Initial commit for LongVILA-7b-256frames-tile2

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.wandb filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,5 @@
+wandb/
+logs/
+*.wandb
+*.tmp
+

config.json

@@ -0,0 +1,270 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2",
+  "architectures": [
+    "LlavaLlamaModel"
+  ],
+  "chat_template": null,
+  "drop_path_rate": 0.0,
+  "dynamic_s2": false,
+  "fps": 2.0,
+  "hidden_size": 3584,
+  "image_aspect_ratio": "dynamic",
+  "interpolate_mode": "linear",
+  "llm_cfg": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2/llm",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "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": 151645,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 28,
+    "min_length": 0,
+    "model_max_length": 131072,
+    "model_type": "qwen2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "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,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 15300000,
+    "sep_token_id": null,
+    "sliding_window": 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": 131072,
+    "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,
+    "use_sliding_window": false,
+    "vocab_size": 151648
+  },
+  "mm_hidden_size": 1152,
+  "mm_projector_cfg": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2/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_2x2_fix",
+    "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": true,
+  "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_time_tokens": 0,
+  "num_video_frames": 128,
+  "resume_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2",
+  "s2": false,
+  "s2_max_split_size": 336,
+  "s2_resize_output_to_scale_idx": 0,
+  "s2_scales": "336,672,1008",
+  "soft_ce_std": 1.0,
+  "time_token_format": "<t{t}>",
+  "time_token_ids": [],
+  "transformers_version": "4.46.0",
+  "tune_language_model": true,
+  "tune_mm_projector": true,
+  "tune_vision_tower": true,
+  "vision_resolution": -1,
+  "vision_tower_cfg": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2/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": 448,
+    "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_image_tokens": 256,
+    "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,
+    "projection_dim": 2048,
+    "projector_hidden_act": "gelu_fast",
+    "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,
+    "vision_use_head": false
+  }
+}

llm/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "[BOS]": 151646,
+  "[PAD]": 151647
+}

llm/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2/llm",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_max_length": 131072,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 15300000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 131072,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151648
+}

llm/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.0"
+}

llm/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b7b9d8687fb66bfe52cb5efb9e5ae659098c20cf4ae60f6f0855dc23113168
+size 4874678888

llm/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52bfdc3dc48b0d1fe1ffb5192506eff445df2523a7d4bc726e20a3075b0880a1
+size 4932751008

llm/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fc8dd710321e5920b6f36e5ac2e6b91c2c41cbfc33069b7e5f9b41c1960a9c
+size 4330865200

llm/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585b1ef951780ef86cdeff49f507d65f1d1f2d9e58aa37d03886555a853d7546
+size 1087012992

llm/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15225269248
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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-00003-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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

llm/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llm/tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "[BOS]",
+  "chat_template": "{% if messages[0]['role'] != 'system' %}{{ '<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n' }}{% endif %}{% for message in messages if message['content'] is not none %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

mm_projector/config.json

@@ -0,0 +1,10 @@
+{
+  "_name_or_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2/mm_projector",
+  "architectures": [
+    "MultimodalProjector"
+  ],
+  "mm_projector_type": "mlp_downsample_2x2_fix",
+  "model_type": "v2l_projector",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0"
+}

mm_projector/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6ec64f81f87d4bd3b6ab1a56f99f693a4f9f86583ab26b80dff87e12b94a7c
+size 58753552

trainer_state.json

@@ -0,0 +1,1512 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.996835443037975,
+  "eval_steps": 500,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 10.745909104013029,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 3.7358,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 11.845140833151277,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 3.6856,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 11.845140833151277,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 3.2154,
+      "step": 3
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 11.845140833151277,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 3.5768,
+      "step": 4
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 11.845140833151277,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 3.7658,
+      "step": 5
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 8.676633993597468,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 3.0183,
+      "step": 6
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8.614508991145888,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 3.4849,
+      "step": 7
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 8.614508991145888,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 3.6352,
+      "step": 8
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.822334238607632,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 3.4481,
+      "step": 9
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.922253600804103,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 3.2409,
+      "step": 10
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 15.131671312747258,
+      "learning_rate": 2e-05,
+      "loss": 4.014,
+      "step": 11
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 3.43,
+      "step": 12
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 3.8237,
+      "step": 13
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 3.3954,
+      "step": 14
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 3.8053,
+      "step": 15
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 2.9549,
+      "step": 16
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 3.3261,
+      "step": 17
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 3.3888,
+      "step": 18
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 10.832518268660342,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 3.1681,
+      "step": 19
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 9.859756972439765,
+      "learning_rate": 1.9995210358660037e-05,
+      "loss": 3.3455,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.150942345154002,
+      "learning_rate": 1.9989224382388813e-05,
+      "loss": 3.4818,
+      "step": 21
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 8.547022254412862,
+      "learning_rate": 1.9980846022772978e-05,
+      "loss": 3.6079,
+      "step": 22
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 8.547022254412862,
+      "learning_rate": 1.9980846022772978e-05,
+      "loss": 3.0004,
+      "step": 23
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 7.504048709301798,
+      "learning_rate": 1.997007728639956e-05,
+      "loss": 3.3215,
+      "step": 24
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 6.539987611168741,
+      "learning_rate": 1.9956920752342226e-05,
+      "loss": 3.0279,
+      "step": 25
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 6.539987611168741,
+      "learning_rate": 1.9956920752342226e-05,
+      "loss": 3.4405,
+      "step": 26
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 6.539987611168741,
+      "learning_rate": 1.9956920752342226e-05,
+      "loss": 3.0967,
+      "step": 27
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.539987611168741,
+      "learning_rate": 1.9956920752342226e-05,
+      "loss": 3.088,
+      "step": 28
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 6.539987611168741,
+      "learning_rate": 1.9956920752342226e-05,
+      "loss": 2.7919,
+      "step": 29
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.442478841503217,
+      "learning_rate": 1.9941379571543597e-05,
+      "loss": 3.4199,
+      "step": 30
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.442478841503217,
+      "learning_rate": 1.9941379571543597e-05,
+      "loss": 3.1446,
+      "step": 31
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.683918200190512,
+      "learning_rate": 1.9923457466060637e-05,
+      "loss": 3.2384,
+      "step": 32
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.829342444256826,
+      "learning_rate": 1.9903158728173206e-05,
+      "loss": 3.1535,
+      "step": 33
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.829342444256826,
+      "learning_rate": 1.9903158728173206e-05,
+      "loss": 2.8555,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.829342444256826,
+      "learning_rate": 1.9903158728173206e-05,
+      "loss": 2.7903,
+      "step": 35
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 9.6288495968318,
+      "learning_rate": 1.9880488219356086e-05,
+      "loss": 4.6632,
+      "step": 36
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 4.404098574989548,
+      "learning_rate": 1.9855451369114677e-05,
+      "loss": 2.9321,
+      "step": 37
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 4.404098574989548,
+      "learning_rate": 1.9855451369114677e-05,
+      "loss": 2.4582,
+      "step": 38
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 4.404098574989548,
+      "learning_rate": 1.9855451369114677e-05,
+      "loss": 3.016,
+      "step": 39
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.404098574989548,
+      "learning_rate": 1.9855451369114677e-05,
+      "loss": 3.0601,
+      "step": 40
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 4.404098574989548,
+      "learning_rate": 1.9855451369114677e-05,
+      "loss": 2.3929,
+      "step": 41
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 4.266672410944561,
+      "learning_rate": 1.9828054173684646e-05,
+      "loss": 2.3491,
+      "step": 42
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 4.266672410944561,
+      "learning_rate": 1.9828054173684646e-05,
+      "loss": 3.1275,
+      "step": 43
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.534933083803799,
+      "learning_rate": 1.9798303194595846e-05,
+      "loss": 2.7681,
+      "step": 44
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 4.3832140222345215,
+      "learning_rate": 1.976620555710087e-05,
+      "loss": 2.569,
+      "step": 45
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 5.567358591451238,
+      "learning_rate": 1.973176894846855e-05,
+      "loss": 2.6533,
+      "step": 46
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 4.972447642952155,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 2.4035,
+      "step": 47
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 4.972447642952155,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 3.6331,
+      "step": 48
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 4.972447642952155,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 3.4085,
+      "step": 49
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 4.972447642952155,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 3.5906,
+      "step": 50
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 2.8645,
+      "step": 51
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 3.2456,
+      "step": 52
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 3.3121,
+      "step": 53
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 3.0871,
+      "step": 54
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 4.577929884798453,
+      "learning_rate": 1.965591236576794e-05,
+      "loss": 2.4911,
+      "step": 55
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.8893577161525945,
+      "learning_rate": 1.9614510559078626e-05,
+      "loss": 2.4741,
+      "step": 56
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 5.738612095999555,
+      "learning_rate": 1.95708061116589e-05,
+      "loss": 2.448,
+      "step": 57
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 5.738612095999555,
+      "learning_rate": 1.95708061116589e-05,
+      "loss": 2.9737,
+      "step": 58
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 5.060793895344798,
+      "learning_rate": 1.9524809490566878e-05,
+      "loss": 2.3368,
+      "step": 59
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 4.455225187190013,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 2.2524,
+      "step": 60
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 4.455225187190013,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 3.4379,
+      "step": 61
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 4.455225187190013,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 3.1004,
+      "step": 62
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.455225187190013,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 3.0873,
+      "step": 63
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 4.455225187190013,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 2.7873,
+      "step": 64
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 6.133721749895579,
+      "learning_rate": 1.942598433779687e-05,
+      "loss": 2.322,
+      "step": 65
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 6.133721749895579,
+      "learning_rate": 1.942598433779687e-05,
+      "loss": 3.181,
+      "step": 66
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 5.44690388478305,
+      "learning_rate": 1.9373179474387858e-05,
+      "loss": 2.3634,
+      "step": 67
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 5.399452825068645,
+      "learning_rate": 1.9318129768176033e-05,
+      "loss": 2.3324,
+      "step": 68
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.399452825068645,
+      "learning_rate": 1.9318129768176033e-05,
+      "loss": 2.9248,
+      "step": 69
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.399452825068645,
+      "learning_rate": 1.9318129768176033e-05,
+      "loss": 2.8532,
+      "step": 70
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 5.246839436820852,
+      "learning_rate": 1.926084840336821e-05,
+      "loss": 2.8837,
+      "step": 71
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 6.320135133123584,
+      "learning_rate": 1.9201349098645433e-05,
+      "loss": 3.3816,
+      "step": 72
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 6.320135133123584,
+      "learning_rate": 1.9201349098645433e-05,
+      "loss": 2.9535,
+      "step": 73
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 4.3276729104087295,
+      "learning_rate": 1.9139646103877378e-05,
+      "loss": 2.8788,
+      "step": 74
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 5.437918020961627,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 2.8748,
+      "step": 75
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 5.437918020961627,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 2.9727,
+      "step": 76
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 5.437918020961627,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 3.2969,
+      "step": 77
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 5.437918020961627,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 3.0428,
+      "step": 78
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 5.437918020961627,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 2.8944,
+      "step": 79
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 4.920021016187099,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 3.2227,
+      "step": 80
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 4.711625687761842,
+      "learning_rate": 1.894146537327533e-05,
+      "loss": 3.3434,
+      "step": 81
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 3.9759783965517874,
+      "learning_rate": 1.8871100618699553e-05,
+      "loss": 2.8305,
+      "step": 82
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 6.647061826435325,
+      "learning_rate": 1.8798611267402745e-05,
+      "loss": 3.6359,
+      "step": 83
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 6.647061826435325,
+      "learning_rate": 1.8798611267402745e-05,
+      "loss": 2.7353,
+      "step": 84
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 6.647061826435325,
+      "learning_rate": 1.8798611267402745e-05,
+      "loss": 3.1311,
+      "step": 85
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 6.461044629826689,
+      "learning_rate": 1.872401468032406e-05,
+      "loss": 3.6868,
+      "step": 86
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 4.5526001477701765,
+      "learning_rate": 1.864732872307804e-05,
+      "loss": 2.2986,
+      "step": 87
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.5526001477701765,
+      "learning_rate": 1.864732872307804e-05,
+      "loss": 2.41,
+      "step": 88
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 4.5526001477701765,
+      "learning_rate": 1.864732872307804e-05,
+      "loss": 2.9752,
+      "step": 89
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 4.5526001477701765,
+      "learning_rate": 1.864732872307804e-05,
+      "loss": 2.9911,
+      "step": 90
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 4.5526001477701765,
+      "learning_rate": 1.864732872307804e-05,
+      "loss": 2.342,
+      "step": 91
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.066251715555047,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 1.8423,
+      "step": 92
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.066251715555047,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 3.0791,
+      "step": 93
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 4.068156270977161,
+      "learning_rate": 1.8487762658126872e-05,
+      "loss": 2.1676,
+      "step": 94
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.8689084112155943,
+      "learning_rate": 1.8404920765920898e-05,
+      "loss": 1.9859,
+      "step": 95
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 4.7150189322065374,
+      "learning_rate": 1.8320065925393468e-05,
+      "loss": 1.885,
+      "step": 96
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 4.354015459893575,
+      "learning_rate": 1.8233218458973984e-05,
+      "loss": 1.605,
+      "step": 97
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 4.354015459893575,
+      "learning_rate": 1.8233218458973984e-05,
+      "loss": 3.7732,
+      "step": 98
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 4.354015459893575,
+      "learning_rate": 1.8233218458973984e-05,
+      "loss": 3.4874,
+      "step": 99
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 4.354015459893575,
+      "learning_rate": 1.8233218458973984e-05,
+      "loss": 3.7074,
+      "step": 100
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8233218458973984e-05,
+      "loss": 3.2998,
+      "step": 101
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 4.626614627051075,
+      "learning_rate": 1.814439916631857e-05,
+      "loss": 1.5941,
+      "step": 102
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 4.983632390206286,
+      "learning_rate": 1.8053629319328662e-05,
+      "loss": 1.4982,
+      "step": 103
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 4.983632390206286,
+      "learning_rate": 1.8053629319328662e-05,
+      "loss": 3.1327,
+      "step": 104
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.983632390206286,
+      "learning_rate": 1.8053629319328662e-05,
+      "loss": 3.0876,
+      "step": 105
+    },
+    {
+      "epoch": 3.03,
+      "grad_norm": 4.7246349324630454,
+      "learning_rate": 1.796093065705644e-05,
+      "loss": 1.7214,
+      "step": 106
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 6.478189895530414,
+      "learning_rate": 1.786632538049842e-05,
+      "loss": 2.2154,
+      "step": 107
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 6.478189895530414,
+      "learning_rate": 1.786632538049842e-05,
+      "loss": 3.3134,
+      "step": 108
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 5.5921238659005725,
+      "learning_rate": 1.776983614727838e-05,
+      "loss": 2.2517,
+      "step": 109
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 5.534943060953176,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 2.082,
+      "step": 110
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 5.534943060953176,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 3.1982,
+      "step": 111
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.534943060953176,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 3.5452,
+      "step": 112
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 5.534943060953176,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 3.2572,
+      "step": 113
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 5.534943060953176,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 3.093,
+      "step": 114
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 6.028567841224762,
+      "learning_rate": 1.757129869181718e-05,
+      "loss": 2.4001,
+      "step": 115
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 6.3075138811264475,
+      "learning_rate": 1.746929801858317e-05,
+      "loss": 2.547,
+      "step": 116
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 5.078979153195962,
+      "learning_rate": 1.736550847531366e-05,
+      "loss": 2.2615,
+      "step": 117
+    },
+    {
+      "epoch": 3.37,
+      "grad_norm": 6.8686015465430925,
+      "learning_rate": 1.725995491923131e-05,
+      "loss": 2.5536,
+      "step": 118
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 6.8686015465430925,
+      "learning_rate": 1.725995491923131e-05,
+      "loss": 2.9249,
+      "step": 119
+    },
+    {
+      "epoch": 3.42,
+      "grad_norm": 6.8686015465430925,
+      "learning_rate": 1.725995491923131e-05,
+      "loss": 3.3196,
+      "step": 120
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 6.790172880419949,
+      "learning_rate": 1.7152662630033506e-05,
+      "loss": 2.9955,
+      "step": 121
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 6.536740333558469,
+      "learning_rate": 1.7043657303837965e-05,
+      "loss": 3.3799,
+      "step": 122
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 6.536740333558469,
+      "learning_rate": 1.7043657303837965e-05,
+      "loss": 3.1293,
+      "step": 123
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 7.076899389694803,
+      "learning_rate": 1.693296504702862e-05,
+      "loss": 3.7154,
+      "step": 124
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 7.076899389694803,
+      "learning_rate": 1.693296504702862e-05,
+      "loss": 3.01,
+      "step": 125
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 7.076899389694803,
+      "learning_rate": 1.693296504702862e-05,
+      "loss": 3.0141,
+      "step": 126
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 7.076899389694803,
+      "learning_rate": 1.693296504702862e-05,
+      "loss": 3.4354,
+      "step": 127
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 7.076899389694803,
+      "learning_rate": 1.693296504702862e-05,
+      "loss": 2.937,
+      "step": 128
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 7.31807712363732,
+      "learning_rate": 1.682061237000322e-05,
+      "loss": 3.1611,
+      "step": 129
+    },
+    {
+      "epoch": 3.71,
+      "grad_norm": 7.31807712363732,
+      "learning_rate": 1.682061237000322e-05,
+      "loss": 3.0004,
+      "step": 130
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 7.31807712363732,
+      "learning_rate": 1.682061237000322e-05,
+      "loss": 3.0685,
+      "step": 131
+    },
+    {
+      "epoch": 3.77,
+      "grad_norm": 6.751859406216805,
+      "learning_rate": 1.6706626180824185e-05,
+      "loss": 3.1218,
+      "step": 132
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 6.085383457658417,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 3.0829,
+      "step": 133
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 6.085383457658417,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 3.1848,
+      "step": 134
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 6.085383457658417,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 3.0089,
+      "step": 135
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 9.365062981714178,
+      "learning_rate": 1.647386284781828e-05,
+      "loss": 3.6731,
+      "step": 136
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 6.610030487412542,
+      "learning_rate": 1.6355141449973254e-05,
+      "loss": 1.9927,
+      "step": 137
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 6.610030487412542,
+      "learning_rate": 1.6355141449973254e-05,
+      "loss": 2.4353,
+      "step": 138
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 6.610030487412542,
+      "learning_rate": 1.6355141449973254e-05,
+      "loss": 3.0121,
+      "step": 139
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 6.610030487412542,
+      "learning_rate": 1.6355141449973254e-05,
+      "loss": 3.0222,
+      "step": 140
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 6.610030487412542,
+      "learning_rate": 1.6355141449973254e-05,
+      "loss": 2.3583,
+      "step": 141
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 5.5450540859525095,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 1.5504,
+      "step": 142
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 5.5450540859525095,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 3.111,
+      "step": 143
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 5.733431452998195,
+      "learning_rate": 1.611316135153026e-05,
+      "loss": 1.7954,
+      "step": 144
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 5.034610729523613,
+      "learning_rate": 1.598996060429634e-05,
+      "loss": 1.6,
+      "step": 145
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 4.914809599403493,
+      "learning_rate": 1.586532528302183e-05,
+      "loss": 1.4157,
+      "step": 146
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 4.744024069441604,
+      "learning_rate": 1.5739285237418323e-05,
+      "loss": 1.1664,
+      "step": 147
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 4.744024069441604,
+      "learning_rate": 1.5739285237418323e-05,
+      "loss": 3.9526,
+      "step": 148
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 4.744024069441604,
+      "learning_rate": 1.5739285237418323e-05,
+      "loss": 3.6555,
+      "step": 149
+    },
+    {
+      "epoch": 3.42,
+      "grad_norm": 4.744024069441604,
+      "learning_rate": 1.5739285237418323e-05,
+      "loss": 3.8614,
+      "step": 150
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 4.1768497310203125,
+      "learning_rate": 1.5611870653623826e-05,
+      "loss": 1.1103,
+      "step": 151
+    },
+    {
+      "epoch": 4.34,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 1.4397,
+      "step": 152
+    },
+    {
+      "epoch": 4.37,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 4.2716,
+      "step": 153
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 3.7013,
+      "step": 154
+    },
+    {
+      "epoch": 4.43,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 4.1961,
+      "step": 155
+    },
+    {
+      "epoch": 4.46,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 3.2478,
+      "step": 156
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 3.6599,
+      "step": 157
+    },
+    {
+      "epoch": 4.51,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 3.7179,
+      "step": 158
+    },
+    {
+      "epoch": 4.54,
+      "grad_norm": 3.910064558844921,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 3.5381,
+      "step": 159
+    },
+    {
+      "epoch": 4.57,
+      "grad_norm": 5.202243594230388,
+      "learning_rate": 1.5353040254690396e-05,
+      "loss": 1.7474,
+      "step": 160
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 5.234307741068539,
+      "learning_rate": 1.5221686428501929e-05,
+      "loss": 1.5038,
+      "step": 161
+    },
+    {
+      "epoch": 4.63,
+      "grad_norm": 5.454826834012641,
+      "learning_rate": 1.5089082027177291e-05,
+      "loss": 1.3784,
+      "step": 162
+    },
+    {
+      "epoch": 4.66,
+      "grad_norm": 5.454826834012641,
+      "learning_rate": 1.5089082027177291e-05,
+      "loss": 3.3226,
+      "step": 163
+    },
+    {
+      "epoch": 4.68,
+      "grad_norm": 5.377130386285983,
+      "learning_rate": 1.4955258808994096e-05,
+      "loss": 1.4163,
+      "step": 164
+    },
+    {
+      "epoch": 4.71,
+      "grad_norm": 5.630263152807122,
+      "learning_rate": 1.4820248824132221e-05,
+      "loss": 1.4215,
+      "step": 165
+    },
+    {
+      "epoch": 4.74,
+      "grad_norm": 5.630263152807122,
+      "learning_rate": 1.4820248824132221e-05,
+      "loss": 3.822,
+      "step": 166
+    },
+    {
+      "epoch": 4.77,
+      "grad_norm": 5.630263152807122,
+      "learning_rate": 1.4820248824132221e-05,
+      "loss": 3.4931,
+      "step": 167
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 5.630263152807122,
+      "learning_rate": 1.4820248824132221e-05,
+      "loss": 3.5133,
+      "step": 168
+    },
+    {
+      "epoch": 4.83,
+      "grad_norm": 5.630263152807122,
+      "learning_rate": 1.4820248824132221e-05,
+      "loss": 3.1357,
+      "step": 169
+    },
+    {
+      "epoch": 4.85,
+      "grad_norm": 5.788425426880448,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 1.2746,
+      "step": 170
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 5.788425426880448,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 3.5869,
+      "step": 171
+    },
+    {
+      "epoch": 4.91,
+      "grad_norm": 4.874795766816558,
+      "learning_rate": 1.4546798168479756e-05,
+      "loss": 0.8619,
+      "step": 172
+    },
+    {
+      "epoch": 4.94,
+      "grad_norm": 4.729179130081543,
+      "learning_rate": 1.4408422988138585e-05,
+      "loss": 0.765,
+      "step": 173
+    },
+    {
+      "epoch": 4.97,
+      "grad_norm": 4.729179130081543,
+      "learning_rate": 1.4408422988138585e-05,
+      "loss": 3.3551,
+      "step": 174
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.729179130081543,
+      "learning_rate": 1.4408422988138585e-05,
+      "loss": 3.3105,
+      "step": 175
+    },
+    {
+      "epoch": 5.03,
+      "grad_norm": 5.290997290947021,
+      "learning_rate": 1.4268992006332847e-05,
+      "loss": 0.826,
+      "step": 176
+    },
+    {
+      "epoch": 5.05,
+      "grad_norm": 5.646691617523086,
+      "learning_rate": 1.412853861628166e-05,
+      "loss": 1.0013,
+      "step": 177
+    },
+    {
+      "epoch": 5.08,
+      "grad_norm": 5.646691617523086,
+      "learning_rate": 1.412853861628166e-05,
+      "loss": 3.592,
+      "step": 178
+    },
+    {
+      "epoch": 5.11,
+      "grad_norm": 5.293182617266683,
+      "learning_rate": 1.3987096456067236e-05,
+      "loss": 1.0919,
+      "step": 179
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 5.709228089784577,
+      "learning_rate": 1.3844699400578696e-05,
+      "loss": 0.8435,
+      "step": 180
+    },
+    {
+      "epoch": 5.17,
+      "grad_norm": 5.709228089784577,
+      "learning_rate": 1.3844699400578696e-05,
+      "loss": 3.6846,
+      "step": 181
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 5.709228089784577,
+      "learning_rate": 1.3844699400578696e-05,
+      "loss": 4.0876,
+      "step": 182
+    },
+    {
+      "epoch": 5.22,
+      "grad_norm": 5.709228089784577,
+      "learning_rate": 1.3844699400578696e-05,
+      "loss": 3.7682,
+      "step": 183
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 5.709228089784577,
+      "learning_rate": 1.3844699400578696e-05,
+      "loss": 3.5682,
+      "step": 184
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 6.993362529212867,
+      "learning_rate": 1.3701381553399147e-05,
+      "loss": 1.1277,
+      "step": 185
+    },
+    {
+      "epoch": 5.02,
+      "grad_norm": 10.857085356276176,
+      "learning_rate": 1.3557177238637987e-05,
+      "loss": 2.0418,
+      "step": 186
+    },
+    {
+      "epoch": 5.05,
+      "grad_norm": 7.182316855738663,
+      "learning_rate": 1.3412120992710425e-05,
+      "loss": 1.5863,
+      "step": 187
+    },
+    {
+      "epoch": 5.08,
+      "grad_norm": 7.182316855738663,
+      "learning_rate": 1.3412120992710425e-05,
+      "loss": 2.8401,
+      "step": 188
+    },
+    {
+      "epoch": 5.11,
+      "grad_norm": 7.182316855738663,
+      "learning_rate": 1.3412120992710425e-05,
+      "loss": 3.5382,
+      "step": 189
+    },
+    {
+      "epoch": 5.14,
+      "grad_norm": 7.182316855738663,
+      "learning_rate": 1.3412120992710425e-05,
+      "loss": 3.5492,
+      "step": 190
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 7.182316855738663,
+      "learning_rate": 1.3412120992710425e-05,
+      "loss": 2.7031,
+      "step": 191
+    },
+    {
+      "epoch": 5.19,
+      "grad_norm": 5.454569997331726,
+      "learning_rate": 1.3266247556066122e-05,
+      "loss": 1.2064,
+      "step": 192
+    },
+    {
+      "epoch": 5.22,
+      "grad_norm": 5.454569997331726,
+      "learning_rate": 1.3266247556066122e-05,
+      "loss": 3.4975,
+      "step": 193
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 6.05413267530256,
+      "learning_rate": 1.3119591864868979e-05,
+      "loss": 1.3958,
+      "step": 194
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 4.86763555215196,
+      "learning_rate": 1.2972189042630044e-05,
+      "loss": 1.1746,
+      "step": 195
+    },
+    {
+      "epoch": 5.31,
+      "grad_norm": 4.818024421862567,
+      "learning_rate": 1.2824074391795571e-05,
+      "loss": 0.7361,
+      "step": 196
+    },
+    {
+      "epoch": 5.34,
+      "grad_norm": 3.9313752517714686,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 0.5405,
+      "step": 197
+    },
+    {
+      "epoch": 5.36,
+      "grad_norm": 3.9313752517714686,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 3.8222,
+      "step": 198
+    },
+    {
+      "epoch": 5.39,
+      "grad_norm": 3.9313752517714686,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 3.8457,
+      "step": 199
+    },
+    {
+      "epoch": 5.42,
+      "grad_norm": 3.9313752517714686,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 4.0919,
+      "step": 200
+    },
+    {
+      "epoch": 5.74,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 3.8764,
+      "step": 201
+    },
+    {
+      "epoch": 5.77,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 3.5465,
+      "step": 202
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 3.5141,
+      "step": 203
+    },
+    {
+      "epoch": 5.83,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 3.1509,
+      "step": 204
+    },
+    {
+      "epoch": 5.85,
+      "grad_norm": 5.547510343712912,
+      "learning_rate": 1.252585165803135e-05,
+      "loss": 0.7488,
+      "step": 205
+    },
+    {
+      "epoch": 5.88,
+      "grad_norm": 5.547510343712912,
+      "learning_rate": 1.252585165803135e-05,
+      "loss": 3.6736,
+      "step": 206
+    },
+    {
+      "epoch": 5.91,
+      "grad_norm": 4.401046390597762,
+      "learning_rate": 1.2375814998374714e-05,
+      "loss": 0.5788,
+      "step": 207
+    },
+    {
+      "epoch": 5.94,
+      "grad_norm": 3.5202118867023735,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.5075,
+      "step": 208
+    },
+    {
+      "epoch": 5.97,
+      "grad_norm": 3.5202118867023735,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 3.4362,
+      "step": 209
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.5202118867023735,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 3.3736,
+      "step": 210
+    },
+    {
+      "epoch": 6.0,
+      "step": 210,
+      "total_flos": 0.0,
+      "train_loss": 0.12574415859721955,
+      "train_runtime": 2485.1499,
+      "train_samples_per_second": 171.382,
+      "train_steps_per_second": 0.085
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

vision_tower/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "./output/qwen2-7b-448-baseline-v13-sft-20241008072327-64k-fromstage3-256frames-hd-tile2-run2/vision_tower",
+  "architectures": [
+    "SiglipVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "image_size": 448,
+  "intermediate_size": 4304,
+  "layer_norm_eps": 1e-06,
+  "model_type": "siglip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 27,
+  "num_image_tokens": 256,
+  "patch_size": 14,
+  "projection_dim": 2048,
+  "projector_hidden_act": "gelu_fast",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "vision_use_head": false
+}

vision_tower/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfa777561065166f4f91578178acad064a2ea62fc258f75ff6b47a9d0146378
+size 826707904

vision_tower/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "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": 448,
+    "width": 448
+  }
+}