Add GeoSR static and dynamic checkpoints
Browse files- GeoSR3D-Model/added_tokens.json +24 -0
- GeoSR3D-Model/chat_template.json +3 -0
- GeoSR3D-Model/config.json +74 -0
- GeoSR3D-Model/generation_config.json +12 -0
- GeoSR3D-Model/merges.txt +0 -0
- GeoSR3D-Model/model-00001-of-00004.safetensors +3 -0
- GeoSR3D-Model/model-00002-of-00004.safetensors +3 -0
- GeoSR3D-Model/model-00003-of-00004.safetensors +3 -0
- GeoSR3D-Model/model-00004-of-00004.safetensors +3 -0
- GeoSR3D-Model/model.safetensors.index.json +0 -0
- GeoSR3D-Model/preprocessor_config.json +29 -0
- GeoSR3D-Model/special_tokens_map.json +31 -0
- GeoSR3D-Model/tokenizer_config.json +209 -0
- GeoSR3D-Model/trainer_state.json +694 -0
- GeoSR3D-Model/vocab.json +0 -0
- GeoSR4D-Model/added_tokens.json +24 -0
- GeoSR4D-Model/config.json +71 -0
- GeoSR4D-Model/generation_config.json +13 -0
- GeoSR4D-Model/merges.txt +0 -0
- GeoSR4D-Model/model-00001-of-00004.safetensors +3 -0
- GeoSR4D-Model/model-00002-of-00004.safetensors +3 -0
- GeoSR4D-Model/model-00003-of-00004.safetensors +3 -0
- GeoSR4D-Model/model-00004-of-00004.safetensors +3 -0
- GeoSR4D-Model/model.safetensors.index.json +1128 -0
- GeoSR4D-Model/preprocessor_config.json +29 -0
- GeoSR4D-Model/special_tokens_map.json +31 -0
- GeoSR4D-Model/tokenizer_config.json +209 -0
- GeoSR4D-Model/trainer_state.json +1240 -0
- GeoSR4D-Model/vocab.json +0 -0
- README.md +70 -3
GeoSR3D-Model/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
GeoSR3D-Model/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
GeoSR3D-Model/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGenerationWithVGGT"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"feature_fusion_method": "gated",
|
| 9 |
+
"fusion_num_layers": 1,
|
| 10 |
+
"geometry_encoder_type": "vggt",
|
| 11 |
+
"geometry_merger_type": "mlp",
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 3584,
|
| 14 |
+
"image_token_id": 151655,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"reference_frame": "first",
|
| 24 |
+
"rms_norm_eps": 1e-06,
|
| 25 |
+
"rope_scaling": {
|
| 26 |
+
"mrope_section": [
|
| 27 |
+
16,
|
| 28 |
+
24,
|
| 29 |
+
24
|
| 30 |
+
],
|
| 31 |
+
"rope_type": "default",
|
| 32 |
+
"type": "default"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 1000000.0,
|
| 35 |
+
"sliding_window": 32768,
|
| 36 |
+
"tie_word_embeddings": false,
|
| 37 |
+
"torch_dtype": "bfloat16",
|
| 38 |
+
"transformers_version": "4.50.0",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"use_geometry_encoder": true,
|
| 41 |
+
"use_sliding_window": false,
|
| 42 |
+
"video_token_id": 151656,
|
| 43 |
+
"vision_config": {
|
| 44 |
+
"depth": 32,
|
| 45 |
+
"fullatt_block_indexes": [
|
| 46 |
+
7,
|
| 47 |
+
15,
|
| 48 |
+
23,
|
| 49 |
+
31
|
| 50 |
+
],
|
| 51 |
+
"hidden_act": "silu",
|
| 52 |
+
"hidden_size": 1280,
|
| 53 |
+
"in_channels": 3,
|
| 54 |
+
"in_chans": 3,
|
| 55 |
+
"intermediate_size": 3420,
|
| 56 |
+
"model_type": "qwen2_5_vl",
|
| 57 |
+
"num_heads": 16,
|
| 58 |
+
"out_hidden_size": 3584,
|
| 59 |
+
"patch_size": 14,
|
| 60 |
+
"spatial_merge_size": 2,
|
| 61 |
+
"spatial_patch_size": 14,
|
| 62 |
+
"temporal_patch_size": 2,
|
| 63 |
+
"tokens_per_second": 2,
|
| 64 |
+
"torch_dtype": "bfloat16",
|
| 65 |
+
"window_size": 112
|
| 66 |
+
},
|
| 67 |
+
"vision_end_token_id": 151653,
|
| 68 |
+
"vision_mask_apply_prob": 0.5,
|
| 69 |
+
"vision_mask_keep_prob": 0.19999999999999996,
|
| 70 |
+
"vision_mask_prob": 0.8,
|
| 71 |
+
"vision_start_token_id": 151652,
|
| 72 |
+
"vision_token_id": 151654,
|
| 73 |
+
"vocab_size": 152064
|
| 74 |
+
}
|
GeoSR3D-Model/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 1e-06,
|
| 11 |
+
"transformers_version": "4.50.0"
|
| 12 |
+
}
|
GeoSR3D-Model/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
GeoSR3D-Model/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c941ffb9e92de16be1651bac54e952dbf898eaf92fce58839c17f217b423cc84
|
| 3 |
+
size 4934281216
|
GeoSR3D-Model/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44db390f4354340e6e21859996867e6eda8e34b2a1bf6ef40302f44764bfffbb
|
| 3 |
+
size 4932750944
|
GeoSR3D-Model/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54817dd2e6dce0f0621497c7301b17e0865cd72cda44e72f7b567c7cd66d6a88
|
| 3 |
+
size 4991495888
|
GeoSR3D-Model/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0006683a861c0adc2cf6101de2002a73a8e4b294646bc0220adf2b79a0131686
|
| 3 |
+
size 3692182944
|
GeoSR3D-Model/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
GeoSR3D-Model/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 451584,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 12544,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 451584,
|
| 26 |
+
"shortest_edge": 12544
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
GeoSR3D-Model/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
GeoSR3D-Model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 12800,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"padding_side": "right",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
GeoSR3D-Model/trainer_state.json
ADDED
|
@@ -0,0 +1,694 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9998523628652342,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4656,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.010737246164789885,
|
| 14 |
+
"grad_norm": 122.58504486083984,
|
| 15 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 16 |
+
"loss": 25.5971,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02147449232957977,
|
| 21 |
+
"grad_norm": 92.14105224609375,
|
| 22 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 23 |
+
"loss": 15.8095,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03221173849436966,
|
| 28 |
+
"grad_norm": 88.2498779296875,
|
| 29 |
+
"learning_rate": 9.999879015387978e-06,
|
| 30 |
+
"loss": 14.4751,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04294898465915954,
|
| 35 |
+
"grad_norm": 79.90851593017578,
|
| 36 |
+
"learning_rate": 9.995645168701038e-06,
|
| 37 |
+
"loss": 10.6395,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05368623082394943,
|
| 42 |
+
"grad_norm": 98.06950378417969,
|
| 43 |
+
"learning_rate": 9.98536794504998e-06,
|
| 44 |
+
"loss": 11.1393,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06442347698873932,
|
| 49 |
+
"grad_norm": 95.09337615966797,
|
| 50 |
+
"learning_rate": 9.969059777090564e-06,
|
| 51 |
+
"loss": 11.2403,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0751607231535292,
|
| 56 |
+
"grad_norm": 94.5640869140625,
|
| 57 |
+
"learning_rate": 9.946740393286928e-06,
|
| 58 |
+
"loss": 10.161,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08589796931831908,
|
| 63 |
+
"grad_norm": 45.75733947753906,
|
| 64 |
+
"learning_rate": 9.918436794045507e-06,
|
| 65 |
+
"loss": 9.6319,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09663521548310897,
|
| 70 |
+
"grad_norm": 44.17033767700195,
|
| 71 |
+
"learning_rate": 9.884183219051837e-06,
|
| 72 |
+
"loss": 10.4065,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.10737246164789886,
|
| 77 |
+
"grad_norm": 41.16874694824219,
|
| 78 |
+
"learning_rate": 9.844021105849837e-06,
|
| 79 |
+
"loss": 7.8502,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11810970781268874,
|
| 84 |
+
"grad_norm": 84.32959747314453,
|
| 85 |
+
"learning_rate": 9.797999039713586e-06,
|
| 86 |
+
"loss": 9.3041,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12884695397747864,
|
| 91 |
+
"grad_norm": 39.66738510131836,
|
| 92 |
+
"learning_rate": 9.746172694872332e-06,
|
| 93 |
+
"loss": 8.5279,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13958420014226852,
|
| 98 |
+
"grad_norm": 39.50006866455078,
|
| 99 |
+
"learning_rate": 9.688604767159736e-06,
|
| 100 |
+
"loss": 9.5201,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1503214463070584,
|
| 105 |
+
"grad_norm": 38.226261138916016,
|
| 106 |
+
"learning_rate": 9.62536489816892e-06,
|
| 107 |
+
"loss": 9.9717,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.16105869247184829,
|
| 112 |
+
"grad_norm": 35.42646789550781,
|
| 113 |
+
"learning_rate": 9.556529591005001e-06,
|
| 114 |
+
"loss": 9.0548,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.17179593863663817,
|
| 119 |
+
"grad_norm": 44.124263763427734,
|
| 120 |
+
"learning_rate": 9.482182117737066e-06,
|
| 121 |
+
"loss": 8.9763,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.18253318480142805,
|
| 126 |
+
"grad_norm": 43.76786422729492,
|
| 127 |
+
"learning_rate": 9.402412418661541e-06,
|
| 128 |
+
"loss": 9.8142,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.19327043096621793,
|
| 133 |
+
"grad_norm": 34.88469314575195,
|
| 134 |
+
"learning_rate": 9.317316993498788e-06,
|
| 135 |
+
"loss": 8.6092,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.20400767713100781,
|
| 140 |
+
"grad_norm": 38.54001998901367,
|
| 141 |
+
"learning_rate": 9.226998784654606e-06,
|
| 142 |
+
"loss": 7.4996,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.21474492329579772,
|
| 147 |
+
"grad_norm": 74.26197814941406,
|
| 148 |
+
"learning_rate": 9.131567052687811e-06,
|
| 149 |
+
"loss": 9.0709,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2254821694605876,
|
| 154 |
+
"grad_norm": 41.04670333862305,
|
| 155 |
+
"learning_rate": 9.03113724413456e-06,
|
| 156 |
+
"loss": 10.0284,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2362194156253775,
|
| 161 |
+
"grad_norm": 42.67012405395508,
|
| 162 |
+
"learning_rate": 8.925830851849338e-06,
|
| 163 |
+
"loss": 7.9923,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.24695666179016737,
|
| 168 |
+
"grad_norm": 49.978736877441406,
|
| 169 |
+
"learning_rate": 8.815775268031514e-06,
|
| 170 |
+
"loss": 8.8409,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2576939079549573,
|
| 175 |
+
"grad_norm": 80.3055419921875,
|
| 176 |
+
"learning_rate": 8.701103630115303e-06,
|
| 177 |
+
"loss": 8.9708,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.26843115411974716,
|
| 182 |
+
"grad_norm": 31.320579528808594,
|
| 183 |
+
"learning_rate": 8.581954659709549e-06,
|
| 184 |
+
"loss": 9.6101,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.27916840028453704,
|
| 189 |
+
"grad_norm": 35.097434997558594,
|
| 190 |
+
"learning_rate": 8.458472494782169e-06,
|
| 191 |
+
"loss": 9.1278,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2899056464493269,
|
| 196 |
+
"grad_norm": 79.29938507080078,
|
| 197 |
+
"learning_rate": 8.330806515292271e-06,
|
| 198 |
+
"loss": 8.365,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3006428926141168,
|
| 203 |
+
"grad_norm": 35.84828186035156,
|
| 204 |
+
"learning_rate": 8.199111162480871e-06,
|
| 205 |
+
"loss": 9.4828,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3113801387789067,
|
| 210 |
+
"grad_norm": 28.13869857788086,
|
| 211 |
+
"learning_rate": 8.063545752038854e-06,
|
| 212 |
+
"loss": 7.6841,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.32211738494369657,
|
| 217 |
+
"grad_norm": 48.257423400878906,
|
| 218 |
+
"learning_rate": 7.924274281378153e-06,
|
| 219 |
+
"loss": 7.3778,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.33285463110848645,
|
| 224 |
+
"grad_norm": 39.27827835083008,
|
| 225 |
+
"learning_rate": 7.781465231239318e-06,
|
| 226 |
+
"loss": 10.1326,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.34359187727327634,
|
| 231 |
+
"grad_norm": 29.741004943847656,
|
| 232 |
+
"learning_rate": 7.635291361875474e-06,
|
| 233 |
+
"loss": 8.61,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3543291234380662,
|
| 238 |
+
"grad_norm": 39.182769775390625,
|
| 239 |
+
"learning_rate": 7.485929504059234e-06,
|
| 240 |
+
"loss": 8.702,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3650663696028561,
|
| 245 |
+
"grad_norm": 32.254554748535156,
|
| 246 |
+
"learning_rate": 7.333560345165371e-06,
|
| 247 |
+
"loss": 7.5357,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.375803615767646,
|
| 252 |
+
"grad_norm": 28.51645851135254,
|
| 253 |
+
"learning_rate": 7.178368210588067e-06,
|
| 254 |
+
"loss": 7.2457,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.38654086193243586,
|
| 259 |
+
"grad_norm": 28.341947555541992,
|
| 260 |
+
"learning_rate": 7.020540840757124e-06,
|
| 261 |
+
"loss": 9.2959,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.39727810809722575,
|
| 266 |
+
"grad_norm": 42.67914581298828,
|
| 267 |
+
"learning_rate": 6.860269164022921e-06,
|
| 268 |
+
"loss": 9.1062,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.40801535426201563,
|
| 273 |
+
"grad_norm": 31.293323516845703,
|
| 274 |
+
"learning_rate": 6.697747065684851e-06,
|
| 275 |
+
"loss": 9.5109,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4187526004268055,
|
| 280 |
+
"grad_norm": 35.099021911621094,
|
| 281 |
+
"learning_rate": 6.5331711534426326e-06,
|
| 282 |
+
"loss": 8.1034,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.42948984659159545,
|
| 287 |
+
"grad_norm": 35.72314453125,
|
| 288 |
+
"learning_rate": 6.366740519554286e-06,
|
| 289 |
+
"loss": 7.9167,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.44022709275638533,
|
| 294 |
+
"grad_norm": 73.83097076416016,
|
| 295 |
+
"learning_rate": 6.198656499988444e-06,
|
| 296 |
+
"loss": 8.5164,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4509643389211752,
|
| 301 |
+
"grad_norm": 30.618099212646484,
|
| 302 |
+
"learning_rate": 6.029122430862373e-06,
|
| 303 |
+
"loss": 9.6928,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4617015850859651,
|
| 308 |
+
"grad_norm": 74.77922058105469,
|
| 309 |
+
"learning_rate": 5.858343402460391e-06,
|
| 310 |
+
"loss": 8.1368,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.472438831250755,
|
| 315 |
+
"grad_norm": 26.513835906982422,
|
| 316 |
+
"learning_rate": 5.68652601113019e-06,
|
| 317 |
+
"loss": 7.5154,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.48317607741554486,
|
| 322 |
+
"grad_norm": 70.47901916503906,
|
| 323 |
+
"learning_rate": 5.513878109357228e-06,
|
| 324 |
+
"loss": 8.6317,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.49391332358033474,
|
| 329 |
+
"grad_norm": 33.31165313720703,
|
| 330 |
+
"learning_rate": 5.3406085543195555e-06,
|
| 331 |
+
"loss": 9.8199,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5046505697451246,
|
| 336 |
+
"grad_norm": 36.43808364868164,
|
| 337 |
+
"learning_rate": 5.166926955227224e-06,
|
| 338 |
+
"loss": 9.8981,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5153878159099146,
|
| 343 |
+
"grad_norm": 35.49153137207031,
|
| 344 |
+
"learning_rate": 4.993043419751933e-06,
|
| 345 |
+
"loss": 7.7103,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5261250620747044,
|
| 350 |
+
"grad_norm": 27.446149826049805,
|
| 351 |
+
"learning_rate": 4.8191682998536905e-06,
|
| 352 |
+
"loss": 7.0446,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5368623082394943,
|
| 357 |
+
"grad_norm": 35.19398498535156,
|
| 358 |
+
"learning_rate": 4.645511937311934e-06,
|
| 359 |
+
"loss": 8.806,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5475995544042842,
|
| 364 |
+
"grad_norm": 77.66211700439453,
|
| 365 |
+
"learning_rate": 4.472284409268976e-06,
|
| 366 |
+
"loss": 10.2757,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5583368005690741,
|
| 371 |
+
"grad_norm": 29.25933837890625,
|
| 372 |
+
"learning_rate": 4.299695274093593e-06,
|
| 373 |
+
"loss": 9.8498,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.569074046733864,
|
| 378 |
+
"grad_norm": 32.54759979248047,
|
| 379 |
+
"learning_rate": 4.1279533178721755e-06,
|
| 380 |
+
"loss": 9.312,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5798112928986539,
|
| 385 |
+
"grad_norm": 77.79645538330078,
|
| 386 |
+
"learning_rate": 3.957266301834145e-06,
|
| 387 |
+
"loss": 8.5012,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5905485390634437,
|
| 392 |
+
"grad_norm": 30.680482864379883,
|
| 393 |
+
"learning_rate": 3.7878407110171646e-06,
|
| 394 |
+
"loss": 8.1592,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6012857852282336,
|
| 399 |
+
"grad_norm": 30.990217208862305,
|
| 400 |
+
"learning_rate": 3.6198815044761847e-06,
|
| 401 |
+
"loss": 9.4135,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6120230313930235,
|
| 406 |
+
"grad_norm": 34.311153411865234,
|
| 407 |
+
"learning_rate": 3.4535918673385456e-06,
|
| 408 |
+
"loss": 8.7601,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6227602775578134,
|
| 413 |
+
"grad_norm": 34.08210754394531,
|
| 414 |
+
"learning_rate": 3.2891729650050096e-06,
|
| 415 |
+
"loss": 8.4742,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6334975237226033,
|
| 420 |
+
"grad_norm": 30.370546340942383,
|
| 421 |
+
"learning_rate": 3.1268236997941535e-06,
|
| 422 |
+
"loss": 7.6472,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6442347698873931,
|
| 427 |
+
"grad_norm": 76.85076141357422,
|
| 428 |
+
"learning_rate": 2.966740470324451e-06,
|
| 429 |
+
"loss": 10.3334,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.654972016052183,
|
| 434 |
+
"grad_norm": 33.31392288208008,
|
| 435 |
+
"learning_rate": 2.8091169339251644e-06,
|
| 436 |
+
"loss": 8.1425,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6657092622169729,
|
| 441 |
+
"grad_norm": 28.994285583496094,
|
| 442 |
+
"learning_rate": 2.654143772363455e-06,
|
| 443 |
+
"loss": 8.2618,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6764465083817628,
|
| 448 |
+
"grad_norm": 33.96207809448242,
|
| 449 |
+
"learning_rate": 2.502008461171114e-06,
|
| 450 |
+
"loss": 7.9787,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6871837545465527,
|
| 455 |
+
"grad_norm": 44.06400680541992,
|
| 456 |
+
"learning_rate": 2.352895042849965e-06,
|
| 457 |
+
"loss": 8.0353,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6979210007113426,
|
| 462 |
+
"grad_norm": 35.88554000854492,
|
| 463 |
+
"learning_rate": 2.20698390423032e-06,
|
| 464 |
+
"loss": 9.3106,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7086582468761324,
|
| 469 |
+
"grad_norm": 31.703388214111328,
|
| 470 |
+
"learning_rate": 2.0644515582517803e-06,
|
| 471 |
+
"loss": 8.5185,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.7193954930409223,
|
| 476 |
+
"grad_norm": 34.17527770996094,
|
| 477 |
+
"learning_rate": 1.9254704304304174e-06,
|
| 478 |
+
"loss": 9.1151,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.7301327392057122,
|
| 483 |
+
"grad_norm": 29.952329635620117,
|
| 484 |
+
"learning_rate": 1.7902086502706256e-06,
|
| 485 |
+
"loss": 7.4807,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.7408699853705021,
|
| 490 |
+
"grad_norm": 29.618684768676758,
|
| 491 |
+
"learning_rate": 1.658829847873965e-06,
|
| 492 |
+
"loss": 8.402,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.751607231535292,
|
| 497 |
+
"grad_norm": 35.65748596191406,
|
| 498 |
+
"learning_rate": 1.5314929559910985e-06,
|
| 499 |
+
"loss": 8.7392,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7623444777000818,
|
| 504 |
+
"grad_norm": 40.38413619995117,
|
| 505 |
+
"learning_rate": 1.4083520177562154e-06,
|
| 506 |
+
"loss": 6.4324,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7730817238648717,
|
| 511 |
+
"grad_norm": 38.58983612060547,
|
| 512 |
+
"learning_rate": 1.2895560003365837e-06,
|
| 513 |
+
"loss": 9.4396,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7838189700296616,
|
| 518 |
+
"grad_norm": 33.327510833740234,
|
| 519 |
+
"learning_rate": 1.1752486147226505e-06,
|
| 520 |
+
"loss": 7.8763,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7945562161944515,
|
| 525 |
+
"grad_norm": 31.827482223510742,
|
| 526 |
+
"learning_rate": 1.0655681418766772e-06,
|
| 527 |
+
"loss": 8.1159,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8052934623592414,
|
| 532 |
+
"grad_norm": 37.83740997314453,
|
| 533 |
+
"learning_rate": 9.60647265450249e-07,
|
| 534 |
+
"loss": 7.1248,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8160307085240313,
|
| 539 |
+
"grad_norm": 68.32665252685547,
|
| 540 |
+
"learning_rate": 8.60612911273011e-07,
|
| 541 |
+
"loss": 8.8583,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.8267679546888211,
|
| 546 |
+
"grad_norm": 28.628252029418945,
|
| 547 |
+
"learning_rate": 7.655860938068071e-07,
|
| 548 |
+
"loss": 6.5486,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.837505200853611,
|
| 553 |
+
"grad_norm": 35.551815032958984,
|
| 554 |
+
"learning_rate": 6.756817697509755e-07,
|
| 555 |
+
"loss": 8.1337,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8482424470184009,
|
| 560 |
+
"grad_norm": 29.21653175354004,
|
| 561 |
+
"learning_rate": 5.910086989758862e-07,
|
| 562 |
+
"loss": 7.0004,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8589796931831909,
|
| 567 |
+
"grad_norm": 28.43161392211914,
|
| 568 |
+
"learning_rate": 5.11669312952977e-07,
|
| 569 |
+
"loss": 8.2137,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8697169393479808,
|
| 574 |
+
"grad_norm": 27.239362716674805,
|
| 575 |
+
"learning_rate": 4.377595908404225e-07,
|
| 576 |
+
"loss": 7.9611,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.8804541855127707,
|
| 581 |
+
"grad_norm": 27.20981788635254,
|
| 582 |
+
"learning_rate": 3.693689433743658e-07,
|
| 583 |
+
"loss": 8.2071,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8911914316775605,
|
| 588 |
+
"grad_norm": 30.86234474182129,
|
| 589 |
+
"learning_rate": 3.065801047061517e-07,
|
| 590 |
+
"loss": 6.6662,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9019286778423504,
|
| 595 |
+
"grad_norm": 72.03483581542969,
|
| 596 |
+
"learning_rate": 2.4946903231642727e-07,
|
| 597 |
+
"loss": 9.2256,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.9126659240071403,
|
| 602 |
+
"grad_norm": 35.229248046875,
|
| 603 |
+
"learning_rate": 1.9810481512716638e-07,
|
| 604 |
+
"loss": 7.8211,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9234031701719302,
|
| 609 |
+
"grad_norm": 29.196678161621094,
|
| 610 |
+
"learning_rate": 1.5254958992280022e-07,
|
| 611 |
+
"loss": 7.9577,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.9341404163367201,
|
| 616 |
+
"grad_norm": 31.289777755737305,
|
| 617 |
+
"learning_rate": 1.128584661815435e-07,
|
| 618 |
+
"loss": 7.572,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.94487766250151,
|
| 623 |
+
"grad_norm": 29.68185043334961,
|
| 624 |
+
"learning_rate": 7.907945940786033e-08,
|
| 625 |
+
"loss": 7.5517,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.9556149086662998,
|
| 630 |
+
"grad_norm": 28.52676773071289,
|
| 631 |
+
"learning_rate": 5.125343304671459e-08,
|
| 632 |
+
"loss": 10.374,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9663521548310897,
|
| 637 |
+
"grad_norm": 34.890655517578125,
|
| 638 |
+
"learning_rate": 2.9414049049872883e-08,
|
| 639 |
+
"loss": 7.1905,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.9770894009958796,
|
| 644 |
+
"grad_norm": 40.517208099365234,
|
| 645 |
+
"learning_rate": 1.35877271540652e-08,
|
| 646 |
+
"loss": 8.6259,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9878266471606695,
|
| 651 |
+
"grad_norm": 29.639062881469727,
|
| 652 |
+
"learning_rate": 3.7936129202648106e-09,
|
| 653 |
+
"loss": 6.9152,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9985638933254594,
|
| 658 |
+
"grad_norm": 43.505428314208984,
|
| 659 |
+
"learning_rate": 4.3554572743409463e-11,
|
| 660 |
+
"loss": 10.0409,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9998523628652342,
|
| 665 |
+
"step": 4656,
|
| 666 |
+
"total_flos": 3.2168639765195784e+19,
|
| 667 |
+
"train_loss": 8.979798909315129,
|
| 668 |
+
"train_runtime": 72260.7648,
|
| 669 |
+
"train_samples_per_second": 4.124,
|
| 670 |
+
"train_steps_per_second": 0.064
|
| 671 |
+
}
|
| 672 |
+
],
|
| 673 |
+
"logging_steps": 50,
|
| 674 |
+
"max_steps": 4656,
|
| 675 |
+
"num_input_tokens_seen": 0,
|
| 676 |
+
"num_train_epochs": 1,
|
| 677 |
+
"save_steps": 1000,
|
| 678 |
+
"stateful_callbacks": {
|
| 679 |
+
"TrainerControl": {
|
| 680 |
+
"args": {
|
| 681 |
+
"should_epoch_stop": false,
|
| 682 |
+
"should_evaluate": false,
|
| 683 |
+
"should_log": false,
|
| 684 |
+
"should_save": true,
|
| 685 |
+
"should_training_stop": true
|
| 686 |
+
},
|
| 687 |
+
"attributes": {}
|
| 688 |
+
}
|
| 689 |
+
},
|
| 690 |
+
"total_flos": 3.2168639765195784e+19,
|
| 691 |
+
"train_batch_size": 1,
|
| 692 |
+
"trial_name": null,
|
| 693 |
+
"trial_params": null
|
| 694 |
+
}
|
GeoSR3D-Model/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
GeoSR4D-Model/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
GeoSR4D-Model/config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration_Spatial"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 3584,
|
| 10 |
+
"image_token_id": 151655,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
+
"max_position_embeddings": 128000,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2_5_vl",
|
| 16 |
+
"num_attention_heads": 28,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.51.0",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"video_token_id": 151656,
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"config_all": {
|
| 39 |
+
"model_type": "qwen2_5_vl"
|
| 40 |
+
},
|
| 41 |
+
"depth": 32,
|
| 42 |
+
"fullatt_block_indexes": [
|
| 43 |
+
7,
|
| 44 |
+
15,
|
| 45 |
+
23,
|
| 46 |
+
31
|
| 47 |
+
],
|
| 48 |
+
"hidden_act": "silu",
|
| 49 |
+
"hidden_size": 1280,
|
| 50 |
+
"in_channels": 3,
|
| 51 |
+
"in_chans": 3,
|
| 52 |
+
"intermediate_size": 3420,
|
| 53 |
+
"model_type": "qwen2_5_vl",
|
| 54 |
+
"num_heads": 16,
|
| 55 |
+
"out_hidden_size": 3584,
|
| 56 |
+
"patch_size": 14,
|
| 57 |
+
"spatial_merge_size": 2,
|
| 58 |
+
"spatial_patch_size": 14,
|
| 59 |
+
"temporal_patch_size": 2,
|
| 60 |
+
"tokens_per_second": 2,
|
| 61 |
+
"torch_dtype": "bfloat16",
|
| 62 |
+
"window_size": 112
|
| 63 |
+
},
|
| 64 |
+
"vision_end_token_id": 151653,
|
| 65 |
+
"vision_mask_apply_prob": 0.5,
|
| 66 |
+
"vision_mask_keep_prob": 0.19999999999999996,
|
| 67 |
+
"vision_mask_prob": 0.8,
|
| 68 |
+
"vision_start_token_id": 151652,
|
| 69 |
+
"vision_token_id": 151654,
|
| 70 |
+
"vocab_size": 152064
|
| 71 |
+
}
|
GeoSR4D-Model/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attn_implementation": "flash_attention_2",
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"repetition_penalty": 1.05,
|
| 11 |
+
"temperature": 1e-06,
|
| 12 |
+
"transformers_version": "4.51.0"
|
| 13 |
+
}
|
GeoSR4D-Model/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
GeoSR4D-Model/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fc86d147c58b0ef98ba6c9db55273db5cbd6930b6055f3beb22521b92814635
|
| 3 |
+
size 4992396592
|
GeoSR4D-Model/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeb4f2f57b49e41b84d4ab6351b40456c45497ac34ae67d7c685abbd3e90a424
|
| 3 |
+
size 4991495784
|
GeoSR4D-Model/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4414d604a2a37ec066d75359aab03f2eb8e4364b6fec24143b37116bbdf0a283
|
| 3 |
+
size 4932751040
|
GeoSR4D-Model/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49a5c162765b85895b7d7d5f769ae1df80c28cb5c44a0f034d6da3ec76bb78d4
|
| 3 |
+
size 3556392240
|
GeoSR4D-Model/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 18472907776
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 345 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 346 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 348 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 350 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 352 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 354 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 358 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 360 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 362 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 364 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 366 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 370 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 372 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 374 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 376 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 378 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 382 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 384 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 386 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 388 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 390 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 394 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 396 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 398 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 400 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 402 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 406 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 407 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 408 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 409 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 410 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 411 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 412 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 413 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 414 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 415 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 418 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 419 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 420 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 421 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 422 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 423 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 424 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 425 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 426 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 427 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 429 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 430 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 431 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 432 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 433 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 434 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 435 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 436 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 437 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 438 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 439 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 441 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 442 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 443 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 444 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 445 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 446 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 447 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 448 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 449 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 450 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 451 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 453 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 454 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 455 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 456 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 457 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 458 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 459 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 460 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 461 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 462 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 463 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 465 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 466 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 467 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 468 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 469 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 470 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 471 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 472 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 473 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 474 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 475 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 477 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 478 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 479 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 480 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 481 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 482 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 483 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 484 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 485 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 486 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 487 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 489 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 490 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 491 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 492 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 493 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 494 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 495 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 496 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 497 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 498 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 499 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 501 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 502 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 503 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 504 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 505 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 506 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 507 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 508 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 509 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 510 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 511 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 514 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 515 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 516 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 517 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 518 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 519 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 520 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 521 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 522 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 523 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 525 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 526 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 527 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 528 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 529 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 530 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 531 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 532 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 533 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 534 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 535 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 537 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 538 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 539 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 540 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 541 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 542 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 543 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 544 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 545 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 546 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 547 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 549 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 550 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 551 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 552 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 553 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 554 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 555 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 556 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 557 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 558 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 559 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 561 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 562 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 563 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 564 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 565 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 566 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 567 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 568 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 569 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 570 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 571 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 573 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 574 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 575 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 576 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 577 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 578 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 579 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 580 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 581 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 582 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 583 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 586 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 587 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 588 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 589 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 590 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 591 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 592 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 593 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 594 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 598 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 599 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 600 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 601 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 602 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 603 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 604 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 605 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 606 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 610 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 611 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 612 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 613 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 614 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 615 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 616 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 617 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 618 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 622 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 623 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 624 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 625 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 626 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 627 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 628 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 629 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 630 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 631 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 634 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 635 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 636 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 637 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 638 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 639 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 640 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 641 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 642 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
| 645 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 646 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 647 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 648 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 649 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 650 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 651 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 652 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 653 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 654 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 658 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 659 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 660 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 661 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 662 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 663 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 664 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 665 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 666 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 670 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 671 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 672 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 673 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 674 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 675 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 676 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 677 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 678 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 679 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 681 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 682 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 683 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 684 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 685 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 686 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 687 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 688 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 689 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 690 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 691 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 693 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 694 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 695 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 696 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 697 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 698 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 699 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 700 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 701 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 702 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 703 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 705 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 706 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 707 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 708 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 709 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 710 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 711 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 712 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 713 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 714 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 715 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 717 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 718 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 719 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 720 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 721 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 722 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 723 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 724 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 725 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 726 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 727 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 729 |
+
"visual.gated_fusion_norm_geometry.bias": "model-00001-of-00004.safetensors",
|
| 730 |
+
"visual.gated_fusion_norm_geometry.weight": "model-00001-of-00004.safetensors",
|
| 731 |
+
"visual.gated_fusion_norm_visual.bias": "model-00001-of-00004.safetensors",
|
| 732 |
+
"visual.gated_fusion_norm_visual.weight": "model-00001-of-00004.safetensors",
|
| 733 |
+
"visual.gated_fusion_proj.0.bias": "model-00001-of-00004.safetensors",
|
| 734 |
+
"visual.gated_fusion_proj.0.weight": "model-00001-of-00004.safetensors",
|
| 735 |
+
"visual.geometry_kv_attn.in_proj_bias": "model-00001-of-00004.safetensors",
|
| 736 |
+
"visual.geometry_kv_attn.in_proj_weight": "model-00001-of-00004.safetensors",
|
| 737 |
+
"visual.geometry_kv_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
| 738 |
+
"visual.geometry_kv_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 739 |
+
"visual.geometry_kv_norm.weight": "model-00001-of-00004.safetensors",
|
| 740 |
+
"visual.geometry_q_norm.weight": "model-00001-of-00004.safetensors",
|
| 741 |
+
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
| 743 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
| 745 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 747 |
+
"visual.q_former_1.attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 748 |
+
"visual.q_former_1.attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 749 |
+
"visual.q_former_1.attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 750 |
+
"visual.q_former_1.attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 751 |
+
"visual.q_former_1.attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 752 |
+
"visual.q_former_1.attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 753 |
+
"visual.q_former_1.attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"visual.q_former_1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"visual.q_former_1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 756 |
+
"visual.q_former_1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 757 |
+
"visual.q_former_1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 758 |
+
"visual.q_former_1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 759 |
+
"visual.q_former_1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 760 |
+
"visual.q_former_1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 761 |
+
"visual.q_former_1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 762 |
+
"visual.q_former_2.attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 763 |
+
"visual.q_former_2.attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 764 |
+
"visual.q_former_2.attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 765 |
+
"visual.q_former_2.attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 766 |
+
"visual.q_former_2.attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 767 |
+
"visual.q_former_2.attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 768 |
+
"visual.q_former_2.attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 769 |
+
"visual.q_former_2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 770 |
+
"visual.q_former_2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 771 |
+
"visual.q_former_2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 772 |
+
"visual.q_former_2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 773 |
+
"visual.q_former_2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 774 |
+
"visual.q_former_2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 775 |
+
"visual.q_former_2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 776 |
+
"visual.q_former_2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 777 |
+
"visual.q_former_norm.weight": "model-00001-of-00004.safetensors",
|
| 778 |
+
"visual.q_former_queries": "model-00001-of-00004.safetensors",
|
| 779 |
+
"visual.spatial_encoder.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 780 |
+
"visual.spatial_encoder.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 781 |
+
"visual.spatial_encoder.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 782 |
+
"visual.spatial_encoder.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 783 |
+
"visual.spatial_encoder.blocks.0.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 784 |
+
"visual.spatial_encoder.blocks.0.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 785 |
+
"visual.spatial_encoder.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 786 |
+
"visual.spatial_encoder.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 787 |
+
"visual.spatial_encoder.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 788 |
+
"visual.spatial_encoder.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 789 |
+
"visual.spatial_encoder.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 790 |
+
"visual.spatial_encoder.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 791 |
+
"visual.spatial_encoder.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 792 |
+
"visual.spatial_encoder.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 793 |
+
"visual.spatial_encoder.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 794 |
+
"visual.spatial_encoder.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 795 |
+
"visual.spatial_encoder.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 796 |
+
"visual.spatial_encoder.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 797 |
+
"visual.spatial_encoder.blocks.1.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 798 |
+
"visual.spatial_encoder.blocks.1.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 799 |
+
"visual.spatial_encoder.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 800 |
+
"visual.spatial_encoder.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 801 |
+
"visual.spatial_encoder.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 802 |
+
"visual.spatial_encoder.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 803 |
+
"visual.spatial_encoder.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 804 |
+
"visual.spatial_encoder.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 805 |
+
"visual.spatial_encoder.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 806 |
+
"visual.spatial_encoder.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 807 |
+
"visual.spatial_encoder.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 808 |
+
"visual.spatial_encoder.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 809 |
+
"visual.spatial_encoder.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 810 |
+
"visual.spatial_encoder.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 811 |
+
"visual.spatial_encoder.blocks.10.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 812 |
+
"visual.spatial_encoder.blocks.10.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 813 |
+
"visual.spatial_encoder.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 814 |
+
"visual.spatial_encoder.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 815 |
+
"visual.spatial_encoder.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 816 |
+
"visual.spatial_encoder.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 817 |
+
"visual.spatial_encoder.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 818 |
+
"visual.spatial_encoder.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 819 |
+
"visual.spatial_encoder.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 820 |
+
"visual.spatial_encoder.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 821 |
+
"visual.spatial_encoder.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 822 |
+
"visual.spatial_encoder.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 823 |
+
"visual.spatial_encoder.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 824 |
+
"visual.spatial_encoder.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 825 |
+
"visual.spatial_encoder.blocks.11.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 826 |
+
"visual.spatial_encoder.blocks.11.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 827 |
+
"visual.spatial_encoder.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 828 |
+
"visual.spatial_encoder.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 829 |
+
"visual.spatial_encoder.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 830 |
+
"visual.spatial_encoder.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 831 |
+
"visual.spatial_encoder.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 832 |
+
"visual.spatial_encoder.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 833 |
+
"visual.spatial_encoder.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 834 |
+
"visual.spatial_encoder.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 835 |
+
"visual.spatial_encoder.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 836 |
+
"visual.spatial_encoder.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 837 |
+
"visual.spatial_encoder.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 838 |
+
"visual.spatial_encoder.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 839 |
+
"visual.spatial_encoder.blocks.12.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 840 |
+
"visual.spatial_encoder.blocks.12.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 841 |
+
"visual.spatial_encoder.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 842 |
+
"visual.spatial_encoder.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 843 |
+
"visual.spatial_encoder.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 844 |
+
"visual.spatial_encoder.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 845 |
+
"visual.spatial_encoder.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 846 |
+
"visual.spatial_encoder.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 847 |
+
"visual.spatial_encoder.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 848 |
+
"visual.spatial_encoder.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 849 |
+
"visual.spatial_encoder.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 850 |
+
"visual.spatial_encoder.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 851 |
+
"visual.spatial_encoder.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 852 |
+
"visual.spatial_encoder.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 853 |
+
"visual.spatial_encoder.blocks.13.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 854 |
+
"visual.spatial_encoder.blocks.13.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 855 |
+
"visual.spatial_encoder.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 856 |
+
"visual.spatial_encoder.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 857 |
+
"visual.spatial_encoder.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 858 |
+
"visual.spatial_encoder.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 859 |
+
"visual.spatial_encoder.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 860 |
+
"visual.spatial_encoder.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 861 |
+
"visual.spatial_encoder.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 862 |
+
"visual.spatial_encoder.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 863 |
+
"visual.spatial_encoder.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 864 |
+
"visual.spatial_encoder.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 865 |
+
"visual.spatial_encoder.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 866 |
+
"visual.spatial_encoder.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 867 |
+
"visual.spatial_encoder.blocks.14.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 868 |
+
"visual.spatial_encoder.blocks.14.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 869 |
+
"visual.spatial_encoder.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 870 |
+
"visual.spatial_encoder.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 871 |
+
"visual.spatial_encoder.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 872 |
+
"visual.spatial_encoder.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 873 |
+
"visual.spatial_encoder.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 874 |
+
"visual.spatial_encoder.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 875 |
+
"visual.spatial_encoder.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 876 |
+
"visual.spatial_encoder.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 877 |
+
"visual.spatial_encoder.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 878 |
+
"visual.spatial_encoder.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 879 |
+
"visual.spatial_encoder.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 880 |
+
"visual.spatial_encoder.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 881 |
+
"visual.spatial_encoder.blocks.15.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 882 |
+
"visual.spatial_encoder.blocks.15.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 883 |
+
"visual.spatial_encoder.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 884 |
+
"visual.spatial_encoder.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 885 |
+
"visual.spatial_encoder.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 886 |
+
"visual.spatial_encoder.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 887 |
+
"visual.spatial_encoder.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 888 |
+
"visual.spatial_encoder.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 889 |
+
"visual.spatial_encoder.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 890 |
+
"visual.spatial_encoder.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 891 |
+
"visual.spatial_encoder.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 892 |
+
"visual.spatial_encoder.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 893 |
+
"visual.spatial_encoder.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 894 |
+
"visual.spatial_encoder.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 895 |
+
"visual.spatial_encoder.blocks.16.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 896 |
+
"visual.spatial_encoder.blocks.16.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 897 |
+
"visual.spatial_encoder.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 898 |
+
"visual.spatial_encoder.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 899 |
+
"visual.spatial_encoder.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 900 |
+
"visual.spatial_encoder.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 901 |
+
"visual.spatial_encoder.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 902 |
+
"visual.spatial_encoder.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 903 |
+
"visual.spatial_encoder.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 904 |
+
"visual.spatial_encoder.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 905 |
+
"visual.spatial_encoder.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 906 |
+
"visual.spatial_encoder.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 907 |
+
"visual.spatial_encoder.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 908 |
+
"visual.spatial_encoder.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 909 |
+
"visual.spatial_encoder.blocks.17.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 910 |
+
"visual.spatial_encoder.blocks.17.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 911 |
+
"visual.spatial_encoder.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 912 |
+
"visual.spatial_encoder.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 913 |
+
"visual.spatial_encoder.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 914 |
+
"visual.spatial_encoder.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 915 |
+
"visual.spatial_encoder.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 916 |
+
"visual.spatial_encoder.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 917 |
+
"visual.spatial_encoder.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 918 |
+
"visual.spatial_encoder.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 919 |
+
"visual.spatial_encoder.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 920 |
+
"visual.spatial_encoder.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 921 |
+
"visual.spatial_encoder.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 922 |
+
"visual.spatial_encoder.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 923 |
+
"visual.spatial_encoder.blocks.18.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 924 |
+
"visual.spatial_encoder.blocks.18.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 925 |
+
"visual.spatial_encoder.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 926 |
+
"visual.spatial_encoder.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 927 |
+
"visual.spatial_encoder.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 928 |
+
"visual.spatial_encoder.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 929 |
+
"visual.spatial_encoder.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 930 |
+
"visual.spatial_encoder.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 931 |
+
"visual.spatial_encoder.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 932 |
+
"visual.spatial_encoder.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 933 |
+
"visual.spatial_encoder.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 934 |
+
"visual.spatial_encoder.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 935 |
+
"visual.spatial_encoder.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 936 |
+
"visual.spatial_encoder.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 937 |
+
"visual.spatial_encoder.blocks.19.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 938 |
+
"visual.spatial_encoder.blocks.19.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 939 |
+
"visual.spatial_encoder.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 940 |
+
"visual.spatial_encoder.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 941 |
+
"visual.spatial_encoder.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 942 |
+
"visual.spatial_encoder.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 943 |
+
"visual.spatial_encoder.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 944 |
+
"visual.spatial_encoder.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 945 |
+
"visual.spatial_encoder.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 946 |
+
"visual.spatial_encoder.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 947 |
+
"visual.spatial_encoder.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 948 |
+
"visual.spatial_encoder.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 949 |
+
"visual.spatial_encoder.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 950 |
+
"visual.spatial_encoder.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 951 |
+
"visual.spatial_encoder.blocks.2.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 952 |
+
"visual.spatial_encoder.blocks.2.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 953 |
+
"visual.spatial_encoder.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 954 |
+
"visual.spatial_encoder.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 955 |
+
"visual.spatial_encoder.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 956 |
+
"visual.spatial_encoder.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 957 |
+
"visual.spatial_encoder.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 958 |
+
"visual.spatial_encoder.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 959 |
+
"visual.spatial_encoder.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 960 |
+
"visual.spatial_encoder.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 961 |
+
"visual.spatial_encoder.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 962 |
+
"visual.spatial_encoder.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 963 |
+
"visual.spatial_encoder.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 964 |
+
"visual.spatial_encoder.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 965 |
+
"visual.spatial_encoder.blocks.20.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 966 |
+
"visual.spatial_encoder.blocks.20.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 967 |
+
"visual.spatial_encoder.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 968 |
+
"visual.spatial_encoder.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 969 |
+
"visual.spatial_encoder.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 970 |
+
"visual.spatial_encoder.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 971 |
+
"visual.spatial_encoder.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 972 |
+
"visual.spatial_encoder.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 973 |
+
"visual.spatial_encoder.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 974 |
+
"visual.spatial_encoder.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 975 |
+
"visual.spatial_encoder.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 976 |
+
"visual.spatial_encoder.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 977 |
+
"visual.spatial_encoder.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 978 |
+
"visual.spatial_encoder.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 979 |
+
"visual.spatial_encoder.blocks.21.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 980 |
+
"visual.spatial_encoder.blocks.21.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 981 |
+
"visual.spatial_encoder.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 982 |
+
"visual.spatial_encoder.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 983 |
+
"visual.spatial_encoder.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 984 |
+
"visual.spatial_encoder.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 985 |
+
"visual.spatial_encoder.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 986 |
+
"visual.spatial_encoder.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 987 |
+
"visual.spatial_encoder.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 988 |
+
"visual.spatial_encoder.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 989 |
+
"visual.spatial_encoder.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 990 |
+
"visual.spatial_encoder.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 991 |
+
"visual.spatial_encoder.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 992 |
+
"visual.spatial_encoder.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 993 |
+
"visual.spatial_encoder.blocks.22.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 994 |
+
"visual.spatial_encoder.blocks.22.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 995 |
+
"visual.spatial_encoder.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 996 |
+
"visual.spatial_encoder.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 997 |
+
"visual.spatial_encoder.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 998 |
+
"visual.spatial_encoder.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 999 |
+
"visual.spatial_encoder.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1000 |
+
"visual.spatial_encoder.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1001 |
+
"visual.spatial_encoder.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1002 |
+
"visual.spatial_encoder.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1003 |
+
"visual.spatial_encoder.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1004 |
+
"visual.spatial_encoder.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1005 |
+
"visual.spatial_encoder.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1006 |
+
"visual.spatial_encoder.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1007 |
+
"visual.spatial_encoder.blocks.23.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1008 |
+
"visual.spatial_encoder.blocks.23.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1009 |
+
"visual.spatial_encoder.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1010 |
+
"visual.spatial_encoder.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1011 |
+
"visual.spatial_encoder.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1012 |
+
"visual.spatial_encoder.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1013 |
+
"visual.spatial_encoder.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1014 |
+
"visual.spatial_encoder.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1015 |
+
"visual.spatial_encoder.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1016 |
+
"visual.spatial_encoder.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1017 |
+
"visual.spatial_encoder.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1018 |
+
"visual.spatial_encoder.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1019 |
+
"visual.spatial_encoder.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1020 |
+
"visual.spatial_encoder.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1021 |
+
"visual.spatial_encoder.blocks.3.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1022 |
+
"visual.spatial_encoder.blocks.3.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1023 |
+
"visual.spatial_encoder.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1024 |
+
"visual.spatial_encoder.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1025 |
+
"visual.spatial_encoder.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1026 |
+
"visual.spatial_encoder.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1027 |
+
"visual.spatial_encoder.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1028 |
+
"visual.spatial_encoder.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1029 |
+
"visual.spatial_encoder.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1030 |
+
"visual.spatial_encoder.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1031 |
+
"visual.spatial_encoder.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1032 |
+
"visual.spatial_encoder.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1033 |
+
"visual.spatial_encoder.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1034 |
+
"visual.spatial_encoder.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1035 |
+
"visual.spatial_encoder.blocks.4.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1036 |
+
"visual.spatial_encoder.blocks.4.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1037 |
+
"visual.spatial_encoder.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1038 |
+
"visual.spatial_encoder.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1039 |
+
"visual.spatial_encoder.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1040 |
+
"visual.spatial_encoder.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1041 |
+
"visual.spatial_encoder.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1042 |
+
"visual.spatial_encoder.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1043 |
+
"visual.spatial_encoder.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1044 |
+
"visual.spatial_encoder.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1045 |
+
"visual.spatial_encoder.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1046 |
+
"visual.spatial_encoder.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1047 |
+
"visual.spatial_encoder.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1048 |
+
"visual.spatial_encoder.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1049 |
+
"visual.spatial_encoder.blocks.5.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1050 |
+
"visual.spatial_encoder.blocks.5.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1051 |
+
"visual.spatial_encoder.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1052 |
+
"visual.spatial_encoder.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1053 |
+
"visual.spatial_encoder.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1054 |
+
"visual.spatial_encoder.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1055 |
+
"visual.spatial_encoder.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1056 |
+
"visual.spatial_encoder.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1057 |
+
"visual.spatial_encoder.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1058 |
+
"visual.spatial_encoder.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1059 |
+
"visual.spatial_encoder.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1060 |
+
"visual.spatial_encoder.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1061 |
+
"visual.spatial_encoder.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1062 |
+
"visual.spatial_encoder.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1063 |
+
"visual.spatial_encoder.blocks.6.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1064 |
+
"visual.spatial_encoder.blocks.6.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1065 |
+
"visual.spatial_encoder.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1066 |
+
"visual.spatial_encoder.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1067 |
+
"visual.spatial_encoder.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1068 |
+
"visual.spatial_encoder.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1069 |
+
"visual.spatial_encoder.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1070 |
+
"visual.spatial_encoder.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1071 |
+
"visual.spatial_encoder.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1072 |
+
"visual.spatial_encoder.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1073 |
+
"visual.spatial_encoder.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1074 |
+
"visual.spatial_encoder.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1075 |
+
"visual.spatial_encoder.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1076 |
+
"visual.spatial_encoder.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1077 |
+
"visual.spatial_encoder.blocks.7.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1078 |
+
"visual.spatial_encoder.blocks.7.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1079 |
+
"visual.spatial_encoder.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1080 |
+
"visual.spatial_encoder.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1081 |
+
"visual.spatial_encoder.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1082 |
+
"visual.spatial_encoder.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1083 |
+
"visual.spatial_encoder.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1084 |
+
"visual.spatial_encoder.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1085 |
+
"visual.spatial_encoder.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1086 |
+
"visual.spatial_encoder.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1087 |
+
"visual.spatial_encoder.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1088 |
+
"visual.spatial_encoder.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1089 |
+
"visual.spatial_encoder.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1090 |
+
"visual.spatial_encoder.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1091 |
+
"visual.spatial_encoder.blocks.8.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1092 |
+
"visual.spatial_encoder.blocks.8.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1093 |
+
"visual.spatial_encoder.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1094 |
+
"visual.spatial_encoder.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1095 |
+
"visual.spatial_encoder.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1096 |
+
"visual.spatial_encoder.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1097 |
+
"visual.spatial_encoder.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1098 |
+
"visual.spatial_encoder.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1099 |
+
"visual.spatial_encoder.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1100 |
+
"visual.spatial_encoder.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1101 |
+
"visual.spatial_encoder.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1102 |
+
"visual.spatial_encoder.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1103 |
+
"visual.spatial_encoder.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1104 |
+
"visual.spatial_encoder.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1105 |
+
"visual.spatial_encoder.blocks.9.ls1.gamma": "model-00001-of-00004.safetensors",
|
| 1106 |
+
"visual.spatial_encoder.blocks.9.ls2.gamma": "model-00001-of-00004.safetensors",
|
| 1107 |
+
"visual.spatial_encoder.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 1108 |
+
"visual.spatial_encoder.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 1109 |
+
"visual.spatial_encoder.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 1110 |
+
"visual.spatial_encoder.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 1111 |
+
"visual.spatial_encoder.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1112 |
+
"visual.spatial_encoder.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1113 |
+
"visual.spatial_encoder.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1114 |
+
"visual.spatial_encoder.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1115 |
+
"visual.spatial_encoder.cls_token": "model-00001-of-00004.safetensors",
|
| 1116 |
+
"visual.spatial_encoder.norm.bias": "model-00001-of-00004.safetensors",
|
| 1117 |
+
"visual.spatial_encoder.norm.weight": "model-00001-of-00004.safetensors",
|
| 1118 |
+
"visual.spatial_encoder.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 1119 |
+
"visual.spatial_encoder.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 1120 |
+
"visual.spatial_encoder.pos_embed": "model-00001-of-00004.safetensors",
|
| 1121 |
+
"visual.spatial_encoder.register_tokens": "model-00001-of-00004.safetensors",
|
| 1122 |
+
"visual.spatial_merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
| 1123 |
+
"visual.spatial_merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
| 1124 |
+
"visual.spatial_merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
| 1125 |
+
"visual.spatial_merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
| 1126 |
+
"visual.spatial_merger.mlp.2.weight": "model-00001-of-00004.safetensors"
|
| 1127 |
+
}
|
| 1128 |
+
}
|
GeoSR4D-Model/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 230400,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 784,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 230400,
|
| 26 |
+
"shortest_edge": 784
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
GeoSR4D-Model/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
GeoSR4D-Model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 8192,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"padding_side": "right",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
GeoSR4D-Model/trainer_state.json
ADDED
|
@@ -0,0 +1,1240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.999781770568124,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1718,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0058194515166945515,
|
| 14 |
+
"grad_norm": 292.5841369628906,
|
| 15 |
+
"learning_rate": 1.1654988945205933e-07,
|
| 16 |
+
"loss": 3.4335,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.011638903033389103,
|
| 21 |
+
"grad_norm": 310.4792785644531,
|
| 22 |
+
"learning_rate": 1.5163490216845022e-07,
|
| 23 |
+
"loss": 3.3043,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.017458354550083655,
|
| 28 |
+
"grad_norm": 255.72767639160156,
|
| 29 |
+
"learning_rate": 1.721583189448638e-07,
|
| 30 |
+
"loss": 2.6653,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.023277806066778206,
|
| 35 |
+
"grad_norm": 148.07073974609375,
|
| 36 |
+
"learning_rate": 1.867199148848411e-07,
|
| 37 |
+
"loss": 1.4797,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.029097257583472758,
|
| 42 |
+
"grad_norm": 68.8450927734375,
|
| 43 |
+
"learning_rate": 1.9801476618772772e-07,
|
| 44 |
+
"loss": 0.8688,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03491670910016731,
|
| 49 |
+
"grad_norm": 17.056119918823242,
|
| 50 |
+
"learning_rate": 2e-07,
|
| 51 |
+
"loss": 0.4755,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.04073616061686186,
|
| 56 |
+
"grad_norm": 18.346956253051758,
|
| 57 |
+
"learning_rate": 2e-07,
|
| 58 |
+
"loss": 0.4493,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.04655561213355641,
|
| 63 |
+
"grad_norm": 12.33590316772461,
|
| 64 |
+
"learning_rate": 2e-07,
|
| 65 |
+
"loss": 0.4181,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.052375063650250964,
|
| 70 |
+
"grad_norm": 10.863751411437988,
|
| 71 |
+
"learning_rate": 2e-07,
|
| 72 |
+
"loss": 0.423,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.058194515166945515,
|
| 77 |
+
"grad_norm": 12.51539421081543,
|
| 78 |
+
"learning_rate": 2e-07,
|
| 79 |
+
"loss": 0.4138,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.06401396668364007,
|
| 84 |
+
"grad_norm": 10.982370376586914,
|
| 85 |
+
"learning_rate": 2e-07,
|
| 86 |
+
"loss": 0.3545,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06983341820033462,
|
| 91 |
+
"grad_norm": 14.997520446777344,
|
| 92 |
+
"learning_rate": 2e-07,
|
| 93 |
+
"loss": 0.4036,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.07565286971702917,
|
| 98 |
+
"grad_norm": 15.653407096862793,
|
| 99 |
+
"learning_rate": 2e-07,
|
| 100 |
+
"loss": 0.3872,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.08147232123372372,
|
| 105 |
+
"grad_norm": 14.640938758850098,
|
| 106 |
+
"learning_rate": 2e-07,
|
| 107 |
+
"loss": 0.3816,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08729177275041827,
|
| 112 |
+
"grad_norm": 12.07015609741211,
|
| 113 |
+
"learning_rate": 2e-07,
|
| 114 |
+
"loss": 0.3119,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.09311122426711282,
|
| 119 |
+
"grad_norm": 23.116605758666992,
|
| 120 |
+
"learning_rate": 2e-07,
|
| 121 |
+
"loss": 0.3326,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.09893067578380738,
|
| 126 |
+
"grad_norm": 14.743234634399414,
|
| 127 |
+
"learning_rate": 2e-07,
|
| 128 |
+
"loss": 0.3304,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.10475012730050193,
|
| 133 |
+
"grad_norm": 13.361212730407715,
|
| 134 |
+
"learning_rate": 2e-07,
|
| 135 |
+
"loss": 0.3284,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.11056957881719648,
|
| 140 |
+
"grad_norm": 14.600347518920898,
|
| 141 |
+
"learning_rate": 2e-07,
|
| 142 |
+
"loss": 0.2876,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.11638903033389103,
|
| 147 |
+
"grad_norm": 16.508502960205078,
|
| 148 |
+
"learning_rate": 2e-07,
|
| 149 |
+
"loss": 0.3143,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.12220848185058558,
|
| 154 |
+
"grad_norm": 11.057723999023438,
|
| 155 |
+
"learning_rate": 2e-07,
|
| 156 |
+
"loss": 0.2918,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.12802793336728013,
|
| 161 |
+
"grad_norm": 14.558637619018555,
|
| 162 |
+
"learning_rate": 2e-07,
|
| 163 |
+
"loss": 0.3074,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.13384738488397468,
|
| 168 |
+
"grad_norm": 11.879530906677246,
|
| 169 |
+
"learning_rate": 2e-07,
|
| 170 |
+
"loss": 0.28,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13966683640066924,
|
| 175 |
+
"grad_norm": 11.994890213012695,
|
| 176 |
+
"learning_rate": 2e-07,
|
| 177 |
+
"loss": 0.2601,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1454862879173638,
|
| 182 |
+
"grad_norm": 15.544328689575195,
|
| 183 |
+
"learning_rate": 2e-07,
|
| 184 |
+
"loss": 0.281,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.15130573943405834,
|
| 189 |
+
"grad_norm": 11.14696979522705,
|
| 190 |
+
"learning_rate": 2e-07,
|
| 191 |
+
"loss": 0.2891,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1571251909507529,
|
| 196 |
+
"grad_norm": 8.271623611450195,
|
| 197 |
+
"learning_rate": 2e-07,
|
| 198 |
+
"loss": 0.2932,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.16294464246744744,
|
| 203 |
+
"grad_norm": 16.06687355041504,
|
| 204 |
+
"learning_rate": 2e-07,
|
| 205 |
+
"loss": 0.2363,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.168764093984142,
|
| 210 |
+
"grad_norm": 8.106555938720703,
|
| 211 |
+
"learning_rate": 2e-07,
|
| 212 |
+
"loss": 0.2313,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.17458354550083655,
|
| 217 |
+
"grad_norm": 13.634657859802246,
|
| 218 |
+
"learning_rate": 2e-07,
|
| 219 |
+
"loss": 0.2727,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1804029970175311,
|
| 224 |
+
"grad_norm": 14.710253715515137,
|
| 225 |
+
"learning_rate": 2e-07,
|
| 226 |
+
"loss": 0.2649,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.18622244853422565,
|
| 231 |
+
"grad_norm": 9.026782035827637,
|
| 232 |
+
"learning_rate": 2e-07,
|
| 233 |
+
"loss": 0.2547,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.1920419000509202,
|
| 238 |
+
"grad_norm": 10.011273384094238,
|
| 239 |
+
"learning_rate": 2e-07,
|
| 240 |
+
"loss": 0.2771,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.19786135156761475,
|
| 245 |
+
"grad_norm": 13.526799201965332,
|
| 246 |
+
"learning_rate": 2e-07,
|
| 247 |
+
"loss": 0.2589,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2036808030843093,
|
| 252 |
+
"grad_norm": 16.426071166992188,
|
| 253 |
+
"learning_rate": 2e-07,
|
| 254 |
+
"loss": 0.2436,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.20950025460100385,
|
| 259 |
+
"grad_norm": 14.218461036682129,
|
| 260 |
+
"learning_rate": 2e-07,
|
| 261 |
+
"loss": 0.2593,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2153197061176984,
|
| 266 |
+
"grad_norm": 6.507007122039795,
|
| 267 |
+
"learning_rate": 2e-07,
|
| 268 |
+
"loss": 0.2245,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.22113915763439296,
|
| 273 |
+
"grad_norm": 19.18690299987793,
|
| 274 |
+
"learning_rate": 2e-07,
|
| 275 |
+
"loss": 0.2447,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.2269586091510875,
|
| 280 |
+
"grad_norm": 7.621412754058838,
|
| 281 |
+
"learning_rate": 2e-07,
|
| 282 |
+
"loss": 0.2131,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.23277806066778206,
|
| 287 |
+
"grad_norm": 9.732011795043945,
|
| 288 |
+
"learning_rate": 2e-07,
|
| 289 |
+
"loss": 0.2495,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.2385975121844766,
|
| 294 |
+
"grad_norm": 15.301701545715332,
|
| 295 |
+
"learning_rate": 2e-07,
|
| 296 |
+
"loss": 0.2427,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.24441696370117116,
|
| 301 |
+
"grad_norm": 8.665528297424316,
|
| 302 |
+
"learning_rate": 2e-07,
|
| 303 |
+
"loss": 0.2281,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2502364152178657,
|
| 308 |
+
"grad_norm": 9.586000442504883,
|
| 309 |
+
"learning_rate": 2e-07,
|
| 310 |
+
"loss": 0.232,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.25605586673456027,
|
| 315 |
+
"grad_norm": 13.73252010345459,
|
| 316 |
+
"learning_rate": 2e-07,
|
| 317 |
+
"loss": 0.2326,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.2618753182512548,
|
| 322 |
+
"grad_norm": 14.053579330444336,
|
| 323 |
+
"learning_rate": 2e-07,
|
| 324 |
+
"loss": 0.2483,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.26769476976794937,
|
| 329 |
+
"grad_norm": 9.641685485839844,
|
| 330 |
+
"learning_rate": 2e-07,
|
| 331 |
+
"loss": 0.2461,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2735142212846439,
|
| 336 |
+
"grad_norm": 13.011364936828613,
|
| 337 |
+
"learning_rate": 2e-07,
|
| 338 |
+
"loss": 0.1929,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2793336728013385,
|
| 343 |
+
"grad_norm": 13.232110023498535,
|
| 344 |
+
"learning_rate": 2e-07,
|
| 345 |
+
"loss": 0.204,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.285153124318033,
|
| 350 |
+
"grad_norm": 10.551194190979004,
|
| 351 |
+
"learning_rate": 2e-07,
|
| 352 |
+
"loss": 0.2341,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2909725758347276,
|
| 357 |
+
"grad_norm": 11.238757133483887,
|
| 358 |
+
"learning_rate": 2e-07,
|
| 359 |
+
"loss": 0.2342,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2967920273514221,
|
| 364 |
+
"grad_norm": 14.688443183898926,
|
| 365 |
+
"learning_rate": 2e-07,
|
| 366 |
+
"loss": 0.2177,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3026114788681167,
|
| 371 |
+
"grad_norm": 14.724873542785645,
|
| 372 |
+
"learning_rate": 2e-07,
|
| 373 |
+
"loss": 0.1969,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.30843093038481123,
|
| 378 |
+
"grad_norm": 11.847085952758789,
|
| 379 |
+
"learning_rate": 2e-07,
|
| 380 |
+
"loss": 0.1847,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3142503819015058,
|
| 385 |
+
"grad_norm": 11.497530937194824,
|
| 386 |
+
"learning_rate": 2e-07,
|
| 387 |
+
"loss": 0.2017,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.32006983341820033,
|
| 392 |
+
"grad_norm": 11.654367446899414,
|
| 393 |
+
"learning_rate": 2e-07,
|
| 394 |
+
"loss": 0.2206,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3258892849348949,
|
| 399 |
+
"grad_norm": 12.561141967773438,
|
| 400 |
+
"learning_rate": 2e-07,
|
| 401 |
+
"loss": 0.2275,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.33170873645158944,
|
| 406 |
+
"grad_norm": 10.0696382522583,
|
| 407 |
+
"learning_rate": 2e-07,
|
| 408 |
+
"loss": 0.2008,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.337528187968284,
|
| 413 |
+
"grad_norm": 11.895383834838867,
|
| 414 |
+
"learning_rate": 2e-07,
|
| 415 |
+
"loss": 0.2192,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.34334763948497854,
|
| 420 |
+
"grad_norm": 15.39511489868164,
|
| 421 |
+
"learning_rate": 2e-07,
|
| 422 |
+
"loss": 0.2113,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3491670910016731,
|
| 427 |
+
"grad_norm": 11.026963233947754,
|
| 428 |
+
"learning_rate": 2e-07,
|
| 429 |
+
"loss": 0.2042,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.35498654251836764,
|
| 434 |
+
"grad_norm": 10.234797477722168,
|
| 435 |
+
"learning_rate": 2e-07,
|
| 436 |
+
"loss": 0.2026,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.3608059940350622,
|
| 441 |
+
"grad_norm": 11.014677047729492,
|
| 442 |
+
"learning_rate": 2e-07,
|
| 443 |
+
"loss": 0.2051,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.36662544555175675,
|
| 448 |
+
"grad_norm": 9.119762420654297,
|
| 449 |
+
"learning_rate": 2e-07,
|
| 450 |
+
"loss": 0.2137,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3724448970684513,
|
| 455 |
+
"grad_norm": 6.889257907867432,
|
| 456 |
+
"learning_rate": 2e-07,
|
| 457 |
+
"loss": 0.1647,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.37826434858514585,
|
| 462 |
+
"grad_norm": 7.318251132965088,
|
| 463 |
+
"learning_rate": 2e-07,
|
| 464 |
+
"loss": 0.1973,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3840838001018404,
|
| 469 |
+
"grad_norm": 13.953539848327637,
|
| 470 |
+
"learning_rate": 2e-07,
|
| 471 |
+
"loss": 0.1962,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.38990325161853495,
|
| 476 |
+
"grad_norm": 11.493965148925781,
|
| 477 |
+
"learning_rate": 2e-07,
|
| 478 |
+
"loss": 0.2017,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.3957227031352295,
|
| 483 |
+
"grad_norm": 9.594313621520996,
|
| 484 |
+
"learning_rate": 2e-07,
|
| 485 |
+
"loss": 0.2475,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.40154215465192405,
|
| 490 |
+
"grad_norm": 8.401884078979492,
|
| 491 |
+
"learning_rate": 2e-07,
|
| 492 |
+
"loss": 0.1946,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.4073616061686186,
|
| 497 |
+
"grad_norm": 9.508219718933105,
|
| 498 |
+
"learning_rate": 2e-07,
|
| 499 |
+
"loss": 0.2113,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.41318105768531316,
|
| 504 |
+
"grad_norm": 11.010660171508789,
|
| 505 |
+
"learning_rate": 2e-07,
|
| 506 |
+
"loss": 0.2058,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.4190005092020077,
|
| 511 |
+
"grad_norm": 15.212239265441895,
|
| 512 |
+
"learning_rate": 2e-07,
|
| 513 |
+
"loss": 0.2155,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.42481996071870226,
|
| 518 |
+
"grad_norm": 8.596692085266113,
|
| 519 |
+
"learning_rate": 2e-07,
|
| 520 |
+
"loss": 0.2143,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.4306394122353968,
|
| 525 |
+
"grad_norm": 18.07278823852539,
|
| 526 |
+
"learning_rate": 2e-07,
|
| 527 |
+
"loss": 0.1929,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.43645886375209136,
|
| 532 |
+
"grad_norm": 11.786556243896484,
|
| 533 |
+
"learning_rate": 2e-07,
|
| 534 |
+
"loss": 0.2149,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.4422783152687859,
|
| 539 |
+
"grad_norm": 5.36111307144165,
|
| 540 |
+
"learning_rate": 2e-07,
|
| 541 |
+
"loss": 0.201,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.44809776678548047,
|
| 546 |
+
"grad_norm": 17.974634170532227,
|
| 547 |
+
"learning_rate": 2e-07,
|
| 548 |
+
"loss": 0.2216,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.453917218302175,
|
| 553 |
+
"grad_norm": 7.572098731994629,
|
| 554 |
+
"learning_rate": 2e-07,
|
| 555 |
+
"loss": 0.2137,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.45973666981886957,
|
| 560 |
+
"grad_norm": 10.07806396484375,
|
| 561 |
+
"learning_rate": 2e-07,
|
| 562 |
+
"loss": 0.2011,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4655561213355641,
|
| 567 |
+
"grad_norm": 11.195019721984863,
|
| 568 |
+
"learning_rate": 2e-07,
|
| 569 |
+
"loss": 0.1976,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4713755728522587,
|
| 574 |
+
"grad_norm": 13.922369956970215,
|
| 575 |
+
"learning_rate": 2e-07,
|
| 576 |
+
"loss": 0.1755,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.4771950243689532,
|
| 581 |
+
"grad_norm": 14.419588088989258,
|
| 582 |
+
"learning_rate": 2e-07,
|
| 583 |
+
"loss": 0.2261,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.4830144758856478,
|
| 588 |
+
"grad_norm": 7.6839070320129395,
|
| 589 |
+
"learning_rate": 2e-07,
|
| 590 |
+
"loss": 0.1957,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.4888339274023423,
|
| 595 |
+
"grad_norm": 18.723840713500977,
|
| 596 |
+
"learning_rate": 2e-07,
|
| 597 |
+
"loss": 0.1964,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.4946533789190369,
|
| 602 |
+
"grad_norm": 11.51264476776123,
|
| 603 |
+
"learning_rate": 2e-07,
|
| 604 |
+
"loss": 0.2429,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.5004728304357314,
|
| 609 |
+
"grad_norm": 14.401782989501953,
|
| 610 |
+
"learning_rate": 2e-07,
|
| 611 |
+
"loss": 0.2077,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.506292281952426,
|
| 616 |
+
"grad_norm": 7.909298896789551,
|
| 617 |
+
"learning_rate": 2e-07,
|
| 618 |
+
"loss": 0.1981,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.5121117334691205,
|
| 623 |
+
"grad_norm": 9.616816520690918,
|
| 624 |
+
"learning_rate": 2e-07,
|
| 625 |
+
"loss": 0.2059,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5179311849858151,
|
| 630 |
+
"grad_norm": 14.229058265686035,
|
| 631 |
+
"learning_rate": 2e-07,
|
| 632 |
+
"loss": 0.1838,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.5237506365025096,
|
| 637 |
+
"grad_norm": 8.7423734664917,
|
| 638 |
+
"learning_rate": 2e-07,
|
| 639 |
+
"loss": 0.1883,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.5295700880192042,
|
| 644 |
+
"grad_norm": 7.891780853271484,
|
| 645 |
+
"learning_rate": 2e-07,
|
| 646 |
+
"loss": 0.2177,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.5353895395358987,
|
| 651 |
+
"grad_norm": 15.503663063049316,
|
| 652 |
+
"learning_rate": 2e-07,
|
| 653 |
+
"loss": 0.2028,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5412089910525933,
|
| 658 |
+
"grad_norm": 10.924641609191895,
|
| 659 |
+
"learning_rate": 2e-07,
|
| 660 |
+
"loss": 0.1923,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5470284425692878,
|
| 665 |
+
"grad_norm": 14.79828929901123,
|
| 666 |
+
"learning_rate": 2e-07,
|
| 667 |
+
"loss": 0.2322,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5528478940859824,
|
| 672 |
+
"grad_norm": 11.492549896240234,
|
| 673 |
+
"learning_rate": 2e-07,
|
| 674 |
+
"loss": 0.2306,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.558667345602677,
|
| 679 |
+
"grad_norm": 5.280726909637451,
|
| 680 |
+
"learning_rate": 2e-07,
|
| 681 |
+
"loss": 0.1846,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5644867971193716,
|
| 686 |
+
"grad_norm": 7.49058198928833,
|
| 687 |
+
"learning_rate": 2e-07,
|
| 688 |
+
"loss": 0.186,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.570306248636066,
|
| 693 |
+
"grad_norm": 17.624052047729492,
|
| 694 |
+
"learning_rate": 2e-07,
|
| 695 |
+
"loss": 0.2145,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5761257001527607,
|
| 700 |
+
"grad_norm": 11.165759086608887,
|
| 701 |
+
"learning_rate": 2e-07,
|
| 702 |
+
"loss": 0.201,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.5819451516694552,
|
| 707 |
+
"grad_norm": 7.842067718505859,
|
| 708 |
+
"learning_rate": 2e-07,
|
| 709 |
+
"loss": 0.1968,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.5877646031861498,
|
| 714 |
+
"grad_norm": 9.594118118286133,
|
| 715 |
+
"learning_rate": 2e-07,
|
| 716 |
+
"loss": 0.2136,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.5935840547028443,
|
| 721 |
+
"grad_norm": 14.04518985748291,
|
| 722 |
+
"learning_rate": 2e-07,
|
| 723 |
+
"loss": 0.2075,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.5994035062195389,
|
| 728 |
+
"grad_norm": 15.331314086914062,
|
| 729 |
+
"learning_rate": 2e-07,
|
| 730 |
+
"loss": 0.2023,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.6052229577362334,
|
| 735 |
+
"grad_norm": 8.51887321472168,
|
| 736 |
+
"learning_rate": 2e-07,
|
| 737 |
+
"loss": 0.1713,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.611042409252928,
|
| 742 |
+
"grad_norm": 11.08820629119873,
|
| 743 |
+
"learning_rate": 2e-07,
|
| 744 |
+
"loss": 0.1868,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.6168618607696225,
|
| 749 |
+
"grad_norm": 12.212711334228516,
|
| 750 |
+
"learning_rate": 2e-07,
|
| 751 |
+
"loss": 0.1876,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.6226813122863171,
|
| 756 |
+
"grad_norm": 11.730500221252441,
|
| 757 |
+
"learning_rate": 2e-07,
|
| 758 |
+
"loss": 0.1934,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.6285007638030116,
|
| 763 |
+
"grad_norm": 9.89484977722168,
|
| 764 |
+
"learning_rate": 2e-07,
|
| 765 |
+
"loss": 0.2097,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.6343202153197062,
|
| 770 |
+
"grad_norm": 7.291867256164551,
|
| 771 |
+
"learning_rate": 2e-07,
|
| 772 |
+
"loss": 0.1582,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.6401396668364007,
|
| 777 |
+
"grad_norm": 7.9038920402526855,
|
| 778 |
+
"learning_rate": 2e-07,
|
| 779 |
+
"loss": 0.21,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.6459591183530953,
|
| 784 |
+
"grad_norm": 18.028404235839844,
|
| 785 |
+
"learning_rate": 2e-07,
|
| 786 |
+
"loss": 0.2293,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.6517785698697898,
|
| 791 |
+
"grad_norm": 12.41182804107666,
|
| 792 |
+
"learning_rate": 2e-07,
|
| 793 |
+
"loss": 0.2048,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6575980213864844,
|
| 798 |
+
"grad_norm": 11.216751098632812,
|
| 799 |
+
"learning_rate": 2e-07,
|
| 800 |
+
"loss": 0.1903,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6634174729031789,
|
| 805 |
+
"grad_norm": 13.232751846313477,
|
| 806 |
+
"learning_rate": 2e-07,
|
| 807 |
+
"loss": 0.19,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.6692369244198735,
|
| 812 |
+
"grad_norm": 9.882608413696289,
|
| 813 |
+
"learning_rate": 2e-07,
|
| 814 |
+
"loss": 0.1936,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.675056375936568,
|
| 819 |
+
"grad_norm": 9.839518547058105,
|
| 820 |
+
"learning_rate": 2e-07,
|
| 821 |
+
"loss": 0.2019,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.6808758274532626,
|
| 826 |
+
"grad_norm": 12.619885444641113,
|
| 827 |
+
"learning_rate": 2e-07,
|
| 828 |
+
"loss": 0.2124,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.6866952789699571,
|
| 833 |
+
"grad_norm": 12.874058723449707,
|
| 834 |
+
"learning_rate": 2e-07,
|
| 835 |
+
"loss": 0.1875,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.6925147304866517,
|
| 840 |
+
"grad_norm": 13.787298202514648,
|
| 841 |
+
"learning_rate": 2e-07,
|
| 842 |
+
"loss": 0.2071,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.6983341820033462,
|
| 847 |
+
"grad_norm": 11.749211311340332,
|
| 848 |
+
"learning_rate": 2e-07,
|
| 849 |
+
"loss": 0.1957,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.7041536335200408,
|
| 854 |
+
"grad_norm": 12.892156600952148,
|
| 855 |
+
"learning_rate": 2e-07,
|
| 856 |
+
"loss": 0.1748,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.7099730850367353,
|
| 861 |
+
"grad_norm": 14.410128593444824,
|
| 862 |
+
"learning_rate": 2e-07,
|
| 863 |
+
"loss": 0.1934,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.7157925365534299,
|
| 868 |
+
"grad_norm": 11.821023941040039,
|
| 869 |
+
"learning_rate": 2e-07,
|
| 870 |
+
"loss": 0.2113,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.7216119880701244,
|
| 875 |
+
"grad_norm": 7.469109058380127,
|
| 876 |
+
"learning_rate": 2e-07,
|
| 877 |
+
"loss": 0.177,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.727431439586819,
|
| 882 |
+
"grad_norm": 11.144964218139648,
|
| 883 |
+
"learning_rate": 2e-07,
|
| 884 |
+
"loss": 0.2026,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.7332508911035135,
|
| 889 |
+
"grad_norm": 8.659164428710938,
|
| 890 |
+
"learning_rate": 2e-07,
|
| 891 |
+
"loss": 0.1866,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.7390703426202081,
|
| 896 |
+
"grad_norm": 12.093481063842773,
|
| 897 |
+
"learning_rate": 2e-07,
|
| 898 |
+
"loss": 0.1819,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.7448897941369026,
|
| 903 |
+
"grad_norm": 9.76320743560791,
|
| 904 |
+
"learning_rate": 2e-07,
|
| 905 |
+
"loss": 0.1826,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.7507092456535972,
|
| 910 |
+
"grad_norm": 9.821404457092285,
|
| 911 |
+
"learning_rate": 2e-07,
|
| 912 |
+
"loss": 0.1916,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.7565286971702917,
|
| 917 |
+
"grad_norm": 13.206873893737793,
|
| 918 |
+
"learning_rate": 2e-07,
|
| 919 |
+
"loss": 0.2037,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.7623481486869863,
|
| 924 |
+
"grad_norm": 11.560912132263184,
|
| 925 |
+
"learning_rate": 2e-07,
|
| 926 |
+
"loss": 0.179,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.7681676002036808,
|
| 931 |
+
"grad_norm": 14.256608009338379,
|
| 932 |
+
"learning_rate": 2e-07,
|
| 933 |
+
"loss": 0.1879,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.7739870517203754,
|
| 938 |
+
"grad_norm": 17.668615341186523,
|
| 939 |
+
"learning_rate": 2e-07,
|
| 940 |
+
"loss": 0.1772,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.7798065032370699,
|
| 945 |
+
"grad_norm": 11.932788848876953,
|
| 946 |
+
"learning_rate": 2e-07,
|
| 947 |
+
"loss": 0.1657,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.7856259547537645,
|
| 952 |
+
"grad_norm": 8.989192008972168,
|
| 953 |
+
"learning_rate": 2e-07,
|
| 954 |
+
"loss": 0.18,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.791445406270459,
|
| 959 |
+
"grad_norm": 8.768953323364258,
|
| 960 |
+
"learning_rate": 2e-07,
|
| 961 |
+
"loss": 0.2002,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7972648577871536,
|
| 966 |
+
"grad_norm": 16.538890838623047,
|
| 967 |
+
"learning_rate": 2e-07,
|
| 968 |
+
"loss": 0.1693,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.8030843093038481,
|
| 973 |
+
"grad_norm": 7.928899765014648,
|
| 974 |
+
"learning_rate": 2e-07,
|
| 975 |
+
"loss": 0.1926,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.8089037608205427,
|
| 980 |
+
"grad_norm": 11.980950355529785,
|
| 981 |
+
"learning_rate": 2e-07,
|
| 982 |
+
"loss": 0.2042,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8147232123372372,
|
| 987 |
+
"grad_norm": 14.4302978515625,
|
| 988 |
+
"learning_rate": 2e-07,
|
| 989 |
+
"loss": 0.1797,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.8205426638539318,
|
| 994 |
+
"grad_norm": 11.229952812194824,
|
| 995 |
+
"learning_rate": 2e-07,
|
| 996 |
+
"loss": 0.17,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.8263621153706263,
|
| 1001 |
+
"grad_norm": 11.317793846130371,
|
| 1002 |
+
"learning_rate": 2e-07,
|
| 1003 |
+
"loss": 0.1728,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.8321815668873209,
|
| 1008 |
+
"grad_norm": 10.537130355834961,
|
| 1009 |
+
"learning_rate": 2e-07,
|
| 1010 |
+
"loss": 0.1787,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.8380010184040154,
|
| 1015 |
+
"grad_norm": 11.120368003845215,
|
| 1016 |
+
"learning_rate": 2e-07,
|
| 1017 |
+
"loss": 0.1621,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.84382046992071,
|
| 1022 |
+
"grad_norm": 13.397139549255371,
|
| 1023 |
+
"learning_rate": 2e-07,
|
| 1024 |
+
"loss": 0.1639,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.8496399214374045,
|
| 1029 |
+
"grad_norm": 12.438237190246582,
|
| 1030 |
+
"learning_rate": 2e-07,
|
| 1031 |
+
"loss": 0.1769,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.8554593729540991,
|
| 1036 |
+
"grad_norm": 11.550435066223145,
|
| 1037 |
+
"learning_rate": 2e-07,
|
| 1038 |
+
"loss": 0.2065,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.8612788244707936,
|
| 1043 |
+
"grad_norm": 6.573584079742432,
|
| 1044 |
+
"learning_rate": 2e-07,
|
| 1045 |
+
"loss": 0.2021,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.8670982759874882,
|
| 1050 |
+
"grad_norm": 6.305631637573242,
|
| 1051 |
+
"learning_rate": 2e-07,
|
| 1052 |
+
"loss": 0.1811,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.8729177275041827,
|
| 1057 |
+
"grad_norm": 9.760597229003906,
|
| 1058 |
+
"learning_rate": 2e-07,
|
| 1059 |
+
"loss": 0.1937,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.8787371790208773,
|
| 1064 |
+
"grad_norm": 13.0894193649292,
|
| 1065 |
+
"learning_rate": 2e-07,
|
| 1066 |
+
"loss": 0.176,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.8845566305375718,
|
| 1071 |
+
"grad_norm": 7.848855495452881,
|
| 1072 |
+
"learning_rate": 2e-07,
|
| 1073 |
+
"loss": 0.1773,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.8903760820542664,
|
| 1078 |
+
"grad_norm": 14.45218563079834,
|
| 1079 |
+
"learning_rate": 2e-07,
|
| 1080 |
+
"loss": 0.2096,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.8961955335709609,
|
| 1085 |
+
"grad_norm": 7.301393032073975,
|
| 1086 |
+
"learning_rate": 2e-07,
|
| 1087 |
+
"loss": 0.1656,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.9020149850876555,
|
| 1092 |
+
"grad_norm": 10.425517082214355,
|
| 1093 |
+
"learning_rate": 2e-07,
|
| 1094 |
+
"loss": 0.1802,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.90783443660435,
|
| 1099 |
+
"grad_norm": 12.547024726867676,
|
| 1100 |
+
"learning_rate": 2e-07,
|
| 1101 |
+
"loss": 0.1922,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.9136538881210446,
|
| 1106 |
+
"grad_norm": 12.041275978088379,
|
| 1107 |
+
"learning_rate": 2e-07,
|
| 1108 |
+
"loss": 0.1827,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.9194733396377391,
|
| 1113 |
+
"grad_norm": 10.960613250732422,
|
| 1114 |
+
"learning_rate": 2e-07,
|
| 1115 |
+
"loss": 0.2234,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.9252927911544337,
|
| 1120 |
+
"grad_norm": 11.155454635620117,
|
| 1121 |
+
"learning_rate": 2e-07,
|
| 1122 |
+
"loss": 0.1615,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.9311122426711282,
|
| 1127 |
+
"grad_norm": 17.65553092956543,
|
| 1128 |
+
"learning_rate": 2e-07,
|
| 1129 |
+
"loss": 0.1892,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.9369316941878228,
|
| 1134 |
+
"grad_norm": 18.907163619995117,
|
| 1135 |
+
"learning_rate": 2e-07,
|
| 1136 |
+
"loss": 0.1915,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.9427511457045173,
|
| 1141 |
+
"grad_norm": 14.12991714477539,
|
| 1142 |
+
"learning_rate": 2e-07,
|
| 1143 |
+
"loss": 0.2156,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.948570597221212,
|
| 1148 |
+
"grad_norm": 9.105369567871094,
|
| 1149 |
+
"learning_rate": 2e-07,
|
| 1150 |
+
"loss": 0.1808,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.9543900487379064,
|
| 1155 |
+
"grad_norm": 10.135030746459961,
|
| 1156 |
+
"learning_rate": 2e-07,
|
| 1157 |
+
"loss": 0.1842,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.9602095002546011,
|
| 1162 |
+
"grad_norm": 33.01081466674805,
|
| 1163 |
+
"learning_rate": 2e-07,
|
| 1164 |
+
"loss": 0.1757,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.9660289517712956,
|
| 1169 |
+
"grad_norm": 7.512867450714111,
|
| 1170 |
+
"learning_rate": 2e-07,
|
| 1171 |
+
"loss": 0.1591,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.9718484032879902,
|
| 1176 |
+
"grad_norm": 7.911075592041016,
|
| 1177 |
+
"learning_rate": 2e-07,
|
| 1178 |
+
"loss": 0.1885,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.9776678548046847,
|
| 1183 |
+
"grad_norm": 4.568904399871826,
|
| 1184 |
+
"learning_rate": 2e-07,
|
| 1185 |
+
"loss": 0.1929,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.9834873063213793,
|
| 1190 |
+
"grad_norm": 14.508501052856445,
|
| 1191 |
+
"learning_rate": 2e-07,
|
| 1192 |
+
"loss": 0.2354,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.9893067578380738,
|
| 1197 |
+
"grad_norm": 9.957372665405273,
|
| 1198 |
+
"learning_rate": 2e-07,
|
| 1199 |
+
"loss": 0.1523,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.9951262093547684,
|
| 1204 |
+
"grad_norm": 8.227477073669434,
|
| 1205 |
+
"learning_rate": 2e-07,
|
| 1206 |
+
"loss": 0.1816,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.999781770568124,
|
| 1211 |
+
"step": 1718,
|
| 1212 |
+
"total_flos": 6.783175773021798e+16,
|
| 1213 |
+
"train_loss": 0.28378574687193936,
|
| 1214 |
+
"train_runtime": 68908.423,
|
| 1215 |
+
"train_samples_per_second": 0.798,
|
| 1216 |
+
"train_steps_per_second": 0.025
|
| 1217 |
+
}
|
| 1218 |
+
],
|
| 1219 |
+
"logging_steps": 10,
|
| 1220 |
+
"max_steps": 1718,
|
| 1221 |
+
"num_input_tokens_seen": 0,
|
| 1222 |
+
"num_train_epochs": 1,
|
| 1223 |
+
"save_steps": 100,
|
| 1224 |
+
"stateful_callbacks": {
|
| 1225 |
+
"TrainerControl": {
|
| 1226 |
+
"args": {
|
| 1227 |
+
"should_epoch_stop": false,
|
| 1228 |
+
"should_evaluate": false,
|
| 1229 |
+
"should_log": false,
|
| 1230 |
+
"should_save": true,
|
| 1231 |
+
"should_training_stop": true
|
| 1232 |
+
},
|
| 1233 |
+
"attributes": {}
|
| 1234 |
+
}
|
| 1235 |
+
},
|
| 1236 |
+
"total_flos": 6.783175773021798e+16,
|
| 1237 |
+
"train_batch_size": 1,
|
| 1238 |
+
"trial_name": null,
|
| 1239 |
+
"trial_params": null
|
| 1240 |
+
}
|
GeoSR4D-Model/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
README.md
CHANGED
|
@@ -1,3 +1,70 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- vision-language-model
|
| 6 |
+
- spatial-reasoning
|
| 7 |
+
- qwen2_5_vl
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# GeoSR Model Zoo
|
| 11 |
+
|
| 12 |
+
This repository hosts the released checkpoints for **GeoSR: Make Geometry Matter for Spatial Reasoning**.
|
| 13 |
+
|
| 14 |
+
## Checkpoints
|
| 15 |
+
|
| 16 |
+
| Folder | Branch / task | Notes |
|
| 17 |
+
| --- | --- | --- |
|
| 18 |
+
| `GeoSR3D-Model/` | `static` branch | GeoSR checkpoint for static spatial reasoning |
|
| 19 |
+
| `GeoSR4D-Model/` | `dynamic` branch | GeoSR checkpoint for dynamic spatial reasoning |
|
| 20 |
+
|
| 21 |
+
The model files are stored exactly as exported from our training directories.
|
| 22 |
+
|
| 23 |
+
## Download
|
| 24 |
+
|
| 25 |
+
Install the client first if needed:
|
| 26 |
+
|
| 27 |
+
```bash
|
| 28 |
+
pip install -U huggingface_hub
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
Download only the static checkpoint:
|
| 32 |
+
|
| 33 |
+
```bash
|
| 34 |
+
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='SuhZhang/GeoSR-Model', local_dir='data/models', allow_patterns=['GeoSR3D-Model/*'])"
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
Download only the dynamic checkpoint:
|
| 38 |
+
|
| 39 |
+
```bash
|
| 40 |
+
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='SuhZhang/GeoSR-Model', local_dir='data/models', allow_patterns=['GeoSR4D-Model/*'])"
|
| 41 |
+
```
|
| 42 |
+
|
| 43 |
+
Download the whole repository:
|
| 44 |
+
|
| 45 |
+
```bash
|
| 46 |
+
git lfs install
|
| 47 |
+
git clone https://huggingface.co/SuhZhang/GeoSR-Model
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
## Usage
|
| 51 |
+
|
| 52 |
+
In the main GeoSR code repository:
|
| 53 |
+
|
| 54 |
+
- `static` branch evaluation can use `MODEL_PATH=./data/models/GeoSR3D-Model`
|
| 55 |
+
- `dynamic` branch evaluation can use `GEOSR4D_EVAL_MODEL_PATH=../../../data/models/GeoSR4D-Model`
|
| 56 |
+
|
| 57 |
+
Please refer to the main code repository for full training and evaluation instructions:
|
| 58 |
+
|
| 59 |
+
- Code: https://github.com/SuhZhang/GeoSR
|
| 60 |
+
- Project page: https://suhzhang.github.io/GeoSR/
|
| 61 |
+
|
| 62 |
+
## Citation
|
| 63 |
+
|
| 64 |
+
```bibtex
|
| 65 |
+
@misc{zhang2026geosr,
|
| 66 |
+
title={Make Geometry Matter for Spatial Reasoning},
|
| 67 |
+
author={Shihua Zhang and Qiuhong Shen and Shizun Wang and Tianbo Pan and Xinchao Wang},
|
| 68 |
+
year={2026}
|
| 69 |
+
}
|
| 70 |
+
```
|