Upload to Hugging Face
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- added_tokens.json +6 -0
- checkpoint-100/added_tokens.json +6 -0
- checkpoint-100/config.json +222 -0
- checkpoint-100/generation_config.json +14 -0
- checkpoint-100/merges.txt +0 -0
- checkpoint-100/model-00001-of-00004.safetensors +3 -0
- checkpoint-100/model-00002-of-00004.safetensors +3 -0
- checkpoint-100/model-00003-of-00004.safetensors +3 -0
- checkpoint-100/model-00004-of-00004.safetensors +3 -0
- checkpoint-100/model.safetensors.index.json +772 -0
- checkpoint-100/special_tokens_map.json +20 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer_config.json +53 -0
- checkpoint-100/trainer_state.json +721 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-100/vocab.json +0 -0
- checkpoint-150/added_tokens.json +6 -0
- checkpoint-150/config.json +222 -0
- checkpoint-150/generation_config.json +14 -0
- checkpoint-150/merges.txt +0 -0
- checkpoint-150/model-00001-of-00004.safetensors +3 -0
- checkpoint-150/model-00002-of-00004.safetensors +3 -0
- checkpoint-150/model-00003-of-00004.safetensors +3 -0
- checkpoint-150/model-00004-of-00004.safetensors +3 -0
- checkpoint-150/model.safetensors.index.json +772 -0
- checkpoint-150/special_tokens_map.json +20 -0
- checkpoint-150/tokenizer.json +0 -0
- checkpoint-150/tokenizer_config.json +53 -0
- checkpoint-150/trainer_state.json +1071 -0
- checkpoint-150/training_args.bin +3 -0
- checkpoint-150/vocab.json +0 -0
- checkpoint-200/added_tokens.json +6 -0
- checkpoint-200/config.json +222 -0
- checkpoint-200/generation_config.json +14 -0
- checkpoint-200/merges.txt +0 -0
- checkpoint-200/model-00001-of-00004.safetensors +3 -0
- checkpoint-200/model-00002-of-00004.safetensors +3 -0
- checkpoint-200/model-00003-of-00004.safetensors +3 -0
- checkpoint-200/model-00004-of-00004.safetensors +3 -0
- checkpoint-200/model.safetensors.index.json +772 -0
- checkpoint-200/special_tokens_map.json +20 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer_config.json +53 -0
- checkpoint-200/trainer_state.json +1421 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-200/vocab.json +0 -0
- checkpoint-250/added_tokens.json +6 -0
- checkpoint-250/config.json +222 -0
- checkpoint-250/generation_config.json +14 -0
- checkpoint-250/merges.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image>": 151646,
|
| 3 |
+
"<|endoftext|>": 151643,
|
| 4 |
+
"<|im_end|>": 151645,
|
| 5 |
+
"<|im_start|>": 151644
|
| 6 |
+
}
|
checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image>": 151646,
|
| 3 |
+
"<|endoftext|>": 151643,
|
| 4 |
+
"<|im_end|>": 151645,
|
| 5 |
+
"<|im_start|>": 151644
|
| 6 |
+
}
|
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/project/mlmlongvideo/checkpoints/pure_text_extend_llava_qwen/checkpoint-200/",
|
| 3 |
+
"add_faster_video": false,
|
| 4 |
+
"add_time_instruction": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlavaQwenForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 151643,
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": true,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"ignore_index": -100,
|
| 16 |
+
"image_aspect_ratio": "anyres_max_9",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": [
|
| 19 |
+
[
|
| 20 |
+
384,
|
| 21 |
+
384
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
384,
|
| 25 |
+
768
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
384,
|
| 29 |
+
1152
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
384,
|
| 33 |
+
1536
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
384,
|
| 37 |
+
1920
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
384,
|
| 41 |
+
2304
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
768,
|
| 45 |
+
384
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
768,
|
| 49 |
+
768
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
768,
|
| 53 |
+
1152
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
768,
|
| 57 |
+
1536
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
768,
|
| 61 |
+
1920
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
768,
|
| 65 |
+
2304
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
1152,
|
| 69 |
+
384
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
1152,
|
| 73 |
+
768
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
1152,
|
| 77 |
+
1152
|
| 78 |
+
],
|
| 79 |
+
[
|
| 80 |
+
1152,
|
| 81 |
+
1536
|
| 82 |
+
],
|
| 83 |
+
[
|
| 84 |
+
1152,
|
| 85 |
+
1920
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
1152,
|
| 89 |
+
2304
|
| 90 |
+
],
|
| 91 |
+
[
|
| 92 |
+
1536,
|
| 93 |
+
384
|
| 94 |
+
],
|
| 95 |
+
[
|
| 96 |
+
1536,
|
| 97 |
+
768
|
| 98 |
+
],
|
| 99 |
+
[
|
| 100 |
+
1536,
|
| 101 |
+
1152
|
| 102 |
+
],
|
| 103 |
+
[
|
| 104 |
+
1536,
|
| 105 |
+
1536
|
| 106 |
+
],
|
| 107 |
+
[
|
| 108 |
+
1536,
|
| 109 |
+
1920
|
| 110 |
+
],
|
| 111 |
+
[
|
| 112 |
+
1536,
|
| 113 |
+
2304
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
1920,
|
| 117 |
+
384
|
| 118 |
+
],
|
| 119 |
+
[
|
| 120 |
+
1920,
|
| 121 |
+
768
|
| 122 |
+
],
|
| 123 |
+
[
|
| 124 |
+
1920,
|
| 125 |
+
1152
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
1920,
|
| 129 |
+
1536
|
| 130 |
+
],
|
| 131 |
+
[
|
| 132 |
+
1920,
|
| 133 |
+
1920
|
| 134 |
+
],
|
| 135 |
+
[
|
| 136 |
+
1920,
|
| 137 |
+
2304
|
| 138 |
+
],
|
| 139 |
+
[
|
| 140 |
+
2304,
|
| 141 |
+
384
|
| 142 |
+
],
|
| 143 |
+
[
|
| 144 |
+
2304,
|
| 145 |
+
768
|
| 146 |
+
],
|
| 147 |
+
[
|
| 148 |
+
2304,
|
| 149 |
+
1152
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
2304,
|
| 153 |
+
1536
|
| 154 |
+
],
|
| 155 |
+
[
|
| 156 |
+
2304,
|
| 157 |
+
1920
|
| 158 |
+
],
|
| 159 |
+
[
|
| 160 |
+
2304,
|
| 161 |
+
2304
|
| 162 |
+
]
|
| 163 |
+
],
|
| 164 |
+
"image_split_resolution": null,
|
| 165 |
+
"image_token_index": 151646,
|
| 166 |
+
"initializer_range": 0.02,
|
| 167 |
+
"intermediate_size": 18944,
|
| 168 |
+
"max_position_embeddings": 32768,
|
| 169 |
+
"max_window_layers": 28,
|
| 170 |
+
"mm_hidden_size": 1152,
|
| 171 |
+
"mm_newline_position": "grid",
|
| 172 |
+
"mm_patch_merge_type": "spatial_unpad",
|
| 173 |
+
"mm_projector_lr": null,
|
| 174 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 175 |
+
"mm_resampler_type": null,
|
| 176 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 177 |
+
"mm_spatial_pool_stride": 2,
|
| 178 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
| 179 |
+
"mm_use_im_patch_token": false,
|
| 180 |
+
"mm_use_im_start_end": false,
|
| 181 |
+
"mm_vision_select_feature": "patch",
|
| 182 |
+
"mm_vision_select_layer": -2,
|
| 183 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
| 184 |
+
"mm_vision_tower_lr": 2e-06,
|
| 185 |
+
"model_type": "llava",
|
| 186 |
+
"num_attention_heads": 28,
|
| 187 |
+
"num_hidden_layers": 28,
|
| 188 |
+
"num_key_value_heads": 4,
|
| 189 |
+
"pos_skipping_range": 4096,
|
| 190 |
+
"projector_hidden_act": "gelu",
|
| 191 |
+
"rms_norm_eps": 1e-06,
|
| 192 |
+
"rope_scaling": null,
|
| 193 |
+
"rope_theta": 1000000000.0,
|
| 194 |
+
"sliding_window": 131072,
|
| 195 |
+
"text_config": {
|
| 196 |
+
"model_type": "llama",
|
| 197 |
+
"vocab_size": 152064
|
| 198 |
+
},
|
| 199 |
+
"tie_word_embeddings": false,
|
| 200 |
+
"tokenizer_model_max_length": 28000,
|
| 201 |
+
"tokenizer_padding_side": "right",
|
| 202 |
+
"torch_dtype": "bfloat16",
|
| 203 |
+
"transformers_version": "4.40.0.dev0",
|
| 204 |
+
"use_cache": false,
|
| 205 |
+
"use_mm_proj": true,
|
| 206 |
+
"use_pos_skipping": false,
|
| 207 |
+
"use_sliding_window": false,
|
| 208 |
+
"vision_config": {
|
| 209 |
+
"hidden_size": 1024,
|
| 210 |
+
"image_size": 336,
|
| 211 |
+
"intermediate_size": 4096,
|
| 212 |
+
"model_type": "clip_vision_model",
|
| 213 |
+
"num_attention_heads": 16,
|
| 214 |
+
"num_hidden_layers": 24,
|
| 215 |
+
"patch_size": 14,
|
| 216 |
+
"projection_dim": 768,
|
| 217 |
+
"vocab_size": 32000
|
| 218 |
+
},
|
| 219 |
+
"vision_feature_layer": -2,
|
| 220 |
+
"vision_feature_select_strategy": "default",
|
| 221 |
+
"vision_tower_pretrained": null
|
| 222 |
+
}
|
checkpoint-100/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.40.0.dev0"
|
| 14 |
+
}
|
checkpoint-100/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5feacb373774cbdb7ea1740c5dc6227ab5fefdf951533472d5bb01fc5812f4a4
|
| 3 |
+
size 4877668032
|
checkpoint-100/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f926c9c490a425948dfe395b05b02f216a5a53404797f4447721c8b436cecb5a
|
| 3 |
+
size 4932751008
|
checkpoint-100/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0edc3e3861ef16f1ac618b6496d36f5abf3d29b540b4e4f3d7e0dba65902a01e
|
| 3 |
+
size 4994571904
|
checkpoint-100/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3ec9a29bf23d721192681cca117a285e46fbef1c7edbe7fef7380b5762bd4a2
|
| 3 |
+
size 1255812224
|
checkpoint-100/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16060697664
|
| 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.image_newline": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 308 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 320 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.norm.weight": "model-00003-of-00004.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 701 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 702 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 703 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 704 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 705 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 706 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 707 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 708 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 709 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 710 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 711 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 712 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 713 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 714 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 715 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 716 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 717 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 718 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 719 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 720 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 721 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 722 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 723 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 724 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 725 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 726 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 727 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 728 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 729 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 730 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 731 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 732 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 733 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 734 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 735 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 736 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 737 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 738 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 739 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 740 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 741 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 742 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 743 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 744 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 745 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 746 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 747 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 748 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 749 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 750 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 751 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 752 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 753 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 754 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 755 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 756 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 757 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 758 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 759 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 760 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 761 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 762 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 763 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 764 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 765 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 766 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 767 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 768 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 769 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
|
| 770 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
|
| 771 |
+
}
|
| 772 |
+
}
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<image>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"additional_special_tokens": [
|
| 38 |
+
"<|im_start|>",
|
| 39 |
+
"<|im_end|>"
|
| 40 |
+
],
|
| 41 |
+
"bos_token": null,
|
| 42 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 43 |
+
"clean_up_tokenization_spaces": false,
|
| 44 |
+
"eos_token": "<|im_end|>",
|
| 45 |
+
"errors": "replace",
|
| 46 |
+
"model_max_length": 28000,
|
| 47 |
+
"pad_token": "<|endoftext|>",
|
| 48 |
+
"padding_side": "right",
|
| 49 |
+
"processor_class": "LlavaProcessor",
|
| 50 |
+
"split_special_tokens": false,
|
| 51 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 52 |
+
"unk_token": null
|
| 53 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.31859816806053365,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 10.092560768127441,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 1.9497,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 8.963287353515625,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 1.951,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 9.27600383758545,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 1.9345,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 5.632405757904053,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 1.9157,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 5.668580055236816,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 1.9026,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 3.8046553134918213,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 1.8923,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"grad_norm": 4.357985973358154,
|
| 56 |
+
"learning_rate": 7e-06,
|
| 57 |
+
"loss": 1.8241,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 4.685062885284424,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 1.8467,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"grad_norm": 4.768229961395264,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 1.8199,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03,
|
| 76 |
+
"grad_norm": 4.796407699584961,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 1.8374,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"grad_norm": 5.7536139488220215,
|
| 84 |
+
"learning_rate": 9.999731248679734e-06,
|
| 85 |
+
"loss": 1.779,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04,
|
| 90 |
+
"grad_norm": 4.202663898468018,
|
| 91 |
+
"learning_rate": 9.99892502360984e-06,
|
| 92 |
+
"loss": 1.7579,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"grad_norm": 2.9114131927490234,
|
| 98 |
+
"learning_rate": 9.99758141145994e-06,
|
| 99 |
+
"loss": 1.7433,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.04,
|
| 104 |
+
"grad_norm": 2.3823723793029785,
|
| 105 |
+
"learning_rate": 9.995700556669052e-06,
|
| 106 |
+
"loss": 1.7212,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05,
|
| 111 |
+
"grad_norm": 2.3254876136779785,
|
| 112 |
+
"learning_rate": 9.993282661430058e-06,
|
| 113 |
+
"loss": 1.7218,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.05,
|
| 118 |
+
"grad_norm": 2.053166151046753,
|
| 119 |
+
"learning_rate": 9.990327985667972e-06,
|
| 120 |
+
"loss": 1.7256,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.05,
|
| 125 |
+
"grad_norm": 2.3782012462615967,
|
| 126 |
+
"learning_rate": 9.986836847012001e-06,
|
| 127 |
+
"loss": 1.713,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06,
|
| 132 |
+
"grad_norm": 2.1311683654785156,
|
| 133 |
+
"learning_rate": 9.98280962076139e-06,
|
| 134 |
+
"loss": 1.6785,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"grad_norm": 2.325747489929199,
|
| 140 |
+
"learning_rate": 9.978246739845095e-06,
|
| 141 |
+
"loss": 1.7167,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.06,
|
| 146 |
+
"grad_norm": 2.1330366134643555,
|
| 147 |
+
"learning_rate": 9.973148694775217e-06,
|
| 148 |
+
"loss": 1.676,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07,
|
| 153 |
+
"grad_norm": 2.2632806301116943,
|
| 154 |
+
"learning_rate": 9.967516033594295e-06,
|
| 155 |
+
"loss": 1.7033,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.07,
|
| 160 |
+
"grad_norm": 2.6582744121551514,
|
| 161 |
+
"learning_rate": 9.961349361816384e-06,
|
| 162 |
+
"loss": 1.6957,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.07,
|
| 167 |
+
"grad_norm": 1.9663337469100952,
|
| 168 |
+
"learning_rate": 9.954649342361952e-06,
|
| 169 |
+
"loss": 1.6729,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08,
|
| 174 |
+
"grad_norm": 2.2557435035705566,
|
| 175 |
+
"learning_rate": 9.947416695486633e-06,
|
| 176 |
+
"loss": 1.6399,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"grad_norm": 2.090054512023926,
|
| 182 |
+
"learning_rate": 9.939652198703785e-06,
|
| 183 |
+
"loss": 1.6792,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08,
|
| 188 |
+
"grad_norm": 2.1648776531219482,
|
| 189 |
+
"learning_rate": 9.93135668670091e-06,
|
| 190 |
+
"loss": 1.6625,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.09,
|
| 195 |
+
"grad_norm": 2.1209850311279297,
|
| 196 |
+
"learning_rate": 9.92253105124993e-06,
|
| 197 |
+
"loss": 1.7057,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.09,
|
| 202 |
+
"grad_norm": 2.2777392864227295,
|
| 203 |
+
"learning_rate": 9.91317624111132e-06,
|
| 204 |
+
"loss": 1.6052,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.09,
|
| 209 |
+
"grad_norm": 2.1739561557769775,
|
| 210 |
+
"learning_rate": 9.903293261932106e-06,
|
| 211 |
+
"loss": 1.6139,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1,
|
| 216 |
+
"grad_norm": 2.4518871307373047,
|
| 217 |
+
"learning_rate": 9.89288317613777e-06,
|
| 218 |
+
"loss": 1.6759,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"grad_norm": 1.795519471168518,
|
| 224 |
+
"learning_rate": 9.881947102818036e-06,
|
| 225 |
+
"loss": 1.7036,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1,
|
| 230 |
+
"grad_norm": 2.150223731994629,
|
| 231 |
+
"learning_rate": 9.870486217606557e-06,
|
| 232 |
+
"loss": 1.6469,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.11,
|
| 237 |
+
"grad_norm": 1.91805899143219,
|
| 238 |
+
"learning_rate": 9.858501752554548e-06,
|
| 239 |
+
"loss": 1.6353,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.11,
|
| 244 |
+
"grad_norm": 1.8129810094833374,
|
| 245 |
+
"learning_rate": 9.845994995998332e-06,
|
| 246 |
+
"loss": 1.6551,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11,
|
| 251 |
+
"grad_norm": 2.1308679580688477,
|
| 252 |
+
"learning_rate": 9.83296729242084e-06,
|
| 253 |
+
"loss": 1.617,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.11,
|
| 258 |
+
"grad_norm": 1.8321012258529663,
|
| 259 |
+
"learning_rate": 9.819420042307091e-06,
|
| 260 |
+
"loss": 1.6213,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"grad_norm": 1.9112164974212646,
|
| 266 |
+
"learning_rate": 9.805354701993624e-06,
|
| 267 |
+
"loss": 1.6245,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.12,
|
| 272 |
+
"grad_norm": 2.1160471439361572,
|
| 273 |
+
"learning_rate": 9.79077278351195e-06,
|
| 274 |
+
"loss": 1.6405,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.12,
|
| 279 |
+
"grad_norm": 2.6318371295928955,
|
| 280 |
+
"learning_rate": 9.77567585442601e-06,
|
| 281 |
+
"loss": 1.6234,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.13,
|
| 286 |
+
"grad_norm": 3.238373279571533,
|
| 287 |
+
"learning_rate": 9.76006553766365e-06,
|
| 288 |
+
"loss": 1.6452,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.13,
|
| 293 |
+
"grad_norm": 2.056736469268799,
|
| 294 |
+
"learning_rate": 9.743943511342168e-06,
|
| 295 |
+
"loss": 1.679,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.13,
|
| 300 |
+
"grad_norm": 2.000826358795166,
|
| 301 |
+
"learning_rate": 9.727311508587907e-06,
|
| 302 |
+
"loss": 1.6904,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14,
|
| 307 |
+
"grad_norm": 2.089482069015503,
|
| 308 |
+
"learning_rate": 9.710171317349946e-06,
|
| 309 |
+
"loss": 1.62,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.14,
|
| 314 |
+
"grad_norm": 2.5748705863952637,
|
| 315 |
+
"learning_rate": 9.692524780207897e-06,
|
| 316 |
+
"loss": 1.6669,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.14,
|
| 321 |
+
"grad_norm": 1.9039987325668335,
|
| 322 |
+
"learning_rate": 9.674373794173818e-06,
|
| 323 |
+
"loss": 1.6489,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.15,
|
| 328 |
+
"grad_norm": 1.8047181367874146,
|
| 329 |
+
"learning_rate": 9.655720310488298e-06,
|
| 330 |
+
"loss": 1.6227,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15,
|
| 335 |
+
"grad_norm": 2.0552868843078613,
|
| 336 |
+
"learning_rate": 9.636566334410682e-06,
|
| 337 |
+
"loss": 1.5898,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.15,
|
| 342 |
+
"grad_norm": 2.252218008041382,
|
| 343 |
+
"learning_rate": 9.616913925003514e-06,
|
| 344 |
+
"loss": 1.6667,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16,
|
| 349 |
+
"grad_norm": 2.015887498855591,
|
| 350 |
+
"learning_rate": 9.596765194911182e-06,
|
| 351 |
+
"loss": 1.6668,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16,
|
| 356 |
+
"grad_norm": 2.582007884979248,
|
| 357 |
+
"learning_rate": 9.576122310132814e-06,
|
| 358 |
+
"loss": 1.6542,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.16,
|
| 363 |
+
"grad_norm": 1.9070011377334595,
|
| 364 |
+
"learning_rate": 9.554987489789426e-06,
|
| 365 |
+
"loss": 1.691,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.17,
|
| 370 |
+
"grad_norm": 1.9671483039855957,
|
| 371 |
+
"learning_rate": 9.533363005885362e-06,
|
| 372 |
+
"loss": 1.6116,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.17,
|
| 377 |
+
"grad_norm": 2.4808287620544434,
|
| 378 |
+
"learning_rate": 9.511251183064068e-06,
|
| 379 |
+
"loss": 1.6653,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.17,
|
| 384 |
+
"grad_norm": 2.237518548965454,
|
| 385 |
+
"learning_rate": 9.48865439835817e-06,
|
| 386 |
+
"loss": 1.6571,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.18,
|
| 391 |
+
"grad_norm": 2.142627477645874,
|
| 392 |
+
"learning_rate": 9.465575080933959e-06,
|
| 393 |
+
"loss": 1.6247,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.18,
|
| 398 |
+
"grad_norm": 2.0365779399871826,
|
| 399 |
+
"learning_rate": 9.442015711830246e-06,
|
| 400 |
+
"loss": 1.6323,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.18,
|
| 405 |
+
"grad_norm": 2.427443742752075,
|
| 406 |
+
"learning_rate": 9.417978823691652e-06,
|
| 407 |
+
"loss": 1.6646,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.18,
|
| 412 |
+
"grad_norm": 2.014340877532959,
|
| 413 |
+
"learning_rate": 9.393467000496345e-06,
|
| 414 |
+
"loss": 1.5754,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.19,
|
| 419 |
+
"grad_norm": 2.6110949516296387,
|
| 420 |
+
"learning_rate": 9.368482877278264e-06,
|
| 421 |
+
"loss": 1.657,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.19,
|
| 426 |
+
"grad_norm": 2.048231363296509,
|
| 427 |
+
"learning_rate": 9.34302913984385e-06,
|
| 428 |
+
"loss": 1.61,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19,
|
| 433 |
+
"grad_norm": 2.672330379486084,
|
| 434 |
+
"learning_rate": 9.317108524483319e-06,
|
| 435 |
+
"loss": 1.5894,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2,
|
| 440 |
+
"grad_norm": 2.6745121479034424,
|
| 441 |
+
"learning_rate": 9.29072381767651e-06,
|
| 442 |
+
"loss": 1.5623,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2,
|
| 447 |
+
"grad_norm": 2.1490442752838135,
|
| 448 |
+
"learning_rate": 9.26387785579334e-06,
|
| 449 |
+
"loss": 1.6668,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2,
|
| 454 |
+
"grad_norm": 3.805147171020508,
|
| 455 |
+
"learning_rate": 9.236573524788888e-06,
|
| 456 |
+
"loss": 1.6274,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.21,
|
| 461 |
+
"grad_norm": 2.243023157119751,
|
| 462 |
+
"learning_rate": 9.208813759893158e-06,
|
| 463 |
+
"loss": 1.6496,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.21,
|
| 468 |
+
"grad_norm": 2.5260114669799805,
|
| 469 |
+
"learning_rate": 9.180601545295535e-06,
|
| 470 |
+
"loss": 1.623,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21,
|
| 475 |
+
"grad_norm": 2.0329606533050537,
|
| 476 |
+
"learning_rate": 9.151939913823988e-06,
|
| 477 |
+
"loss": 1.5873,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.22,
|
| 482 |
+
"grad_norm": 3.3269598484039307,
|
| 483 |
+
"learning_rate": 9.122831946619038e-06,
|
| 484 |
+
"loss": 1.6327,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.22,
|
| 489 |
+
"grad_norm": 2.1953978538513184,
|
| 490 |
+
"learning_rate": 9.093280772802527e-06,
|
| 491 |
+
"loss": 1.6321,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.22,
|
| 496 |
+
"grad_norm": 3.2001328468322754,
|
| 497 |
+
"learning_rate": 9.063289569141251e-06,
|
| 498 |
+
"loss": 1.6338,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.23,
|
| 503 |
+
"grad_norm": 2.076502799987793,
|
| 504 |
+
"learning_rate": 9.032861559705442e-06,
|
| 505 |
+
"loss": 1.6648,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.23,
|
| 510 |
+
"grad_norm": 2.0800352096557617,
|
| 511 |
+
"learning_rate": 9.002000015522182e-06,
|
| 512 |
+
"loss": 1.5694,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23,
|
| 517 |
+
"grad_norm": 2.0901432037353516,
|
| 518 |
+
"learning_rate": 8.970708254223768e-06,
|
| 519 |
+
"loss": 1.6571,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.24,
|
| 524 |
+
"grad_norm": 3.1389923095703125,
|
| 525 |
+
"learning_rate": 8.938989639691068e-06,
|
| 526 |
+
"loss": 1.6151,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.24,
|
| 531 |
+
"grad_norm": 2.0514352321624756,
|
| 532 |
+
"learning_rate": 8.90684758169189e-06,
|
| 533 |
+
"loss": 1.618,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.24,
|
| 538 |
+
"grad_norm": 1.9462100267410278,
|
| 539 |
+
"learning_rate": 8.87428553551445e-06,
|
| 540 |
+
"loss": 1.6367,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.25,
|
| 545 |
+
"grad_norm": 2.2343838214874268,
|
| 546 |
+
"learning_rate": 8.841307001595904e-06,
|
| 547 |
+
"loss": 1.6321,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.25,
|
| 552 |
+
"grad_norm": 2.6064207553863525,
|
| 553 |
+
"learning_rate": 8.807915525146065e-06,
|
| 554 |
+
"loss": 1.5913,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.25,
|
| 559 |
+
"grad_norm": 2.589186191558838,
|
| 560 |
+
"learning_rate": 8.774114695766286e-06,
|
| 561 |
+
"loss": 1.6,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.25,
|
| 566 |
+
"grad_norm": 2.0082924365997314,
|
| 567 |
+
"learning_rate": 8.739908147063576e-06,
|
| 568 |
+
"loss": 1.6266,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.26,
|
| 573 |
+
"grad_norm": 1.9739817380905151,
|
| 574 |
+
"learning_rate": 8.705299556259986e-06,
|
| 575 |
+
"loss": 1.5926,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.26,
|
| 580 |
+
"grad_norm": 2.9566433429718018,
|
| 581 |
+
"learning_rate": 8.670292643797302e-06,
|
| 582 |
+
"loss": 1.624,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.26,
|
| 587 |
+
"grad_norm": 2.10595703125,
|
| 588 |
+
"learning_rate": 8.634891172937102e-06,
|
| 589 |
+
"loss": 1.6437,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.27,
|
| 594 |
+
"grad_norm": 1.7080891132354736,
|
| 595 |
+
"learning_rate": 8.599098949356201e-06,
|
| 596 |
+
"loss": 1.6131,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.27,
|
| 601 |
+
"grad_norm": 2.358856678009033,
|
| 602 |
+
"learning_rate": 8.562919820737537e-06,
|
| 603 |
+
"loss": 1.5748,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.27,
|
| 608 |
+
"grad_norm": 2.030383825302124,
|
| 609 |
+
"learning_rate": 8.526357676356538e-06,
|
| 610 |
+
"loss": 1.6389,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.28,
|
| 615 |
+
"grad_norm": 2.3567280769348145,
|
| 616 |
+
"learning_rate": 8.489416446663037e-06,
|
| 617 |
+
"loss": 1.6288,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.28,
|
| 622 |
+
"grad_norm": 2.1183040142059326,
|
| 623 |
+
"learning_rate": 8.452100102858734e-06,
|
| 624 |
+
"loss": 1.5929,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.28,
|
| 629 |
+
"grad_norm": 2.467944860458374,
|
| 630 |
+
"learning_rate": 8.414412656470297e-06,
|
| 631 |
+
"loss": 1.5579,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.29,
|
| 636 |
+
"grad_norm": 2.200274705886841,
|
| 637 |
+
"learning_rate": 8.376358158918114e-06,
|
| 638 |
+
"loss": 1.587,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.29,
|
| 643 |
+
"grad_norm": 2.3279902935028076,
|
| 644 |
+
"learning_rate": 8.33794070108077e-06,
|
| 645 |
+
"loss": 1.6496,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.29,
|
| 650 |
+
"grad_norm": 2.7403910160064697,
|
| 651 |
+
"learning_rate": 8.299164412855268e-06,
|
| 652 |
+
"loss": 1.5665,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.3,
|
| 657 |
+
"grad_norm": 2.5097343921661377,
|
| 658 |
+
"learning_rate": 8.260033462713073e-06,
|
| 659 |
+
"loss": 1.6245,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3,
|
| 664 |
+
"grad_norm": 2.2657604217529297,
|
| 665 |
+
"learning_rate": 8.22055205725199e-06,
|
| 666 |
+
"loss": 1.5785,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3,
|
| 671 |
+
"grad_norm": 2.4038476943969727,
|
| 672 |
+
"learning_rate": 8.180724440743957e-06,
|
| 673 |
+
"loss": 1.6912,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.31,
|
| 678 |
+
"grad_norm": 2.811049461364746,
|
| 679 |
+
"learning_rate": 8.14055489467878e-06,
|
| 680 |
+
"loss": 1.6059,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.31,
|
| 685 |
+
"grad_norm": 2.474153518676758,
|
| 686 |
+
"learning_rate": 8.100047737303877e-06,
|
| 687 |
+
"loss": 1.6423,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.31,
|
| 692 |
+
"grad_norm": 2.351736307144165,
|
| 693 |
+
"learning_rate": 8.059207323160057e-06,
|
| 694 |
+
"loss": 1.6199,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.32,
|
| 699 |
+
"grad_norm": 2.3526997566223145,
|
| 700 |
+
"learning_rate": 8.018038042613407e-06,
|
| 701 |
+
"loss": 1.5856,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.32,
|
| 706 |
+
"grad_norm": 2.075406789779663,
|
| 707 |
+
"learning_rate": 7.97654432138333e-06,
|
| 708 |
+
"loss": 1.5901,
|
| 709 |
+
"step": 100
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 1.0,
|
| 713 |
+
"max_steps": 313,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 1,
|
| 716 |
+
"save_steps": 50,
|
| 717 |
+
"total_flos": 104692442988544.0,
|
| 718 |
+
"train_batch_size": 1,
|
| 719 |
+
"trial_name": null,
|
| 720 |
+
"trial_params": null
|
| 721 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45889d4d7acf868bd2e29b69a995aa63651cb92ff4aa6b4d21447f675a78dfa2
|
| 3 |
+
size 7352
|
checkpoint-100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-150/added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image>": 151646,
|
| 3 |
+
"<|endoftext|>": 151643,
|
| 4 |
+
"<|im_end|>": 151645,
|
| 5 |
+
"<|im_start|>": 151644
|
| 6 |
+
}
|
checkpoint-150/config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/project/mlmlongvideo/checkpoints/pure_text_extend_llava_qwen/checkpoint-200/",
|
| 3 |
+
"add_faster_video": false,
|
| 4 |
+
"add_time_instruction": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlavaQwenForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 151643,
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": true,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"ignore_index": -100,
|
| 16 |
+
"image_aspect_ratio": "anyres_max_9",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": [
|
| 19 |
+
[
|
| 20 |
+
384,
|
| 21 |
+
384
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
384,
|
| 25 |
+
768
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
384,
|
| 29 |
+
1152
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
384,
|
| 33 |
+
1536
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
384,
|
| 37 |
+
1920
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
384,
|
| 41 |
+
2304
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
768,
|
| 45 |
+
384
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
768,
|
| 49 |
+
768
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
768,
|
| 53 |
+
1152
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
768,
|
| 57 |
+
1536
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
768,
|
| 61 |
+
1920
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
768,
|
| 65 |
+
2304
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
1152,
|
| 69 |
+
384
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
1152,
|
| 73 |
+
768
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
1152,
|
| 77 |
+
1152
|
| 78 |
+
],
|
| 79 |
+
[
|
| 80 |
+
1152,
|
| 81 |
+
1536
|
| 82 |
+
],
|
| 83 |
+
[
|
| 84 |
+
1152,
|
| 85 |
+
1920
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
1152,
|
| 89 |
+
2304
|
| 90 |
+
],
|
| 91 |
+
[
|
| 92 |
+
1536,
|
| 93 |
+
384
|
| 94 |
+
],
|
| 95 |
+
[
|
| 96 |
+
1536,
|
| 97 |
+
768
|
| 98 |
+
],
|
| 99 |
+
[
|
| 100 |
+
1536,
|
| 101 |
+
1152
|
| 102 |
+
],
|
| 103 |
+
[
|
| 104 |
+
1536,
|
| 105 |
+
1536
|
| 106 |
+
],
|
| 107 |
+
[
|
| 108 |
+
1536,
|
| 109 |
+
1920
|
| 110 |
+
],
|
| 111 |
+
[
|
| 112 |
+
1536,
|
| 113 |
+
2304
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
1920,
|
| 117 |
+
384
|
| 118 |
+
],
|
| 119 |
+
[
|
| 120 |
+
1920,
|
| 121 |
+
768
|
| 122 |
+
],
|
| 123 |
+
[
|
| 124 |
+
1920,
|
| 125 |
+
1152
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
1920,
|
| 129 |
+
1536
|
| 130 |
+
],
|
| 131 |
+
[
|
| 132 |
+
1920,
|
| 133 |
+
1920
|
| 134 |
+
],
|
| 135 |
+
[
|
| 136 |
+
1920,
|
| 137 |
+
2304
|
| 138 |
+
],
|
| 139 |
+
[
|
| 140 |
+
2304,
|
| 141 |
+
384
|
| 142 |
+
],
|
| 143 |
+
[
|
| 144 |
+
2304,
|
| 145 |
+
768
|
| 146 |
+
],
|
| 147 |
+
[
|
| 148 |
+
2304,
|
| 149 |
+
1152
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
2304,
|
| 153 |
+
1536
|
| 154 |
+
],
|
| 155 |
+
[
|
| 156 |
+
2304,
|
| 157 |
+
1920
|
| 158 |
+
],
|
| 159 |
+
[
|
| 160 |
+
2304,
|
| 161 |
+
2304
|
| 162 |
+
]
|
| 163 |
+
],
|
| 164 |
+
"image_split_resolution": null,
|
| 165 |
+
"image_token_index": 151646,
|
| 166 |
+
"initializer_range": 0.02,
|
| 167 |
+
"intermediate_size": 18944,
|
| 168 |
+
"max_position_embeddings": 32768,
|
| 169 |
+
"max_window_layers": 28,
|
| 170 |
+
"mm_hidden_size": 1152,
|
| 171 |
+
"mm_newline_position": "grid",
|
| 172 |
+
"mm_patch_merge_type": "spatial_unpad",
|
| 173 |
+
"mm_projector_lr": null,
|
| 174 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 175 |
+
"mm_resampler_type": null,
|
| 176 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 177 |
+
"mm_spatial_pool_stride": 2,
|
| 178 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
| 179 |
+
"mm_use_im_patch_token": false,
|
| 180 |
+
"mm_use_im_start_end": false,
|
| 181 |
+
"mm_vision_select_feature": "patch",
|
| 182 |
+
"mm_vision_select_layer": -2,
|
| 183 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
| 184 |
+
"mm_vision_tower_lr": 2e-06,
|
| 185 |
+
"model_type": "llava",
|
| 186 |
+
"num_attention_heads": 28,
|
| 187 |
+
"num_hidden_layers": 28,
|
| 188 |
+
"num_key_value_heads": 4,
|
| 189 |
+
"pos_skipping_range": 4096,
|
| 190 |
+
"projector_hidden_act": "gelu",
|
| 191 |
+
"rms_norm_eps": 1e-06,
|
| 192 |
+
"rope_scaling": null,
|
| 193 |
+
"rope_theta": 1000000000.0,
|
| 194 |
+
"sliding_window": 131072,
|
| 195 |
+
"text_config": {
|
| 196 |
+
"model_type": "llama",
|
| 197 |
+
"vocab_size": 152064
|
| 198 |
+
},
|
| 199 |
+
"tie_word_embeddings": false,
|
| 200 |
+
"tokenizer_model_max_length": 28000,
|
| 201 |
+
"tokenizer_padding_side": "right",
|
| 202 |
+
"torch_dtype": "bfloat16",
|
| 203 |
+
"transformers_version": "4.40.0.dev0",
|
| 204 |
+
"use_cache": false,
|
| 205 |
+
"use_mm_proj": true,
|
| 206 |
+
"use_pos_skipping": false,
|
| 207 |
+
"use_sliding_window": false,
|
| 208 |
+
"vision_config": {
|
| 209 |
+
"hidden_size": 1024,
|
| 210 |
+
"image_size": 336,
|
| 211 |
+
"intermediate_size": 4096,
|
| 212 |
+
"model_type": "clip_vision_model",
|
| 213 |
+
"num_attention_heads": 16,
|
| 214 |
+
"num_hidden_layers": 24,
|
| 215 |
+
"patch_size": 14,
|
| 216 |
+
"projection_dim": 768,
|
| 217 |
+
"vocab_size": 32000
|
| 218 |
+
},
|
| 219 |
+
"vision_feature_layer": -2,
|
| 220 |
+
"vision_feature_select_strategy": "default",
|
| 221 |
+
"vision_tower_pretrained": null
|
| 222 |
+
}
|
checkpoint-150/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.40.0.dev0"
|
| 14 |
+
}
|
checkpoint-150/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-150/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8172295aa7b542fbc1073e3c4803c75b8e5d9b4fcfed62d29adde3adb745cdb3
|
| 3 |
+
size 4877668032
|
checkpoint-150/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fd5a0fb1591abf10ef87e34f5c55e526f8b8cf61898d71dd4906c0c49cf9ada
|
| 3 |
+
size 4932751008
|
checkpoint-150/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1884f9b61d408ccc92bedee7af6f6d956e9ce5ca6f0adadef237a124e588f077
|
| 3 |
+
size 4994571904
|
checkpoint-150/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9689b4081463464d8e0f8057e53a0e03906210b533a949ddfb7f559edd913e5
|
| 3 |
+
size 1255812224
|
checkpoint-150/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16060697664
|
| 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.image_newline": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 308 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 320 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.norm.weight": "model-00003-of-00004.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 701 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 702 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 703 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 704 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 705 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 706 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 707 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 708 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 709 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 710 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 711 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 712 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 713 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 714 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 715 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 716 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 717 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 718 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 719 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 720 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 721 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 722 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 723 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 724 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 725 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 726 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 727 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 728 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 729 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 730 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 731 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 732 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 733 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 734 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 735 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 736 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 737 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 738 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 739 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 740 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 741 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 742 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 743 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 744 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 745 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 746 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 747 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 748 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 749 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 750 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 751 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 752 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 753 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 754 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 755 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 756 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 757 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 758 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 759 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 760 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 761 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 762 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 763 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 764 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 765 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 766 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 767 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 768 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 769 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
|
| 770 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
|
| 771 |
+
}
|
| 772 |
+
}
|
checkpoint-150/special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
checkpoint-150/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-150/tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<image>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"additional_special_tokens": [
|
| 38 |
+
"<|im_start|>",
|
| 39 |
+
"<|im_end|>"
|
| 40 |
+
],
|
| 41 |
+
"bos_token": null,
|
| 42 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 43 |
+
"clean_up_tokenization_spaces": false,
|
| 44 |
+
"eos_token": "<|im_end|>",
|
| 45 |
+
"errors": "replace",
|
| 46 |
+
"model_max_length": 28000,
|
| 47 |
+
"pad_token": "<|endoftext|>",
|
| 48 |
+
"padding_side": "right",
|
| 49 |
+
"processor_class": "LlavaProcessor",
|
| 50 |
+
"split_special_tokens": false,
|
| 51 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 52 |
+
"unk_token": null
|
| 53 |
+
}
|
checkpoint-150/trainer_state.json
ADDED
|
@@ -0,0 +1,1071 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4778972520908005,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 150,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 10.092560768127441,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 1.9497,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 8.963287353515625,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 1.951,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 9.27600383758545,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 1.9345,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 5.632405757904053,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 1.9157,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 5.668580055236816,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 1.9026,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 3.8046553134918213,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 1.8923,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"grad_norm": 4.357985973358154,
|
| 56 |
+
"learning_rate": 7e-06,
|
| 57 |
+
"loss": 1.8241,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 4.685062885284424,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 1.8467,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"grad_norm": 4.768229961395264,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 1.8199,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03,
|
| 76 |
+
"grad_norm": 4.796407699584961,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 1.8374,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"grad_norm": 5.7536139488220215,
|
| 84 |
+
"learning_rate": 9.999731248679734e-06,
|
| 85 |
+
"loss": 1.779,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04,
|
| 90 |
+
"grad_norm": 4.202663898468018,
|
| 91 |
+
"learning_rate": 9.99892502360984e-06,
|
| 92 |
+
"loss": 1.7579,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"grad_norm": 2.9114131927490234,
|
| 98 |
+
"learning_rate": 9.99758141145994e-06,
|
| 99 |
+
"loss": 1.7433,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.04,
|
| 104 |
+
"grad_norm": 2.3823723793029785,
|
| 105 |
+
"learning_rate": 9.995700556669052e-06,
|
| 106 |
+
"loss": 1.7212,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05,
|
| 111 |
+
"grad_norm": 2.3254876136779785,
|
| 112 |
+
"learning_rate": 9.993282661430058e-06,
|
| 113 |
+
"loss": 1.7218,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.05,
|
| 118 |
+
"grad_norm": 2.053166151046753,
|
| 119 |
+
"learning_rate": 9.990327985667972e-06,
|
| 120 |
+
"loss": 1.7256,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.05,
|
| 125 |
+
"grad_norm": 2.3782012462615967,
|
| 126 |
+
"learning_rate": 9.986836847012001e-06,
|
| 127 |
+
"loss": 1.713,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06,
|
| 132 |
+
"grad_norm": 2.1311683654785156,
|
| 133 |
+
"learning_rate": 9.98280962076139e-06,
|
| 134 |
+
"loss": 1.6785,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"grad_norm": 2.325747489929199,
|
| 140 |
+
"learning_rate": 9.978246739845095e-06,
|
| 141 |
+
"loss": 1.7167,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.06,
|
| 146 |
+
"grad_norm": 2.1330366134643555,
|
| 147 |
+
"learning_rate": 9.973148694775217e-06,
|
| 148 |
+
"loss": 1.676,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07,
|
| 153 |
+
"grad_norm": 2.2632806301116943,
|
| 154 |
+
"learning_rate": 9.967516033594295e-06,
|
| 155 |
+
"loss": 1.7033,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.07,
|
| 160 |
+
"grad_norm": 2.6582744121551514,
|
| 161 |
+
"learning_rate": 9.961349361816384e-06,
|
| 162 |
+
"loss": 1.6957,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.07,
|
| 167 |
+
"grad_norm": 1.9663337469100952,
|
| 168 |
+
"learning_rate": 9.954649342361952e-06,
|
| 169 |
+
"loss": 1.6729,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08,
|
| 174 |
+
"grad_norm": 2.2557435035705566,
|
| 175 |
+
"learning_rate": 9.947416695486633e-06,
|
| 176 |
+
"loss": 1.6399,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"grad_norm": 2.090054512023926,
|
| 182 |
+
"learning_rate": 9.939652198703785e-06,
|
| 183 |
+
"loss": 1.6792,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08,
|
| 188 |
+
"grad_norm": 2.1648776531219482,
|
| 189 |
+
"learning_rate": 9.93135668670091e-06,
|
| 190 |
+
"loss": 1.6625,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.09,
|
| 195 |
+
"grad_norm": 2.1209850311279297,
|
| 196 |
+
"learning_rate": 9.92253105124993e-06,
|
| 197 |
+
"loss": 1.7057,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.09,
|
| 202 |
+
"grad_norm": 2.2777392864227295,
|
| 203 |
+
"learning_rate": 9.91317624111132e-06,
|
| 204 |
+
"loss": 1.6052,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.09,
|
| 209 |
+
"grad_norm": 2.1739561557769775,
|
| 210 |
+
"learning_rate": 9.903293261932106e-06,
|
| 211 |
+
"loss": 1.6139,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1,
|
| 216 |
+
"grad_norm": 2.4518871307373047,
|
| 217 |
+
"learning_rate": 9.89288317613777e-06,
|
| 218 |
+
"loss": 1.6759,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"grad_norm": 1.795519471168518,
|
| 224 |
+
"learning_rate": 9.881947102818036e-06,
|
| 225 |
+
"loss": 1.7036,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1,
|
| 230 |
+
"grad_norm": 2.150223731994629,
|
| 231 |
+
"learning_rate": 9.870486217606557e-06,
|
| 232 |
+
"loss": 1.6469,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.11,
|
| 237 |
+
"grad_norm": 1.91805899143219,
|
| 238 |
+
"learning_rate": 9.858501752554548e-06,
|
| 239 |
+
"loss": 1.6353,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.11,
|
| 244 |
+
"grad_norm": 1.8129810094833374,
|
| 245 |
+
"learning_rate": 9.845994995998332e-06,
|
| 246 |
+
"loss": 1.6551,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11,
|
| 251 |
+
"grad_norm": 2.1308679580688477,
|
| 252 |
+
"learning_rate": 9.83296729242084e-06,
|
| 253 |
+
"loss": 1.617,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.11,
|
| 258 |
+
"grad_norm": 1.8321012258529663,
|
| 259 |
+
"learning_rate": 9.819420042307091e-06,
|
| 260 |
+
"loss": 1.6213,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"grad_norm": 1.9112164974212646,
|
| 266 |
+
"learning_rate": 9.805354701993624e-06,
|
| 267 |
+
"loss": 1.6245,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.12,
|
| 272 |
+
"grad_norm": 2.1160471439361572,
|
| 273 |
+
"learning_rate": 9.79077278351195e-06,
|
| 274 |
+
"loss": 1.6405,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.12,
|
| 279 |
+
"grad_norm": 2.6318371295928955,
|
| 280 |
+
"learning_rate": 9.77567585442601e-06,
|
| 281 |
+
"loss": 1.6234,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.13,
|
| 286 |
+
"grad_norm": 3.238373279571533,
|
| 287 |
+
"learning_rate": 9.76006553766365e-06,
|
| 288 |
+
"loss": 1.6452,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.13,
|
| 293 |
+
"grad_norm": 2.056736469268799,
|
| 294 |
+
"learning_rate": 9.743943511342168e-06,
|
| 295 |
+
"loss": 1.679,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.13,
|
| 300 |
+
"grad_norm": 2.000826358795166,
|
| 301 |
+
"learning_rate": 9.727311508587907e-06,
|
| 302 |
+
"loss": 1.6904,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14,
|
| 307 |
+
"grad_norm": 2.089482069015503,
|
| 308 |
+
"learning_rate": 9.710171317349946e-06,
|
| 309 |
+
"loss": 1.62,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.14,
|
| 314 |
+
"grad_norm": 2.5748705863952637,
|
| 315 |
+
"learning_rate": 9.692524780207897e-06,
|
| 316 |
+
"loss": 1.6669,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.14,
|
| 321 |
+
"grad_norm": 1.9039987325668335,
|
| 322 |
+
"learning_rate": 9.674373794173818e-06,
|
| 323 |
+
"loss": 1.6489,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.15,
|
| 328 |
+
"grad_norm": 1.8047181367874146,
|
| 329 |
+
"learning_rate": 9.655720310488298e-06,
|
| 330 |
+
"loss": 1.6227,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15,
|
| 335 |
+
"grad_norm": 2.0552868843078613,
|
| 336 |
+
"learning_rate": 9.636566334410682e-06,
|
| 337 |
+
"loss": 1.5898,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.15,
|
| 342 |
+
"grad_norm": 2.252218008041382,
|
| 343 |
+
"learning_rate": 9.616913925003514e-06,
|
| 344 |
+
"loss": 1.6667,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16,
|
| 349 |
+
"grad_norm": 2.015887498855591,
|
| 350 |
+
"learning_rate": 9.596765194911182e-06,
|
| 351 |
+
"loss": 1.6668,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16,
|
| 356 |
+
"grad_norm": 2.582007884979248,
|
| 357 |
+
"learning_rate": 9.576122310132814e-06,
|
| 358 |
+
"loss": 1.6542,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.16,
|
| 363 |
+
"grad_norm": 1.9070011377334595,
|
| 364 |
+
"learning_rate": 9.554987489789426e-06,
|
| 365 |
+
"loss": 1.691,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.17,
|
| 370 |
+
"grad_norm": 1.9671483039855957,
|
| 371 |
+
"learning_rate": 9.533363005885362e-06,
|
| 372 |
+
"loss": 1.6116,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.17,
|
| 377 |
+
"grad_norm": 2.4808287620544434,
|
| 378 |
+
"learning_rate": 9.511251183064068e-06,
|
| 379 |
+
"loss": 1.6653,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.17,
|
| 384 |
+
"grad_norm": 2.237518548965454,
|
| 385 |
+
"learning_rate": 9.48865439835817e-06,
|
| 386 |
+
"loss": 1.6571,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.18,
|
| 391 |
+
"grad_norm": 2.142627477645874,
|
| 392 |
+
"learning_rate": 9.465575080933959e-06,
|
| 393 |
+
"loss": 1.6247,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.18,
|
| 398 |
+
"grad_norm": 2.0365779399871826,
|
| 399 |
+
"learning_rate": 9.442015711830246e-06,
|
| 400 |
+
"loss": 1.6323,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.18,
|
| 405 |
+
"grad_norm": 2.427443742752075,
|
| 406 |
+
"learning_rate": 9.417978823691652e-06,
|
| 407 |
+
"loss": 1.6646,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.18,
|
| 412 |
+
"grad_norm": 2.014340877532959,
|
| 413 |
+
"learning_rate": 9.393467000496345e-06,
|
| 414 |
+
"loss": 1.5754,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.19,
|
| 419 |
+
"grad_norm": 2.6110949516296387,
|
| 420 |
+
"learning_rate": 9.368482877278264e-06,
|
| 421 |
+
"loss": 1.657,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.19,
|
| 426 |
+
"grad_norm": 2.048231363296509,
|
| 427 |
+
"learning_rate": 9.34302913984385e-06,
|
| 428 |
+
"loss": 1.61,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19,
|
| 433 |
+
"grad_norm": 2.672330379486084,
|
| 434 |
+
"learning_rate": 9.317108524483319e-06,
|
| 435 |
+
"loss": 1.5894,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2,
|
| 440 |
+
"grad_norm": 2.6745121479034424,
|
| 441 |
+
"learning_rate": 9.29072381767651e-06,
|
| 442 |
+
"loss": 1.5623,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2,
|
| 447 |
+
"grad_norm": 2.1490442752838135,
|
| 448 |
+
"learning_rate": 9.26387785579334e-06,
|
| 449 |
+
"loss": 1.6668,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2,
|
| 454 |
+
"grad_norm": 3.805147171020508,
|
| 455 |
+
"learning_rate": 9.236573524788888e-06,
|
| 456 |
+
"loss": 1.6274,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.21,
|
| 461 |
+
"grad_norm": 2.243023157119751,
|
| 462 |
+
"learning_rate": 9.208813759893158e-06,
|
| 463 |
+
"loss": 1.6496,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.21,
|
| 468 |
+
"grad_norm": 2.5260114669799805,
|
| 469 |
+
"learning_rate": 9.180601545295535e-06,
|
| 470 |
+
"loss": 1.623,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21,
|
| 475 |
+
"grad_norm": 2.0329606533050537,
|
| 476 |
+
"learning_rate": 9.151939913823988e-06,
|
| 477 |
+
"loss": 1.5873,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.22,
|
| 482 |
+
"grad_norm": 3.3269598484039307,
|
| 483 |
+
"learning_rate": 9.122831946619038e-06,
|
| 484 |
+
"loss": 1.6327,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.22,
|
| 489 |
+
"grad_norm": 2.1953978538513184,
|
| 490 |
+
"learning_rate": 9.093280772802527e-06,
|
| 491 |
+
"loss": 1.6321,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.22,
|
| 496 |
+
"grad_norm": 3.2001328468322754,
|
| 497 |
+
"learning_rate": 9.063289569141251e-06,
|
| 498 |
+
"loss": 1.6338,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.23,
|
| 503 |
+
"grad_norm": 2.076502799987793,
|
| 504 |
+
"learning_rate": 9.032861559705442e-06,
|
| 505 |
+
"loss": 1.6648,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.23,
|
| 510 |
+
"grad_norm": 2.0800352096557617,
|
| 511 |
+
"learning_rate": 9.002000015522182e-06,
|
| 512 |
+
"loss": 1.5694,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23,
|
| 517 |
+
"grad_norm": 2.0901432037353516,
|
| 518 |
+
"learning_rate": 8.970708254223768e-06,
|
| 519 |
+
"loss": 1.6571,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.24,
|
| 524 |
+
"grad_norm": 3.1389923095703125,
|
| 525 |
+
"learning_rate": 8.938989639691068e-06,
|
| 526 |
+
"loss": 1.6151,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.24,
|
| 531 |
+
"grad_norm": 2.0514352321624756,
|
| 532 |
+
"learning_rate": 8.90684758169189e-06,
|
| 533 |
+
"loss": 1.618,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.24,
|
| 538 |
+
"grad_norm": 1.9462100267410278,
|
| 539 |
+
"learning_rate": 8.87428553551445e-06,
|
| 540 |
+
"loss": 1.6367,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.25,
|
| 545 |
+
"grad_norm": 2.2343838214874268,
|
| 546 |
+
"learning_rate": 8.841307001595904e-06,
|
| 547 |
+
"loss": 1.6321,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.25,
|
| 552 |
+
"grad_norm": 2.6064207553863525,
|
| 553 |
+
"learning_rate": 8.807915525146065e-06,
|
| 554 |
+
"loss": 1.5913,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.25,
|
| 559 |
+
"grad_norm": 2.589186191558838,
|
| 560 |
+
"learning_rate": 8.774114695766286e-06,
|
| 561 |
+
"loss": 1.6,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.25,
|
| 566 |
+
"grad_norm": 2.0082924365997314,
|
| 567 |
+
"learning_rate": 8.739908147063576e-06,
|
| 568 |
+
"loss": 1.6266,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.26,
|
| 573 |
+
"grad_norm": 1.9739817380905151,
|
| 574 |
+
"learning_rate": 8.705299556259986e-06,
|
| 575 |
+
"loss": 1.5926,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.26,
|
| 580 |
+
"grad_norm": 2.9566433429718018,
|
| 581 |
+
"learning_rate": 8.670292643797302e-06,
|
| 582 |
+
"loss": 1.624,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.26,
|
| 587 |
+
"grad_norm": 2.10595703125,
|
| 588 |
+
"learning_rate": 8.634891172937102e-06,
|
| 589 |
+
"loss": 1.6437,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.27,
|
| 594 |
+
"grad_norm": 1.7080891132354736,
|
| 595 |
+
"learning_rate": 8.599098949356201e-06,
|
| 596 |
+
"loss": 1.6131,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.27,
|
| 601 |
+
"grad_norm": 2.358856678009033,
|
| 602 |
+
"learning_rate": 8.562919820737537e-06,
|
| 603 |
+
"loss": 1.5748,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.27,
|
| 608 |
+
"grad_norm": 2.030383825302124,
|
| 609 |
+
"learning_rate": 8.526357676356538e-06,
|
| 610 |
+
"loss": 1.6389,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.28,
|
| 615 |
+
"grad_norm": 2.3567280769348145,
|
| 616 |
+
"learning_rate": 8.489416446663037e-06,
|
| 617 |
+
"loss": 1.6288,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.28,
|
| 622 |
+
"grad_norm": 2.1183040142059326,
|
| 623 |
+
"learning_rate": 8.452100102858734e-06,
|
| 624 |
+
"loss": 1.5929,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.28,
|
| 629 |
+
"grad_norm": 2.467944860458374,
|
| 630 |
+
"learning_rate": 8.414412656470297e-06,
|
| 631 |
+
"loss": 1.5579,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.29,
|
| 636 |
+
"grad_norm": 2.200274705886841,
|
| 637 |
+
"learning_rate": 8.376358158918114e-06,
|
| 638 |
+
"loss": 1.587,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.29,
|
| 643 |
+
"grad_norm": 2.3279902935028076,
|
| 644 |
+
"learning_rate": 8.33794070108077e-06,
|
| 645 |
+
"loss": 1.6496,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.29,
|
| 650 |
+
"grad_norm": 2.7403910160064697,
|
| 651 |
+
"learning_rate": 8.299164412855268e-06,
|
| 652 |
+
"loss": 1.5665,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.3,
|
| 657 |
+
"grad_norm": 2.5097343921661377,
|
| 658 |
+
"learning_rate": 8.260033462713073e-06,
|
| 659 |
+
"loss": 1.6245,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3,
|
| 664 |
+
"grad_norm": 2.2657604217529297,
|
| 665 |
+
"learning_rate": 8.22055205725199e-06,
|
| 666 |
+
"loss": 1.5785,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3,
|
| 671 |
+
"grad_norm": 2.4038476943969727,
|
| 672 |
+
"learning_rate": 8.180724440743957e-06,
|
| 673 |
+
"loss": 1.6912,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.31,
|
| 678 |
+
"grad_norm": 2.811049461364746,
|
| 679 |
+
"learning_rate": 8.14055489467878e-06,
|
| 680 |
+
"loss": 1.6059,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.31,
|
| 685 |
+
"grad_norm": 2.474153518676758,
|
| 686 |
+
"learning_rate": 8.100047737303877e-06,
|
| 687 |
+
"loss": 1.6423,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.31,
|
| 692 |
+
"grad_norm": 2.351736307144165,
|
| 693 |
+
"learning_rate": 8.059207323160057e-06,
|
| 694 |
+
"loss": 1.6199,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.32,
|
| 699 |
+
"grad_norm": 2.3526997566223145,
|
| 700 |
+
"learning_rate": 8.018038042613407e-06,
|
| 701 |
+
"loss": 1.5856,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.32,
|
| 706 |
+
"grad_norm": 2.075406789779663,
|
| 707 |
+
"learning_rate": 7.97654432138333e-06,
|
| 708 |
+
"loss": 1.5901,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.32,
|
| 713 |
+
"grad_norm": 2.6973438262939453,
|
| 714 |
+
"learning_rate": 7.93473062006677e-06,
|
| 715 |
+
"loss": 1.5696,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.32,
|
| 720 |
+
"grad_norm": 2.6449167728424072,
|
| 721 |
+
"learning_rate": 7.892601433658705e-06,
|
| 722 |
+
"loss": 1.5939,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.33,
|
| 727 |
+
"grad_norm": 2.360849380493164,
|
| 728 |
+
"learning_rate": 7.850161291068915e-06,
|
| 729 |
+
"loss": 1.5449,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.33,
|
| 734 |
+
"grad_norm": 2.467226028442383,
|
| 735 |
+
"learning_rate": 7.807414754635145e-06,
|
| 736 |
+
"loss": 1.5926,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.33,
|
| 741 |
+
"grad_norm": 2.449989080429077,
|
| 742 |
+
"learning_rate": 7.764366419632636e-06,
|
| 743 |
+
"loss": 1.5591,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.34,
|
| 748 |
+
"grad_norm": 5.518803119659424,
|
| 749 |
+
"learning_rate": 7.721020913780137e-06,
|
| 750 |
+
"loss": 1.5406,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.34,
|
| 755 |
+
"grad_norm": 2.6841485500335693,
|
| 756 |
+
"learning_rate": 7.677382896742417e-06,
|
| 757 |
+
"loss": 1.5797,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.34,
|
| 762 |
+
"grad_norm": 2.475085496902466,
|
| 763 |
+
"learning_rate": 7.63345705962935e-06,
|
| 764 |
+
"loss": 1.5653,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.35,
|
| 769 |
+
"grad_norm": 2.3905832767486572,
|
| 770 |
+
"learning_rate": 7.589248124491627e-06,
|
| 771 |
+
"loss": 1.5641,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.35,
|
| 776 |
+
"grad_norm": 2.7013638019561768,
|
| 777 |
+
"learning_rate": 7.544760843813122e-06,
|
| 778 |
+
"loss": 1.5837,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.35,
|
| 783 |
+
"grad_norm": 2.500148296356201,
|
| 784 |
+
"learning_rate": 7.500000000000001e-06,
|
| 785 |
+
"loss": 1.6255,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.36,
|
| 790 |
+
"grad_norm": 2.106887102127075,
|
| 791 |
+
"learning_rate": 7.454970404866612e-06,
|
| 792 |
+
"loss": 1.6069,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.36,
|
| 797 |
+
"grad_norm": 2.1840200424194336,
|
| 798 |
+
"learning_rate": 7.409676899118213e-06,
|
| 799 |
+
"loss": 1.5959,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.36,
|
| 804 |
+
"grad_norm": 5.758022308349609,
|
| 805 |
+
"learning_rate": 7.3641243518305915e-06,
|
| 806 |
+
"loss": 1.616,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.37,
|
| 811 |
+
"grad_norm": 2.24625301361084,
|
| 812 |
+
"learning_rate": 7.318317659926637e-06,
|
| 813 |
+
"loss": 1.639,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.37,
|
| 818 |
+
"grad_norm": 3.8651440143585205,
|
| 819 |
+
"learning_rate": 7.272261747649922e-06,
|
| 820 |
+
"loss": 1.6287,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.37,
|
| 825 |
+
"grad_norm": 1.9262839555740356,
|
| 826 |
+
"learning_rate": 7.225961566035335e-06,
|
| 827 |
+
"loss": 1.5851,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.38,
|
| 832 |
+
"grad_norm": 2.4312078952789307,
|
| 833 |
+
"learning_rate": 7.179422092376856e-06,
|
| 834 |
+
"loss": 1.5934,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.38,
|
| 839 |
+
"grad_norm": 2.391693592071533,
|
| 840 |
+
"learning_rate": 7.132648329692478e-06,
|
| 841 |
+
"loss": 1.5719,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.38,
|
| 846 |
+
"grad_norm": 2.10438871383667,
|
| 847 |
+
"learning_rate": 7.085645306186391e-06,
|
| 848 |
+
"loss": 1.5876,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.39,
|
| 853 |
+
"grad_norm": 1.984710931777954,
|
| 854 |
+
"learning_rate": 7.038418074708444e-06,
|
| 855 |
+
"loss": 1.6506,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.39,
|
| 860 |
+
"grad_norm": 2.4563817977905273,
|
| 861 |
+
"learning_rate": 6.990971712210966e-06,
|
| 862 |
+
"loss": 1.5578,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.39,
|
| 867 |
+
"grad_norm": 1.856941819190979,
|
| 868 |
+
"learning_rate": 6.943311319202976e-06,
|
| 869 |
+
"loss": 1.5806,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.4,
|
| 874 |
+
"grad_norm": 2.228983163833618,
|
| 875 |
+
"learning_rate": 6.895442019201898e-06,
|
| 876 |
+
"loss": 1.5639,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.4,
|
| 881 |
+
"grad_norm": 2.9688351154327393,
|
| 882 |
+
"learning_rate": 6.8473689581827585e-06,
|
| 883 |
+
"loss": 1.5939,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.4,
|
| 888 |
+
"grad_norm": 2.028876304626465,
|
| 889 |
+
"learning_rate": 6.7990973040250055e-06,
|
| 890 |
+
"loss": 1.6096,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.4,
|
| 895 |
+
"grad_norm": 2.385794162750244,
|
| 896 |
+
"learning_rate": 6.750632245956954e-06,
|
| 897 |
+
"loss": 1.5617,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.41,
|
| 902 |
+
"grad_norm": 2.0037996768951416,
|
| 903 |
+
"learning_rate": 6.701978993997942e-06,
|
| 904 |
+
"loss": 1.6028,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.41,
|
| 909 |
+
"grad_norm": 2.0149664878845215,
|
| 910 |
+
"learning_rate": 6.653142778398247e-06,
|
| 911 |
+
"loss": 1.583,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.41,
|
| 916 |
+
"grad_norm": 2.466585874557495,
|
| 917 |
+
"learning_rate": 6.6041288490768385e-06,
|
| 918 |
+
"loss": 1.6368,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.42,
|
| 923 |
+
"grad_norm": 2.181319236755371,
|
| 924 |
+
"learning_rate": 6.554942475057003e-06,
|
| 925 |
+
"loss": 1.5819,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.42,
|
| 930 |
+
"grad_norm": 1.9432387351989746,
|
| 931 |
+
"learning_rate": 6.505588943899923e-06,
|
| 932 |
+
"loss": 1.5551,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.42,
|
| 937 |
+
"grad_norm": 2.277068614959717,
|
| 938 |
+
"learning_rate": 6.456073561136261e-06,
|
| 939 |
+
"loss": 1.5788,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.43,
|
| 944 |
+
"grad_norm": 1.9018107652664185,
|
| 945 |
+
"learning_rate": 6.406401649695814e-06,
|
| 946 |
+
"loss": 1.5639,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.43,
|
| 951 |
+
"grad_norm": 2.755958318710327,
|
| 952 |
+
"learning_rate": 6.356578549335295e-06,
|
| 953 |
+
"loss": 1.6015,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.43,
|
| 958 |
+
"grad_norm": 2.2761142253875732,
|
| 959 |
+
"learning_rate": 6.306609616064304e-06,
|
| 960 |
+
"loss": 1.6054,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.44,
|
| 965 |
+
"grad_norm": 3.212486505508423,
|
| 966 |
+
"learning_rate": 6.256500221569556e-06,
|
| 967 |
+
"loss": 1.5953,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.44,
|
| 972 |
+
"grad_norm": 2.2175703048706055,
|
| 973 |
+
"learning_rate": 6.2062557526374226e-06,
|
| 974 |
+
"loss": 1.5745,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.44,
|
| 979 |
+
"grad_norm": 1.9958215951919556,
|
| 980 |
+
"learning_rate": 6.15588161057485e-06,
|
| 981 |
+
"loss": 1.5981,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.45,
|
| 986 |
+
"grad_norm": 2.4180896282196045,
|
| 987 |
+
"learning_rate": 6.10538321062871e-06,
|
| 988 |
+
"loss": 1.5836,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.45,
|
| 993 |
+
"grad_norm": 2.0187716484069824,
|
| 994 |
+
"learning_rate": 6.0547659814036664e-06,
|
| 995 |
+
"loss": 1.6062,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.45,
|
| 1000 |
+
"grad_norm": 2.3086986541748047,
|
| 1001 |
+
"learning_rate": 6.004035364278593e-06,
|
| 1002 |
+
"loss": 1.5764,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.46,
|
| 1007 |
+
"grad_norm": 1.9949414730072021,
|
| 1008 |
+
"learning_rate": 5.953196812821622e-06,
|
| 1009 |
+
"loss": 1.6037,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.46,
|
| 1014 |
+
"grad_norm": 1.8632932901382446,
|
| 1015 |
+
"learning_rate": 5.902255792203882e-06,
|
| 1016 |
+
"loss": 1.6051,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.46,
|
| 1021 |
+
"grad_norm": 2.034745931625366,
|
| 1022 |
+
"learning_rate": 5.851217778611994e-06,
|
| 1023 |
+
"loss": 1.6386,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.47,
|
| 1028 |
+
"grad_norm": 2.1993603706359863,
|
| 1029 |
+
"learning_rate": 5.800088258659371e-06,
|
| 1030 |
+
"loss": 1.6081,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.47,
|
| 1035 |
+
"grad_norm": 2.0585718154907227,
|
| 1036 |
+
"learning_rate": 5.748872728796409e-06,
|
| 1037 |
+
"loss": 1.5955,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.47,
|
| 1042 |
+
"grad_norm": 2.2753782272338867,
|
| 1043 |
+
"learning_rate": 5.697576694719616e-06,
|
| 1044 |
+
"loss": 1.5655,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.47,
|
| 1049 |
+
"grad_norm": 3.237483024597168,
|
| 1050 |
+
"learning_rate": 5.646205670779745e-06,
|
| 1051 |
+
"loss": 1.6004,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.48,
|
| 1056 |
+
"grad_norm": 3.019814968109131,
|
| 1057 |
+
"learning_rate": 5.594765179389003e-06,
|
| 1058 |
+
"loss": 1.5721,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
}
|
| 1061 |
+
],
|
| 1062 |
+
"logging_steps": 1.0,
|
| 1063 |
+
"max_steps": 313,
|
| 1064 |
+
"num_input_tokens_seen": 0,
|
| 1065 |
+
"num_train_epochs": 1,
|
| 1066 |
+
"save_steps": 50,
|
| 1067 |
+
"total_flos": 164924379693056.0,
|
| 1068 |
+
"train_batch_size": 1,
|
| 1069 |
+
"trial_name": null,
|
| 1070 |
+
"trial_params": null
|
| 1071 |
+
}
|
checkpoint-150/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45889d4d7acf868bd2e29b69a995aa63651cb92ff4aa6b4d21447f675a78dfa2
|
| 3 |
+
size 7352
|
checkpoint-150/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image>": 151646,
|
| 3 |
+
"<|endoftext|>": 151643,
|
| 4 |
+
"<|im_end|>": 151645,
|
| 5 |
+
"<|im_start|>": 151644
|
| 6 |
+
}
|
checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/project/mlmlongvideo/checkpoints/pure_text_extend_llava_qwen/checkpoint-200/",
|
| 3 |
+
"add_faster_video": false,
|
| 4 |
+
"add_time_instruction": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlavaQwenForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 151643,
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": true,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"ignore_index": -100,
|
| 16 |
+
"image_aspect_ratio": "anyres_max_9",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": [
|
| 19 |
+
[
|
| 20 |
+
384,
|
| 21 |
+
384
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
384,
|
| 25 |
+
768
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
384,
|
| 29 |
+
1152
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
384,
|
| 33 |
+
1536
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
384,
|
| 37 |
+
1920
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
384,
|
| 41 |
+
2304
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
768,
|
| 45 |
+
384
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
768,
|
| 49 |
+
768
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
768,
|
| 53 |
+
1152
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
768,
|
| 57 |
+
1536
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
768,
|
| 61 |
+
1920
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
768,
|
| 65 |
+
2304
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
1152,
|
| 69 |
+
384
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
1152,
|
| 73 |
+
768
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
1152,
|
| 77 |
+
1152
|
| 78 |
+
],
|
| 79 |
+
[
|
| 80 |
+
1152,
|
| 81 |
+
1536
|
| 82 |
+
],
|
| 83 |
+
[
|
| 84 |
+
1152,
|
| 85 |
+
1920
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
1152,
|
| 89 |
+
2304
|
| 90 |
+
],
|
| 91 |
+
[
|
| 92 |
+
1536,
|
| 93 |
+
384
|
| 94 |
+
],
|
| 95 |
+
[
|
| 96 |
+
1536,
|
| 97 |
+
768
|
| 98 |
+
],
|
| 99 |
+
[
|
| 100 |
+
1536,
|
| 101 |
+
1152
|
| 102 |
+
],
|
| 103 |
+
[
|
| 104 |
+
1536,
|
| 105 |
+
1536
|
| 106 |
+
],
|
| 107 |
+
[
|
| 108 |
+
1536,
|
| 109 |
+
1920
|
| 110 |
+
],
|
| 111 |
+
[
|
| 112 |
+
1536,
|
| 113 |
+
2304
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
1920,
|
| 117 |
+
384
|
| 118 |
+
],
|
| 119 |
+
[
|
| 120 |
+
1920,
|
| 121 |
+
768
|
| 122 |
+
],
|
| 123 |
+
[
|
| 124 |
+
1920,
|
| 125 |
+
1152
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
1920,
|
| 129 |
+
1536
|
| 130 |
+
],
|
| 131 |
+
[
|
| 132 |
+
1920,
|
| 133 |
+
1920
|
| 134 |
+
],
|
| 135 |
+
[
|
| 136 |
+
1920,
|
| 137 |
+
2304
|
| 138 |
+
],
|
| 139 |
+
[
|
| 140 |
+
2304,
|
| 141 |
+
384
|
| 142 |
+
],
|
| 143 |
+
[
|
| 144 |
+
2304,
|
| 145 |
+
768
|
| 146 |
+
],
|
| 147 |
+
[
|
| 148 |
+
2304,
|
| 149 |
+
1152
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
2304,
|
| 153 |
+
1536
|
| 154 |
+
],
|
| 155 |
+
[
|
| 156 |
+
2304,
|
| 157 |
+
1920
|
| 158 |
+
],
|
| 159 |
+
[
|
| 160 |
+
2304,
|
| 161 |
+
2304
|
| 162 |
+
]
|
| 163 |
+
],
|
| 164 |
+
"image_split_resolution": null,
|
| 165 |
+
"image_token_index": 151646,
|
| 166 |
+
"initializer_range": 0.02,
|
| 167 |
+
"intermediate_size": 18944,
|
| 168 |
+
"max_position_embeddings": 32768,
|
| 169 |
+
"max_window_layers": 28,
|
| 170 |
+
"mm_hidden_size": 1152,
|
| 171 |
+
"mm_newline_position": "grid",
|
| 172 |
+
"mm_patch_merge_type": "spatial_unpad",
|
| 173 |
+
"mm_projector_lr": null,
|
| 174 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 175 |
+
"mm_resampler_type": null,
|
| 176 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 177 |
+
"mm_spatial_pool_stride": 2,
|
| 178 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
| 179 |
+
"mm_use_im_patch_token": false,
|
| 180 |
+
"mm_use_im_start_end": false,
|
| 181 |
+
"mm_vision_select_feature": "patch",
|
| 182 |
+
"mm_vision_select_layer": -2,
|
| 183 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
| 184 |
+
"mm_vision_tower_lr": 2e-06,
|
| 185 |
+
"model_type": "llava",
|
| 186 |
+
"num_attention_heads": 28,
|
| 187 |
+
"num_hidden_layers": 28,
|
| 188 |
+
"num_key_value_heads": 4,
|
| 189 |
+
"pos_skipping_range": 4096,
|
| 190 |
+
"projector_hidden_act": "gelu",
|
| 191 |
+
"rms_norm_eps": 1e-06,
|
| 192 |
+
"rope_scaling": null,
|
| 193 |
+
"rope_theta": 1000000000.0,
|
| 194 |
+
"sliding_window": 131072,
|
| 195 |
+
"text_config": {
|
| 196 |
+
"model_type": "llama",
|
| 197 |
+
"vocab_size": 152064
|
| 198 |
+
},
|
| 199 |
+
"tie_word_embeddings": false,
|
| 200 |
+
"tokenizer_model_max_length": 28000,
|
| 201 |
+
"tokenizer_padding_side": "right",
|
| 202 |
+
"torch_dtype": "bfloat16",
|
| 203 |
+
"transformers_version": "4.40.0.dev0",
|
| 204 |
+
"use_cache": false,
|
| 205 |
+
"use_mm_proj": true,
|
| 206 |
+
"use_pos_skipping": false,
|
| 207 |
+
"use_sliding_window": false,
|
| 208 |
+
"vision_config": {
|
| 209 |
+
"hidden_size": 1024,
|
| 210 |
+
"image_size": 336,
|
| 211 |
+
"intermediate_size": 4096,
|
| 212 |
+
"model_type": "clip_vision_model",
|
| 213 |
+
"num_attention_heads": 16,
|
| 214 |
+
"num_hidden_layers": 24,
|
| 215 |
+
"patch_size": 14,
|
| 216 |
+
"projection_dim": 768,
|
| 217 |
+
"vocab_size": 32000
|
| 218 |
+
},
|
| 219 |
+
"vision_feature_layer": -2,
|
| 220 |
+
"vision_feature_select_strategy": "default",
|
| 221 |
+
"vision_tower_pretrained": null
|
| 222 |
+
}
|
checkpoint-200/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.40.0.dev0"
|
| 14 |
+
}
|
checkpoint-200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7859a9171c532e6343dd403ff4b07d5f82dac5bbe9f7e7cb58f0524e0ac3e3ca
|
| 3 |
+
size 4877668032
|
checkpoint-200/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3db0b9b2ab0e2872412651834939c4bc1f1b06f82f4a795ed9262910bc0f2007
|
| 3 |
+
size 4932751008
|
checkpoint-200/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39c3ecabe1050a1c18350809a30c5265140b3e473e53a055438dbdf6f17783aa
|
| 3 |
+
size 4994571904
|
checkpoint-200/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc0eadb7d146af311e496860f4c081e9a6d270c7ea0349569d6ad6a153f7fff2
|
| 3 |
+
size 1255812224
|
checkpoint-200/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16060697664
|
| 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.image_newline": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 308 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 320 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.norm.weight": "model-00003-of-00004.safetensors",
|
| 350 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 701 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 702 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 703 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 704 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 705 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 706 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 707 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 708 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 709 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 710 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 711 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 712 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 713 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 714 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 715 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 716 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 717 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 718 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 719 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 720 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 721 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 722 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 723 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 724 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 725 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 726 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 727 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 728 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 729 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 730 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 731 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 732 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 733 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 734 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 735 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 736 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 737 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 738 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 739 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 740 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 741 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 742 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 743 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 744 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 745 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 746 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 747 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 748 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 749 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 750 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 751 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 752 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 753 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 754 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 755 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 756 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 757 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 758 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 759 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 760 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 761 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 762 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 763 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 764 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 765 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 766 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 767 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 768 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 769 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
|
| 770 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
|
| 771 |
+
}
|
| 772 |
+
}
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<image>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"additional_special_tokens": [
|
| 38 |
+
"<|im_start|>",
|
| 39 |
+
"<|im_end|>"
|
| 40 |
+
],
|
| 41 |
+
"bos_token": null,
|
| 42 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 43 |
+
"clean_up_tokenization_spaces": false,
|
| 44 |
+
"eos_token": "<|im_end|>",
|
| 45 |
+
"errors": "replace",
|
| 46 |
+
"model_max_length": 28000,
|
| 47 |
+
"pad_token": "<|endoftext|>",
|
| 48 |
+
"padding_side": "right",
|
| 49 |
+
"processor_class": "LlavaProcessor",
|
| 50 |
+
"split_special_tokens": false,
|
| 51 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 52 |
+
"unk_token": null
|
| 53 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,1421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6371963361210673,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 10.092560768127441,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 1.9497,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 8.963287353515625,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 1.951,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 9.27600383758545,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 1.9345,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 5.632405757904053,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 1.9157,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 5.668580055236816,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 1.9026,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 3.8046553134918213,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 1.8923,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"grad_norm": 4.357985973358154,
|
| 56 |
+
"learning_rate": 7e-06,
|
| 57 |
+
"loss": 1.8241,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 4.685062885284424,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 1.8467,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"grad_norm": 4.768229961395264,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 1.8199,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03,
|
| 76 |
+
"grad_norm": 4.796407699584961,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 1.8374,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"grad_norm": 5.7536139488220215,
|
| 84 |
+
"learning_rate": 9.999731248679734e-06,
|
| 85 |
+
"loss": 1.779,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04,
|
| 90 |
+
"grad_norm": 4.202663898468018,
|
| 91 |
+
"learning_rate": 9.99892502360984e-06,
|
| 92 |
+
"loss": 1.7579,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"grad_norm": 2.9114131927490234,
|
| 98 |
+
"learning_rate": 9.99758141145994e-06,
|
| 99 |
+
"loss": 1.7433,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.04,
|
| 104 |
+
"grad_norm": 2.3823723793029785,
|
| 105 |
+
"learning_rate": 9.995700556669052e-06,
|
| 106 |
+
"loss": 1.7212,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05,
|
| 111 |
+
"grad_norm": 2.3254876136779785,
|
| 112 |
+
"learning_rate": 9.993282661430058e-06,
|
| 113 |
+
"loss": 1.7218,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.05,
|
| 118 |
+
"grad_norm": 2.053166151046753,
|
| 119 |
+
"learning_rate": 9.990327985667972e-06,
|
| 120 |
+
"loss": 1.7256,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.05,
|
| 125 |
+
"grad_norm": 2.3782012462615967,
|
| 126 |
+
"learning_rate": 9.986836847012001e-06,
|
| 127 |
+
"loss": 1.713,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06,
|
| 132 |
+
"grad_norm": 2.1311683654785156,
|
| 133 |
+
"learning_rate": 9.98280962076139e-06,
|
| 134 |
+
"loss": 1.6785,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"grad_norm": 2.325747489929199,
|
| 140 |
+
"learning_rate": 9.978246739845095e-06,
|
| 141 |
+
"loss": 1.7167,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.06,
|
| 146 |
+
"grad_norm": 2.1330366134643555,
|
| 147 |
+
"learning_rate": 9.973148694775217e-06,
|
| 148 |
+
"loss": 1.676,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07,
|
| 153 |
+
"grad_norm": 2.2632806301116943,
|
| 154 |
+
"learning_rate": 9.967516033594295e-06,
|
| 155 |
+
"loss": 1.7033,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.07,
|
| 160 |
+
"grad_norm": 2.6582744121551514,
|
| 161 |
+
"learning_rate": 9.961349361816384e-06,
|
| 162 |
+
"loss": 1.6957,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.07,
|
| 167 |
+
"grad_norm": 1.9663337469100952,
|
| 168 |
+
"learning_rate": 9.954649342361952e-06,
|
| 169 |
+
"loss": 1.6729,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08,
|
| 174 |
+
"grad_norm": 2.2557435035705566,
|
| 175 |
+
"learning_rate": 9.947416695486633e-06,
|
| 176 |
+
"loss": 1.6399,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"grad_norm": 2.090054512023926,
|
| 182 |
+
"learning_rate": 9.939652198703785e-06,
|
| 183 |
+
"loss": 1.6792,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08,
|
| 188 |
+
"grad_norm": 2.1648776531219482,
|
| 189 |
+
"learning_rate": 9.93135668670091e-06,
|
| 190 |
+
"loss": 1.6625,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.09,
|
| 195 |
+
"grad_norm": 2.1209850311279297,
|
| 196 |
+
"learning_rate": 9.92253105124993e-06,
|
| 197 |
+
"loss": 1.7057,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.09,
|
| 202 |
+
"grad_norm": 2.2777392864227295,
|
| 203 |
+
"learning_rate": 9.91317624111132e-06,
|
| 204 |
+
"loss": 1.6052,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.09,
|
| 209 |
+
"grad_norm": 2.1739561557769775,
|
| 210 |
+
"learning_rate": 9.903293261932106e-06,
|
| 211 |
+
"loss": 1.6139,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1,
|
| 216 |
+
"grad_norm": 2.4518871307373047,
|
| 217 |
+
"learning_rate": 9.89288317613777e-06,
|
| 218 |
+
"loss": 1.6759,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"grad_norm": 1.795519471168518,
|
| 224 |
+
"learning_rate": 9.881947102818036e-06,
|
| 225 |
+
"loss": 1.7036,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1,
|
| 230 |
+
"grad_norm": 2.150223731994629,
|
| 231 |
+
"learning_rate": 9.870486217606557e-06,
|
| 232 |
+
"loss": 1.6469,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.11,
|
| 237 |
+
"grad_norm": 1.91805899143219,
|
| 238 |
+
"learning_rate": 9.858501752554548e-06,
|
| 239 |
+
"loss": 1.6353,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.11,
|
| 244 |
+
"grad_norm": 1.8129810094833374,
|
| 245 |
+
"learning_rate": 9.845994995998332e-06,
|
| 246 |
+
"loss": 1.6551,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11,
|
| 251 |
+
"grad_norm": 2.1308679580688477,
|
| 252 |
+
"learning_rate": 9.83296729242084e-06,
|
| 253 |
+
"loss": 1.617,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.11,
|
| 258 |
+
"grad_norm": 1.8321012258529663,
|
| 259 |
+
"learning_rate": 9.819420042307091e-06,
|
| 260 |
+
"loss": 1.6213,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"grad_norm": 1.9112164974212646,
|
| 266 |
+
"learning_rate": 9.805354701993624e-06,
|
| 267 |
+
"loss": 1.6245,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.12,
|
| 272 |
+
"grad_norm": 2.1160471439361572,
|
| 273 |
+
"learning_rate": 9.79077278351195e-06,
|
| 274 |
+
"loss": 1.6405,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.12,
|
| 279 |
+
"grad_norm": 2.6318371295928955,
|
| 280 |
+
"learning_rate": 9.77567585442601e-06,
|
| 281 |
+
"loss": 1.6234,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.13,
|
| 286 |
+
"grad_norm": 3.238373279571533,
|
| 287 |
+
"learning_rate": 9.76006553766365e-06,
|
| 288 |
+
"loss": 1.6452,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.13,
|
| 293 |
+
"grad_norm": 2.056736469268799,
|
| 294 |
+
"learning_rate": 9.743943511342168e-06,
|
| 295 |
+
"loss": 1.679,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.13,
|
| 300 |
+
"grad_norm": 2.000826358795166,
|
| 301 |
+
"learning_rate": 9.727311508587907e-06,
|
| 302 |
+
"loss": 1.6904,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14,
|
| 307 |
+
"grad_norm": 2.089482069015503,
|
| 308 |
+
"learning_rate": 9.710171317349946e-06,
|
| 309 |
+
"loss": 1.62,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.14,
|
| 314 |
+
"grad_norm": 2.5748705863952637,
|
| 315 |
+
"learning_rate": 9.692524780207897e-06,
|
| 316 |
+
"loss": 1.6669,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.14,
|
| 321 |
+
"grad_norm": 1.9039987325668335,
|
| 322 |
+
"learning_rate": 9.674373794173818e-06,
|
| 323 |
+
"loss": 1.6489,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.15,
|
| 328 |
+
"grad_norm": 1.8047181367874146,
|
| 329 |
+
"learning_rate": 9.655720310488298e-06,
|
| 330 |
+
"loss": 1.6227,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15,
|
| 335 |
+
"grad_norm": 2.0552868843078613,
|
| 336 |
+
"learning_rate": 9.636566334410682e-06,
|
| 337 |
+
"loss": 1.5898,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.15,
|
| 342 |
+
"grad_norm": 2.252218008041382,
|
| 343 |
+
"learning_rate": 9.616913925003514e-06,
|
| 344 |
+
"loss": 1.6667,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16,
|
| 349 |
+
"grad_norm": 2.015887498855591,
|
| 350 |
+
"learning_rate": 9.596765194911182e-06,
|
| 351 |
+
"loss": 1.6668,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16,
|
| 356 |
+
"grad_norm": 2.582007884979248,
|
| 357 |
+
"learning_rate": 9.576122310132814e-06,
|
| 358 |
+
"loss": 1.6542,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.16,
|
| 363 |
+
"grad_norm": 1.9070011377334595,
|
| 364 |
+
"learning_rate": 9.554987489789426e-06,
|
| 365 |
+
"loss": 1.691,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.17,
|
| 370 |
+
"grad_norm": 1.9671483039855957,
|
| 371 |
+
"learning_rate": 9.533363005885362e-06,
|
| 372 |
+
"loss": 1.6116,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.17,
|
| 377 |
+
"grad_norm": 2.4808287620544434,
|
| 378 |
+
"learning_rate": 9.511251183064068e-06,
|
| 379 |
+
"loss": 1.6653,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.17,
|
| 384 |
+
"grad_norm": 2.237518548965454,
|
| 385 |
+
"learning_rate": 9.48865439835817e-06,
|
| 386 |
+
"loss": 1.6571,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.18,
|
| 391 |
+
"grad_norm": 2.142627477645874,
|
| 392 |
+
"learning_rate": 9.465575080933959e-06,
|
| 393 |
+
"loss": 1.6247,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.18,
|
| 398 |
+
"grad_norm": 2.0365779399871826,
|
| 399 |
+
"learning_rate": 9.442015711830246e-06,
|
| 400 |
+
"loss": 1.6323,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.18,
|
| 405 |
+
"grad_norm": 2.427443742752075,
|
| 406 |
+
"learning_rate": 9.417978823691652e-06,
|
| 407 |
+
"loss": 1.6646,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.18,
|
| 412 |
+
"grad_norm": 2.014340877532959,
|
| 413 |
+
"learning_rate": 9.393467000496345e-06,
|
| 414 |
+
"loss": 1.5754,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.19,
|
| 419 |
+
"grad_norm": 2.6110949516296387,
|
| 420 |
+
"learning_rate": 9.368482877278264e-06,
|
| 421 |
+
"loss": 1.657,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.19,
|
| 426 |
+
"grad_norm": 2.048231363296509,
|
| 427 |
+
"learning_rate": 9.34302913984385e-06,
|
| 428 |
+
"loss": 1.61,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19,
|
| 433 |
+
"grad_norm": 2.672330379486084,
|
| 434 |
+
"learning_rate": 9.317108524483319e-06,
|
| 435 |
+
"loss": 1.5894,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2,
|
| 440 |
+
"grad_norm": 2.6745121479034424,
|
| 441 |
+
"learning_rate": 9.29072381767651e-06,
|
| 442 |
+
"loss": 1.5623,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2,
|
| 447 |
+
"grad_norm": 2.1490442752838135,
|
| 448 |
+
"learning_rate": 9.26387785579334e-06,
|
| 449 |
+
"loss": 1.6668,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2,
|
| 454 |
+
"grad_norm": 3.805147171020508,
|
| 455 |
+
"learning_rate": 9.236573524788888e-06,
|
| 456 |
+
"loss": 1.6274,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.21,
|
| 461 |
+
"grad_norm": 2.243023157119751,
|
| 462 |
+
"learning_rate": 9.208813759893158e-06,
|
| 463 |
+
"loss": 1.6496,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.21,
|
| 468 |
+
"grad_norm": 2.5260114669799805,
|
| 469 |
+
"learning_rate": 9.180601545295535e-06,
|
| 470 |
+
"loss": 1.623,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21,
|
| 475 |
+
"grad_norm": 2.0329606533050537,
|
| 476 |
+
"learning_rate": 9.151939913823988e-06,
|
| 477 |
+
"loss": 1.5873,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.22,
|
| 482 |
+
"grad_norm": 3.3269598484039307,
|
| 483 |
+
"learning_rate": 9.122831946619038e-06,
|
| 484 |
+
"loss": 1.6327,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.22,
|
| 489 |
+
"grad_norm": 2.1953978538513184,
|
| 490 |
+
"learning_rate": 9.093280772802527e-06,
|
| 491 |
+
"loss": 1.6321,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.22,
|
| 496 |
+
"grad_norm": 3.2001328468322754,
|
| 497 |
+
"learning_rate": 9.063289569141251e-06,
|
| 498 |
+
"loss": 1.6338,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.23,
|
| 503 |
+
"grad_norm": 2.076502799987793,
|
| 504 |
+
"learning_rate": 9.032861559705442e-06,
|
| 505 |
+
"loss": 1.6648,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.23,
|
| 510 |
+
"grad_norm": 2.0800352096557617,
|
| 511 |
+
"learning_rate": 9.002000015522182e-06,
|
| 512 |
+
"loss": 1.5694,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23,
|
| 517 |
+
"grad_norm": 2.0901432037353516,
|
| 518 |
+
"learning_rate": 8.970708254223768e-06,
|
| 519 |
+
"loss": 1.6571,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.24,
|
| 524 |
+
"grad_norm": 3.1389923095703125,
|
| 525 |
+
"learning_rate": 8.938989639691068e-06,
|
| 526 |
+
"loss": 1.6151,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.24,
|
| 531 |
+
"grad_norm": 2.0514352321624756,
|
| 532 |
+
"learning_rate": 8.90684758169189e-06,
|
| 533 |
+
"loss": 1.618,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.24,
|
| 538 |
+
"grad_norm": 1.9462100267410278,
|
| 539 |
+
"learning_rate": 8.87428553551445e-06,
|
| 540 |
+
"loss": 1.6367,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.25,
|
| 545 |
+
"grad_norm": 2.2343838214874268,
|
| 546 |
+
"learning_rate": 8.841307001595904e-06,
|
| 547 |
+
"loss": 1.6321,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.25,
|
| 552 |
+
"grad_norm": 2.6064207553863525,
|
| 553 |
+
"learning_rate": 8.807915525146065e-06,
|
| 554 |
+
"loss": 1.5913,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.25,
|
| 559 |
+
"grad_norm": 2.589186191558838,
|
| 560 |
+
"learning_rate": 8.774114695766286e-06,
|
| 561 |
+
"loss": 1.6,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.25,
|
| 566 |
+
"grad_norm": 2.0082924365997314,
|
| 567 |
+
"learning_rate": 8.739908147063576e-06,
|
| 568 |
+
"loss": 1.6266,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.26,
|
| 573 |
+
"grad_norm": 1.9739817380905151,
|
| 574 |
+
"learning_rate": 8.705299556259986e-06,
|
| 575 |
+
"loss": 1.5926,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.26,
|
| 580 |
+
"grad_norm": 2.9566433429718018,
|
| 581 |
+
"learning_rate": 8.670292643797302e-06,
|
| 582 |
+
"loss": 1.624,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.26,
|
| 587 |
+
"grad_norm": 2.10595703125,
|
| 588 |
+
"learning_rate": 8.634891172937102e-06,
|
| 589 |
+
"loss": 1.6437,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.27,
|
| 594 |
+
"grad_norm": 1.7080891132354736,
|
| 595 |
+
"learning_rate": 8.599098949356201e-06,
|
| 596 |
+
"loss": 1.6131,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.27,
|
| 601 |
+
"grad_norm": 2.358856678009033,
|
| 602 |
+
"learning_rate": 8.562919820737537e-06,
|
| 603 |
+
"loss": 1.5748,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.27,
|
| 608 |
+
"grad_norm": 2.030383825302124,
|
| 609 |
+
"learning_rate": 8.526357676356538e-06,
|
| 610 |
+
"loss": 1.6389,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.28,
|
| 615 |
+
"grad_norm": 2.3567280769348145,
|
| 616 |
+
"learning_rate": 8.489416446663037e-06,
|
| 617 |
+
"loss": 1.6288,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.28,
|
| 622 |
+
"grad_norm": 2.1183040142059326,
|
| 623 |
+
"learning_rate": 8.452100102858734e-06,
|
| 624 |
+
"loss": 1.5929,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.28,
|
| 629 |
+
"grad_norm": 2.467944860458374,
|
| 630 |
+
"learning_rate": 8.414412656470297e-06,
|
| 631 |
+
"loss": 1.5579,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.29,
|
| 636 |
+
"grad_norm": 2.200274705886841,
|
| 637 |
+
"learning_rate": 8.376358158918114e-06,
|
| 638 |
+
"loss": 1.587,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.29,
|
| 643 |
+
"grad_norm": 2.3279902935028076,
|
| 644 |
+
"learning_rate": 8.33794070108077e-06,
|
| 645 |
+
"loss": 1.6496,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.29,
|
| 650 |
+
"grad_norm": 2.7403910160064697,
|
| 651 |
+
"learning_rate": 8.299164412855268e-06,
|
| 652 |
+
"loss": 1.5665,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.3,
|
| 657 |
+
"grad_norm": 2.5097343921661377,
|
| 658 |
+
"learning_rate": 8.260033462713073e-06,
|
| 659 |
+
"loss": 1.6245,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3,
|
| 664 |
+
"grad_norm": 2.2657604217529297,
|
| 665 |
+
"learning_rate": 8.22055205725199e-06,
|
| 666 |
+
"loss": 1.5785,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3,
|
| 671 |
+
"grad_norm": 2.4038476943969727,
|
| 672 |
+
"learning_rate": 8.180724440743957e-06,
|
| 673 |
+
"loss": 1.6912,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.31,
|
| 678 |
+
"grad_norm": 2.811049461364746,
|
| 679 |
+
"learning_rate": 8.14055489467878e-06,
|
| 680 |
+
"loss": 1.6059,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.31,
|
| 685 |
+
"grad_norm": 2.474153518676758,
|
| 686 |
+
"learning_rate": 8.100047737303877e-06,
|
| 687 |
+
"loss": 1.6423,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.31,
|
| 692 |
+
"grad_norm": 2.351736307144165,
|
| 693 |
+
"learning_rate": 8.059207323160057e-06,
|
| 694 |
+
"loss": 1.6199,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.32,
|
| 699 |
+
"grad_norm": 2.3526997566223145,
|
| 700 |
+
"learning_rate": 8.018038042613407e-06,
|
| 701 |
+
"loss": 1.5856,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.32,
|
| 706 |
+
"grad_norm": 2.075406789779663,
|
| 707 |
+
"learning_rate": 7.97654432138333e-06,
|
| 708 |
+
"loss": 1.5901,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.32,
|
| 713 |
+
"grad_norm": 2.6973438262939453,
|
| 714 |
+
"learning_rate": 7.93473062006677e-06,
|
| 715 |
+
"loss": 1.5696,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.32,
|
| 720 |
+
"grad_norm": 2.6449167728424072,
|
| 721 |
+
"learning_rate": 7.892601433658705e-06,
|
| 722 |
+
"loss": 1.5939,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.33,
|
| 727 |
+
"grad_norm": 2.360849380493164,
|
| 728 |
+
"learning_rate": 7.850161291068915e-06,
|
| 729 |
+
"loss": 1.5449,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.33,
|
| 734 |
+
"grad_norm": 2.467226028442383,
|
| 735 |
+
"learning_rate": 7.807414754635145e-06,
|
| 736 |
+
"loss": 1.5926,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.33,
|
| 741 |
+
"grad_norm": 2.449989080429077,
|
| 742 |
+
"learning_rate": 7.764366419632636e-06,
|
| 743 |
+
"loss": 1.5591,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.34,
|
| 748 |
+
"grad_norm": 5.518803119659424,
|
| 749 |
+
"learning_rate": 7.721020913780137e-06,
|
| 750 |
+
"loss": 1.5406,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.34,
|
| 755 |
+
"grad_norm": 2.6841485500335693,
|
| 756 |
+
"learning_rate": 7.677382896742417e-06,
|
| 757 |
+
"loss": 1.5797,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.34,
|
| 762 |
+
"grad_norm": 2.475085496902466,
|
| 763 |
+
"learning_rate": 7.63345705962935e-06,
|
| 764 |
+
"loss": 1.5653,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.35,
|
| 769 |
+
"grad_norm": 2.3905832767486572,
|
| 770 |
+
"learning_rate": 7.589248124491627e-06,
|
| 771 |
+
"loss": 1.5641,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.35,
|
| 776 |
+
"grad_norm": 2.7013638019561768,
|
| 777 |
+
"learning_rate": 7.544760843813122e-06,
|
| 778 |
+
"loss": 1.5837,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.35,
|
| 783 |
+
"grad_norm": 2.500148296356201,
|
| 784 |
+
"learning_rate": 7.500000000000001e-06,
|
| 785 |
+
"loss": 1.6255,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.36,
|
| 790 |
+
"grad_norm": 2.106887102127075,
|
| 791 |
+
"learning_rate": 7.454970404866612e-06,
|
| 792 |
+
"loss": 1.6069,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.36,
|
| 797 |
+
"grad_norm": 2.1840200424194336,
|
| 798 |
+
"learning_rate": 7.409676899118213e-06,
|
| 799 |
+
"loss": 1.5959,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.36,
|
| 804 |
+
"grad_norm": 5.758022308349609,
|
| 805 |
+
"learning_rate": 7.3641243518305915e-06,
|
| 806 |
+
"loss": 1.616,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.37,
|
| 811 |
+
"grad_norm": 2.24625301361084,
|
| 812 |
+
"learning_rate": 7.318317659926637e-06,
|
| 813 |
+
"loss": 1.639,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.37,
|
| 818 |
+
"grad_norm": 3.8651440143585205,
|
| 819 |
+
"learning_rate": 7.272261747649922e-06,
|
| 820 |
+
"loss": 1.6287,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.37,
|
| 825 |
+
"grad_norm": 1.9262839555740356,
|
| 826 |
+
"learning_rate": 7.225961566035335e-06,
|
| 827 |
+
"loss": 1.5851,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.38,
|
| 832 |
+
"grad_norm": 2.4312078952789307,
|
| 833 |
+
"learning_rate": 7.179422092376856e-06,
|
| 834 |
+
"loss": 1.5934,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.38,
|
| 839 |
+
"grad_norm": 2.391693592071533,
|
| 840 |
+
"learning_rate": 7.132648329692478e-06,
|
| 841 |
+
"loss": 1.5719,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.38,
|
| 846 |
+
"grad_norm": 2.10438871383667,
|
| 847 |
+
"learning_rate": 7.085645306186391e-06,
|
| 848 |
+
"loss": 1.5876,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.39,
|
| 853 |
+
"grad_norm": 1.984710931777954,
|
| 854 |
+
"learning_rate": 7.038418074708444e-06,
|
| 855 |
+
"loss": 1.6506,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.39,
|
| 860 |
+
"grad_norm": 2.4563817977905273,
|
| 861 |
+
"learning_rate": 6.990971712210966e-06,
|
| 862 |
+
"loss": 1.5578,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.39,
|
| 867 |
+
"grad_norm": 1.856941819190979,
|
| 868 |
+
"learning_rate": 6.943311319202976e-06,
|
| 869 |
+
"loss": 1.5806,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.4,
|
| 874 |
+
"grad_norm": 2.228983163833618,
|
| 875 |
+
"learning_rate": 6.895442019201898e-06,
|
| 876 |
+
"loss": 1.5639,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.4,
|
| 881 |
+
"grad_norm": 2.9688351154327393,
|
| 882 |
+
"learning_rate": 6.8473689581827585e-06,
|
| 883 |
+
"loss": 1.5939,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.4,
|
| 888 |
+
"grad_norm": 2.028876304626465,
|
| 889 |
+
"learning_rate": 6.7990973040250055e-06,
|
| 890 |
+
"loss": 1.6096,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.4,
|
| 895 |
+
"grad_norm": 2.385794162750244,
|
| 896 |
+
"learning_rate": 6.750632245956954e-06,
|
| 897 |
+
"loss": 1.5617,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.41,
|
| 902 |
+
"grad_norm": 2.0037996768951416,
|
| 903 |
+
"learning_rate": 6.701978993997942e-06,
|
| 904 |
+
"loss": 1.6028,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.41,
|
| 909 |
+
"grad_norm": 2.0149664878845215,
|
| 910 |
+
"learning_rate": 6.653142778398247e-06,
|
| 911 |
+
"loss": 1.583,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.41,
|
| 916 |
+
"grad_norm": 2.466585874557495,
|
| 917 |
+
"learning_rate": 6.6041288490768385e-06,
|
| 918 |
+
"loss": 1.6368,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.42,
|
| 923 |
+
"grad_norm": 2.181319236755371,
|
| 924 |
+
"learning_rate": 6.554942475057003e-06,
|
| 925 |
+
"loss": 1.5819,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.42,
|
| 930 |
+
"grad_norm": 1.9432387351989746,
|
| 931 |
+
"learning_rate": 6.505588943899923e-06,
|
| 932 |
+
"loss": 1.5551,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.42,
|
| 937 |
+
"grad_norm": 2.277068614959717,
|
| 938 |
+
"learning_rate": 6.456073561136261e-06,
|
| 939 |
+
"loss": 1.5788,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.43,
|
| 944 |
+
"grad_norm": 1.9018107652664185,
|
| 945 |
+
"learning_rate": 6.406401649695814e-06,
|
| 946 |
+
"loss": 1.5639,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.43,
|
| 951 |
+
"grad_norm": 2.755958318710327,
|
| 952 |
+
"learning_rate": 6.356578549335295e-06,
|
| 953 |
+
"loss": 1.6015,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.43,
|
| 958 |
+
"grad_norm": 2.2761142253875732,
|
| 959 |
+
"learning_rate": 6.306609616064304e-06,
|
| 960 |
+
"loss": 1.6054,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.44,
|
| 965 |
+
"grad_norm": 3.212486505508423,
|
| 966 |
+
"learning_rate": 6.256500221569556e-06,
|
| 967 |
+
"loss": 1.5953,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.44,
|
| 972 |
+
"grad_norm": 2.2175703048706055,
|
| 973 |
+
"learning_rate": 6.2062557526374226e-06,
|
| 974 |
+
"loss": 1.5745,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.44,
|
| 979 |
+
"grad_norm": 1.9958215951919556,
|
| 980 |
+
"learning_rate": 6.15588161057485e-06,
|
| 981 |
+
"loss": 1.5981,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.45,
|
| 986 |
+
"grad_norm": 2.4180896282196045,
|
| 987 |
+
"learning_rate": 6.10538321062871e-06,
|
| 988 |
+
"loss": 1.5836,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.45,
|
| 993 |
+
"grad_norm": 2.0187716484069824,
|
| 994 |
+
"learning_rate": 6.0547659814036664e-06,
|
| 995 |
+
"loss": 1.6062,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.45,
|
| 1000 |
+
"grad_norm": 2.3086986541748047,
|
| 1001 |
+
"learning_rate": 6.004035364278593e-06,
|
| 1002 |
+
"loss": 1.5764,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.46,
|
| 1007 |
+
"grad_norm": 1.9949414730072021,
|
| 1008 |
+
"learning_rate": 5.953196812821622e-06,
|
| 1009 |
+
"loss": 1.6037,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.46,
|
| 1014 |
+
"grad_norm": 1.8632932901382446,
|
| 1015 |
+
"learning_rate": 5.902255792203882e-06,
|
| 1016 |
+
"loss": 1.6051,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.46,
|
| 1021 |
+
"grad_norm": 2.034745931625366,
|
| 1022 |
+
"learning_rate": 5.851217778611994e-06,
|
| 1023 |
+
"loss": 1.6386,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.47,
|
| 1028 |
+
"grad_norm": 2.1993603706359863,
|
| 1029 |
+
"learning_rate": 5.800088258659371e-06,
|
| 1030 |
+
"loss": 1.6081,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.47,
|
| 1035 |
+
"grad_norm": 2.0585718154907227,
|
| 1036 |
+
"learning_rate": 5.748872728796409e-06,
|
| 1037 |
+
"loss": 1.5955,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.47,
|
| 1042 |
+
"grad_norm": 2.2753782272338867,
|
| 1043 |
+
"learning_rate": 5.697576694719616e-06,
|
| 1044 |
+
"loss": 1.5655,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.47,
|
| 1049 |
+
"grad_norm": 3.237483024597168,
|
| 1050 |
+
"learning_rate": 5.646205670779745e-06,
|
| 1051 |
+
"loss": 1.6004,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.48,
|
| 1056 |
+
"grad_norm": 3.019814968109131,
|
| 1057 |
+
"learning_rate": 5.594765179389003e-06,
|
| 1058 |
+
"loss": 1.5721,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.48,
|
| 1063 |
+
"grad_norm": 2.3698084354400635,
|
| 1064 |
+
"learning_rate": 5.543260750427373e-06,
|
| 1065 |
+
"loss": 1.5946,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.48,
|
| 1070 |
+
"grad_norm": 2.441636085510254,
|
| 1071 |
+
"learning_rate": 5.4916979206481745e-06,
|
| 1072 |
+
"loss": 1.5522,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.49,
|
| 1077 |
+
"grad_norm": 2.149003267288208,
|
| 1078 |
+
"learning_rate": 5.440082233082837e-06,
|
| 1079 |
+
"loss": 1.5935,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.49,
|
| 1084 |
+
"grad_norm": 2.03369402885437,
|
| 1085 |
+
"learning_rate": 5.388419236445033e-06,
|
| 1086 |
+
"loss": 1.5912,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.49,
|
| 1091 |
+
"grad_norm": 1.9619389772415161,
|
| 1092 |
+
"learning_rate": 5.336714484534183e-06,
|
| 1093 |
+
"loss": 1.5324,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.5,
|
| 1098 |
+
"grad_norm": 3.591277837753296,
|
| 1099 |
+
"learning_rate": 5.284973535638424e-06,
|
| 1100 |
+
"loss": 1.5662,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.5,
|
| 1105 |
+
"grad_norm": 2.212984323501587,
|
| 1106 |
+
"learning_rate": 5.233201951937088e-06,
|
| 1107 |
+
"loss": 1.6589,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.5,
|
| 1112 |
+
"grad_norm": 1.835900902748108,
|
| 1113 |
+
"learning_rate": 5.181405298902763e-06,
|
| 1114 |
+
"loss": 1.597,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.51,
|
| 1119 |
+
"grad_norm": 2.046597480773926,
|
| 1120 |
+
"learning_rate": 5.1295891447030056e-06,
|
| 1121 |
+
"loss": 1.5742,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.51,
|
| 1126 |
+
"grad_norm": 2.5161941051483154,
|
| 1127 |
+
"learning_rate": 5.077759059601756e-06,
|
| 1128 |
+
"loss": 1.5848,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.51,
|
| 1133 |
+
"grad_norm": 2.1808998584747314,
|
| 1134 |
+
"learning_rate": 5.025920615360532e-06,
|
| 1135 |
+
"loss": 1.5684,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.52,
|
| 1140 |
+
"grad_norm": 2.5023722648620605,
|
| 1141 |
+
"learning_rate": 4.974079384639469e-06,
|
| 1142 |
+
"loss": 1.5815,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.52,
|
| 1147 |
+
"grad_norm": 2.056931734085083,
|
| 1148 |
+
"learning_rate": 4.922240940398246e-06,
|
| 1149 |
+
"loss": 1.5334,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.52,
|
| 1154 |
+
"grad_norm": 2.1214613914489746,
|
| 1155 |
+
"learning_rate": 4.870410855296994e-06,
|
| 1156 |
+
"loss": 1.5726,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.53,
|
| 1161 |
+
"grad_norm": 3.080734968185425,
|
| 1162 |
+
"learning_rate": 4.818594701097239e-06,
|
| 1163 |
+
"loss": 1.5869,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.53,
|
| 1168 |
+
"grad_norm": 2.13873028755188,
|
| 1169 |
+
"learning_rate": 4.766798048062913e-06,
|
| 1170 |
+
"loss": 1.6214,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.53,
|
| 1175 |
+
"grad_norm": 2.4381258487701416,
|
| 1176 |
+
"learning_rate": 4.715026464361576e-06,
|
| 1177 |
+
"loss": 1.5921,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.54,
|
| 1182 |
+
"grad_norm": 2.3654768466949463,
|
| 1183 |
+
"learning_rate": 4.663285515465818e-06,
|
| 1184 |
+
"loss": 1.5598,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.54,
|
| 1189 |
+
"grad_norm": 2.3201935291290283,
|
| 1190 |
+
"learning_rate": 4.611580763554969e-06,
|
| 1191 |
+
"loss": 1.5339,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.54,
|
| 1196 |
+
"grad_norm": 2.3482742309570312,
|
| 1197 |
+
"learning_rate": 4.559917766917166e-06,
|
| 1198 |
+
"loss": 1.5501,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.54,
|
| 1203 |
+
"grad_norm": 2.296869993209839,
|
| 1204 |
+
"learning_rate": 4.508302079351827e-06,
|
| 1205 |
+
"loss": 1.542,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.55,
|
| 1210 |
+
"grad_norm": 2.0012331008911133,
|
| 1211 |
+
"learning_rate": 4.456739249572628e-06,
|
| 1212 |
+
"loss": 1.5223,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.55,
|
| 1217 |
+
"grad_norm": 2.4259610176086426,
|
| 1218 |
+
"learning_rate": 4.405234820611001e-06,
|
| 1219 |
+
"loss": 1.5929,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.55,
|
| 1224 |
+
"grad_norm": 2.1162846088409424,
|
| 1225 |
+
"learning_rate": 4.3537943292202555e-06,
|
| 1226 |
+
"loss": 1.5213,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.56,
|
| 1231 |
+
"grad_norm": 4.398637771606445,
|
| 1232 |
+
"learning_rate": 4.3024233052803855e-06,
|
| 1233 |
+
"loss": 1.5698,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.56,
|
| 1238 |
+
"grad_norm": 2.08495831489563,
|
| 1239 |
+
"learning_rate": 4.251127271203593e-06,
|
| 1240 |
+
"loss": 1.6086,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.56,
|
| 1245 |
+
"grad_norm": 5.053515911102295,
|
| 1246 |
+
"learning_rate": 4.199911741340631e-06,
|
| 1247 |
+
"loss": 1.6036,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.57,
|
| 1252 |
+
"grad_norm": 3.257359266281128,
|
| 1253 |
+
"learning_rate": 4.148782221388007e-06,
|
| 1254 |
+
"loss": 1.6246,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.57,
|
| 1259 |
+
"grad_norm": 2.1245572566986084,
|
| 1260 |
+
"learning_rate": 4.097744207796119e-06,
|
| 1261 |
+
"loss": 1.5544,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.57,
|
| 1266 |
+
"grad_norm": 2.556488275527954,
|
| 1267 |
+
"learning_rate": 4.04680318717838e-06,
|
| 1268 |
+
"loss": 1.5516,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.58,
|
| 1273 |
+
"grad_norm": 2.438620090484619,
|
| 1274 |
+
"learning_rate": 3.995964635721409e-06,
|
| 1275 |
+
"loss": 1.5524,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.58,
|
| 1280 |
+
"grad_norm": 1.9453068971633911,
|
| 1281 |
+
"learning_rate": 3.945234018596335e-06,
|
| 1282 |
+
"loss": 1.5657,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.58,
|
| 1287 |
+
"grad_norm": 2.2514045238494873,
|
| 1288 |
+
"learning_rate": 3.8946167893712916e-06,
|
| 1289 |
+
"loss": 1.5916,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.59,
|
| 1294 |
+
"grad_norm": 2.2144711017608643,
|
| 1295 |
+
"learning_rate": 3.844118389425154e-06,
|
| 1296 |
+
"loss": 1.6051,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.59,
|
| 1301 |
+
"grad_norm": 2.4618723392486572,
|
| 1302 |
+
"learning_rate": 3.7937442473625787e-06,
|
| 1303 |
+
"loss": 1.5841,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.59,
|
| 1308 |
+
"grad_norm": 2.2561230659484863,
|
| 1309 |
+
"learning_rate": 3.743499778430445e-06,
|
| 1310 |
+
"loss": 1.5469,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.6,
|
| 1315 |
+
"grad_norm": 2.2580950260162354,
|
| 1316 |
+
"learning_rate": 3.6933903839356983e-06,
|
| 1317 |
+
"loss": 1.5618,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.6,
|
| 1322 |
+
"grad_norm": 1.8674182891845703,
|
| 1323 |
+
"learning_rate": 3.6434214506647064e-06,
|
| 1324 |
+
"loss": 1.5266,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.6,
|
| 1329 |
+
"grad_norm": 2.33337664604187,
|
| 1330 |
+
"learning_rate": 3.5935983503041864e-06,
|
| 1331 |
+
"loss": 1.5223,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.61,
|
| 1336 |
+
"grad_norm": 1.912142038345337,
|
| 1337 |
+
"learning_rate": 3.5439264388637407e-06,
|
| 1338 |
+
"loss": 1.5331,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.61,
|
| 1343 |
+
"grad_norm": 2.8374595642089844,
|
| 1344 |
+
"learning_rate": 3.4944110561000785e-06,
|
| 1345 |
+
"loss": 1.6068,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.61,
|
| 1350 |
+
"grad_norm": 2.329653024673462,
|
| 1351 |
+
"learning_rate": 3.4450575249429975e-06,
|
| 1352 |
+
"loss": 1.5324,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.61,
|
| 1357 |
+
"grad_norm": 2.3587117195129395,
|
| 1358 |
+
"learning_rate": 3.3958711509231627e-06,
|
| 1359 |
+
"loss": 1.5542,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.62,
|
| 1364 |
+
"grad_norm": 2.657672643661499,
|
| 1365 |
+
"learning_rate": 3.3468572216017536e-06,
|
| 1366 |
+
"loss": 1.5755,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.62,
|
| 1371 |
+
"grad_norm": 2.17305064201355,
|
| 1372 |
+
"learning_rate": 3.29802100600206e-06,
|
| 1373 |
+
"loss": 1.5489,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.62,
|
| 1378 |
+
"grad_norm": 2.5755293369293213,
|
| 1379 |
+
"learning_rate": 3.249367754043047e-06,
|
| 1380 |
+
"loss": 1.5835,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.63,
|
| 1385 |
+
"grad_norm": 3.943556070327759,
|
| 1386 |
+
"learning_rate": 3.200902695974995e-06,
|
| 1387 |
+
"loss": 1.6003,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.63,
|
| 1392 |
+
"grad_norm": 2.425208568572998,
|
| 1393 |
+
"learning_rate": 3.152631041817244e-06,
|
| 1394 |
+
"loss": 1.5649,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.63,
|
| 1399 |
+
"grad_norm": 2.0712738037109375,
|
| 1400 |
+
"learning_rate": 3.104557980798104e-06,
|
| 1401 |
+
"loss": 1.5363,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.64,
|
| 1406 |
+
"grad_norm": 2.3942067623138428,
|
| 1407 |
+
"learning_rate": 3.056688680797024e-06,
|
| 1408 |
+
"loss": 1.5522,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
}
|
| 1411 |
+
],
|
| 1412 |
+
"logging_steps": 1.0,
|
| 1413 |
+
"max_steps": 313,
|
| 1414 |
+
"num_input_tokens_seen": 0,
|
| 1415 |
+
"num_train_epochs": 1,
|
| 1416 |
+
"save_steps": 50,
|
| 1417 |
+
"total_flos": 235037684727808.0,
|
| 1418 |
+
"train_batch_size": 1,
|
| 1419 |
+
"trial_name": null,
|
| 1420 |
+
"trial_params": null
|
| 1421 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45889d4d7acf868bd2e29b69a995aa63651cb92ff4aa6b4d21447f675a78dfa2
|
| 3 |
+
size 7352
|
checkpoint-200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-250/added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image>": 151646,
|
| 3 |
+
"<|endoftext|>": 151643,
|
| 4 |
+
"<|im_end|>": 151645,
|
| 5 |
+
"<|im_start|>": 151644
|
| 6 |
+
}
|
checkpoint-250/config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/project/mlmlongvideo/checkpoints/pure_text_extend_llava_qwen/checkpoint-200/",
|
| 3 |
+
"add_faster_video": false,
|
| 4 |
+
"add_time_instruction": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlavaQwenForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 151643,
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"faster_token_stride": 10,
|
| 12 |
+
"force_sample": true,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"ignore_index": -100,
|
| 16 |
+
"image_aspect_ratio": "anyres_max_9",
|
| 17 |
+
"image_crop_resolution": null,
|
| 18 |
+
"image_grid_pinpoints": [
|
| 19 |
+
[
|
| 20 |
+
384,
|
| 21 |
+
384
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
384,
|
| 25 |
+
768
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
384,
|
| 29 |
+
1152
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
384,
|
| 33 |
+
1536
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
384,
|
| 37 |
+
1920
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
384,
|
| 41 |
+
2304
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
768,
|
| 45 |
+
384
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
768,
|
| 49 |
+
768
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
768,
|
| 53 |
+
1152
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
768,
|
| 57 |
+
1536
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
768,
|
| 61 |
+
1920
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
768,
|
| 65 |
+
2304
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
1152,
|
| 69 |
+
384
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
1152,
|
| 73 |
+
768
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
1152,
|
| 77 |
+
1152
|
| 78 |
+
],
|
| 79 |
+
[
|
| 80 |
+
1152,
|
| 81 |
+
1536
|
| 82 |
+
],
|
| 83 |
+
[
|
| 84 |
+
1152,
|
| 85 |
+
1920
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
1152,
|
| 89 |
+
2304
|
| 90 |
+
],
|
| 91 |
+
[
|
| 92 |
+
1536,
|
| 93 |
+
384
|
| 94 |
+
],
|
| 95 |
+
[
|
| 96 |
+
1536,
|
| 97 |
+
768
|
| 98 |
+
],
|
| 99 |
+
[
|
| 100 |
+
1536,
|
| 101 |
+
1152
|
| 102 |
+
],
|
| 103 |
+
[
|
| 104 |
+
1536,
|
| 105 |
+
1536
|
| 106 |
+
],
|
| 107 |
+
[
|
| 108 |
+
1536,
|
| 109 |
+
1920
|
| 110 |
+
],
|
| 111 |
+
[
|
| 112 |
+
1536,
|
| 113 |
+
2304
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
1920,
|
| 117 |
+
384
|
| 118 |
+
],
|
| 119 |
+
[
|
| 120 |
+
1920,
|
| 121 |
+
768
|
| 122 |
+
],
|
| 123 |
+
[
|
| 124 |
+
1920,
|
| 125 |
+
1152
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
1920,
|
| 129 |
+
1536
|
| 130 |
+
],
|
| 131 |
+
[
|
| 132 |
+
1920,
|
| 133 |
+
1920
|
| 134 |
+
],
|
| 135 |
+
[
|
| 136 |
+
1920,
|
| 137 |
+
2304
|
| 138 |
+
],
|
| 139 |
+
[
|
| 140 |
+
2304,
|
| 141 |
+
384
|
| 142 |
+
],
|
| 143 |
+
[
|
| 144 |
+
2304,
|
| 145 |
+
768
|
| 146 |
+
],
|
| 147 |
+
[
|
| 148 |
+
2304,
|
| 149 |
+
1152
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
2304,
|
| 153 |
+
1536
|
| 154 |
+
],
|
| 155 |
+
[
|
| 156 |
+
2304,
|
| 157 |
+
1920
|
| 158 |
+
],
|
| 159 |
+
[
|
| 160 |
+
2304,
|
| 161 |
+
2304
|
| 162 |
+
]
|
| 163 |
+
],
|
| 164 |
+
"image_split_resolution": null,
|
| 165 |
+
"image_token_index": 151646,
|
| 166 |
+
"initializer_range": 0.02,
|
| 167 |
+
"intermediate_size": 18944,
|
| 168 |
+
"max_position_embeddings": 32768,
|
| 169 |
+
"max_window_layers": 28,
|
| 170 |
+
"mm_hidden_size": 1152,
|
| 171 |
+
"mm_newline_position": "grid",
|
| 172 |
+
"mm_patch_merge_type": "spatial_unpad",
|
| 173 |
+
"mm_projector_lr": null,
|
| 174 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 175 |
+
"mm_resampler_type": null,
|
| 176 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 177 |
+
"mm_spatial_pool_stride": 2,
|
| 178 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
| 179 |
+
"mm_use_im_patch_token": false,
|
| 180 |
+
"mm_use_im_start_end": false,
|
| 181 |
+
"mm_vision_select_feature": "patch",
|
| 182 |
+
"mm_vision_select_layer": -2,
|
| 183 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
| 184 |
+
"mm_vision_tower_lr": 2e-06,
|
| 185 |
+
"model_type": "llava",
|
| 186 |
+
"num_attention_heads": 28,
|
| 187 |
+
"num_hidden_layers": 28,
|
| 188 |
+
"num_key_value_heads": 4,
|
| 189 |
+
"pos_skipping_range": 4096,
|
| 190 |
+
"projector_hidden_act": "gelu",
|
| 191 |
+
"rms_norm_eps": 1e-06,
|
| 192 |
+
"rope_scaling": null,
|
| 193 |
+
"rope_theta": 1000000000.0,
|
| 194 |
+
"sliding_window": 131072,
|
| 195 |
+
"text_config": {
|
| 196 |
+
"model_type": "llama",
|
| 197 |
+
"vocab_size": 152064
|
| 198 |
+
},
|
| 199 |
+
"tie_word_embeddings": false,
|
| 200 |
+
"tokenizer_model_max_length": 28000,
|
| 201 |
+
"tokenizer_padding_side": "right",
|
| 202 |
+
"torch_dtype": "bfloat16",
|
| 203 |
+
"transformers_version": "4.40.0.dev0",
|
| 204 |
+
"use_cache": false,
|
| 205 |
+
"use_mm_proj": true,
|
| 206 |
+
"use_pos_skipping": false,
|
| 207 |
+
"use_sliding_window": false,
|
| 208 |
+
"vision_config": {
|
| 209 |
+
"hidden_size": 1024,
|
| 210 |
+
"image_size": 336,
|
| 211 |
+
"intermediate_size": 4096,
|
| 212 |
+
"model_type": "clip_vision_model",
|
| 213 |
+
"num_attention_heads": 16,
|
| 214 |
+
"num_hidden_layers": 24,
|
| 215 |
+
"patch_size": 14,
|
| 216 |
+
"projection_dim": 768,
|
| 217 |
+
"vocab_size": 32000
|
| 218 |
+
},
|
| 219 |
+
"vision_feature_layer": -2,
|
| 220 |
+
"vision_feature_select_strategy": "default",
|
| 221 |
+
"vision_tower_pretrained": null
|
| 222 |
+
}
|
checkpoint-250/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.40.0.dev0"
|
| 14 |
+
}
|
checkpoint-250/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|