Upload files with huggingface_hub

Upload longvila8b_sft_v7_oss_256k_512frames_v41/config.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/trainer_state.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00004-of-00004.safetensors
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/config.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/generation_config.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00003-of-00004.safetensors
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/model.safetensors.index.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/tokenizer.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/tokenizer_config.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/special_tokens_map.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00001-of-00004.safetensors
Upload longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00002-of-00004.safetensors
Upload longvila8b_sft_v7_oss_256k_512frames_v41/mm_projector/config.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/mm_projector/model.safetensors
Upload longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower/config.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower/preprocessor_config.json
Upload longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower/model.safetensors

longvila8b_sft_v7_oss_256k_512frames_v41/config.json

@@ -0,0 +1,254 @@
+{
+  "_name_or_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41",
+  "architectures": [
+    "LlavaLlamaModel"
+  ],
+  "drop_path_rate": 0.0,
+  "fps": 2.0,
+  "hidden_size": 4096,
+  "image_aspect_ratio": "resize",
+  "interpolate_mode": "linear",
+  "llm_cfg": {
+    "_name_or_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41/llm",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 128001,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 262144,
+    "min_length": 0,
+    "model_max_length": 262144,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 207112184,
+    "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": false,
+    "tokenizer_class": null,
+    "tokenizer_model_max_length": 262144,
+    "tokenizer_padding_side": "right",
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128257
+  },
+  "mm_hidden_size": 1152,
+  "mm_projector_cfg": {
+    "_name_or_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41/mm_projector",
+    "add_cross_attention": false,
+    "architectures": [
+      "MultimodalProjector"
+    ],
+    "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,
+    "early_stopping": false,
+    "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,
+    "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,
+    "mm_projector_type": "mlp_downsample",
+    "model_type": "v2l_projector",
+    "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,
+    "prefix": null,
+    "problem_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": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "mm_projector_lr": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "cls_patch",
+  "mm_vision_select_layer": -2,
+  "model_dtype": "torch.bfloat16",
+  "model_type": "llava_llama",
+  "num_video_frames": 512,
+  "resume_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41",
+  "s2": false,
+  "s2_max_split_size": 336,
+  "s2_scales": "336,672,1008",
+  "transformers_version": "4.37.2",
+  "tune_language_model": true,
+  "tune_mm_projector": true,
+  "tune_vision_tower": true,
+  "vision_resolution": -1,
+  "vision_tower_cfg": {
+    "_name_or_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower",
+    "add_cross_attention": false,
+    "architectures": [
+      "SiglipVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "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,
+    "early_stopping": false,
+    "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,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "siglip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_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": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

longvila8b_sft_v7_oss_256k_512frames_v41/llm/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41/llm",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 262144,
+  "model_max_length": 262144,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 207112184,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 262144,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 128257
+}

longvila8b_sft_v7_oss_256k_512frames_v41/llm/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.37.2"
+}

longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73098730ff635d6c8cebd53656a2a1f814d7bb02448b744dfb3dd0962b0185ef
+size 4976706864

longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288f4b605e3705ad167139f8581b71879de53f585811b07bcc0b6950a38c7bd3
+size 4999802720

longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d02aa83fadbf82e7c902814f8062716f326516b8d6bd6f3929c463530128ad
+size 4915916176

longvila8b_sft_v7_oss_256k_512frames_v41/llm/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700a00dec4d8f3a0de46b6c5772b7d3c4b6c6dff45c05d899f9d91f4bc03d90e
+size 1168147000

longvila8b_sft_v7_oss_256k_512frames_v41/llm/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060538880
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

longvila8b_sft_v7_oss_256k_512frames_v41/llm/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

longvila8b_sft_v7_oss_256k_512frames_v41/llm/tokenizer_config.json

@@ -0,0 +1,2073 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 262144,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

longvila8b_sft_v7_oss_256k_512frames_v41/mm_projector/config.json

@@ -0,0 +1,10 @@
+{
+  "_name_or_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41/mm_projector",
+  "architectures": [
+    "MultimodalProjector"
+  ],
+  "mm_projector_type": "mlp_downsample",
+  "model_type": "v2l_projector",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2"
+}

longvila8b_sft_v7_oss_256k_512frames_v41/mm_projector/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5bb4f0a38dca72573ff1f3b9216a3acaf1dd9ba21fe51a757418ce3137a881
+size 71338512

longvila8b_sft_v7_oss_256k_512frames_v41/trainer_state.json

@@ -0,0 +1,1254 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.870503597122302,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 3.7385,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 2.9618,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 3.7651,
+      "step": 3
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 2.5572,
+      "step": 4
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 3.2352,
+      "step": 5
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 3.7965,
+      "step": 6
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5e-05,
+      "loss": 3.4411,
+      "step": 7
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.999682116415026e-05,
+      "loss": 3.2539,
+      "step": 8
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.998728546500082e-05,
+      "loss": 3.2295,
+      "step": 9
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.9971395327545466e-05,
+      "loss": 3.8146,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.9949154792755286e-05,
+      "loss": 2.9204,
+      "step": 11
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.992056951655103e-05,
+      "loss": 2.4845,
+      "step": 12
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.988564676836475e-05,
+      "loss": 2.3794,
+      "step": 13
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.984439542929117e-05,
+      "loss": 2.3144,
+      "step": 14
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.979682598982912e-05,
+      "loss": 2.8456,
+      "step": 15
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.974295054721377e-05,
+      "loss": 3.0537,
+      "step": 16
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.9682782802340184e-05,
+      "loss": 2.7413,
+      "step": 17
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.9616338056279124e-05,
+      "loss": 2.8134,
+      "step": 18
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.9543633206385834e-05,
+      "loss": 3.6205,
+      "step": 19
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.9464686742003006e-05,
+      "loss": 3.5697,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.937951873975871e-05,
+      "loss": 2.8348,
+      "step": 21
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.928815085846087e-05,
+      "loss": 3.3747,
+      "step": 22
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.9190606333589194e-05,
+      "loss": 3.0038,
+      "step": 23
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.9086909971386305e-05,
+      "loss": 3.1921,
+      "step": 24
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.8977088142549285e-05,
+      "loss": 2.6579,
+      "step": 25
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.886116877552347e-05,
+      "loss": 3.2293,
+      "step": 26
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.873918134940002e-05,
+      "loss": 4.1384,
+      "step": 27
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.8611156886419206e-05,
+      "loss": 2.6833,
+      "step": 28
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.847712794408124e-05,
+      "loss": 3.4143,
+      "step": 29
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.833712860686666e-05,
+      "loss": 3.9069,
+      "step": 30
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.8191194477568435e-05,
+      "loss": 3.1464,
+      "step": 31
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.803936266823792e-05,
+      "loss": 3.9239,
+      "step": 32
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.7881671790747e-05,
+      "loss": 2.982,
+      "step": 33
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.7718161946968835e-05,
+      "loss": 2.9096,
+      "step": 34
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.754887471857969e-05,
+      "loss": 2.772,
+      "step": 35
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 4.7373853156484406e-05,
+      "loss": 2.9948,
+      "step": 36
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.7193141769868265e-05,
+      "loss": 2.9775,
+      "step": 37
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 4.7006786514877997e-05,
+      "loss": 2.534,
+      "step": 38
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.6814834782934844e-05,
+      "loss": 2.3817,
+      "step": 39
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.6617335388682556e-05,
+      "loss": 3.223,
+      "step": 40
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 4.641433855757351e-05,
+      "loss": 3.3482,
+      "step": 41
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 4.620589591309603e-05,
+      "loss": 2.992,
+      "step": 42
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.59920604636462e-05,
+      "loss": 2.4652,
+      "step": 43
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 4.577288658904741e-05,
+      "loss": 2.8348,
+      "step": 44
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 4.554843002672129e-05,
+      "loss": 4.1209,
+      "step": 45
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.531874785751317e-05,
+      "loss": 3.5458,
+      "step": 46
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.5083898491176136e-05,
+      "loss": 3.3499,
+      "step": 47
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.4843941651517e-05,
+      "loss": 2.5327,
+      "step": 48
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.4598938361208095e-05,
+      "loss": 2.9724,
+      "step": 49
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.434895092626883e-05,
+      "loss": 2.4149,
+      "step": 50
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 4.409404292022081e-05,
+      "loss": 2.8688,
+      "step": 51
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.38342791679207e-05,
+      "loss": 2.9715,
+      "step": 52
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.356972572907473e-05,
+      "loss": 2.6849,
+      "step": 53
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 4.3300449881439375e-05,
+      "loss": 3.185,
+      "step": 54
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.302652010371205e-05,
+      "loss": 3.1415,
+      "step": 55
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.274800605811658e-05,
+      "loss": 2.5797,
+      "step": 56
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.246497857268759e-05,
+      "loss": 2.2357,
+      "step": 57
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.2177509623258456e-05,
+      "loss": 2.8965,
+      "step": 58
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.1885672315157346e-05,
+      "loss": 3.1428,
+      "step": 59
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.1589540864616025e-05,
+      "loss": 2.3255,
+      "step": 60
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.128919057989622e-05,
+      "loss": 3.001,
+      "step": 61
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.098469784213812e-05,
+      "loss": 3.0732,
+      "step": 62
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.0676140085936186e-05,
+      "loss": 2.7686,
+      "step": 63
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 4.0363595779647e-05,
+      "loss": 3.1581,
+      "step": 64
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.0047144405434175e-05,
+      "loss": 3.8875,
+      "step": 65
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.972686643905558e-05,
+      "loss": 3.9603,
+      "step": 66
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 3.940284332939771e-05,
+      "loss": 3.6382,
+      "step": 67
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.9075157477762744e-05,
+      "loss": 3.5762,
+      "step": 68
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.874389221691329e-05,
+      "loss": 2.7994,
+      "step": 69
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 3.84091317898803e-05,
+      "loss": 3.0237,
+      "step": 70
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 3.8070961328539525e-05,
+      "loss": 2.4911,
+      "step": 71
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 3.772946683196179e-05,
+      "loss": 3.264,
+      "step": 72
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 3.738473514454297e-05,
+      "loss": 3.1732,
+      "step": 73
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.7036853933918784e-05,
+      "loss": 3.5421,
+      "step": 74
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.668591166867035e-05,
+      "loss": 3.8679,
+      "step": 75
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.633199759582596e-05,
+      "loss": 3.2613,
+      "step": 76
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.597520171816503e-05,
+      "loss": 3.3075,
+      "step": 77
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.5615614771329706e-05,
+      "loss": 2.6811,
+      "step": 78
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.5253328200750224e-05,
+      "loss": 3.0083,
+      "step": 79
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 3.488843413838963e-05,
+      "loss": 3.3417,
+      "step": 80
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 3.452102537931408e-05,
+      "loss": 2.4357,
+      "step": 81
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 3.4151195358094365e-05,
+      "loss": 3.2885,
+      "step": 82
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 3.377903812504487e-05,
+      "loss": 3.3224,
+      "step": 83
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.340464832230592e-05,
+      "loss": 3.2192,
+      "step": 84
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 3.3028121159775656e-05,
+      "loss": 2.8256,
+      "step": 85
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 3.2649552390897494e-05,
+      "loss": 2.0816,
+      "step": 86
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 3.226903828830935e-05,
+      "loss": 3.1104,
+      "step": 87
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 3.1886675619360885e-05,
+      "loss": 3.0006,
+      "step": 88
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.1502561621504874e-05,
+      "loss": 2.4053,
+      "step": 89
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.111679397756906e-05,
+      "loss": 3.3762,
+      "step": 90
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 3.072947079091472e-05,
+      "loss": 2.9438,
+      "step": 91
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.034069056048837e-05,
+      "loss": 3.9727,
+      "step": 92
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.9950552155772743e-05,
+      "loss": 3.3063,
+      "step": 93
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.95591547916436e-05,
+      "loss": 2.9004,
+      "step": 94
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 2.9166598003138766e-05,
+      "loss": 3.149,
+      "step": 95
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.8772981620145623e-05,
+      "loss": 2.7673,
+      "step": 96
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.8378405742013713e-05,
+      "loss": 2.4541,
+      "step": 97
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.7982970712098794e-05,
+      "loss": 2.7791,
+      "step": 98
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.7586777092244804e-05,
+      "loss": 3.8837,
+      "step": 99
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.7189925637210323e-05,
+      "loss": 2.5179,
+      "step": 100
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.6792517269045943e-05,
+      "loss": 3.7649,
+      "step": 101
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.6394653051429064e-05,
+      "loss": 3.5913,
+      "step": 102
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.5996434163962763e-05,
+      "loss": 5.0055,
+      "step": 103
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2.5597961876445077e-05,
+      "loss": 2.6826,
+      "step": 104
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 2.5199337523115418e-05,
+      "loss": 3.1971,
+      "step": 105
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 2.480066247688459e-05,
+      "loss": 3.0641,
+      "step": 106
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 2.4402038123554933e-05,
+      "loss": 2.9264,
+      "step": 107
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 2.4003565836037246e-05,
+      "loss": 2.5069,
+      "step": 108
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 2.360534694857094e-05,
+      "loss": 4.365,
+      "step": 109
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 2.3207482730954063e-05,
+      "loss": 3.4356,
+      "step": 110
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 2.2810074362789676e-05,
+      "loss": 3.2688,
+      "step": 111
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 2.2413222907755195e-05,
+      "loss": 2.7195,
+      "step": 112
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 2.2017029287901212e-05,
+      "loss": 2.6272,
+      "step": 113
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 2.162159425798629e-05,
+      "loss": 2.8288,
+      "step": 114
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 2.1227018379854383e-05,
+      "loss": 2.0868,
+      "step": 115
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 2.083340199686124e-05,
+      "loss": 3.5304,
+      "step": 116
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 2.0440845208356402e-05,
+      "loss": 3.0078,
+      "step": 117
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 2.0049447844227266e-05,
+      "loss": 3.5883,
+      "step": 118
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 1.9659309439511628e-05,
+      "loss": 2.6867,
+      "step": 119
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.927052920908528e-05,
+      "loss": 2.3407,
+      "step": 120
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.8883206022430956e-05,
+      "loss": 3.6757,
+      "step": 121
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.849743837849513e-05,
+      "loss": 4.9815,
+      "step": 122
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 1.8113324380639117e-05,
+      "loss": 3.0576,
+      "step": 123
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 1.7730961711690655e-05,
+      "loss": 2.4852,
+      "step": 124
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.735044760910251e-05,
+      "loss": 2.6612,
+      "step": 125
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.6971878840224346e-05,
+      "loss": 2.9253,
+      "step": 126
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.6595351677694083e-05,
+      "loss": 3.4379,
+      "step": 127
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 1.6220961874955134e-05,
+      "loss": 2.8997,
+      "step": 128
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.5848804641905634e-05,
+      "loss": 3.2326,
+      "step": 129
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.547897462068592e-05,
+      "loss": 2.8364,
+      "step": 130
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.5111565861610378e-05,
+      "loss": 2.5979,
+      "step": 131
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.4746671799249784e-05,
+      "loss": 3.2094,
+      "step": 132
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.4384385228670288e-05,
+      "loss": 2.2841,
+      "step": 133
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 1.4024798281834966e-05,
+      "loss": 3.333,
+      "step": 134
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.3668002404174047e-05,
+      "loss": 3.1955,
+      "step": 135
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.331408833132966e-05,
+      "loss": 1.9727,
+      "step": 136
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.2963146066081217e-05,
+      "loss": 2.5208,
+      "step": 137
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.2615264855457038e-05,
+      "loss": 2.4915,
+      "step": 138
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2270533168038217e-05,
+      "loss": 2.6322,
+      "step": 139
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.1929038671460486e-05,
+      "loss": 3.6504,
+      "step": 140
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 1.1590868210119692e-05,
+      "loss": 2.9824,
+      "step": 141
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 1.125610778308672e-05,
+      "loss": 2.6982,
+      "step": 142
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 1.0924842522237267e-05,
+      "loss": 4.0364,
+      "step": 143
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 1.0597156670602299e-05,
+      "loss": 2.9809,
+      "step": 144
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 1.027313356094443e-05,
+      "loss": 1.7772,
+      "step": 145
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 9.95285559456583e-06,
+      "loss": 1.9795,
+      "step": 146
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 9.636404220353013e-06,
+      "loss": 2.0211,
+      "step": 147
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 9.323859914063814e-06,
+      "loss": 2.3984,
+      "step": 148
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 9.015302157861883e-06,
+      "loss": 2.1658,
+      "step": 149
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 8.710809420103789e-06,
+      "loss": 2.0633,
+      "step": 150
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 8.41045913538398e-06,
+      "loss": 2.5502,
+      "step": 151
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 8.11432768484267e-06,
+      "loss": 2.2849,
+      "step": 152
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 7.822490376741554e-06,
+      "loss": 2.1318,
+      "step": 153
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 7.535021427312417e-06,
+      "loss": 3.1577,
+      "step": 154
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 7.251993941883428e-06,
+      "loss": 2.4369,
+      "step": 155
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 6.9734798962879575e-06,
+      "loss": 2.7381,
+      "step": 156
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 6.699550118560632e-06,
+      "loss": 2.8945,
+      "step": 157
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 6.430274270925271e-06,
+      "loss": 1.8788,
+      "step": 158
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 6.1657208320793054e-06,
+      "loss": 3.3476,
+      "step": 159
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 5.905957079779187e-06,
+      "loss": 2.3672,
+      "step": 160
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 5.6510490737311735e-06,
+      "loss": 3.0826,
+      "step": 161
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 5.4010616387919095e-06,
+      "loss": 2.4247,
+      "step": 162
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 5.156058348483006e-06,
+      "loss": 2.9849,
+      "step": 163
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 4.916101508823873e-06,
+      "loss": 3.2181,
+      "step": 164
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 4.681252142486841e-06,
+      "loss": 2.756,
+      "step": 165
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 4.451569973278719e-06,
+      "loss": 2.5613,
+      "step": 166
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 4.227113410952585e-06,
+      "loss": 3.7162,
+      "step": 167
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 4.007939536353805e-06,
+      "loss": 2.9746,
+      "step": 168
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 3.7941040869039714e-06,
+      "loss": 2.4908,
+      "step": 169
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 3.585661442426494e-06,
+      "loss": 2.2047,
+      "step": 170
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 3.382664611317446e-06,
+      "loss": 2.5563,
+      "step": 171
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 3.1851652170651584e-06,
+      "loss": 2.804,
+      "step": 172
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 2.9932134851220038e-06,
+      "loss": 3.0241,
+      "step": 173
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 2.8068582301317425e-06,
+      "loss": 2.2791,
+      "step": 174
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 2.6261468435155978e-06,
+      "loss": 2.997,
+      "step": 175
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 2.4511252814203107e-06,
+      "loss": 2.8508,
+      "step": 176
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 2.2818380530311655e-06,
+      "loss": 2.4406,
+      "step": 177
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.1183282092530065e-06,
+      "loss": 2.5544,
+      "step": 178
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 1.960637331762091e-06,
+      "loss": 2.9358,
+      "step": 179
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 1.8088055224315697e-06,
+      "loss": 2.2767,
+      "step": 180
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 1.6628713931333445e-06,
+      "loss": 3.5501,
+      "step": 181
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 1.5228720559187642e-06,
+      "loss": 2.3521,
+      "step": 182
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 1.3888431135807956e-06,
+      "loss": 2.6828,
+      "step": 183
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 1.2608186505999847e-06,
+      "loss": 3.3842,
+      "step": 184
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 1.138831224476533e-06,
+      "loss": 3.7512,
+      "step": 185
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 1.0229118574507174e-06,
+      "loss": 2.5144,
+      "step": 186
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 9.130900286137001e-07,
+      "loss": 1.8449,
+      "step": 187
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 8.093936664108071e-07,
+      "loss": 2.3796,
+      "step": 188
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 7.118491415391337e-07,
+      "loss": 3.1911,
+      "step": 189
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 6.204812602412902e-07,
+      "loss": 3.3982,
+      "step": 190
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 5.353132579969972e-07,
+      "loss": 2.5562,
+      "step": 191
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 4.56366793614163e-07,
+      "loss": 3.1778,
+      "step": 192
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 3.8366194372088384e-07,
+      "loss": 2.8666,
+      "step": 193
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 3.1721719765981926e-07,
+      "loss": 1.849,
+      "step": 194
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 2.5704945278623436e-07,
+      "loss": 2.9817,
+      "step": 195
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 2.0317401017088122e-07,
+      "loss": 2.8708,
+      "step": 196
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 1.5560457070883105e-07,
+      "loss": 1.9914,
+      "step": 197
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 1.1435323163525025e-07,
+      "loss": 2.631,
+      "step": 198
+    },
+    {
+      "epoch": 5.73,
+      "learning_rate": 7.94304834489723e-08,
+      "loss": 3.1964,
+      "step": 199
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 5.0845207244715196e-08,
+      "loss": 3.1362,
+      "step": 200
+    },
+    {
+      "epoch": 5.78,
+      "learning_rate": 2.8604672454538018e-08,
+      "loss": 2.4684,
+      "step": 201
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 1.2714534999183625e-08,
+      "loss": 2.9911,
+      "step": 202
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 3.1788358497431005e-09,
+      "loss": 2.7763,
+      "step": 203
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 0.0,
+      "loss": 3.1651,
+      "step": 204
+    },
+    {
+      "epoch": 5.87,
+      "step": 204,
+      "total_flos": 0.0,
+      "train_loss": 2.9658100090774835,
+      "train_runtime": 18093.1922,
+      "train_samples_per_second": 23.54,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 50,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower/config.json

@@ -0,0 +1,19 @@
+{
+  "_name_or_path": "/mnt/amlfs-01/home/fuzhaox/checkpoints/longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower",
+  "architectures": [
+    "SiglipVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "image_size": 384,
+  "intermediate_size": 4304,
+  "layer_norm_eps": 1e-06,
+  "model_type": "siglip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 27,
+  "patch_size": 14,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2"
+}

longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd418974dfd73a5446f05cee0eb8d6d70593201aa18198915e692459457bc63
+size 856506120

longvila8b_sft_v7_oss_256k_512frames_v41/vision_tower/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}