Training in progress, epoch 1

config.json

@@ -0,0 +1,205 @@
+{
+  "_commit_hash": "344d954da76eb8ad47a7aaff42d012e30c15b8fe",
+  "add_projections": false,
+  "architectures": [
+    "JinaCLIPModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "jinaai/jina-clip-implementation--configuration_clip.JinaCLIPConfig",
+    "AutoModel": "jinaai/jina-clip-implementation--modeling_clip.JinaCLIPModel"
+  },
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "matryoshka_dimensions": [
+    32,
+    64,
+    128,
+    256,
+    512,
+    768,
+    1024
+  ],
+  "model_type": "jina_clip",
+  "projection_dim": 1024,
+  "text_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "default_instruction_task": null,
+    "default_lora_task": "retrieval.query",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embed_dim": 1024,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hf_model_config_kwargs": {
+      "load_trained_adapters": false,
+      "lora_adaptations": [
+        "retrieval.query"
+      ],
+      "lora_alpha": 4,
+      "lora_dropout_p": 0.0,
+      "lora_main_params_trainable": false,
+      "lora_rank": 4,
+      "task_instructions": {
+        "retrieval.query": "Represent the query for retrieving evidence documents: "
+      },
+      "use_flash_attn": false
+    },
+    "hf_model_name_or_path": "jinaai/jina-embeddings-v3",
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "jina_clip_text",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "pooler_type": "mean_pooler",
+    "prefix": null,
+    "problem_type": null,
+    "proj_bias": false,
+    "proj_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.51.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": true
+    }
+  },
+  "transformers_version": null,
+  "truncate_dim": null,
+  "use_text_flash_attn": false,
+  "use_vision_xformers": false,
+  "vision_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "early_stopping": false,
+    "embed_dim": 1024,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "fused_layer_norm": false,
+    "head_width": 64,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 512,
+    "intp_freq": true,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 24,
+    "length_penalty": 1.0,
+    "ls_init_value": null,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 2.6667,
+    "model_type": "jina_clip_vision",
+    "naive_swiglu": true,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_dropout": 0.1,
+    "patch_size": 14,
+    "post_norm": false,
+    "prefix": null,
+    "problem_type": null,
+    "proj_type": null,
+    "pruned_heads": {},
+    "pt_hw_seq_len": 16,
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_embeddings": true,
+    "sep_token_id": null,
+    "subln": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.51.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "width": 1024,
+    "x_attention": false
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdba9157547c3a5d76a3543bde47e42059dc275d38ea997b9d09990acec758ea
+size 1730689642

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de6ce52dfa78c4a578b4a17a71b6a11108d420ae1650616bc6990884ee36c34
+size 5432