93.277,
+      "eval_codesearchnet_pairs_steps_per_second": 11.66,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16055511932506641,
+      "eval_solyanka_qa_loss": 0.4072943925857544,
+      "eval_solyanka_qa_runtime": 58.462,
+      "eval_solyanka_qa_samples_per_second": 85.526,
+      "eval_solyanka_qa_steps_per_second": 10.691,
+      "step": 12000
+    },
+    {
+      "epoch": 0.1632310379804842,
+      "grad_norm": 227.58837890625,
+      "learning_rate": 1.6300755903404913e-05,
+      "loss": 45.9733,
+      "step": 12200
+    },
+    {
+      "epoch": 0.16590695663590196,
+      "grad_norm": 364.53564453125,
+      "learning_rate": 1.6568332329921735e-05,
+      "loss": 44.1369,
+      "step": 12400
+    },
+    {
+      "epoch": 0.16858287529131974,
+      "grad_norm": 178.87033081054688,
+      "learning_rate": 1.683590875643856e-05,
+      "loss": 43.1701,
+      "step": 12600
+    },
+    {
+      "epoch": 0.17125879394673751,
+      "grad_norm": 401.73077392578125,
+      "learning_rate": 1.7103485182955385e-05,
+      "loss": 44.8199,
+      "step": 12800
+    },
+    {
+      "epoch": 0.1739347126021553,
+      "grad_norm": 317.6452331542969,
+      "learning_rate": 1.7371061609472207e-05,
+      "loss": 46.7352,
+      "step": 13000
+    },
+    {
+      "epoch": 0.17661063125757306,
+      "grad_norm": 145.65882873535156,
+      "learning_rate": 1.7638638035989032e-05,
+      "loss": 46.9156,
+      "step": 13200
+    },
+    {
+      "epoch": 0.17928654991299084,
+      "grad_norm": 249.8416748046875,
+      "learning_rate": 1.7906214462505854e-05,
+      "loss": 42.7186,
+      "step": 13400
+    },
+    {
+      "epoch": 0.18196246856840861,
+      "grad_norm": 409.74755859375,
+      "learning_rate": 1.817379088902268e-05,
+      "loss": 45.9776,
+      "step": 13600
+    },
+    {
+      "epoch": 0.1846383872238264,
+      "grad_norm": 326.13922119140625,
+      "learning_rate": 1.84413673155395e-05,
+      "loss": 44.2144,
+      "step": 13800
+    },
+    {
+      "epoch": 0.18731430587924416,
+      "grad_norm": 413.1485290527344,
+      "learning_rate": 1.8708943742056326e-05,
+      "loss": 43.9905,
+      "step": 14000
+    },
+    {
+      "epoch": 0.18731430587924416,
+      "eval_codesearchnet_loss": 0.1342524290084839,
+      "eval_codesearchnet_runtime": 839.9203,
+      "eval_codesearchnet_samples_per_second": 35.718,
+      "eval_codesearchnet_steps_per_second": 4.465,
+      "eval_cosine_accuracy@1": 0.8536666666666667,
+      "eval_cosine_accuracy@10": 0.9584333333333334,
+      "eval_cosine_accuracy@3": 0.9329666666666667,
+      "eval_cosine_accuracy@5": 0.947,
+      "eval_cosine_map@100": 0.8960511109661333,
+      "eval_cosine_mrr@10": 0.8951731349206256,
+      "eval_cosine_ndcg@10": 0.9109296053670202,
+      "eval_cosine_precision@1": 0.8536666666666667,
+      "eval_cosine_precision@10": 0.09584333333333334,
+      "eval_cosine_precision@3": 0.31098888888888887,
+      "eval_cosine_precision@5": 0.1894,
+      "eval_cosine_recall@1": 0.8536666666666667,
+      "eval_cosine_recall@10": 0.9584333333333334,
+      "eval_cosine_recall@3": 0.9329666666666667,
+      "eval_cosine_recall@5": 0.947,
+      "eval_sequential_score": 0.8979273527518223,
+      "step": 14000
+    },
+    {
+      "epoch": 0.18731430587924416,
+      "eval_codesearchnet_en_loss": 0.11381988227367401,
+      "eval_codesearchnet_en_runtime": 471.2802,
+      "eval_codesearchnet_en_samples_per_second": 63.656,
+      "eval_codesearchnet_en_steps_per_second": 7.957,
+      "step": 14000
+    },
+    {
+      "epoch": 0.18731430587924416,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 327.6845,
+      "eval_codesearchnet_pairs_samples_per_second": 91.551,
+      "eval_codesearchnet_pairs_steps_per_second": 11.444,
+      "step": 14000
+    },
+    {
+      "epoch": 0.18731430587924416,
+      "eval_solyanka_qa_loss": 0.3946870267391205,
+      "eval_solyanka_qa_runtime": 64.7708,
+      "eval_solyanka_qa_samples_per_second": 77.195,
+      "eval_solyanka_qa_steps_per_second": 9.649,
+      "step": 14000
+    },
+    {
+      "epoch": 0.18999022453466194,
+      "grad_norm": 335.5275573730469,
+      "learning_rate": 1.8976520168573148e-05,
+      "loss": 46.5119,
+      "step": 14200
+    },
+    {
+      "epoch": 0.19266614319007971,
+      "grad_norm": 579.9873657226562,
+      "learning_rate": 1.9244096595089973e-05,
+      "loss": 45.6215,
+      "step": 14400
+    },
+    {
+      "epoch": 0.19534206184549746,
+      "grad_norm": 335.88873291015625,
+      "learning_rate": 1.95116730216068e-05,
+      "loss": 44.4904,
+      "step": 14600
+    },
+    {
+      "epoch": 0.19801798050091524,
+      "grad_norm": 307.8119201660156,
+      "learning_rate": 1.9779249448123624e-05,
+      "loss": 43.6751,
+      "step": 14800
+    },
+    {
+      "epoch": 0.200693899156333,
+      "grad_norm": 310.07867431640625,
+      "learning_rate": 1.9994796815651182e-05,
+      "loss": 46.2327,
+      "step": 15000
+    },
+    {
+      "epoch": 0.20336981781175079,
+      "grad_norm": 205.63766479492188,
+      "learning_rate": 1.9965064333657914e-05,
+      "loss": 42.6746,
+      "step": 15200
+    },
+    {
+      "epoch": 0.20604573646716856,
+      "grad_norm": 166.04013061523438,
+      "learning_rate": 1.993533185166465e-05,
+      "loss": 43.1429,
+      "step": 15400
+    },
+    {
+      "epoch": 0.20872165512258634,
+      "grad_norm": 295.5857849121094,
+      "learning_rate": 1.9905599369671384e-05,
+      "loss": 46.7794,
+      "step": 15600
+    },
+    {
+      "epoch": 0.2113975737780041,
+      "grad_norm": 268.8268127441406,
+      "learning_rate": 1.9875866887678116e-05,
+      "loss": 45.936,
+      "step": 15800
+    },
+    {
+      "epoch": 0.21407349243342189,
+      "grad_norm": 250.19773864746094,
+      "learning_rate": 1.984613440568485e-05,
+      "loss": 42.8127,
+      "step": 16000
+    },
+    {
+      "epoch": 0.21407349243342189,
+      "eval_codesearchnet_loss": 0.1446487307548523,
+      "eval_codesearchnet_runtime": 846.3808,
+      "eval_codesearchnet_samples_per_second": 35.445,
+      "eval_codesearchnet_steps_per_second": 4.431,
+      "eval_cosine_accuracy@1": 0.8519333333333333,
+      "eval_cosine_accuracy@10": 0.9579666666666666,
+      "eval_cosine_accuracy@3": 0.9310666666666667,
+      "eval_cosine_accuracy@5": 0.946,
+      "eval_cosine_map@100": 0.8943941290146735,
+      "eval_cosine_mrr@10": 0.8935621693121611,
+      "eval_cosine_ndcg@10": 0.9095777024323259,
+      "eval_cosine_precision@1": 0.8519333333333333,
+      "eval_cosine_precision@10": 0.09579666666666667,
+      "eval_cosine_precision@3": 0.3103555555555555,
+      "eval_cosine_precision@5": 0.18920000000000003,
+      "eval_cosine_recall@1": 0.8519333333333333,
+      "eval_cosine_recall@10": 0.9579666666666666,
+      "eval_cosine_recall@3": 0.9310666666666667,
+      "eval_cosine_recall@5": 0.946,
+      "eval_sequential_score": 0.8940870991325514,
+      "step": 16000
+    },
+    {
+      "epoch": 0.21407349243342189,
+      "eval_codesearchnet_en_loss": 0.11211653053760529,
+      "eval_codesearchnet_en_runtime": 473.3649,
+      "eval_codesearchnet_en_samples_per_second": 63.376,
+      "eval_codesearchnet_en_steps_per_second": 7.922,
+      "step": 16000
+    },
+    {
+      "epoch": 0.21407349243342189,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 327.4721,
+      "eval_codesearchnet_pairs_samples_per_second": 91.611,
+      "eval_codesearchnet_pairs_steps_per_second": 11.451,
+      "step": 16000
+    },
+    {
+      "epoch": 0.21407349243342189,
+      "eval_solyanka_qa_loss": 0.33204418420791626,
+      "eval_solyanka_qa_runtime": 64.8163,
+      "eval_solyanka_qa_samples_per_second": 77.141,
+      "eval_solyanka_qa_steps_per_second": 9.643,
+      "step": 16000
+    },
+    {
+      "epoch": 0.21674941108883966,
+      "grad_norm": 238.50421142578125,
+      "learning_rate": 1.9816401923691585e-05,
+      "loss": 43.0956,
+      "step": 16200
+    },
+    {
+      "epoch": 0.21942532974425744,
+      "grad_norm": 255.65469360351562,
+      "learning_rate": 1.978666944169832e-05,
+      "loss": 44.4,
+      "step": 16400
+    },
+    {
+      "epoch": 0.2221012483996752,
+      "grad_norm": 377.43353271484375,
+      "learning_rate": 1.9756936959705055e-05,
+      "loss": 43.7226,
+      "step": 16600
+    },
+    {
+      "epoch": 0.22477716705509299,
+      "grad_norm": 201.8318634033203,
+      "learning_rate": 1.972720447771179e-05,
+      "loss": 41.7398,
+      "step": 16800
+    },
+    {
+      "epoch": 0.22745308571051076,
+      "grad_norm": 376.272705078125,
+      "learning_rate": 1.9697471995718525e-05,
+      "loss": 44.226,
+      "step": 17000
+    },
+    {
+      "epoch": 0.23012900436592854,
+      "grad_norm": 122.7479019165039,
+      "learning_rate": 1.966773951372526e-05,
+      "loss": 45.3254,
+      "step": 17200
+    },
+    {
+      "epoch": 0.2328049230213463,
+      "grad_norm": 198.94793701171875,
+      "learning_rate": 1.9638007031731995e-05,
+      "loss": 42.082,
+      "step": 17400
+    },
+    {
+      "epoch": 0.23548084167676409,
+      "grad_norm": 337.82379150390625,
+      "learning_rate": 1.9608274549738727e-05,
+      "loss": 42.3334,
+      "step": 17600
+    },
+    {
+      "epoch": 0.23815676033218186,
+      "grad_norm": 224.60572814941406,
+      "learning_rate": 1.9578690730155427e-05,
+      "loss": 42.5136,
+      "step": 17800
+    },
+    {
+      "epoch": 0.24083267898759964,
+      "grad_norm": 335.28302001953125,
+      "learning_rate": 1.954895824816216e-05,
+      "loss": 45.5767,
+      "step": 18000
+    },
+    {
+      "epoch": 0.24083267898759964,
+      "eval_codesearchnet_loss": 0.12085237354040146,
+      "eval_codesearchnet_runtime": 839.9773,
+      "eval_codesearchnet_samples_per_second": 35.715,
+      "eval_codesearchnet_steps_per_second": 4.464,
+      "eval_cosine_accuracy@1": 0.8597666666666667,
+      "eval_cosine_accuracy@10": 0.9598666666666666,
+      "eval_cosine_accuracy@3": 0.9346666666666666,
+      "eval_cosine_accuracy@5": 0.9489333333333333,
+      "eval_cosine_map@100": 0.8999127579807348,
+      "eval_cosine_mrr@10": 0.8991146164021084,
+      "eval_cosine_ndcg@10": 0.9142272545662572,
+      "eval_cosine_precision@1": 0.8597666666666667,
+      "eval_cosine_precision@10": 0.09598666666666668,
+      "eval_cosine_precision@3": 0.31155555555555553,
+      "eval_cosine_precision@5": 0.18978666666666671,
+      "eval_cosine_recall@1": 0.8597666666666667,
+      "eval_cosine_recall@10": 0.9598666666666666,
+      "eval_cosine_recall@3": 0.9346666666666666,
+      "eval_cosine_recall@5": 0.9489333333333333,
+      "eval_sequential_score": 0.9040850616361078,
+      "step": 18000
+    },
+    {
+      "epoch": 0.24083267898759964,
+      "eval_codesearchnet_en_loss": 0.1118454858660698,
+      "eval_codesearchnet_en_runtime": 480.5338,
+      "eval_codesearchnet_en_samples_per_second": 62.431,
+      "eval_codesearchnet_en_steps_per_second": 7.804,
+      "step": 18000
+    },
+    {
+      "epoch": 0.24083267898759964,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 325.9853,
+      "eval_codesearchnet_pairs_samples_per_second": 92.029,
+      "eval_codesearchnet_pairs_steps_per_second": 11.504,
+      "step": 18000
+    },
+    {
+      "epoch": 0.24083267898759964,
+      "eval_solyanka_qa_loss": 0.31246528029441833,
+      "eval_solyanka_qa_runtime": 61.4623,
+      "eval_solyanka_qa_samples_per_second": 81.351,
+      "eval_solyanka_qa_steps_per_second": 10.169,
+      "step": 18000
+    },
+    {
+      "epoch": 0.2435085976430174,
+      "grad_norm": 171.11447143554688,
+      "learning_rate": 1.9519225766168897e-05,
+      "loss": 38.4793,
+      "step": 18200
+    },
+    {
+      "epoch": 0.24618451629843519,
+      "grad_norm": 210.1746063232422,
+      "learning_rate": 1.948949328417563e-05,
+      "loss": 43.7497,
+      "step": 18400
+    },
+    {
+      "epoch": 0.24886043495385296,
+      "grad_norm": 325.6775207519531,
+      "learning_rate": 1.9459760802182367e-05,
+      "loss": 43.3697,
+      "step": 18600
+    },
+    {
+      "epoch": 0.25153635360927074,
+      "grad_norm": 420.11273193359375,
+      "learning_rate": 1.94300283201891e-05,
+      "loss": 43.0191,
+      "step": 18800
+    },
+    {
+      "epoch": 0.2542122722646885,
+      "grad_norm": 333.73480224609375,
+      "learning_rate": 1.9400295838195836e-05,
+      "loss": 42.6044,
+      "step": 19000
+    },
+    {
+      "epoch": 0.2568881909201063,
+      "grad_norm": 256.2155456542969,
+      "learning_rate": 1.9370563356202568e-05,
+      "loss": 41.3988,
+      "step": 19200
+    },
+    {
+      "epoch": 0.25956410957552406,
+      "grad_norm": 325.52154541015625,
+      "learning_rate": 1.9340830874209303e-05,
+      "loss": 42.3603,
+      "step": 19400
+    },
+    {
+      "epoch": 0.26224002823094184,
+      "grad_norm": 343.05255126953125,
+      "learning_rate": 1.9311098392216038e-05,
+      "loss": 45.8041,
+      "step": 19600
+    },
+    {
+      "epoch": 0.2649159468863596,
+      "grad_norm": 190.51092529296875,
+      "learning_rate": 1.928136591022277e-05,
+      "loss": 43.3778,
+      "step": 19800
+    },
+    {
+      "epoch": 0.2675918655417774,
+      "grad_norm": 200.10740661621094,
+      "learning_rate": 1.9251633428229505e-05,
+      "loss": 42.0158,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2675918655417774,
+      "eval_codesearchnet_loss": 0.1101187989115715,
+      "eval_codesearchnet_runtime": 840.2065,
+      "eval_codesearchnet_samples_per_second": 35.706,
+      "eval_codesearchnet_steps_per_second": 4.463,
+      "eval_cosine_accuracy@1": 0.8579666666666667,
+      "eval_cosine_accuracy@10": 0.9602,
+      "eval_cosine_accuracy@3": 0.9349666666666666,
+      "eval_cosine_accuracy@5": 0.9494,
+      "eval_cosine_map@100": 0.899321816600937,
+      "eval_cosine_mrr@10": 0.8985201587301509,
+      "eval_cosine_ndcg@10": 0.9138848973172521,
+      "eval_cosine_precision@1": 0.8579666666666667,
+      "eval_cosine_precision@10": 0.09602000000000002,
+      "eval_cosine_precision@3": 0.31165555555555546,
+      "eval_cosine_precision@5": 0.18988000000000002,
+      "eval_cosine_recall@1": 0.8579666666666667,
+      "eval_cosine_recall@10": 0.9602,
+      "eval_cosine_recall@3": 0.9349666666666666,
+      "eval_cosine_recall@5": 0.9494,
+      "eval_sequential_score": 0.9067441949449786,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2675918655417774,
+      "eval_codesearchnet_en_loss": 0.10212653875350952,
+      "eval_codesearchnet_en_runtime": 470.5735,
+      "eval_codesearchnet_en_samples_per_second": 63.752,
+      "eval_codesearchnet_en_steps_per_second": 7.969,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2675918655417774,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 327.6235,
+      "eval_codesearchnet_pairs_samples_per_second": 91.569,
+      "eval_codesearchnet_pairs_steps_per_second": 11.446,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2675918655417774,
+      "eval_solyanka_qa_loss": 0.27736204862594604,
+      "eval_solyanka_qa_runtime": 63.2529,
+      "eval_solyanka_qa_samples_per_second": 79.048,
+      "eval_solyanka_qa_steps_per_second": 9.881,
+      "step": 20000
+    },
+    {
+      "epoch": 0.27026778419719516,
+      "grad_norm": 342.3226318359375,
+      "learning_rate": 1.9222049608646208e-05,
+      "loss": 41.885,
+      "step": 20200
+    },
+    {
+      "epoch": 0.27294370285261293,
+      "grad_norm": 352.00634765625,
+      "learning_rate": 1.9192317126652943e-05,
+      "loss": 42.6263,
+      "step": 20400
+    },
+    {
+      "epoch": 0.2756196215080307,
+      "grad_norm": 342.0988464355469,
+      "learning_rate": 1.9162584644659678e-05,
+      "loss": 39.5869,
+      "step": 20600
+    },
+    {
+      "epoch": 0.27829554016344843,
+      "grad_norm": 236.56777954101562,
+      "learning_rate": 1.9132852162666413e-05,
+      "loss": 42.8813,
+      "step": 20800
+    },
+    {
+      "epoch": 0.2809714588188662,
+      "grad_norm": 267.0386657714844,
+      "learning_rate": 1.9103119680673144e-05,
+      "loss": 40.4135,
+      "step": 21000
+    },
+    {
+      "epoch": 0.283647377474284,
+      "grad_norm": 131.2029266357422,
+      "learning_rate": 1.907338719867988e-05,
+      "loss": 40.7767,
+      "step": 21200
+    },
+    {
+      "epoch": 0.28632329612970175,
+      "grad_norm": 254.9061279296875,
+      "learning_rate": 1.904380337909658e-05,
+      "loss": 42.7641,
+      "step": 21400
+    },
+    {
+      "epoch": 0.28899921478511953,
+      "grad_norm": 308.5098876953125,
+      "learning_rate": 1.9014070897103314e-05,
+      "loss": 41.815,
+      "step": 21600
+    },
+    {
+      "epoch": 0.2916751334405373,
+      "grad_norm": 357.93646240234375,
+      "learning_rate": 1.898433841511005e-05,
+      "loss": 42.6491,
+      "step": 21800
+    },
+    {
+      "epoch": 0.2943510520959551,
+      "grad_norm": 188.13589477539062,
+      "learning_rate": 1.8954605933116784e-05,
+      "loss": 40.8495,
+      "step": 22000
+    },
+    {
+      "epoch": 0.2943510520959551,
+      "eval_codesearchnet_loss": 0.12096109241247177,
+      "eval_codesearchnet_runtime": 838.5539,
+      "eval_codesearchnet_samples_per_second": 35.776,
+      "eval_codesearchnet_steps_per_second": 4.472,
+      "eval_cosine_accuracy@1": 0.8582666666666666,
+      "eval_cosine_accuracy@10": 0.9600666666666666,
+      "eval_cosine_accuracy@3": 0.9344,
+      "eval_cosine_accuracy@5": 0.9484,
+      "eval_cosine_map@100": 0.8989369313373693,
+      "eval_cosine_mrr@10": 0.8981315608465511,
+      "eval_cosine_ndcg@10": 0.9135202550236347,
+      "eval_cosine_precision@1": 0.8582666666666666,
+      "eval_cosine_precision@10": 0.09600666666666667,
+      "eval_cosine_precision@3": 0.3114666666666666,
+      "eval_cosine_precision@5": 0.18968000000000004,
+      "eval_cosine_recall@1": 0.8582666666666666,
+      "eval_cosine_recall@10": 0.9600666666666666,
+      "eval_cosine_recall@3": 0.9344,
+      "eval_cosine_recall@5": 0.9484,
+      "eval_sequential_score": 0.9057351560608176,
+      "step": 22000
+    },
+    {
+      "epoch": 0.2943510520959551,
+      "eval_codesearchnet_en_loss": 0.10828962922096252,
+      "eval_codesearchnet_en_runtime": 471.6406,
+      "eval_codesearchnet_en_samples_per_second": 63.608,
+      "eval_codesearchnet_en_steps_per_second": 7.951,
+      "step": 22000
+    },
+    {
+      "epoch": 0.2943510520959551,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 320.1911,
+      "eval_codesearchnet_pairs_samples_per_second": 93.694,
+      "eval_codesearchnet_pairs_steps_per_second": 11.712,
+      "step": 22000
+    },
+    {
+      "epoch": 0.2943510520959551,
+      "eval_solyanka_qa_loss": 0.27527186274528503,
+      "eval_solyanka_qa_runtime": 59.0971,
+      "eval_solyanka_qa_samples_per_second": 84.607,
+      "eval_solyanka_qa_steps_per_second": 10.576,
+      "step": 22000
+    },
+    {
+      "epoch": 0.29702697075137285,
+      "grad_norm": 391.6092224121094,
+      "learning_rate": 1.892487345112352e-05,
+      "loss": 40.9813,
+      "step": 22200
+    },
+    {
+      "epoch": 0.29970288940679063,
+      "grad_norm": 320.6426696777344,
+      "learning_rate": 1.8895140969130254e-05,
+      "loss": 41.8588,
+      "step": 22400
+    },
+    {
+      "epoch": 0.3023788080622084,
+      "grad_norm": 232.222900390625,
+      "learning_rate": 1.8865408487136985e-05,
+      "loss": 39.9178,
+      "step": 22600
+    },
+    {
+      "epoch": 0.3050547267176262,
+      "grad_norm": 268.02301025390625,
+      "learning_rate": 1.883567600514372e-05,
+      "loss": 39.8329,
+      "step": 22800
+    },
+    {
+      "epoch": 0.30773064537304395,
+      "grad_norm": 225.69508361816406,
+      "learning_rate": 1.8805943523150455e-05,
+      "loss": 40.3366,
+      "step": 23000
+    },
+    {
+      "epoch": 0.31040656402846173,
+      "grad_norm": 387.1187438964844,
+      "learning_rate": 1.877621104115719e-05,
+      "loss": 43.1526,
+      "step": 23200
+    },
+    {
+      "epoch": 0.3130824826838795,
+      "grad_norm": 333.5805969238281,
+      "learning_rate": 1.8746478559163922e-05,
+      "loss": 39.3075,
+      "step": 23400
+    },
+    {
+      "epoch": 0.3157584013392973,
+      "grad_norm": 278.41558837890625,
+      "learning_rate": 1.8716746077170657e-05,
+      "loss": 39.5526,
+      "step": 23600
+    },
+    {
+      "epoch": 0.31843431999471505,
+      "grad_norm": 270.3379821777344,
+      "learning_rate": 1.8687013595177392e-05,
+      "loss": 43.3892,
+      "step": 23800
+    },
+    {
+      "epoch": 0.32111023865013283,
+      "grad_norm": 209.1192169189453,
+      "learning_rate": 1.8657281113184127e-05,
+      "loss": 43.4829,
+      "step": 24000
+    },
+    {
+      "epoch": 0.32111023865013283,
+      "eval_codesearchnet_loss": 0.13343782722949982,
+      "eval_codesearchnet_runtime": 822.5402,
+      "eval_codesearchnet_samples_per_second": 36.472,
+      "eval_codesearchnet_steps_per_second": 4.559,
+      "eval_cosine_accuracy@1": 0.8588333333333333,
+      "eval_cosine_accuracy@10": 0.9597666666666667,
+      "eval_cosine_accuracy@3": 0.9360666666666667,
+      "eval_cosine_accuracy@5": 0.9484333333333334,
+      "eval_cosine_map@100": 0.8994624901702583,
+      "eval_cosine_mrr@10": 0.8986741666666557,
+      "eval_cosine_ndcg@10": 0.9138847354113789,
+      "eval_cosine_precision@1": 0.8588333333333333,
+      "eval_cosine_precision@10": 0.09597666666666668,
+      "eval_cosine_precision@3": 0.3120222222222222,
+      "eval_cosine_precision@5": 0.18968666666666667,
+      "eval_cosine_recall@1": 0.8588333333333333,
+      "eval_cosine_recall@10": 0.9597666666666667,
+      "eval_cosine_recall@3": 0.9360666666666667,
+      "eval_cosine_recall@5": 0.9484333333333334,
+      "eval_sequential_score": 0.9066875960158511,
+      "step": 24000
+    },
+    {
+      "epoch": 0.32111023865013283,
+      "eval_codesearchnet_en_loss": 0.12875226140022278,
+      "eval_codesearchnet_en_runtime": 463.8617,
+      "eval_codesearchnet_en_samples_per_second": 64.674,
+      "eval_codesearchnet_en_steps_per_second": 8.084,
+      "step": 24000
+    },
+    {
+      "epoch": 0.32111023865013283,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 327.726,
+      "eval_codesearchnet_pairs_samples_per_second": 91.54,
+      "eval_codesearchnet_pairs_steps_per_second": 11.442,
+      "step": 24000
+    },
+    {
+      "epoch": 0.32111023865013283,
+      "eval_solyanka_qa_loss": 0.27116355299949646,
+      "eval_solyanka_qa_runtime": 62.4503,
+      "eval_solyanka_qa_samples_per_second": 80.064,
+      "eval_solyanka_qa_steps_per_second": 10.008,
+      "step": 24000
+    },
+    {
+      "epoch": 0.3237861573055506,
+      "grad_norm": 230.99716186523438,
+      "learning_rate": 1.8627548631190862e-05,
+      "loss": 39.3534,
+      "step": 24200
+    },
+    {
+      "epoch": 0.3264620759609684,
+      "grad_norm": 192.94573974609375,
+      "learning_rate": 1.8597816149197597e-05,
+      "loss": 43.841,
+      "step": 24400
+    },
+    {
+      "epoch": 0.32913799461638615,
+      "grad_norm": 226.36752319335938,
+      "learning_rate": 1.8568083667204332e-05,
+      "loss": 41.0659,
+      "step": 24600
+    },
+    {
+      "epoch": 0.33181391327180393,
+      "grad_norm": 258.8309326171875,
+      "learning_rate": 1.8538351185211067e-05,
+      "loss": 40.1334,
+      "step": 24800
+    },
+    {
+      "epoch": 0.3344898319272217,
+      "grad_norm": 141.69883728027344,
+      "learning_rate": 1.85086187032178e-05,
+      "loss": 39.5197,
+      "step": 25000
+    },
+    {
+      "epoch": 0.3371657505826395,
+      "grad_norm": 246.9538116455078,
+      "learning_rate": 1.8478886221224533e-05,
+      "loss": 38.0498,
+      "step": 25200
+    },
+    {
+      "epoch": 0.33984166923805725,
+      "grad_norm": 326.54534912109375,
+      "learning_rate": 1.8449153739231268e-05,
+      "loss": 39.6212,
+      "step": 25400
+    },
+    {
+      "epoch": 0.34251758789347503,
+      "grad_norm": 228.7314910888672,
+      "learning_rate": 1.8419421257238003e-05,
+      "loss": 39.6137,
+      "step": 25600
+    },
+    {
+      "epoch": 0.3451935065488928,
+      "grad_norm": 303.4416198730469,
+      "learning_rate": 1.8389837437654703e-05,
+      "loss": 38.8118,
+      "step": 25800
+    },
+    {
+      "epoch": 0.3478694252043106,
+      "grad_norm": 222.80442810058594,
+      "learning_rate": 1.8360253618071403e-05,
+      "loss": 39.4752,
+      "step": 26000
+    },
+    {
+      "epoch": 0.3478694252043106,
+      "eval_codesearchnet_loss": 0.10732050985097885,
+      "eval_codesearchnet_runtime": 847.5006,
+      "eval_codesearchnet_samples_per_second": 35.398,
+      "eval_codesearchnet_steps_per_second": 4.425,
+      "eval_cosine_accuracy@1": 0.867,
+      "eval_cosine_accuracy@10": 0.9623333333333334,
+      "eval_cosine_accuracy@3": 0.9381,
+      "eval_cosine_accuracy@5": 0.9508666666666666,
+      "eval_cosine_map@100": 0.9051346464930926,
+      "eval_cosine_mrr@10": 0.9044249603174528,
+      "eval_cosine_ndcg@10": 0.9188151689755729,
+      "eval_cosine_precision@1": 0.867,
+      "eval_cosine_precision@10": 0.09623333333333334,
+      "eval_cosine_precision@3": 0.3126999999999999,
+      "eval_cosine_precision@5": 0.19017333333333336,
+      "eval_cosine_recall@1": 0.867,
+      "eval_cosine_recall@10": 0.9623333333333334,
+      "eval_cosine_recall@3": 0.9381,
+      "eval_cosine_recall@5": 0.9508666666666666,
+      "eval_sequential_score": 0.9121087806456172,
+      "step": 26000
+    },
+    {
+      "epoch": 0.3478694252043106,
+      "eval_codesearchnet_en_loss": 0.09826622903347015,
+      "eval_codesearchnet_en_runtime": 466.2908,
+      "eval_codesearchnet_en_samples_per_second": 64.338,
+      "eval_codesearchnet_en_steps_per_second": 8.042,
+      "step": 26000
+    },
+    {
+      "epoch": 0.3478694252043106,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 326.2135,
+      "eval_codesearchnet_pairs_samples_per_second": 91.964,
+      "eval_codesearchnet_pairs_steps_per_second": 11.496,
+      "step": 26000
+    },
+    {
+      "epoch": 0.3478694252043106,
+      "eval_solyanka_qa_loss": 0.26090648770332336,
+      "eval_solyanka_qa_runtime": 63.0923,
+      "eval_solyanka_qa_samples_per_second": 79.249,
+      "eval_solyanka_qa_steps_per_second": 9.906,
+      "step": 26000
+    },
+    {
+      "epoch": 0.35054534385972835,
+      "grad_norm": 138.39620971679688,
+      "learning_rate": 1.8330521136078138e-05,
+      "loss": 39.6027,
+      "step": 26200
+    },
+    {
+      "epoch": 0.35322126251514613,
+      "grad_norm": 188.3811798095703,
+      "learning_rate": 1.8300788654084873e-05,
+      "loss": 38.3638,
+      "step": 26400
+    },
+    {
+      "epoch": 0.3558971811705639,
+      "grad_norm": 94.10308837890625,
+      "learning_rate": 1.8271056172091608e-05,
+      "loss": 39.1931,
+      "step": 26600
+    },
+    {
+      "epoch": 0.3585730998259817,
+      "grad_norm": 384.9344482421875,
+      "learning_rate": 1.8241323690098343e-05,
+      "loss": 39.1136,
+      "step": 26800
+    },
+    {
+      "epoch": 0.36124901848139945,
+      "grad_norm": 224.32579040527344,
+      "learning_rate": 1.8211591208105078e-05,
+      "loss": 38.6532,
+      "step": 27000
+    },
+    {
+      "epoch": 0.36392493713681723,
+      "grad_norm": 296.6976318359375,
+      "learning_rate": 1.818185872611181e-05,
+      "loss": 39.2244,
+      "step": 27200
+    },
+    {
+      "epoch": 0.366600855792235,
+      "grad_norm": 353.5552062988281,
+      "learning_rate": 1.8152126244118544e-05,
+      "loss": 38.8892,
+      "step": 27400
+    },
+    {
+      "epoch": 0.3692767744476528,
+      "grad_norm": 408.9116516113281,
+      "learning_rate": 1.812239376212528e-05,
+      "loss": 38.9584,
+      "step": 27600
+    },
+    {
+      "epoch": 0.37195269310307055,
+      "grad_norm": 216.62933349609375,
+      "learning_rate": 1.8092661280132014e-05,
+      "loss": 37.1875,
+      "step": 27800
+    },
+    {
+      "epoch": 0.37462861175848833,
+      "grad_norm": 253.36082458496094,
+      "learning_rate": 1.806292879813875e-05,
+      "loss": 38.9653,
+      "step": 28000
+    },
+    {
+      "epoch": 0.37462861175848833,
+      "eval_codesearchnet_loss": 0.10111524909734726,
+      "eval_codesearchnet_runtime": 839.8663,
+      "eval_codesearchnet_samples_per_second": 35.72,
+      "eval_codesearchnet_steps_per_second": 4.465,
+      "eval_cosine_accuracy@1": 0.8649666666666667,
+      "eval_cosine_accuracy@10": 0.9618666666666666,
+      "eval_cosine_accuracy@3": 0.9375333333333333,
+      "eval_cosine_accuracy@5": 0.9499333333333333,
+      "eval_cosine_map@100": 0.9038568635968023,
+      "eval_cosine_mrr@10": 0.9030955687830621,
+      "eval_cosine_ndcg@10": 0.9177055847656918,
+      "eval_cosine_precision@1": 0.8649666666666667,
+      "eval_cosine_precision@10": 0.09618666666666668,
+      "eval_cosine_precision@3": 0.3125111111111111,
+      "eval_cosine_precision@5": 0.1899866666666667,
+      "eval_cosine_recall@1": 0.8649666666666667,
+      "eval_cosine_recall@10": 0.9618666666666666,
+      "eval_cosine_recall@3": 0.9375333333333333,
+      "eval_cosine_recall@5": 0.9499333333333333,
+      "eval_sequential_score": 0.9128399280795447,
+      "step": 28000
+    },
+    {
+      "epoch": 0.37462861175848833,
+      "eval_codesearchnet_en_loss": 0.097304567694664,
+      "eval_codesearchnet_en_runtime": 470.9449,
+      "eval_codesearchnet_en_samples_per_second": 63.702,
+      "eval_codesearchnet_en_steps_per_second": 7.963,
+      "step": 28000
+    },
+    {
+      "epoch": 0.37462861175848833,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 323.0644,
+      "eval_codesearchnet_pairs_samples_per_second": 92.861,
+      "eval_codesearchnet_pairs_steps_per_second": 11.608,
+      "step": 28000
+    },
+    {
+      "epoch": 0.37462861175848833,
+      "eval_solyanka_qa_loss": 0.2719764709472656,
+      "eval_solyanka_qa_runtime": 62.7013,
+      "eval_solyanka_qa_samples_per_second": 79.743,
+      "eval_solyanka_qa_steps_per_second": 9.968,
+      "step": 28000
+    },
+    {
+      "epoch": 0.3773045304139061,
+      "grad_norm": 279.5317687988281,
+      "learning_rate": 1.8033196316145484e-05,
+      "loss": 40.4926,
+      "step": 28200
+    },
+    {
+      "epoch": 0.3799804490693239,
+      "grad_norm": 256.0455322265625,
+      "learning_rate": 1.8003463834152216e-05,
+      "loss": 38.0833,
+      "step": 28400
+    },
+    {
+      "epoch": 0.38265636772474165,
+      "grad_norm": 239.24623107910156,
+      "learning_rate": 1.797373135215895e-05,
+      "loss": 40.9772,
+      "step": 28600
+    },
+    {
+      "epoch": 0.38533228638015943,
+      "grad_norm": 204.23681640625,
+      "learning_rate": 1.7943998870165686e-05,
+      "loss": 37.7287,
+      "step": 28800
+    },
+    {
+      "epoch": 0.38800820503557715,
+      "grad_norm": 592.0680541992188,
+      "learning_rate": 1.791426638817242e-05,
+      "loss": 40.0172,
+      "step": 29000
+    },
+    {
+      "epoch": 0.3906841236909949,
+      "grad_norm": 243.32200622558594,
+      "learning_rate": 1.7884533906179156e-05,
+      "loss": 39.6315,
+      "step": 29200
+    },
+    {
+      "epoch": 0.3933600423464127,
+      "grad_norm": 333.1617431640625,
+      "learning_rate": 1.7854801424185887e-05,
+      "loss": 39.0464,
+      "step": 29400
+    },
+    {
+      "epoch": 0.39603596100183047,
+      "grad_norm": 291.46630859375,
+      "learning_rate": 1.7825068942192622e-05,
+      "loss": 38.037,
+      "step": 29600
+    },
+    {
+      "epoch": 0.39871187965724825,
+      "grad_norm": 37.094329833984375,
+      "learning_rate": 1.7795336460199357e-05,
+      "loss": 38.7314,
+      "step": 29800
+    },
+    {
+      "epoch": 0.401387798312666,
+      "grad_norm": 258.26287841796875,
+      "learning_rate": 1.7765603978206092e-05,
+      "loss": 40.522,
+      "step": 30000
+    },
+    {
+      "epoch": 0.401387798312666,
+      "eval_codesearchnet_loss": 0.10270167887210846,
+      "eval_codesearchnet_runtime": 830.3087,
+      "eval_codesearchnet_samples_per_second": 36.131,
+      "eval_codesearchnet_steps_per_second": 4.516,
+      "eval_cosine_accuracy@1": 0.8575,
+      "eval_cosine_accuracy@10": 0.9594,
+      "eval_cosine_accuracy@3": 0.9337333333333333,
+      "eval_cosine_accuracy@5": 0.9475,
+      "eval_cosine_map@100": 0.8984523283785684,
+      "eval_cosine_mrr@10": 0.8976266666666592,
+      "eval_cosine_ndcg@10": 0.9129868394757538,
+      "eval_cosine_precision@1": 0.8575,
+      "eval_cosine_precision@10": 0.09594000000000001,
+      "eval_cosine_precision@3": 0.3112444444444444,
+      "eval_cosine_precision@5": 0.18950000000000003,
+      "eval_cosine_recall@1": 0.8575,
+      "eval_cosine_recall@10": 0.9594,
+      "eval_cosine_recall@3": 0.9337333333333333,
+      "eval_cosine_recall@5": 0.9475,
+      "eval_sequential_score": 0.9064253537173524,
+      "step": 30000
+    },
+    {
+      "epoch": 0.401387798312666,
+      "eval_codesearchnet_en_loss": 0.09448499232530594,
+      "eval_codesearchnet_en_runtime": 465.9181,
+      "eval_codesearchnet_en_samples_per_second": 64.389,
+      "eval_codesearchnet_en_steps_per_second": 8.049,
+      "step": 30000
+    },
+    {
+      "epoch": 0.401387798312666,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 335.6951,
+      "eval_codesearchnet_pairs_samples_per_second": 89.367,
+      "eval_codesearchnet_pairs_steps_per_second": 11.171,
+      "step": 30000
+    },
+    {
+      "epoch": 0.401387798312666,
+      "eval_solyanka_qa_loss": 0.26630938053131104,
+      "eval_solyanka_qa_runtime": 64.5911,
+      "eval_solyanka_qa_samples_per_second": 77.41,
+      "eval_solyanka_qa_steps_per_second": 9.676,
+      "step": 30000
+    },
+    {
+      "epoch": 0.4040637169680838,
+      "grad_norm": 144.2952423095703,
+      "learning_rate": 1.7735871496212827e-05,
+      "loss": 38.8599,
+      "step": 30200
+    },
+    {
+      "epoch": 0.40673963562350157,
+      "grad_norm": 281.8232116699219,
+      "learning_rate": 1.7706139014219562e-05,
+      "loss": 38.7471,
+      "step": 30400
+    },
+    {
+      "epoch": 0.40941555427891935,
+      "grad_norm": 203.18319702148438,
+      "learning_rate": 1.7676406532226297e-05,
+      "loss": 40.4716,
+      "step": 30600
+    },
+    {
+      "epoch": 0.4120914729343371,
+      "grad_norm": 421.0890197753906,
+      "learning_rate": 1.7646674050233032e-05,
+      "loss": 37.2788,
+      "step": 30800
+    },
+    {
+      "epoch": 0.4147673915897549,
+      "grad_norm": 289.92889404296875,
+      "learning_rate": 1.7616941568239764e-05,
+      "loss": 38.8096,
+      "step": 31000
+    },
+    {
+      "epoch": 0.41744331024517267,
+      "grad_norm": 214.85855102539062,
+      "learning_rate": 1.75872090862465e-05,
+      "loss": 37.5472,
+      "step": 31200
+    },
+    {
+      "epoch": 0.42011922890059045,
+      "grad_norm": 386.36749267578125,
+      "learning_rate": 1.7557476604253233e-05,
+      "loss": 39.0019,
+      "step": 31400
+    },
+    {
+      "epoch": 0.4227951475560082,
+      "grad_norm": 277.5880126953125,
+      "learning_rate": 1.7527744122259965e-05,
+      "loss": 38.8078,
+      "step": 31600
+    },
+    {
+      "epoch": 0.425471066211426,
+      "grad_norm": 316.1474304199219,
+      "learning_rate": 1.74980116402667e-05,
+      "loss": 38.923,
+      "step": 31800
+    },
+    {
+      "epoch": 0.42814698486684377,
+      "grad_norm": 336.9049072265625,
+      "learning_rate": 1.7468279158273435e-05,
+      "loss": 40.1538,
+      "step": 32000
+    },
+    {
+      "epoch": 0.42814698486684377,
+      "eval_codesearchnet_loss": 0.09764492511749268,
+      "eval_codesearchnet_runtime": 839.6411,
+      "eval_codesearchnet_samples_per_second": 35.73,
+      "eval_codesearchnet_steps_per_second": 4.466,
+      "eval_cosine_accuracy@1": 0.8566666666666667,
+      "eval_cosine_accuracy@10": 0.9615333333333334,
+      "eval_cosine_accuracy@3": 0.9351,
+      "eval_cosine_accuracy@5": 0.9498,
+      "eval_cosine_map@100": 0.8987165379390405,
+      "eval_cosine_mrr@10": 0.8979227248677167,
+      "eval_cosine_ndcg@10": 0.9137544209587964,
+      "eval_cosine_precision@1": 0.8566666666666667,
+      "eval_cosine_precision@10": 0.09615333333333334,
+      "eval_cosine_precision@3": 0.3117,
+      "eval_cosine_precision@5": 0.18996000000000005,
+      "eval_cosine_recall@1": 0.8566666666666667,
+      "eval_cosine_recall@10": 0.9615333333333334,
+      "eval_cosine_recall@3": 0.9351,
+      "eval_cosine_recall@5": 0.9498,
+      "eval_sequential_score": 0.9058444643442238,
+      "step": 32000
+    },
+    {
+      "epoch": 0.42814698486684377,
+      "eval_codesearchnet_en_loss": 0.09518902748823166,
+      "eval_codesearchnet_en_runtime": 462.3965,
+      "eval_codesearchnet_en_samples_per_second": 64.879,
+      "eval_codesearchnet_en_steps_per_second": 8.11,
+      "step": 32000
+    },
+    {
+      "epoch": 0.42814698486684377,
+      "eval_codesearchnet_pairs_loss": 0.0,
+      "eval_codesearchnet_pairs_runtime": 331.552,
+      "eval_codesearchnet_pairs_samples_per_second": 90.484,
+      "eval_codesearchnet_pairs_steps_per_second": 11.31,
+      "step": 32000
+    },
+    {
+      "epoch": 0.42814698486684377,
+      "eval_solyanka_qa_loss": 0.25171661376953125,
+      "eval_solyanka_qa_runtime": 64.1864,
+      "eval_solyanka_qa_samples_per_second": 77.898,
+      "eval_solyanka_qa_steps_per_second": 9.737,
+      "step": 32000
+    },
+    {
+      "epoch": 0.43082290352226155,
+      "grad_norm": 217.88059997558594,
+      "learning_rate": 1.743854667628017e-05,
+      "loss": 37.7684,
+      "step": 32200
+    },
+    {
+      "epoch": 0.4334988221776793,
+      "grad_norm": 299.6658630371094,
+      "learning_rate": 1.7408962856696873e-05,
+      "loss": 37.6692,
+      "step": 32400
+    },
+    {
+      "epoch": 0.4361747408330971,
+      "grad_norm": 303.449951171875,
+      "learning_rate": 1.7379230374703605e-05,
+      "loss": 36.1706,
+      "step": 32600
+    },
+    {
+      "epoch": 0.43885065948851487,
+      "grad_norm": 266.1694641113281,
+      "learning_rate": 1.734949789271034e-05,
+      "loss": 37.0354,
+      "step": 32800
+    },
+    {
+      "epoch": 0.44152657814393265,
+      "grad_norm": 277.37677001953125,
+      "learning_rate": 1.7319765410717075e-05,
+      "loss": 37.266,
+      "step": 33000
+    },
+    {
+      "epoch": 0.4442024967993504,
+      "grad_norm": 377.0133361816406,
+      "learning_rate": 1.729003292872381e-05,
+      "loss": 35.771,
+      "step": 33200
+    },
+    {
+      "epoch": 0.4468784154547682,
+      "grad_norm": 218.6009063720703,
+      "learning_rate": 1.726030044673054e-05,
+      "loss": 37.9841,
+      "step": 33400
+    },
+    {
+      "epoch": 0.44955433411018597,
+      "grad_norm": 162.18153381347656,
+      "learning_rate": 1.7230567964737276e-05,
+      "loss": 36.5223,
+      "step": 33600
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 149482,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-33600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac828e15d961bff5f0a7f46eb6e91711bae467522b387ac6be519f39235dd16
+size 5688

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "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
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/config.json

@@ -0,0 +1,81 @@
+{
+  "activation_function": "gelu",
+  "allow_embedding_resizing": true,
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_layer": "rope",
+  "attention_probs_dropout_prob": 0.0,
+  "attn_out_bias": false,
+  "attn_out_dropout_prob": 0.1,
+  "attn_qkv_bias": false,
+  "bert_layer": "prenorm",
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "compile_model": true,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embed_dropout_prob": 0.0,
+  "embed_norm": true,
+  "embedding_dropout": 0.0,
+  "embedding_layer": "sans_pos",
+  "eos_token_id": 50282,
+  "final_norm": true,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "head_pred_act": "gelu",
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "init_method": "full_megatron",
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "local_attention": 128,
+  "local_attn_rotary_emb_base": 10000.0,
+  "local_rope_theta": 10000.0,
+  "loss_function": "fa_cross_entropy",
+  "loss_kwargs": {
+    "reduction": "mean"
+  },
+  "masked_prediction": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "mlp_dropout_prob": 0.0,
+  "mlp_in_bias": false,
+  "mlp_layer": "glu",
+  "mlp_out_bias": false,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "norm_kwargs": {
+    "bias": false,
+    "eps": 1e-05
+  },
+  "normalization": "layernorm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "padding": "unpadded",
+  "repad_logits_with_grad": false,
+  "rotary_emb_base": 160000.0,
+  "rotary_emb_dim": null,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "sep_token_id": 50282,
+  "skip_first_prenorm": true,
+  "sliding_window": 128,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "unpad_embeddings": true,
+  "vocab_size": 50368
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.52.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2f54c738998217c535df21250fea61729bce7823ffac555b1baa9e10bebb37
+size 596070136

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fa8edf13d9f7aed4777607b096796c491c3fbda2977b5c7399f5f9cfa046c7
+size 1192227066

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6bfa19346c80ae7e31fe7f5691c2331070afaeb4f218bf6c109e0c13185b0c
+size 14244

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee91e2f12f6cc7ea802b2b385a8796a5ed14d661c6a081706fb7ba53b375c34b
+size 988

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55278d61ec95de9cfc89f373f5dc86e827f4dc6fde97b31da499daa0aa9a50d4
+size 1064

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 8192,
+    "do_lower_case": false
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[PAD]",
+    "[MASK]"
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "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
+  }
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/tokenizer_config.json

@@ -0,0 +1,961 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[PAD]",
+    "[MASK]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 8192,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

RuModernBERT-base_bs64_lr_2e-05/checkpoint-46400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c528e6cf825ab8488eeea0ca0e9c643fb2c22a02594c5b77fcf500b72404461
+size 5688

RuModernBERT-base_bs64_lr_2e-05/checkpoint-82600/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "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
+}