Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +7 -0
- config.json +203 -0
- global_step500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step500/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- global_step500/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- global_step500/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- global_step500/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- global_step500/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
- global_step500/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
- global_step500/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
- global_step500/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
- global_step500/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
- global_step500/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
- global_step500/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
- global_step500/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
- latest +1 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +737 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- trainer_state.json +3534 -0
- training_args.bin +3 -0
- vocab.json +0 -0
- zero_to_fp32.py +760 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_faster_video": false,
|
| 3 |
+
"add_time_instruction": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DiffusionVLQwenVLForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bd3lm_antithetic_sampling": true,
|
| 9 |
+
"bd3lm_block_aligned_eos": true,
|
| 10 |
+
"bd3lm_block_size": 8,
|
| 11 |
+
"bd3lm_sampling_eps_max": 1.0,
|
| 12 |
+
"bd3lm_sampling_eps_min": 0.001,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"enable_bd3lm": true,
|
| 15 |
+
"eos_token_id": 151645,
|
| 16 |
+
"faster_token_stride": 10,
|
| 17 |
+
"force_sample": false,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 3584,
|
| 20 |
+
"image_aspect_ratio": "pad",
|
| 21 |
+
"image_crop_resolution": null,
|
| 22 |
+
"image_grid_pinpoints": null,
|
| 23 |
+
"image_split_resolution": null,
|
| 24 |
+
"image_token_id": null,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 18944,
|
| 27 |
+
"layer_types": [
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention"
|
| 56 |
+
],
|
| 57 |
+
"max_pixels": 262144,
|
| 58 |
+
"max_position_embeddings": 128000,
|
| 59 |
+
"max_window_layers": 28,
|
| 60 |
+
"min_pixels": 147456,
|
| 61 |
+
"mm_hidden_size": 1280,
|
| 62 |
+
"mm_newline_position": "grid",
|
| 63 |
+
"mm_patch_merge_type": "spatial_unpad",
|
| 64 |
+
"mm_projector_lr": null,
|
| 65 |
+
"mm_projector_type": "qwen_merger",
|
| 66 |
+
"mm_resampler_type": null,
|
| 67 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 68 |
+
"mm_spatial_pool_stride": null,
|
| 69 |
+
"mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
|
| 70 |
+
"mm_use_im_patch_token": false,
|
| 71 |
+
"mm_use_im_start_end": false,
|
| 72 |
+
"mm_vision_select_feature": "patch",
|
| 73 |
+
"mm_vision_select_layer": -2,
|
| 74 |
+
"mm_vision_tower": "/home/ameenali_google_com/DiffusionVL/train/done/diffusionvl_qwenvl_finetune/diffusionvl_qwenvl_finetune",
|
| 75 |
+
"mm_vision_tower_lr": 2e-06,
|
| 76 |
+
"model_max_length": 64768,
|
| 77 |
+
"model_type": "diffusionvl_qwenvl",
|
| 78 |
+
"num_attention_heads": 28,
|
| 79 |
+
"num_hidden_layers": 28,
|
| 80 |
+
"num_key_value_heads": 4,
|
| 81 |
+
"pad_token_id": 151643,
|
| 82 |
+
"pos_skipping_range": 4096,
|
| 83 |
+
"rms_norm_eps": 1e-06,
|
| 84 |
+
"rope_scaling": {
|
| 85 |
+
"mrope_section": [
|
| 86 |
+
16,
|
| 87 |
+
24,
|
| 88 |
+
24
|
| 89 |
+
],
|
| 90 |
+
"rope_type": "default",
|
| 91 |
+
"type": "default"
|
| 92 |
+
},
|
| 93 |
+
"rope_theta": 1000000.0,
|
| 94 |
+
"sliding_window": null,
|
| 95 |
+
"text_config": {
|
| 96 |
+
"architectures": [
|
| 97 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 98 |
+
],
|
| 99 |
+
"attention_dropout": 0.0,
|
| 100 |
+
"bos_token_id": 151643,
|
| 101 |
+
"dtype": "float32",
|
| 102 |
+
"eos_token_id": 151645,
|
| 103 |
+
"hidden_act": "silu",
|
| 104 |
+
"hidden_size": 3584,
|
| 105 |
+
"image_token_id": null,
|
| 106 |
+
"initializer_range": 0.02,
|
| 107 |
+
"intermediate_size": 18944,
|
| 108 |
+
"layer_types": [
|
| 109 |
+
"full_attention",
|
| 110 |
+
"full_attention",
|
| 111 |
+
"full_attention",
|
| 112 |
+
"full_attention",
|
| 113 |
+
"full_attention",
|
| 114 |
+
"full_attention",
|
| 115 |
+
"full_attention",
|
| 116 |
+
"full_attention",
|
| 117 |
+
"full_attention",
|
| 118 |
+
"full_attention",
|
| 119 |
+
"full_attention",
|
| 120 |
+
"full_attention",
|
| 121 |
+
"full_attention",
|
| 122 |
+
"full_attention",
|
| 123 |
+
"full_attention",
|
| 124 |
+
"full_attention",
|
| 125 |
+
"full_attention",
|
| 126 |
+
"full_attention",
|
| 127 |
+
"full_attention",
|
| 128 |
+
"full_attention",
|
| 129 |
+
"full_attention",
|
| 130 |
+
"full_attention",
|
| 131 |
+
"full_attention",
|
| 132 |
+
"full_attention",
|
| 133 |
+
"full_attention",
|
| 134 |
+
"full_attention",
|
| 135 |
+
"full_attention",
|
| 136 |
+
"full_attention"
|
| 137 |
+
],
|
| 138 |
+
"max_position_embeddings": 128000,
|
| 139 |
+
"max_window_layers": 28,
|
| 140 |
+
"model_type": "qwen2_5_vl_text",
|
| 141 |
+
"num_attention_heads": 28,
|
| 142 |
+
"num_hidden_layers": 28,
|
| 143 |
+
"num_key_value_heads": 4,
|
| 144 |
+
"rms_norm_eps": 1e-06,
|
| 145 |
+
"rope_scaling": {
|
| 146 |
+
"mrope_section": [
|
| 147 |
+
16,
|
| 148 |
+
24,
|
| 149 |
+
24
|
| 150 |
+
],
|
| 151 |
+
"rope_type": "default",
|
| 152 |
+
"type": "default"
|
| 153 |
+
},
|
| 154 |
+
"rope_theta": 1000000.0,
|
| 155 |
+
"sliding_window": null,
|
| 156 |
+
"use_cache": true,
|
| 157 |
+
"use_sliding_window": false,
|
| 158 |
+
"video_token_id": null,
|
| 159 |
+
"vision_end_token_id": 151653,
|
| 160 |
+
"vision_start_token_id": 151652,
|
| 161 |
+
"vision_token_id": 151654,
|
| 162 |
+
"vocab_size": 152064
|
| 163 |
+
},
|
| 164 |
+
"tie_word_embeddings": false,
|
| 165 |
+
"tokenizer_model_max_length": 64768,
|
| 166 |
+
"tokenizer_padding_side": "right",
|
| 167 |
+
"transformers_version": "4.57.0",
|
| 168 |
+
"use_cache": false,
|
| 169 |
+
"use_mm_proj": true,
|
| 170 |
+
"use_pos_skipping": false,
|
| 171 |
+
"use_sliding_window": false,
|
| 172 |
+
"video_token_id": null,
|
| 173 |
+
"vision_config": {
|
| 174 |
+
"depth": 32,
|
| 175 |
+
"dtype": "float32",
|
| 176 |
+
"fullatt_block_indexes": [
|
| 177 |
+
7,
|
| 178 |
+
15,
|
| 179 |
+
23,
|
| 180 |
+
31
|
| 181 |
+
],
|
| 182 |
+
"hidden_act": "silu",
|
| 183 |
+
"hidden_size": 1280,
|
| 184 |
+
"in_channels": 3,
|
| 185 |
+
"in_chans": 3,
|
| 186 |
+
"initializer_range": 0.02,
|
| 187 |
+
"intermediate_size": 3420,
|
| 188 |
+
"model_type": "qwen2_5_vl",
|
| 189 |
+
"num_heads": 16,
|
| 190 |
+
"out_hidden_size": 3584,
|
| 191 |
+
"patch_size": 14,
|
| 192 |
+
"spatial_merge_size": 2,
|
| 193 |
+
"spatial_patch_size": 14,
|
| 194 |
+
"temporal_patch_size": 2,
|
| 195 |
+
"tokens_per_second": 2,
|
| 196 |
+
"window_size": 112
|
| 197 |
+
},
|
| 198 |
+
"vision_end_token_id": 151653,
|
| 199 |
+
"vision_start_token_id": 151652,
|
| 200 |
+
"vision_token_id": 151654,
|
| 201 |
+
"vision_tower_pretrained": null,
|
| 202 |
+
"vocab_size": 152064
|
| 203 |
+
}
|
global_step500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ca2c2c379a2ad289ed4748ce1de83ff99aff49f60ed65943421974cd98faf5
|
| 3 |
+
size 11490292385
|
global_step500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e56cf069a5be0a129e0367362f966bfcaba55c6418268c9231eb5cdbe05dd68
|
| 3 |
+
size 11490292385
|
global_step500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81b04a4a09c14933785af0c3d52107dbd93f4a9b7ef676e7adf61e6754fd06f2
|
| 3 |
+
size 11490292385
|
global_step500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d3f2df848c68bddd5c2c93b11061fb5dc837cee320d460f7c86f47d9ba8a562
|
| 3 |
+
size 11490292385
|
global_step500/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7396c3bc68a61329eaacd6b72612ea04ea529de3c248a298122a15e9ea6402c
|
| 3 |
+
size 11490292385
|
global_step500/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f849e3ff13fccba919ff49b3f7884b2bf76a86bff29c5bd991dbebfd323d25d
|
| 3 |
+
size 11490292385
|
global_step500/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ba4981e2d24c22f7bfce04760acf62e50ace01ee2b43d065018bd8f79b1aacb
|
| 3 |
+
size 11490292385
|
global_step500/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9bc47f810223bd767650760256484d74255824eed14d7f315340c5ab2746cb9
|
| 3 |
+
size 11490292385
|
global_step500/zero_pp_rank_0_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:376f83d0cd1ab444daed3da814d588eeb72757ef4fbe6191cf6c7ea16da4752a
|
| 3 |
+
size 158488157
|
global_step500/zero_pp_rank_1_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e43736169d2c5818dd7e9ca3d1d840c1df73ee31cbbd57f7c9946e5ed16d2238
|
| 3 |
+
size 158488157
|
global_step500/zero_pp_rank_2_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e364e631721ad9c43acb6d46156efcc3b69e9dc89d8f014e490e5c350efe7584
|
| 3 |
+
size 158488157
|
global_step500/zero_pp_rank_3_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c87959ecd5212f08279d2809589caa3e0972b34fc4dbe76936c8c339861bdc
|
| 3 |
+
size 158488157
|
global_step500/zero_pp_rank_4_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca3660024e5ec4f5af1c428ff3174d63ac159751b2205d8f24c6e725b45a8a0d
|
| 3 |
+
size 158488157
|
global_step500/zero_pp_rank_5_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a10c54cf64087910b0e0024b97ccdb0f29a830e24e49ecb858caec7af9d98fd
|
| 3 |
+
size 158488157
|
global_step500/zero_pp_rank_6_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e9055cce85b3cc314dff3b4275271328731ffb454d504a9b02341ff05c048e4
|
| 3 |
+
size 158488157
|
global_step500/zero_pp_rank_7_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dd53a88800a10a79a4fb57e184423f1e556978bae5fe054f235107b918386ee
|
| 3 |
+
size 158488157
|
latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step500
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f206d48181bb58d27fdd93f64418508c6614f1a9e8109373b6d791b87fc1c6f2
|
| 3 |
+
size 4877660776
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:174d06328999085611bab7cd8c6bb41c05b44bfe1ac9d8a7d342a4569e054dff
|
| 3 |
+
size 4932751008
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d91e23727975a432343ce35b47aa79b3b8c77436a678582682e36a1ad0205a4
|
| 3 |
+
size 4995019896
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a8b6f72b0c1a040ee09e273932fc50407e69ee872d724d0c9983f2a887d3558
|
| 3 |
+
size 1778992544
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,737 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 848896,
|
| 4 |
+
"total_size": 16584333312
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "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.merger.ln_q.weight": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.mm_projector.merger.mlp.0.bias": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.mm_projector.merger.mlp.0.weight": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.mm_projector.merger.mlp.2.bias": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.mm_projector.merger.mlp.2.weight": "model-00004-of-00004.safetensors",
|
| 350 |
+
"model.norm.weight": "model-00003-of-00004.safetensors",
|
| 351 |
+
"model.vision_tower.vision_tower.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 352 |
+
"model.vision_tower.vision_tower.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 353 |
+
"model.vision_tower.vision_tower.blocks.0.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 354 |
+
"model.vision_tower.vision_tower.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 355 |
+
"model.vision_tower.vision_tower.blocks.0.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 356 |
+
"model.vision_tower.vision_tower.blocks.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 357 |
+
"model.vision_tower.vision_tower.blocks.0.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 358 |
+
"model.vision_tower.vision_tower.blocks.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 359 |
+
"model.vision_tower.vision_tower.blocks.0.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 360 |
+
"model.vision_tower.vision_tower.blocks.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 361 |
+
"model.vision_tower.vision_tower.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
|
| 362 |
+
"model.vision_tower.vision_tower.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
|
| 363 |
+
"model.vision_tower.vision_tower.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 364 |
+
"model.vision_tower.vision_tower.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 365 |
+
"model.vision_tower.vision_tower.blocks.1.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 366 |
+
"model.vision_tower.vision_tower.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 367 |
+
"model.vision_tower.vision_tower.blocks.1.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 368 |
+
"model.vision_tower.vision_tower.blocks.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 369 |
+
"model.vision_tower.vision_tower.blocks.1.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 370 |
+
"model.vision_tower.vision_tower.blocks.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 371 |
+
"model.vision_tower.vision_tower.blocks.1.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 372 |
+
"model.vision_tower.vision_tower.blocks.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 373 |
+
"model.vision_tower.vision_tower.blocks.1.norm1.weight": "model-00003-of-00004.safetensors",
|
| 374 |
+
"model.vision_tower.vision_tower.blocks.1.norm2.weight": "model-00003-of-00004.safetensors",
|
| 375 |
+
"model.vision_tower.vision_tower.blocks.10.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 376 |
+
"model.vision_tower.vision_tower.blocks.10.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 377 |
+
"model.vision_tower.vision_tower.blocks.10.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 378 |
+
"model.vision_tower.vision_tower.blocks.10.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 379 |
+
"model.vision_tower.vision_tower.blocks.10.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 380 |
+
"model.vision_tower.vision_tower.blocks.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 381 |
+
"model.vision_tower.vision_tower.blocks.10.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 382 |
+
"model.vision_tower.vision_tower.blocks.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 383 |
+
"model.vision_tower.vision_tower.blocks.10.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 384 |
+
"model.vision_tower.vision_tower.blocks.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 385 |
+
"model.vision_tower.vision_tower.blocks.10.norm1.weight": "model-00003-of-00004.safetensors",
|
| 386 |
+
"model.vision_tower.vision_tower.blocks.10.norm2.weight": "model-00003-of-00004.safetensors",
|
| 387 |
+
"model.vision_tower.vision_tower.blocks.11.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 388 |
+
"model.vision_tower.vision_tower.blocks.11.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 389 |
+
"model.vision_tower.vision_tower.blocks.11.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 390 |
+
"model.vision_tower.vision_tower.blocks.11.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 391 |
+
"model.vision_tower.vision_tower.blocks.11.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 392 |
+
"model.vision_tower.vision_tower.blocks.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 393 |
+
"model.vision_tower.vision_tower.blocks.11.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 394 |
+
"model.vision_tower.vision_tower.blocks.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 395 |
+
"model.vision_tower.vision_tower.blocks.11.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 396 |
+
"model.vision_tower.vision_tower.blocks.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 397 |
+
"model.vision_tower.vision_tower.blocks.11.norm1.weight": "model-00003-of-00004.safetensors",
|
| 398 |
+
"model.vision_tower.vision_tower.blocks.11.norm2.weight": "model-00003-of-00004.safetensors",
|
| 399 |
+
"model.vision_tower.vision_tower.blocks.12.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 400 |
+
"model.vision_tower.vision_tower.blocks.12.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 401 |
+
"model.vision_tower.vision_tower.blocks.12.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 402 |
+
"model.vision_tower.vision_tower.blocks.12.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 403 |
+
"model.vision_tower.vision_tower.blocks.12.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 404 |
+
"model.vision_tower.vision_tower.blocks.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 405 |
+
"model.vision_tower.vision_tower.blocks.12.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 406 |
+
"model.vision_tower.vision_tower.blocks.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 407 |
+
"model.vision_tower.vision_tower.blocks.12.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 408 |
+
"model.vision_tower.vision_tower.blocks.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 409 |
+
"model.vision_tower.vision_tower.blocks.12.norm1.weight": "model-00003-of-00004.safetensors",
|
| 410 |
+
"model.vision_tower.vision_tower.blocks.12.norm2.weight": "model-00003-of-00004.safetensors",
|
| 411 |
+
"model.vision_tower.vision_tower.blocks.13.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 412 |
+
"model.vision_tower.vision_tower.blocks.13.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 413 |
+
"model.vision_tower.vision_tower.blocks.13.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 414 |
+
"model.vision_tower.vision_tower.blocks.13.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 415 |
+
"model.vision_tower.vision_tower.blocks.13.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 416 |
+
"model.vision_tower.vision_tower.blocks.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 417 |
+
"model.vision_tower.vision_tower.blocks.13.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 418 |
+
"model.vision_tower.vision_tower.blocks.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 419 |
+
"model.vision_tower.vision_tower.blocks.13.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 420 |
+
"model.vision_tower.vision_tower.blocks.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 421 |
+
"model.vision_tower.vision_tower.blocks.13.norm1.weight": "model-00003-of-00004.safetensors",
|
| 422 |
+
"model.vision_tower.vision_tower.blocks.13.norm2.weight": "model-00003-of-00004.safetensors",
|
| 423 |
+
"model.vision_tower.vision_tower.blocks.14.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 424 |
+
"model.vision_tower.vision_tower.blocks.14.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 425 |
+
"model.vision_tower.vision_tower.blocks.14.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 426 |
+
"model.vision_tower.vision_tower.blocks.14.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 427 |
+
"model.vision_tower.vision_tower.blocks.14.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 428 |
+
"model.vision_tower.vision_tower.blocks.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 429 |
+
"model.vision_tower.vision_tower.blocks.14.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 430 |
+
"model.vision_tower.vision_tower.blocks.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 431 |
+
"model.vision_tower.vision_tower.blocks.14.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 432 |
+
"model.vision_tower.vision_tower.blocks.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 433 |
+
"model.vision_tower.vision_tower.blocks.14.norm1.weight": "model-00003-of-00004.safetensors",
|
| 434 |
+
"model.vision_tower.vision_tower.blocks.14.norm2.weight": "model-00003-of-00004.safetensors",
|
| 435 |
+
"model.vision_tower.vision_tower.blocks.15.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 436 |
+
"model.vision_tower.vision_tower.blocks.15.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 437 |
+
"model.vision_tower.vision_tower.blocks.15.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 438 |
+
"model.vision_tower.vision_tower.blocks.15.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 439 |
+
"model.vision_tower.vision_tower.blocks.15.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 440 |
+
"model.vision_tower.vision_tower.blocks.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 441 |
+
"model.vision_tower.vision_tower.blocks.15.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 442 |
+
"model.vision_tower.vision_tower.blocks.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 443 |
+
"model.vision_tower.vision_tower.blocks.15.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 444 |
+
"model.vision_tower.vision_tower.blocks.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 445 |
+
"model.vision_tower.vision_tower.blocks.15.norm1.weight": "model-00003-of-00004.safetensors",
|
| 446 |
+
"model.vision_tower.vision_tower.blocks.15.norm2.weight": "model-00003-of-00004.safetensors",
|
| 447 |
+
"model.vision_tower.vision_tower.blocks.16.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 448 |
+
"model.vision_tower.vision_tower.blocks.16.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 449 |
+
"model.vision_tower.vision_tower.blocks.16.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 450 |
+
"model.vision_tower.vision_tower.blocks.16.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 451 |
+
"model.vision_tower.vision_tower.blocks.16.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.vision_tower.vision_tower.blocks.16.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.vision_tower.vision_tower.blocks.16.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 454 |
+
"model.vision_tower.vision_tower.blocks.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 455 |
+
"model.vision_tower.vision_tower.blocks.16.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 456 |
+
"model.vision_tower.vision_tower.blocks.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 457 |
+
"model.vision_tower.vision_tower.blocks.16.norm1.weight": "model-00003-of-00004.safetensors",
|
| 458 |
+
"model.vision_tower.vision_tower.blocks.16.norm2.weight": "model-00003-of-00004.safetensors",
|
| 459 |
+
"model.vision_tower.vision_tower.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.vision_tower.vision_tower.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.vision_tower.vision_tower.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.vision_tower.vision_tower.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.vision_tower.vision_tower.blocks.17.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.vision_tower.vision_tower.blocks.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.vision_tower.vision_tower.blocks.17.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.vision_tower.vision_tower.blocks.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.vision_tower.vision_tower.blocks.17.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.vision_tower.vision_tower.blocks.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.vision_tower.vision_tower.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.vision_tower.vision_tower.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.vision_tower.vision_tower.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.vision_tower.vision_tower.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.vision_tower.vision_tower.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.vision_tower.vision_tower.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.vision_tower.vision_tower.blocks.18.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.vision_tower.vision_tower.blocks.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.vision_tower.vision_tower.blocks.18.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.vision_tower.vision_tower.blocks.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.vision_tower.vision_tower.blocks.18.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.vision_tower.vision_tower.blocks.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.vision_tower.vision_tower.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.vision_tower.vision_tower.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.vision_tower.vision_tower.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.vision_tower.vision_tower.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.vision_tower.vision_tower.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.vision_tower.vision_tower.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.vision_tower.vision_tower.blocks.19.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.vision_tower.vision_tower.blocks.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.vision_tower.vision_tower.blocks.19.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.vision_tower.vision_tower.blocks.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.vision_tower.vision_tower.blocks.19.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.vision_tower.vision_tower.blocks.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.vision_tower.vision_tower.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.vision_tower.vision_tower.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.vision_tower.vision_tower.blocks.2.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 496 |
+
"model.vision_tower.vision_tower.blocks.2.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 497 |
+
"model.vision_tower.vision_tower.blocks.2.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 498 |
+
"model.vision_tower.vision_tower.blocks.2.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 499 |
+
"model.vision_tower.vision_tower.blocks.2.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 500 |
+
"model.vision_tower.vision_tower.blocks.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 501 |
+
"model.vision_tower.vision_tower.blocks.2.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 502 |
+
"model.vision_tower.vision_tower.blocks.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 503 |
+
"model.vision_tower.vision_tower.blocks.2.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 504 |
+
"model.vision_tower.vision_tower.blocks.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 505 |
+
"model.vision_tower.vision_tower.blocks.2.norm1.weight": "model-00003-of-00004.safetensors",
|
| 506 |
+
"model.vision_tower.vision_tower.blocks.2.norm2.weight": "model-00003-of-00004.safetensors",
|
| 507 |
+
"model.vision_tower.vision_tower.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.vision_tower.vision_tower.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.vision_tower.vision_tower.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.vision_tower.vision_tower.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.vision_tower.vision_tower.blocks.20.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.vision_tower.vision_tower.blocks.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.vision_tower.vision_tower.blocks.20.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.vision_tower.vision_tower.blocks.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.vision_tower.vision_tower.blocks.20.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.vision_tower.vision_tower.blocks.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.vision_tower.vision_tower.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.vision_tower.vision_tower.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.vision_tower.vision_tower.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.vision_tower.vision_tower.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.vision_tower.vision_tower.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.vision_tower.vision_tower.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.vision_tower.vision_tower.blocks.21.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.vision_tower.vision_tower.blocks.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.vision_tower.vision_tower.blocks.21.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.vision_tower.vision_tower.blocks.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.vision_tower.vision_tower.blocks.21.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.vision_tower.vision_tower.blocks.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.vision_tower.vision_tower.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.vision_tower.vision_tower.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.vision_tower.vision_tower.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.vision_tower.vision_tower.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.vision_tower.vision_tower.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.vision_tower.vision_tower.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.vision_tower.vision_tower.blocks.22.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.vision_tower.vision_tower.blocks.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.vision_tower.vision_tower.blocks.22.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.vision_tower.vision_tower.blocks.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.vision_tower.vision_tower.blocks.22.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.vision_tower.vision_tower.blocks.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.vision_tower.vision_tower.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.vision_tower.vision_tower.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.vision_tower.vision_tower.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.vision_tower.vision_tower.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.vision_tower.vision_tower.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.vision_tower.vision_tower.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.vision_tower.vision_tower.blocks.23.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.vision_tower.vision_tower.blocks.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.vision_tower.vision_tower.blocks.23.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.vision_tower.vision_tower.blocks.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.vision_tower.vision_tower.blocks.23.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.vision_tower.vision_tower.blocks.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.vision_tower.vision_tower.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.vision_tower.vision_tower.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.vision_tower.vision_tower.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.vision_tower.vision_tower.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.vision_tower.vision_tower.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.vision_tower.vision_tower.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.vision_tower.vision_tower.blocks.24.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.vision_tower.vision_tower.blocks.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.vision_tower.vision_tower.blocks.24.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.vision_tower.vision_tower.blocks.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.vision_tower.vision_tower.blocks.24.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.vision_tower.vision_tower.blocks.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.vision_tower.vision_tower.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.vision_tower.vision_tower.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.vision_tower.vision_tower.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.vision_tower.vision_tower.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.vision_tower.vision_tower.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.vision_tower.vision_tower.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.vision_tower.vision_tower.blocks.25.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.vision_tower.vision_tower.blocks.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.vision_tower.vision_tower.blocks.25.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.vision_tower.vision_tower.blocks.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.vision_tower.vision_tower.blocks.25.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.vision_tower.vision_tower.blocks.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.vision_tower.vision_tower.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.vision_tower.vision_tower.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.vision_tower.vision_tower.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.vision_tower.vision_tower.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.vision_tower.vision_tower.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.vision_tower.vision_tower.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.vision_tower.vision_tower.blocks.26.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.vision_tower.vision_tower.blocks.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.vision_tower.vision_tower.blocks.26.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.vision_tower.vision_tower.blocks.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.vision_tower.vision_tower.blocks.26.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.vision_tower.vision_tower.blocks.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.vision_tower.vision_tower.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.vision_tower.vision_tower.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.vision_tower.vision_tower.blocks.27.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.vision_tower.vision_tower.blocks.27.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.vision_tower.vision_tower.blocks.27.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.vision_tower.vision_tower.blocks.27.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.vision_tower.vision_tower.blocks.27.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.vision_tower.vision_tower.blocks.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.vision_tower.vision_tower.blocks.27.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.vision_tower.vision_tower.blocks.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.vision_tower.vision_tower.blocks.27.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.vision_tower.vision_tower.blocks.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.vision_tower.vision_tower.blocks.27.norm1.weight": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.vision_tower.vision_tower.blocks.27.norm2.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.vision_tower.vision_tower.blocks.28.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.vision_tower.vision_tower.blocks.28.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.vision_tower.vision_tower.blocks.28.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.vision_tower.vision_tower.blocks.28.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.vision_tower.vision_tower.blocks.28.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.vision_tower.vision_tower.blocks.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.vision_tower.vision_tower.blocks.28.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.vision_tower.vision_tower.blocks.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.vision_tower.vision_tower.blocks.28.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.vision_tower.vision_tower.blocks.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.vision_tower.vision_tower.blocks.28.norm1.weight": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.vision_tower.vision_tower.blocks.28.norm2.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.vision_tower.vision_tower.blocks.29.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.vision_tower.vision_tower.blocks.29.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.vision_tower.vision_tower.blocks.29.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.vision_tower.vision_tower.blocks.29.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.vision_tower.vision_tower.blocks.29.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.vision_tower.vision_tower.blocks.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.vision_tower.vision_tower.blocks.29.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.vision_tower.vision_tower.blocks.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.vision_tower.vision_tower.blocks.29.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.vision_tower.vision_tower.blocks.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.vision_tower.vision_tower.blocks.29.norm1.weight": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.vision_tower.vision_tower.blocks.29.norm2.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.vision_tower.vision_tower.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 628 |
+
"model.vision_tower.vision_tower.blocks.3.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 629 |
+
"model.vision_tower.vision_tower.blocks.3.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 630 |
+
"model.vision_tower.vision_tower.blocks.3.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 631 |
+
"model.vision_tower.vision_tower.blocks.3.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 632 |
+
"model.vision_tower.vision_tower.blocks.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 633 |
+
"model.vision_tower.vision_tower.blocks.3.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 634 |
+
"model.vision_tower.vision_tower.blocks.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 635 |
+
"model.vision_tower.vision_tower.blocks.3.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 636 |
+
"model.vision_tower.vision_tower.blocks.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 637 |
+
"model.vision_tower.vision_tower.blocks.3.norm1.weight": "model-00003-of-00004.safetensors",
|
| 638 |
+
"model.vision_tower.vision_tower.blocks.3.norm2.weight": "model-00003-of-00004.safetensors",
|
| 639 |
+
"model.vision_tower.vision_tower.blocks.30.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.vision_tower.vision_tower.blocks.30.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.vision_tower.vision_tower.blocks.30.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.vision_tower.vision_tower.blocks.30.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.vision_tower.vision_tower.blocks.30.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.vision_tower.vision_tower.blocks.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.vision_tower.vision_tower.blocks.30.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.vision_tower.vision_tower.blocks.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.vision_tower.vision_tower.blocks.30.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.vision_tower.vision_tower.blocks.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.vision_tower.vision_tower.blocks.30.norm1.weight": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.vision_tower.vision_tower.blocks.30.norm2.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.vision_tower.vision_tower.blocks.31.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.vision_tower.vision_tower.blocks.31.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.vision_tower.vision_tower.blocks.31.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.vision_tower.vision_tower.blocks.31.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.vision_tower.vision_tower.blocks.31.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.vision_tower.vision_tower.blocks.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.vision_tower.vision_tower.blocks.31.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.vision_tower.vision_tower.blocks.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.vision_tower.vision_tower.blocks.31.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.vision_tower.vision_tower.blocks.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.vision_tower.vision_tower.blocks.31.norm1.weight": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.vision_tower.vision_tower.blocks.31.norm2.weight": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.vision_tower.vision_tower.blocks.4.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 664 |
+
"model.vision_tower.vision_tower.blocks.4.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 665 |
+
"model.vision_tower.vision_tower.blocks.4.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 666 |
+
"model.vision_tower.vision_tower.blocks.4.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 667 |
+
"model.vision_tower.vision_tower.blocks.4.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 668 |
+
"model.vision_tower.vision_tower.blocks.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 669 |
+
"model.vision_tower.vision_tower.blocks.4.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 670 |
+
"model.vision_tower.vision_tower.blocks.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 671 |
+
"model.vision_tower.vision_tower.blocks.4.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 672 |
+
"model.vision_tower.vision_tower.blocks.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 673 |
+
"model.vision_tower.vision_tower.blocks.4.norm1.weight": "model-00003-of-00004.safetensors",
|
| 674 |
+
"model.vision_tower.vision_tower.blocks.4.norm2.weight": "model-00003-of-00004.safetensors",
|
| 675 |
+
"model.vision_tower.vision_tower.blocks.5.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 676 |
+
"model.vision_tower.vision_tower.blocks.5.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 677 |
+
"model.vision_tower.vision_tower.blocks.5.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 678 |
+
"model.vision_tower.vision_tower.blocks.5.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 679 |
+
"model.vision_tower.vision_tower.blocks.5.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 680 |
+
"model.vision_tower.vision_tower.blocks.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.vision_tower.vision_tower.blocks.5.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 682 |
+
"model.vision_tower.vision_tower.blocks.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 683 |
+
"model.vision_tower.vision_tower.blocks.5.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 684 |
+
"model.vision_tower.vision_tower.blocks.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 685 |
+
"model.vision_tower.vision_tower.blocks.5.norm1.weight": "model-00003-of-00004.safetensors",
|
| 686 |
+
"model.vision_tower.vision_tower.blocks.5.norm2.weight": "model-00003-of-00004.safetensors",
|
| 687 |
+
"model.vision_tower.vision_tower.blocks.6.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 688 |
+
"model.vision_tower.vision_tower.blocks.6.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 689 |
+
"model.vision_tower.vision_tower.blocks.6.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 690 |
+
"model.vision_tower.vision_tower.blocks.6.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 691 |
+
"model.vision_tower.vision_tower.blocks.6.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 692 |
+
"model.vision_tower.vision_tower.blocks.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 693 |
+
"model.vision_tower.vision_tower.blocks.6.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 694 |
+
"model.vision_tower.vision_tower.blocks.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 695 |
+
"model.vision_tower.vision_tower.blocks.6.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 696 |
+
"model.vision_tower.vision_tower.blocks.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 697 |
+
"model.vision_tower.vision_tower.blocks.6.norm1.weight": "model-00003-of-00004.safetensors",
|
| 698 |
+
"model.vision_tower.vision_tower.blocks.6.norm2.weight": "model-00003-of-00004.safetensors",
|
| 699 |
+
"model.vision_tower.vision_tower.blocks.7.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 700 |
+
"model.vision_tower.vision_tower.blocks.7.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 701 |
+
"model.vision_tower.vision_tower.blocks.7.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 702 |
+
"model.vision_tower.vision_tower.blocks.7.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 703 |
+
"model.vision_tower.vision_tower.blocks.7.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 704 |
+
"model.vision_tower.vision_tower.blocks.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 705 |
+
"model.vision_tower.vision_tower.blocks.7.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 706 |
+
"model.vision_tower.vision_tower.blocks.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 707 |
+
"model.vision_tower.vision_tower.blocks.7.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 708 |
+
"model.vision_tower.vision_tower.blocks.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 709 |
+
"model.vision_tower.vision_tower.blocks.7.norm1.weight": "model-00003-of-00004.safetensors",
|
| 710 |
+
"model.vision_tower.vision_tower.blocks.7.norm2.weight": "model-00003-of-00004.safetensors",
|
| 711 |
+
"model.vision_tower.vision_tower.blocks.8.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 712 |
+
"model.vision_tower.vision_tower.blocks.8.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 713 |
+
"model.vision_tower.vision_tower.blocks.8.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 714 |
+
"model.vision_tower.vision_tower.blocks.8.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 715 |
+
"model.vision_tower.vision_tower.blocks.8.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 716 |
+
"model.vision_tower.vision_tower.blocks.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 717 |
+
"model.vision_tower.vision_tower.blocks.8.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 718 |
+
"model.vision_tower.vision_tower.blocks.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 719 |
+
"model.vision_tower.vision_tower.blocks.8.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 720 |
+
"model.vision_tower.vision_tower.blocks.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 721 |
+
"model.vision_tower.vision_tower.blocks.8.norm1.weight": "model-00003-of-00004.safetensors",
|
| 722 |
+
"model.vision_tower.vision_tower.blocks.8.norm2.weight": "model-00003-of-00004.safetensors",
|
| 723 |
+
"model.vision_tower.vision_tower.blocks.9.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 724 |
+
"model.vision_tower.vision_tower.blocks.9.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 725 |
+
"model.vision_tower.vision_tower.blocks.9.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 726 |
+
"model.vision_tower.vision_tower.blocks.9.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 727 |
+
"model.vision_tower.vision_tower.blocks.9.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
| 728 |
+
"model.vision_tower.vision_tower.blocks.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 729 |
+
"model.vision_tower.vision_tower.blocks.9.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
| 730 |
+
"model.vision_tower.vision_tower.blocks.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 731 |
+
"model.vision_tower.vision_tower.blocks.9.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
| 732 |
+
"model.vision_tower.vision_tower.blocks.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 733 |
+
"model.vision_tower.vision_tower.blocks.9.norm1.weight": "model-00003-of-00004.safetensors",
|
| 734 |
+
"model.vision_tower.vision_tower.blocks.9.norm2.weight": "model-00003-of-00004.safetensors",
|
| 735 |
+
"model.vision_tower.vision_tower.patch_embed.proj.weight": "model-00003-of-00004.safetensors"
|
| 736 |
+
}
|
| 737 |
+
}
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a94e2a4624e82d10cd334ad99537f34c52dd9981416c7fbbe7084b95c29a38a
|
| 3 |
+
size 16389
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:972c497f8de9c94b6b4b04cedcdd3904930fa2c051bb5782b2b94845b695edaa
|
| 3 |
+
size 16389
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2127c66d4eb5d955229e5695b340bd655c5a05f1cb610fd0af3499d36c1a07f
|
| 3 |
+
size 16389
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b46ed775a486d1dcc9e1b9ae60dd7888a28dd45b79ea7352ed1ca18408626283
|
| 3 |
+
size 16389
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd9d24c0bc529c44cfb907242b0a13f1b7125b017b6f0986e0aef7e809f43067
|
| 3 |
+
size 16389
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1ca4efe1751f31f5b60143b2752563d9e30805e7b712a340f363b380e80177e
|
| 3 |
+
size 16389
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c9e9cb2087d3e66b439a0b2ffbff364525debf4397beeceee7924a9510a1dda
|
| 3 |
+
size 16389
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39e6e59c2cdd19852e97e3fd21c9b44c0ced67b067de2c85e9fbc5db2b96afa8
|
| 3 |
+
size 16389
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03670042ff98b5b35181e3713852a74c0bd2e3ea30e94727ab1476b7d4394645
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 64768,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"padding_side": "right",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0029388599574453078,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 5.877719914890616e-06,
|
| 14 |
+
"grad_norm": 42.02911487791772,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 2.345,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.1755439829781232e-05,
|
| 21 |
+
"grad_norm": 50.85266375433337,
|
| 22 |
+
"learning_rate": 1.958863858961802e-09,
|
| 23 |
+
"loss": 2.6978,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.763315974467185e-05,
|
| 28 |
+
"grad_norm": 47.291375384339034,
|
| 29 |
+
"learning_rate": 3.917727717923604e-09,
|
| 30 |
+
"loss": 2.3933,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.3510879659562463e-05,
|
| 35 |
+
"grad_norm": 46.527545509164675,
|
| 36 |
+
"learning_rate": 5.876591576885407e-09,
|
| 37 |
+
"loss": 2.44,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.938859957445308e-05,
|
| 42 |
+
"grad_norm": 46.977570907906056,
|
| 43 |
+
"learning_rate": 7.835455435847208e-09,
|
| 44 |
+
"loss": 2.5181,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.52663194893437e-05,
|
| 49 |
+
"grad_norm": 36.871286445588595,
|
| 50 |
+
"learning_rate": 9.794319294809012e-09,
|
| 51 |
+
"loss": 2.6618,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 4.114403940423431e-05,
|
| 56 |
+
"grad_norm": 46.385420313464735,
|
| 57 |
+
"learning_rate": 1.1753183153770814e-08,
|
| 58 |
+
"loss": 2.6994,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.702175931912493e-05,
|
| 63 |
+
"grad_norm": 39.33244145538988,
|
| 64 |
+
"learning_rate": 1.3712047012732617e-08,
|
| 65 |
+
"loss": 2.2604,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.289947923401554e-05,
|
| 70 |
+
"grad_norm": 42.2604654612667,
|
| 71 |
+
"learning_rate": 1.5670910871694417e-08,
|
| 72 |
+
"loss": 2.5037,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.877719914890616e-05,
|
| 77 |
+
"grad_norm": 53.35405279929954,
|
| 78 |
+
"learning_rate": 1.7629774730656222e-08,
|
| 79 |
+
"loss": 2.7682,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.465491906379677e-05,
|
| 84 |
+
"grad_norm": 61.096031238374245,
|
| 85 |
+
"learning_rate": 1.9588638589618025e-08,
|
| 86 |
+
"loss": 2.5123,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.05326389786874e-05,
|
| 91 |
+
"grad_norm": 34.35305577230433,
|
| 92 |
+
"learning_rate": 2.1547502448579827e-08,
|
| 93 |
+
"loss": 2.4231,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 7.6410358893578e-05,
|
| 98 |
+
"grad_norm": 46.32288420684808,
|
| 99 |
+
"learning_rate": 2.350636630754163e-08,
|
| 100 |
+
"loss": 2.5667,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 8.228807880846862e-05,
|
| 105 |
+
"grad_norm": 39.6869121212424,
|
| 106 |
+
"learning_rate": 2.546523016650343e-08,
|
| 107 |
+
"loss": 2.6537,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.816579872335923e-05,
|
| 112 |
+
"grad_norm": 38.4473023992043,
|
| 113 |
+
"learning_rate": 2.7424094025465233e-08,
|
| 114 |
+
"loss": 2.5401,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 9.404351863824985e-05,
|
| 119 |
+
"grad_norm": 35.67137817810734,
|
| 120 |
+
"learning_rate": 2.9382957884427032e-08,
|
| 121 |
+
"loss": 2.2622,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 9.992123855314047e-05,
|
| 126 |
+
"grad_norm": 33.63114184351338,
|
| 127 |
+
"learning_rate": 3.1341821743388834e-08,
|
| 128 |
+
"loss": 2.5217,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.00010579895846803108,
|
| 133 |
+
"grad_norm": 39.43620507790292,
|
| 134 |
+
"learning_rate": 3.3300685602350636e-08,
|
| 135 |
+
"loss": 2.4657,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.0001116766783829217,
|
| 140 |
+
"grad_norm": 45.917969482317524,
|
| 141 |
+
"learning_rate": 3.5259549461312445e-08,
|
| 142 |
+
"loss": 2.3468,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.00011755439829781231,
|
| 147 |
+
"grad_norm": 38.078954655149694,
|
| 148 |
+
"learning_rate": 3.721841332027425e-08,
|
| 149 |
+
"loss": 2.508,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.00012343211821270293,
|
| 154 |
+
"grad_norm": 34.493184716086255,
|
| 155 |
+
"learning_rate": 3.917727717923605e-08,
|
| 156 |
+
"loss": 2.2334,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.00012930983812759354,
|
| 161 |
+
"grad_norm": 46.491961411990125,
|
| 162 |
+
"learning_rate": 4.1136141038197845e-08,
|
| 163 |
+
"loss": 2.2112,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.00013518755804248415,
|
| 168 |
+
"grad_norm": 48.89994737190844,
|
| 169 |
+
"learning_rate": 4.3095004897159653e-08,
|
| 170 |
+
"loss": 2.4262,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0001410652779573748,
|
| 175 |
+
"grad_norm": 30.579301696325047,
|
| 176 |
+
"learning_rate": 4.505386875612145e-08,
|
| 177 |
+
"loss": 2.7459,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0001469429978722654,
|
| 182 |
+
"grad_norm": 39.08437638852243,
|
| 183 |
+
"learning_rate": 4.701273261508326e-08,
|
| 184 |
+
"loss": 2.5459,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.000152820717787156,
|
| 189 |
+
"grad_norm": 56.085123066265226,
|
| 190 |
+
"learning_rate": 4.897159647404506e-08,
|
| 191 |
+
"loss": 2.7213,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.00015869843770204662,
|
| 196 |
+
"grad_norm": 36.85335937419735,
|
| 197 |
+
"learning_rate": 5.093046033300686e-08,
|
| 198 |
+
"loss": 2.287,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.00016457615761693723,
|
| 203 |
+
"grad_norm": 34.87118828311202,
|
| 204 |
+
"learning_rate": 5.2889324191968664e-08,
|
| 205 |
+
"loss": 2.3702,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.00017045387753182785,
|
| 210 |
+
"grad_norm": 43.175332148056896,
|
| 211 |
+
"learning_rate": 5.4848188050930466e-08,
|
| 212 |
+
"loss": 2.2459,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.00017633159744671846,
|
| 217 |
+
"grad_norm": 32.266335142325374,
|
| 218 |
+
"learning_rate": 5.680705190989227e-08,
|
| 219 |
+
"loss": 2.5008,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.0001822093173616091,
|
| 224 |
+
"grad_norm": 43.65661992394771,
|
| 225 |
+
"learning_rate": 5.8765915768854064e-08,
|
| 226 |
+
"loss": 2.6555,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0001880870372764997,
|
| 231 |
+
"grad_norm": 43.84715059263309,
|
| 232 |
+
"learning_rate": 6.072477962781587e-08,
|
| 233 |
+
"loss": 2.3591,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.00019396475719139032,
|
| 238 |
+
"grad_norm": 43.406252511374625,
|
| 239 |
+
"learning_rate": 6.268364348677767e-08,
|
| 240 |
+
"loss": 2.0988,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.00019984247710628093,
|
| 245 |
+
"grad_norm": 37.561883875948865,
|
| 246 |
+
"learning_rate": 6.464250734573948e-08,
|
| 247 |
+
"loss": 2.4671,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.00020572019702117154,
|
| 252 |
+
"grad_norm": 49.1466070616366,
|
| 253 |
+
"learning_rate": 6.660137120470127e-08,
|
| 254 |
+
"loss": 2.532,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.00021159791693606215,
|
| 259 |
+
"grad_norm": 39.32458572492562,
|
| 260 |
+
"learning_rate": 6.856023506366308e-08,
|
| 261 |
+
"loss": 2.5906,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.00021747563685095277,
|
| 266 |
+
"grad_norm": 45.58644039702116,
|
| 267 |
+
"learning_rate": 7.051909892262489e-08,
|
| 268 |
+
"loss": 2.7685,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0002233533567658434,
|
| 273 |
+
"grad_norm": 34.380760113202136,
|
| 274 |
+
"learning_rate": 7.247796278158669e-08,
|
| 275 |
+
"loss": 2.2058,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.00022923107668073402,
|
| 280 |
+
"grad_norm": 33.75738146740774,
|
| 281 |
+
"learning_rate": 7.44368266405485e-08,
|
| 282 |
+
"loss": 2.1421,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.00023510879659562463,
|
| 287 |
+
"grad_norm": 58.77325378288631,
|
| 288 |
+
"learning_rate": 7.639569049951029e-08,
|
| 289 |
+
"loss": 2.173,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.00024098651651051524,
|
| 294 |
+
"grad_norm": 48.68423052986121,
|
| 295 |
+
"learning_rate": 7.83545543584721e-08,
|
| 296 |
+
"loss": 2.4029,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.00024686423642540585,
|
| 301 |
+
"grad_norm": 49.077656798823305,
|
| 302 |
+
"learning_rate": 8.031341821743391e-08,
|
| 303 |
+
"loss": 2.5765,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.00025274195634029646,
|
| 308 |
+
"grad_norm": 41.20173204960673,
|
| 309 |
+
"learning_rate": 8.227228207639569e-08,
|
| 310 |
+
"loss": 2.3414,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0002586196762551871,
|
| 315 |
+
"grad_norm": 35.10746373400446,
|
| 316 |
+
"learning_rate": 8.42311459353575e-08,
|
| 317 |
+
"loss": 2.0016,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.0002644973961700777,
|
| 322 |
+
"grad_norm": 49.861035229921576,
|
| 323 |
+
"learning_rate": 8.619000979431931e-08,
|
| 324 |
+
"loss": 2.7158,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.0002703751160849683,
|
| 329 |
+
"grad_norm": 40.8079607718849,
|
| 330 |
+
"learning_rate": 8.814887365328112e-08,
|
| 331 |
+
"loss": 2.3449,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.0002762528359998589,
|
| 336 |
+
"grad_norm": 37.41904404905814,
|
| 337 |
+
"learning_rate": 9.01077375122429e-08,
|
| 338 |
+
"loss": 2.4975,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.0002821305559147496,
|
| 343 |
+
"grad_norm": 46.57678726138831,
|
| 344 |
+
"learning_rate": 9.20666013712047e-08,
|
| 345 |
+
"loss": 2.5687,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.0002880082758296402,
|
| 350 |
+
"grad_norm": 31.29394678361741,
|
| 351 |
+
"learning_rate": 9.402546523016652e-08,
|
| 352 |
+
"loss": 2.1173,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.0002938859957445308,
|
| 357 |
+
"grad_norm": 37.33288236667374,
|
| 358 |
+
"learning_rate": 9.598432908912831e-08,
|
| 359 |
+
"loss": 2.6534,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.0002997637156594214,
|
| 364 |
+
"grad_norm": 34.06484936870885,
|
| 365 |
+
"learning_rate": 9.794319294809012e-08,
|
| 366 |
+
"loss": 2.3917,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.000305641435574312,
|
| 371 |
+
"grad_norm": 48.254524144077536,
|
| 372 |
+
"learning_rate": 9.990205680705191e-08,
|
| 373 |
+
"loss": 2.2721,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.00031151915548920263,
|
| 378 |
+
"grad_norm": 47.77507733499728,
|
| 379 |
+
"learning_rate": 1.0186092066601372e-07,
|
| 380 |
+
"loss": 2.5648,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.00031739687540409324,
|
| 385 |
+
"grad_norm": 39.93090562192217,
|
| 386 |
+
"learning_rate": 1.0381978452497552e-07,
|
| 387 |
+
"loss": 2.7048,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.00032327459531898386,
|
| 392 |
+
"grad_norm": 45.71987876675893,
|
| 393 |
+
"learning_rate": 1.0577864838393733e-07,
|
| 394 |
+
"loss": 2.4546,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.00032915231523387447,
|
| 399 |
+
"grad_norm": 26.902504182785798,
|
| 400 |
+
"learning_rate": 1.0773751224289912e-07,
|
| 401 |
+
"loss": 2.128,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.0003350300351487651,
|
| 406 |
+
"grad_norm": 26.86954323404998,
|
| 407 |
+
"learning_rate": 1.0969637610186093e-07,
|
| 408 |
+
"loss": 2.3557,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.0003409077550636557,
|
| 413 |
+
"grad_norm": 55.89037077858931,
|
| 414 |
+
"learning_rate": 1.1165523996082273e-07,
|
| 415 |
+
"loss": 2.8119,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.0003467854749785463,
|
| 420 |
+
"grad_norm": 42.77040196686266,
|
| 421 |
+
"learning_rate": 1.1361410381978454e-07,
|
| 422 |
+
"loss": 2.6056,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0003526631948934369,
|
| 427 |
+
"grad_norm": 30.77897770617208,
|
| 428 |
+
"learning_rate": 1.1557296767874635e-07,
|
| 429 |
+
"loss": 2.1565,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.0003585409148083276,
|
| 434 |
+
"grad_norm": 28.082285297919455,
|
| 435 |
+
"learning_rate": 1.1753183153770813e-07,
|
| 436 |
+
"loss": 2.3056,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.0003644186347232182,
|
| 441 |
+
"grad_norm": 51.89300221840249,
|
| 442 |
+
"learning_rate": 1.1949069539666995e-07,
|
| 443 |
+
"loss": 2.3585,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.0003702963546381088,
|
| 448 |
+
"grad_norm": 29.104662619846845,
|
| 449 |
+
"learning_rate": 1.2144955925563174e-07,
|
| 450 |
+
"loss": 2.4636,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.0003761740745529994,
|
| 455 |
+
"grad_norm": 40.89677913796411,
|
| 456 |
+
"learning_rate": 1.2340842311459354e-07,
|
| 457 |
+
"loss": 2.3843,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.00038205179446789,
|
| 462 |
+
"grad_norm": 29.068818361443615,
|
| 463 |
+
"learning_rate": 1.2536728697355534e-07,
|
| 464 |
+
"loss": 2.3794,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.00038792951438278064,
|
| 469 |
+
"grad_norm": 27.754009467402703,
|
| 470 |
+
"learning_rate": 1.2732615083251716e-07,
|
| 471 |
+
"loss": 2.3511,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.00039380723429767125,
|
| 476 |
+
"grad_norm": 38.91129852443923,
|
| 477 |
+
"learning_rate": 1.2928501469147895e-07,
|
| 478 |
+
"loss": 2.2822,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.00039968495421256186,
|
| 483 |
+
"grad_norm": 62.770631236350724,
|
| 484 |
+
"learning_rate": 1.3124387855044075e-07,
|
| 485 |
+
"loss": 2.5637,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.00040556267412745247,
|
| 490 |
+
"grad_norm": 43.90327612952796,
|
| 491 |
+
"learning_rate": 1.3320274240940254e-07,
|
| 492 |
+
"loss": 2.5136,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.0004114403940423431,
|
| 497 |
+
"grad_norm": 26.674560667801135,
|
| 498 |
+
"learning_rate": 1.3516160626836437e-07,
|
| 499 |
+
"loss": 1.9693,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.0004173181139572337,
|
| 504 |
+
"grad_norm": 33.42868793910111,
|
| 505 |
+
"learning_rate": 1.3712047012732616e-07,
|
| 506 |
+
"loss": 2.4011,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.0004231958338721243,
|
| 511 |
+
"grad_norm": 35.6133771366324,
|
| 512 |
+
"learning_rate": 1.3907933398628796e-07,
|
| 513 |
+
"loss": 2.2642,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.0004290735537870149,
|
| 518 |
+
"grad_norm": 25.976386072062112,
|
| 519 |
+
"learning_rate": 1.4103819784524978e-07,
|
| 520 |
+
"loss": 2.2197,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.00043495127370190553,
|
| 525 |
+
"grad_norm": 26.220898436195753,
|
| 526 |
+
"learning_rate": 1.4299706170421157e-07,
|
| 527 |
+
"loss": 2.3933,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.0004408289936167962,
|
| 532 |
+
"grad_norm": 31.704081974998505,
|
| 533 |
+
"learning_rate": 1.4495592556317337e-07,
|
| 534 |
+
"loss": 2.3164,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.0004467067135316868,
|
| 539 |
+
"grad_norm": 28.191292094592438,
|
| 540 |
+
"learning_rate": 1.4691478942213517e-07,
|
| 541 |
+
"loss": 2.1898,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.0004525844334465774,
|
| 546 |
+
"grad_norm": 34.07776057624209,
|
| 547 |
+
"learning_rate": 1.48873653281097e-07,
|
| 548 |
+
"loss": 2.1479,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.00045846215336146803,
|
| 553 |
+
"grad_norm": 35.51561977372984,
|
| 554 |
+
"learning_rate": 1.5083251714005878e-07,
|
| 555 |
+
"loss": 2.1504,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.00046433987327635864,
|
| 560 |
+
"grad_norm": 32.37780568021879,
|
| 561 |
+
"learning_rate": 1.5279138099902058e-07,
|
| 562 |
+
"loss": 2.0425,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.00047021759319124925,
|
| 567 |
+
"grad_norm": 26.28474544112387,
|
| 568 |
+
"learning_rate": 1.5475024485798237e-07,
|
| 569 |
+
"loss": 2.535,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.00047609531310613987,
|
| 574 |
+
"grad_norm": 26.94813340817767,
|
| 575 |
+
"learning_rate": 1.567091087169442e-07,
|
| 576 |
+
"loss": 2.3321,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.0004819730330210305,
|
| 581 |
+
"grad_norm": 42.30088898391613,
|
| 582 |
+
"learning_rate": 1.58667972575906e-07,
|
| 583 |
+
"loss": 2.2359,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.0004878507529359211,
|
| 588 |
+
"grad_norm": 26.92802144279086,
|
| 589 |
+
"learning_rate": 1.6062683643486781e-07,
|
| 590 |
+
"loss": 2.3239,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.0004937284728508117,
|
| 595 |
+
"grad_norm": 34.182845875119725,
|
| 596 |
+
"learning_rate": 1.6258570029382958e-07,
|
| 597 |
+
"loss": 2.2904,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.0004996061927657024,
|
| 602 |
+
"grad_norm": 33.83477740859824,
|
| 603 |
+
"learning_rate": 1.6454456415279138e-07,
|
| 604 |
+
"loss": 2.287,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.0005054839126805929,
|
| 609 |
+
"grad_norm": 31.28814971716291,
|
| 610 |
+
"learning_rate": 1.665034280117532e-07,
|
| 611 |
+
"loss": 2.3628,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.0005113616325954836,
|
| 616 |
+
"grad_norm": 24.161461789118633,
|
| 617 |
+
"learning_rate": 1.68462291870715e-07,
|
| 618 |
+
"loss": 2.3799,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.0005172393525103741,
|
| 623 |
+
"grad_norm": 38.85070435824102,
|
| 624 |
+
"learning_rate": 1.7042115572967682e-07,
|
| 625 |
+
"loss": 2.1733,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.0005231170724252648,
|
| 630 |
+
"grad_norm": 26.583507631290228,
|
| 631 |
+
"learning_rate": 1.7238001958863861e-07,
|
| 632 |
+
"loss": 2.0755,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.0005289947923401554,
|
| 637 |
+
"grad_norm": 31.67972636527564,
|
| 638 |
+
"learning_rate": 1.7433888344760038e-07,
|
| 639 |
+
"loss": 1.9064,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.000534872512255046,
|
| 644 |
+
"grad_norm": 18.31955982249094,
|
| 645 |
+
"learning_rate": 1.7629774730656223e-07,
|
| 646 |
+
"loss": 2.3138,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.0005407502321699366,
|
| 651 |
+
"grad_norm": 22.619392174396776,
|
| 652 |
+
"learning_rate": 1.78256611165524e-07,
|
| 653 |
+
"loss": 2.0967,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.0005466279520848273,
|
| 658 |
+
"grad_norm": 28.1552172586705,
|
| 659 |
+
"learning_rate": 1.802154750244858e-07,
|
| 660 |
+
"loss": 2.0212,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.0005525056719997178,
|
| 665 |
+
"grad_norm": 26.39585059625926,
|
| 666 |
+
"learning_rate": 1.8217433888344762e-07,
|
| 667 |
+
"loss": 2.1721,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.0005583833919146085,
|
| 672 |
+
"grad_norm": 56.55570072945738,
|
| 673 |
+
"learning_rate": 1.841332027424094e-07,
|
| 674 |
+
"loss": 2.2185,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.0005642611118294991,
|
| 679 |
+
"grad_norm": 18.255595773563055,
|
| 680 |
+
"learning_rate": 1.8609206660137123e-07,
|
| 681 |
+
"loss": 1.9785,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.0005701388317443897,
|
| 686 |
+
"grad_norm": 24.380219043592408,
|
| 687 |
+
"learning_rate": 1.8805093046033303e-07,
|
| 688 |
+
"loss": 1.9331,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.0005760165516592804,
|
| 693 |
+
"grad_norm": 23.21420086498007,
|
| 694 |
+
"learning_rate": 1.900097943192948e-07,
|
| 695 |
+
"loss": 2.1102,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.0005818942715741709,
|
| 700 |
+
"grad_norm": 25.644314151305732,
|
| 701 |
+
"learning_rate": 1.9196865817825662e-07,
|
| 702 |
+
"loss": 1.8602,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.0005877719914890616,
|
| 707 |
+
"grad_norm": 24.678894252503262,
|
| 708 |
+
"learning_rate": 1.9392752203721842e-07,
|
| 709 |
+
"loss": 1.9086,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.0005936497114039522,
|
| 714 |
+
"grad_norm": 21.140657194454246,
|
| 715 |
+
"learning_rate": 1.9588638589618024e-07,
|
| 716 |
+
"loss": 1.8432,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.0005995274313188428,
|
| 721 |
+
"grad_norm": 22.987569823694244,
|
| 722 |
+
"learning_rate": 1.9784524975514203e-07,
|
| 723 |
+
"loss": 2.1482,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.0006054051512337334,
|
| 728 |
+
"grad_norm": 21.456124991404014,
|
| 729 |
+
"learning_rate": 1.9980411361410383e-07,
|
| 730 |
+
"loss": 1.6048,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.000611282871148624,
|
| 735 |
+
"grad_norm": 23.506513682703766,
|
| 736 |
+
"learning_rate": 2.0176297747306565e-07,
|
| 737 |
+
"loss": 2.1504,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.0006171605910635146,
|
| 742 |
+
"grad_norm": 22.46761557860848,
|
| 743 |
+
"learning_rate": 2.0372184133202745e-07,
|
| 744 |
+
"loss": 2.0595,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.0006230383109784053,
|
| 749 |
+
"grad_norm": 22.25174247662017,
|
| 750 |
+
"learning_rate": 2.0568070519098922e-07,
|
| 751 |
+
"loss": 1.8643,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.0006289160308932958,
|
| 756 |
+
"grad_norm": 20.762128871169335,
|
| 757 |
+
"learning_rate": 2.0763956904995104e-07,
|
| 758 |
+
"loss": 1.8806,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.0006347937508081865,
|
| 763 |
+
"grad_norm": 21.51403808577067,
|
| 764 |
+
"learning_rate": 2.0959843290891283e-07,
|
| 765 |
+
"loss": 1.737,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.0006406714707230772,
|
| 770 |
+
"grad_norm": 14.877184572562975,
|
| 771 |
+
"learning_rate": 2.1155729676787466e-07,
|
| 772 |
+
"loss": 1.8458,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.0006465491906379677,
|
| 777 |
+
"grad_norm": 17.99619216256105,
|
| 778 |
+
"learning_rate": 2.1351616062683645e-07,
|
| 779 |
+
"loss": 1.7246,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.0006524269105528584,
|
| 784 |
+
"grad_norm": 19.28119326563505,
|
| 785 |
+
"learning_rate": 2.1547502448579825e-07,
|
| 786 |
+
"loss": 1.9538,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.0006583046304677489,
|
| 791 |
+
"grad_norm": 32.38937989525677,
|
| 792 |
+
"learning_rate": 2.1743388834476007e-07,
|
| 793 |
+
"loss": 1.9033,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.0006641823503826396,
|
| 798 |
+
"grad_norm": 17.174288277599942,
|
| 799 |
+
"learning_rate": 2.1939275220372186e-07,
|
| 800 |
+
"loss": 1.6582,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.0006700600702975302,
|
| 805 |
+
"grad_norm": 15.380513223594036,
|
| 806 |
+
"learning_rate": 2.2135161606268369e-07,
|
| 807 |
+
"loss": 1.7601,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.0006759377902124208,
|
| 812 |
+
"grad_norm": 18.099381133670537,
|
| 813 |
+
"learning_rate": 2.2331047992164546e-07,
|
| 814 |
+
"loss": 1.7123,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.0006818155101273114,
|
| 819 |
+
"grad_norm": 15.449085025928484,
|
| 820 |
+
"learning_rate": 2.2526934378060725e-07,
|
| 821 |
+
"loss": 2.0434,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.000687693230042202,
|
| 826 |
+
"grad_norm": 18.873494216822824,
|
| 827 |
+
"learning_rate": 2.2722820763956907e-07,
|
| 828 |
+
"loss": 1.9963,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.0006935709499570926,
|
| 833 |
+
"grad_norm": 29.52475437227068,
|
| 834 |
+
"learning_rate": 2.2918707149853087e-07,
|
| 835 |
+
"loss": 1.7232,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.0006994486698719833,
|
| 840 |
+
"grad_norm": 15.33187463191825,
|
| 841 |
+
"learning_rate": 2.311459353574927e-07,
|
| 842 |
+
"loss": 1.4605,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.0007053263897868738,
|
| 847 |
+
"grad_norm": 21.195728129495127,
|
| 848 |
+
"learning_rate": 2.3310479921645449e-07,
|
| 849 |
+
"loss": 1.6452,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.0007112041097017645,
|
| 854 |
+
"grad_norm": 12.616990324376612,
|
| 855 |
+
"learning_rate": 2.3506366307541625e-07,
|
| 856 |
+
"loss": 1.7385,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.0007170818296166552,
|
| 861 |
+
"grad_norm": 16.59194705973793,
|
| 862 |
+
"learning_rate": 2.370225269343781e-07,
|
| 863 |
+
"loss": 1.7001,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.0007229595495315457,
|
| 868 |
+
"grad_norm": 19.98385582713288,
|
| 869 |
+
"learning_rate": 2.389813907933399e-07,
|
| 870 |
+
"loss": 1.8642,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.0007288372694464364,
|
| 875 |
+
"grad_norm": 11.984048679052938,
|
| 876 |
+
"learning_rate": 2.4094025465230167e-07,
|
| 877 |
+
"loss": 1.7128,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.0007347149893613269,
|
| 882 |
+
"grad_norm": 13.817274924710402,
|
| 883 |
+
"learning_rate": 2.428991185112635e-07,
|
| 884 |
+
"loss": 1.9165,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.0007405927092762176,
|
| 889 |
+
"grad_norm": 14.666508072298448,
|
| 890 |
+
"learning_rate": 2.4485798237022526e-07,
|
| 891 |
+
"loss": 1.3521,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.0007464704291911082,
|
| 896 |
+
"grad_norm": 15.886204407427591,
|
| 897 |
+
"learning_rate": 2.468168462291871e-07,
|
| 898 |
+
"loss": 1.6274,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.0007523481491059988,
|
| 903 |
+
"grad_norm": 27.82376758715373,
|
| 904 |
+
"learning_rate": 2.487757100881489e-07,
|
| 905 |
+
"loss": 1.6963,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.0007582258690208894,
|
| 910 |
+
"grad_norm": 32.17667564558956,
|
| 911 |
+
"learning_rate": 2.5073457394711067e-07,
|
| 912 |
+
"loss": 1.6275,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.00076410358893578,
|
| 917 |
+
"grad_norm": 16.30806188824753,
|
| 918 |
+
"learning_rate": 2.526934378060725e-07,
|
| 919 |
+
"loss": 1.5903,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.0007699813088506706,
|
| 924 |
+
"grad_norm": 17.038993207268526,
|
| 925 |
+
"learning_rate": 2.546523016650343e-07,
|
| 926 |
+
"loss": 1.6622,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.0007758590287655613,
|
| 931 |
+
"grad_norm": 14.492825408251898,
|
| 932 |
+
"learning_rate": 2.5661116552399614e-07,
|
| 933 |
+
"loss": 1.7637,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.0007817367486804518,
|
| 938 |
+
"grad_norm": 20.71180708089968,
|
| 939 |
+
"learning_rate": 2.585700293829579e-07,
|
| 940 |
+
"loss": 1.4606,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.0007876144685953425,
|
| 945 |
+
"grad_norm": 15.231619445935591,
|
| 946 |
+
"learning_rate": 2.605288932419197e-07,
|
| 947 |
+
"loss": 1.6682,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.0007934921885102331,
|
| 952 |
+
"grad_norm": 14.170828124279078,
|
| 953 |
+
"learning_rate": 2.624877571008815e-07,
|
| 954 |
+
"loss": 1.8463,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.0007993699084251237,
|
| 959 |
+
"grad_norm": 10.59140070763608,
|
| 960 |
+
"learning_rate": 2.644466209598433e-07,
|
| 961 |
+
"loss": 1.5088,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.0008052476283400144,
|
| 966 |
+
"grad_norm": 26.814590174464087,
|
| 967 |
+
"learning_rate": 2.664054848188051e-07,
|
| 968 |
+
"loss": 1.8973,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.0008111253482549049,
|
| 973 |
+
"grad_norm": 11.60333007084735,
|
| 974 |
+
"learning_rate": 2.683643486777669e-07,
|
| 975 |
+
"loss": 1.6231,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.0008170030681697956,
|
| 980 |
+
"grad_norm": 15.760400853465885,
|
| 981 |
+
"learning_rate": 2.7032321253672873e-07,
|
| 982 |
+
"loss": 1.6369,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.0008228807880846862,
|
| 987 |
+
"grad_norm": 11.039629773110311,
|
| 988 |
+
"learning_rate": 2.7228207639569055e-07,
|
| 989 |
+
"loss": 1.7291,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.0008287585079995768,
|
| 994 |
+
"grad_norm": 13.050093706824535,
|
| 995 |
+
"learning_rate": 2.742409402546523e-07,
|
| 996 |
+
"loss": 1.3813,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.0008346362279144674,
|
| 1001 |
+
"grad_norm": 13.5488482037351,
|
| 1002 |
+
"learning_rate": 2.761998041136141e-07,
|
| 1003 |
+
"loss": 1.8591,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.0008405139478293581,
|
| 1008 |
+
"grad_norm": 11.7620793288059,
|
| 1009 |
+
"learning_rate": 2.781586679725759e-07,
|
| 1010 |
+
"loss": 1.721,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.0008463916677442486,
|
| 1015 |
+
"grad_norm": 10.320957727432353,
|
| 1016 |
+
"learning_rate": 2.8011753183153774e-07,
|
| 1017 |
+
"loss": 1.5765,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.0008522693876591393,
|
| 1022 |
+
"grad_norm": 13.202134714301499,
|
| 1023 |
+
"learning_rate": 2.8207639569049956e-07,
|
| 1024 |
+
"loss": 1.9503,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.0008581471075740298,
|
| 1029 |
+
"grad_norm": 11.162755956662153,
|
| 1030 |
+
"learning_rate": 2.8403525954946133e-07,
|
| 1031 |
+
"loss": 1.5982,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.0008640248274889205,
|
| 1036 |
+
"grad_norm": 11.393460380375336,
|
| 1037 |
+
"learning_rate": 2.8599412340842315e-07,
|
| 1038 |
+
"loss": 1.6087,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.0008699025474038111,
|
| 1043 |
+
"grad_norm": 14.494889123434431,
|
| 1044 |
+
"learning_rate": 2.8795298726738497e-07,
|
| 1045 |
+
"loss": 1.6165,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.0008757802673187017,
|
| 1050 |
+
"grad_norm": 11.174271675177474,
|
| 1051 |
+
"learning_rate": 2.8991185112634674e-07,
|
| 1052 |
+
"loss": 1.7131,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.0008816579872335924,
|
| 1057 |
+
"grad_norm": 9.71406247750616,
|
| 1058 |
+
"learning_rate": 2.918707149853085e-07,
|
| 1059 |
+
"loss": 1.4839,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.000887535707148483,
|
| 1064 |
+
"grad_norm": 14.012114534660885,
|
| 1065 |
+
"learning_rate": 2.9382957884427033e-07,
|
| 1066 |
+
"loss": 1.6935,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.0008934134270633736,
|
| 1071 |
+
"grad_norm": 10.065424608494785,
|
| 1072 |
+
"learning_rate": 2.9578844270323215e-07,
|
| 1073 |
+
"loss": 1.5043,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.0008992911469782642,
|
| 1078 |
+
"grad_norm": 10.291357563146,
|
| 1079 |
+
"learning_rate": 2.97747306562194e-07,
|
| 1080 |
+
"loss": 1.5935,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.0009051688668931548,
|
| 1085 |
+
"grad_norm": 9.468653200556892,
|
| 1086 |
+
"learning_rate": 2.9970617042115574e-07,
|
| 1087 |
+
"loss": 1.437,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.0009110465868080454,
|
| 1092 |
+
"grad_norm": 11.658556544230711,
|
| 1093 |
+
"learning_rate": 3.0166503428011757e-07,
|
| 1094 |
+
"loss": 1.8376,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.0009169243067229361,
|
| 1099 |
+
"grad_norm": 9.056893243480333,
|
| 1100 |
+
"learning_rate": 3.036238981390794e-07,
|
| 1101 |
+
"loss": 1.2717,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.0009228020266378266,
|
| 1106 |
+
"grad_norm": 9.678352816042532,
|
| 1107 |
+
"learning_rate": 3.0558276199804116e-07,
|
| 1108 |
+
"loss": 1.3479,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.0009286797465527173,
|
| 1113 |
+
"grad_norm": 9.018293017844652,
|
| 1114 |
+
"learning_rate": 3.07541625857003e-07,
|
| 1115 |
+
"loss": 1.8007,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.0009345574664676078,
|
| 1120 |
+
"grad_norm": 10.85779758090484,
|
| 1121 |
+
"learning_rate": 3.0950048971596475e-07,
|
| 1122 |
+
"loss": 1.5511,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.0009404351863824985,
|
| 1127 |
+
"grad_norm": 9.215542538487705,
|
| 1128 |
+
"learning_rate": 3.1145935357492657e-07,
|
| 1129 |
+
"loss": 1.5077,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.0009463129062973891,
|
| 1134 |
+
"grad_norm": 10.441875100178423,
|
| 1135 |
+
"learning_rate": 3.134182174338884e-07,
|
| 1136 |
+
"loss": 1.2265,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.0009521906262122797,
|
| 1141 |
+
"grad_norm": 11.707651718323877,
|
| 1142 |
+
"learning_rate": 3.153770812928502e-07,
|
| 1143 |
+
"loss": 1.6223,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.0009580683461271704,
|
| 1148 |
+
"grad_norm": 11.50471640686927,
|
| 1149 |
+
"learning_rate": 3.17335945151812e-07,
|
| 1150 |
+
"loss": 1.5438,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.000963946066042061,
|
| 1155 |
+
"grad_norm": 9.384813095151022,
|
| 1156 |
+
"learning_rate": 3.192948090107738e-07,
|
| 1157 |
+
"loss": 1.5544,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.0009698237859569516,
|
| 1162 |
+
"grad_norm": 16.29679950683345,
|
| 1163 |
+
"learning_rate": 3.2125367286973563e-07,
|
| 1164 |
+
"loss": 1.9744,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.0009757015058718422,
|
| 1169 |
+
"grad_norm": 9.074030216135546,
|
| 1170 |
+
"learning_rate": 3.2321253672869734e-07,
|
| 1171 |
+
"loss": 1.5864,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.0009815792257867328,
|
| 1176 |
+
"grad_norm": 9.283318899361504,
|
| 1177 |
+
"learning_rate": 3.2517140058765917e-07,
|
| 1178 |
+
"loss": 1.3906,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.0009874569457016234,
|
| 1183 |
+
"grad_norm": 10.17393481045071,
|
| 1184 |
+
"learning_rate": 3.27130264446621e-07,
|
| 1185 |
+
"loss": 1.6783,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.000993334665616514,
|
| 1190 |
+
"grad_norm": 10.387335954943156,
|
| 1191 |
+
"learning_rate": 3.2908912830558276e-07,
|
| 1192 |
+
"loss": 1.6027,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.0009992123855314047,
|
| 1197 |
+
"grad_norm": 9.08557174133179,
|
| 1198 |
+
"learning_rate": 3.310479921645446e-07,
|
| 1199 |
+
"loss": 1.3654,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.0010050901054462953,
|
| 1204 |
+
"grad_norm": 9.595202107192796,
|
| 1205 |
+
"learning_rate": 3.330068560235064e-07,
|
| 1206 |
+
"loss": 1.5666,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.0010109678253611858,
|
| 1211 |
+
"grad_norm": 10.31606733640622,
|
| 1212 |
+
"learning_rate": 3.3496571988246817e-07,
|
| 1213 |
+
"loss": 1.6286,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.0010168455452760764,
|
| 1218 |
+
"grad_norm": 9.326281386641854,
|
| 1219 |
+
"learning_rate": 3.3692458374143e-07,
|
| 1220 |
+
"loss": 1.9201,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.0010227232651909672,
|
| 1225 |
+
"grad_norm": 8.994312317847095,
|
| 1226 |
+
"learning_rate": 3.388834476003918e-07,
|
| 1227 |
+
"loss": 1.5568,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.0010286009851058577,
|
| 1232 |
+
"grad_norm": 9.980025494040948,
|
| 1233 |
+
"learning_rate": 3.4084231145935364e-07,
|
| 1234 |
+
"loss": 1.354,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.0010344787050207483,
|
| 1239 |
+
"grad_norm": 11.562220948333023,
|
| 1240 |
+
"learning_rate": 3.428011753183154e-07,
|
| 1241 |
+
"loss": 1.5634,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.001040356424935639,
|
| 1246 |
+
"grad_norm": 9.776227430851645,
|
| 1247 |
+
"learning_rate": 3.4476003917727723e-07,
|
| 1248 |
+
"loss": 1.4959,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.0010462341448505296,
|
| 1253 |
+
"grad_norm": 11.661631330611714,
|
| 1254 |
+
"learning_rate": 3.4671890303623905e-07,
|
| 1255 |
+
"loss": 1.5947,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.0010521118647654202,
|
| 1260 |
+
"grad_norm": 11.68005984757505,
|
| 1261 |
+
"learning_rate": 3.4867776689520076e-07,
|
| 1262 |
+
"loss": 1.5006,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.0010579895846803107,
|
| 1267 |
+
"grad_norm": 12.777534176544883,
|
| 1268 |
+
"learning_rate": 3.506366307541626e-07,
|
| 1269 |
+
"loss": 1.4467,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.0010638673045952015,
|
| 1274 |
+
"grad_norm": 17.41785652701965,
|
| 1275 |
+
"learning_rate": 3.5259549461312446e-07,
|
| 1276 |
+
"loss": 1.9458,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.001069745024510092,
|
| 1281 |
+
"grad_norm": 10.78085942187347,
|
| 1282 |
+
"learning_rate": 3.545543584720862e-07,
|
| 1283 |
+
"loss": 1.5085,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.0010756227444249826,
|
| 1288 |
+
"grad_norm": 16.771876557156034,
|
| 1289 |
+
"learning_rate": 3.56513222331048e-07,
|
| 1290 |
+
"loss": 1.5092,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.0010815004643398732,
|
| 1295 |
+
"grad_norm": 13.15308515651388,
|
| 1296 |
+
"learning_rate": 3.584720861900098e-07,
|
| 1297 |
+
"loss": 1.7019,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.001087378184254764,
|
| 1302 |
+
"grad_norm": 15.191365994444775,
|
| 1303 |
+
"learning_rate": 3.604309500489716e-07,
|
| 1304 |
+
"loss": 1.4493,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.0010932559041696545,
|
| 1309 |
+
"grad_norm": 9.667742910814834,
|
| 1310 |
+
"learning_rate": 3.623898139079334e-07,
|
| 1311 |
+
"loss": 1.4017,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.001099133624084545,
|
| 1316 |
+
"grad_norm": 8.784865132869584,
|
| 1317 |
+
"learning_rate": 3.6434867776689523e-07,
|
| 1318 |
+
"loss": 1.2916,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.0011050113439994356,
|
| 1323 |
+
"grad_norm": 12.035429882395604,
|
| 1324 |
+
"learning_rate": 3.6630754162585706e-07,
|
| 1325 |
+
"loss": 1.5701,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.0011108890639143264,
|
| 1330 |
+
"grad_norm": 10.937854560715525,
|
| 1331 |
+
"learning_rate": 3.682664054848188e-07,
|
| 1332 |
+
"loss": 1.261,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.001116766783829217,
|
| 1337 |
+
"grad_norm": 13.452124396814133,
|
| 1338 |
+
"learning_rate": 3.7022526934378065e-07,
|
| 1339 |
+
"loss": 1.4703,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.0011226445037441075,
|
| 1344 |
+
"grad_norm": 8.894603197974076,
|
| 1345 |
+
"learning_rate": 3.7218413320274247e-07,
|
| 1346 |
+
"loss": 1.4685,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.0011285222236589983,
|
| 1351 |
+
"grad_norm": 15.648678530497842,
|
| 1352 |
+
"learning_rate": 3.7414299706170424e-07,
|
| 1353 |
+
"loss": 1.8496,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.0011343999435738889,
|
| 1358 |
+
"grad_norm": 11.032596124236516,
|
| 1359 |
+
"learning_rate": 3.7610186092066606e-07,
|
| 1360 |
+
"loss": 1.9087,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.0011402776634887794,
|
| 1365 |
+
"grad_norm": 11.308196746519451,
|
| 1366 |
+
"learning_rate": 3.780607247796279e-07,
|
| 1367 |
+
"loss": 1.4356,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.00114615538340367,
|
| 1372 |
+
"grad_norm": 10.712918855934676,
|
| 1373 |
+
"learning_rate": 3.800195886385896e-07,
|
| 1374 |
+
"loss": 1.5941,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.0011520331033185607,
|
| 1379 |
+
"grad_norm": 10.561945446326497,
|
| 1380 |
+
"learning_rate": 3.819784524975514e-07,
|
| 1381 |
+
"loss": 1.1996,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.0011579108232334513,
|
| 1386 |
+
"grad_norm": 9.171518744551488,
|
| 1387 |
+
"learning_rate": 3.8393731635651324e-07,
|
| 1388 |
+
"loss": 1.8124,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.0011637885431483419,
|
| 1393 |
+
"grad_norm": 11.090728930779585,
|
| 1394 |
+
"learning_rate": 3.85896180215475e-07,
|
| 1395 |
+
"loss": 1.5103,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.0011696662630632324,
|
| 1400 |
+
"grad_norm": 21.075458727240783,
|
| 1401 |
+
"learning_rate": 3.8785504407443683e-07,
|
| 1402 |
+
"loss": 1.489,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.0011755439829781232,
|
| 1407 |
+
"grad_norm": 9.785441331082623,
|
| 1408 |
+
"learning_rate": 3.8981390793339866e-07,
|
| 1409 |
+
"loss": 1.3845,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.0011814217028930137,
|
| 1414 |
+
"grad_norm": 10.6811684049893,
|
| 1415 |
+
"learning_rate": 3.917727717923605e-07,
|
| 1416 |
+
"loss": 1.6402,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.0011872994228079043,
|
| 1421 |
+
"grad_norm": 9.419153945057552,
|
| 1422 |
+
"learning_rate": 3.9373163565132225e-07,
|
| 1423 |
+
"loss": 1.4811,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.001193177142722795,
|
| 1428 |
+
"grad_norm": 10.076216378174424,
|
| 1429 |
+
"learning_rate": 3.9569049951028407e-07,
|
| 1430 |
+
"loss": 1.2899,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.0011990548626376856,
|
| 1435 |
+
"grad_norm": 9.960886685047456,
|
| 1436 |
+
"learning_rate": 3.976493633692459e-07,
|
| 1437 |
+
"loss": 1.4358,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.0012049325825525762,
|
| 1442 |
+
"grad_norm": 8.401960196603293,
|
| 1443 |
+
"learning_rate": 3.9960822722820766e-07,
|
| 1444 |
+
"loss": 1.5201,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.0012108103024674668,
|
| 1449 |
+
"grad_norm": 11.58937622232436,
|
| 1450 |
+
"learning_rate": 4.015670910871695e-07,
|
| 1451 |
+
"loss": 1.3173,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.0012166880223823575,
|
| 1456 |
+
"grad_norm": 11.03334640239208,
|
| 1457 |
+
"learning_rate": 4.035259549461313e-07,
|
| 1458 |
+
"loss": 1.4313,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.001222565742297248,
|
| 1463 |
+
"grad_norm": 10.107621975482537,
|
| 1464 |
+
"learning_rate": 4.0548481880509307e-07,
|
| 1465 |
+
"loss": 1.5898,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.0012284434622121386,
|
| 1470 |
+
"grad_norm": 10.061788427468194,
|
| 1471 |
+
"learning_rate": 4.074436826640549e-07,
|
| 1472 |
+
"loss": 1.4872,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.0012343211821270292,
|
| 1477 |
+
"grad_norm": 11.047462590018448,
|
| 1478 |
+
"learning_rate": 4.094025465230167e-07,
|
| 1479 |
+
"loss": 1.4513,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.00124019890204192,
|
| 1484 |
+
"grad_norm": 9.225859001106716,
|
| 1485 |
+
"learning_rate": 4.1136141038197843e-07,
|
| 1486 |
+
"loss": 1.635,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.0012460766219568105,
|
| 1491 |
+
"grad_norm": 9.08800716773603,
|
| 1492 |
+
"learning_rate": 4.1332027424094025e-07,
|
| 1493 |
+
"loss": 1.4819,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.001251954341871701,
|
| 1498 |
+
"grad_norm": 8.868603405154412,
|
| 1499 |
+
"learning_rate": 4.152791380999021e-07,
|
| 1500 |
+
"loss": 1.2301,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.0012578320617865916,
|
| 1505 |
+
"grad_norm": 14.15909109082643,
|
| 1506 |
+
"learning_rate": 4.172380019588639e-07,
|
| 1507 |
+
"loss": 1.9416,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.0012637097817014824,
|
| 1512 |
+
"grad_norm": 9.067239599822472,
|
| 1513 |
+
"learning_rate": 4.1919686581782567e-07,
|
| 1514 |
+
"loss": 1.797,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.001269587501616373,
|
| 1519 |
+
"grad_norm": 12.132058750911389,
|
| 1520 |
+
"learning_rate": 4.211557296767875e-07,
|
| 1521 |
+
"loss": 1.4109,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.0012754652215312635,
|
| 1526 |
+
"grad_norm": 10.075853653825005,
|
| 1527 |
+
"learning_rate": 4.231145935357493e-07,
|
| 1528 |
+
"loss": 1.3572,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.0012813429414461543,
|
| 1533 |
+
"grad_norm": 9.168243399608876,
|
| 1534 |
+
"learning_rate": 4.250734573947111e-07,
|
| 1535 |
+
"loss": 1.8158,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.0012872206613610449,
|
| 1540 |
+
"grad_norm": 11.186175864257553,
|
| 1541 |
+
"learning_rate": 4.270323212536729e-07,
|
| 1542 |
+
"loss": 1.5282,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.0012930983812759354,
|
| 1547 |
+
"grad_norm": 8.733700945605664,
|
| 1548 |
+
"learning_rate": 4.289911851126347e-07,
|
| 1549 |
+
"loss": 1.5974,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.001298976101190826,
|
| 1554 |
+
"grad_norm": 7.788910732857218,
|
| 1555 |
+
"learning_rate": 4.309500489715965e-07,
|
| 1556 |
+
"loss": 1.3257,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.0013048538211057168,
|
| 1561 |
+
"grad_norm": 12.030091770377302,
|
| 1562 |
+
"learning_rate": 4.329089128305583e-07,
|
| 1563 |
+
"loss": 1.1955,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.0013107315410206073,
|
| 1568 |
+
"grad_norm": 10.080106382940905,
|
| 1569 |
+
"learning_rate": 4.3486777668952014e-07,
|
| 1570 |
+
"loss": 1.3482,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.0013166092609354979,
|
| 1575 |
+
"grad_norm": 11.07589048912045,
|
| 1576 |
+
"learning_rate": 4.3682664054848196e-07,
|
| 1577 |
+
"loss": 1.3602,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.0013224869808503884,
|
| 1582 |
+
"grad_norm": 15.065493178868694,
|
| 1583 |
+
"learning_rate": 4.3878550440744373e-07,
|
| 1584 |
+
"loss": 1.248,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.0013283647007652792,
|
| 1589 |
+
"grad_norm": 9.370347727362022,
|
| 1590 |
+
"learning_rate": 4.4074436826640555e-07,
|
| 1591 |
+
"loss": 1.429,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.0013342424206801698,
|
| 1596 |
+
"grad_norm": 9.30558950644716,
|
| 1597 |
+
"learning_rate": 4.4270323212536737e-07,
|
| 1598 |
+
"loss": 1.45,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.0013401201405950603,
|
| 1603 |
+
"grad_norm": 10.25603354658129,
|
| 1604 |
+
"learning_rate": 4.446620959843291e-07,
|
| 1605 |
+
"loss": 1.5622,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.0013459978605099509,
|
| 1610 |
+
"grad_norm": 12.297542220540503,
|
| 1611 |
+
"learning_rate": 4.466209598432909e-07,
|
| 1612 |
+
"loss": 1.2,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.0013518755804248416,
|
| 1617 |
+
"grad_norm": 9.331818179918656,
|
| 1618 |
+
"learning_rate": 4.4857982370225273e-07,
|
| 1619 |
+
"loss": 1.3011,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.0013577533003397322,
|
| 1624 |
+
"grad_norm": 10.585992361010224,
|
| 1625 |
+
"learning_rate": 4.505386875612145e-07,
|
| 1626 |
+
"loss": 1.6246,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.0013636310202546228,
|
| 1631 |
+
"grad_norm": 9.046465495391782,
|
| 1632 |
+
"learning_rate": 4.524975514201763e-07,
|
| 1633 |
+
"loss": 1.6676,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.0013695087401695135,
|
| 1638 |
+
"grad_norm": 8.998925855520136,
|
| 1639 |
+
"learning_rate": 4.5445641527913815e-07,
|
| 1640 |
+
"loss": 1.6056,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.001375386460084404,
|
| 1645 |
+
"grad_norm": 9.986723519133724,
|
| 1646 |
+
"learning_rate": 4.564152791380999e-07,
|
| 1647 |
+
"loss": 1.377,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.0013812641799992947,
|
| 1652 |
+
"grad_norm": 9.61309475151082,
|
| 1653 |
+
"learning_rate": 4.5837414299706174e-07,
|
| 1654 |
+
"loss": 1.4077,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.0013871418999141852,
|
| 1659 |
+
"grad_norm": 12.39156328483041,
|
| 1660 |
+
"learning_rate": 4.6033300685602356e-07,
|
| 1661 |
+
"loss": 1.2681,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.001393019619829076,
|
| 1666 |
+
"grad_norm": 11.93909914894201,
|
| 1667 |
+
"learning_rate": 4.622918707149854e-07,
|
| 1668 |
+
"loss": 1.5578,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.0013988973397439665,
|
| 1673 |
+
"grad_norm": 9.241067526275764,
|
| 1674 |
+
"learning_rate": 4.6425073457394715e-07,
|
| 1675 |
+
"loss": 1.424,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.001404775059658857,
|
| 1680 |
+
"grad_norm": 69.09437420107695,
|
| 1681 |
+
"learning_rate": 4.6620959843290897e-07,
|
| 1682 |
+
"loss": 1.7323,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.0014106527795737477,
|
| 1687 |
+
"grad_norm": 9.993143408906265,
|
| 1688 |
+
"learning_rate": 4.681684622918708e-07,
|
| 1689 |
+
"loss": 1.5018,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.0014165304994886384,
|
| 1694 |
+
"grad_norm": 10.458045510826041,
|
| 1695 |
+
"learning_rate": 4.701273261508325e-07,
|
| 1696 |
+
"loss": 1.3346,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.001422408219403529,
|
| 1701 |
+
"grad_norm": 15.334313398712514,
|
| 1702 |
+
"learning_rate": 4.720861900097944e-07,
|
| 1703 |
+
"loss": 1.4986,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.0014282859393184195,
|
| 1708 |
+
"grad_norm": 13.494956398702698,
|
| 1709 |
+
"learning_rate": 4.740450538687562e-07,
|
| 1710 |
+
"loss": 1.931,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.0014341636592333103,
|
| 1715 |
+
"grad_norm": 10.152689352885435,
|
| 1716 |
+
"learning_rate": 4.760039177277179e-07,
|
| 1717 |
+
"loss": 1.5585,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.0014400413791482009,
|
| 1722 |
+
"grad_norm": 8.834300902788739,
|
| 1723 |
+
"learning_rate": 4.779627815866798e-07,
|
| 1724 |
+
"loss": 1.3602,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.0014459190990630914,
|
| 1729 |
+
"grad_norm": 11.381145111843919,
|
| 1730 |
+
"learning_rate": 4.799216454456416e-07,
|
| 1731 |
+
"loss": 1.7747,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.001451796818977982,
|
| 1736 |
+
"grad_norm": 12.06148998092397,
|
| 1737 |
+
"learning_rate": 4.818805093046033e-07,
|
| 1738 |
+
"loss": 1.5178,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.0014576745388928728,
|
| 1743 |
+
"grad_norm": 8.703106046771826,
|
| 1744 |
+
"learning_rate": 4.838393731635652e-07,
|
| 1745 |
+
"loss": 1.5339,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.0014635522588077633,
|
| 1750 |
+
"grad_norm": 11.925440014048084,
|
| 1751 |
+
"learning_rate": 4.85798237022527e-07,
|
| 1752 |
+
"loss": 1.3716,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.0014694299787226539,
|
| 1757 |
+
"grad_norm": 9.313391960746207,
|
| 1758 |
+
"learning_rate": 4.877571008814888e-07,
|
| 1759 |
+
"loss": 1.5757,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.0014753076986375444,
|
| 1764 |
+
"grad_norm": 8.863788474883224,
|
| 1765 |
+
"learning_rate": 4.897159647404505e-07,
|
| 1766 |
+
"loss": 1.3941,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.0014811854185524352,
|
| 1771 |
+
"grad_norm": 10.606405136809217,
|
| 1772 |
+
"learning_rate": 4.916748285994123e-07,
|
| 1773 |
+
"loss": 1.3419,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.0014870631384673258,
|
| 1778 |
+
"grad_norm": 12.503980336764862,
|
| 1779 |
+
"learning_rate": 4.936336924583742e-07,
|
| 1780 |
+
"loss": 1.4387,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.0014929408583822163,
|
| 1785 |
+
"grad_norm": 11.202398292907109,
|
| 1786 |
+
"learning_rate": 4.95592556317336e-07,
|
| 1787 |
+
"loss": 1.3391,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.0014988185782971069,
|
| 1792 |
+
"grad_norm": 8.526431729740759,
|
| 1793 |
+
"learning_rate": 4.975514201762978e-07,
|
| 1794 |
+
"loss": 1.2921,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.0015046962982119977,
|
| 1799 |
+
"grad_norm": 8.105752184018986,
|
| 1800 |
+
"learning_rate": 4.995102840352596e-07,
|
| 1801 |
+
"loss": 1.6518,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.0015105740181268882,
|
| 1806 |
+
"grad_norm": 8.60563771477929,
|
| 1807 |
+
"learning_rate": 5.014691478942213e-07,
|
| 1808 |
+
"loss": 1.4145,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.0015164517380417788,
|
| 1813 |
+
"grad_norm": 9.153779971343228,
|
| 1814 |
+
"learning_rate": 5.034280117531832e-07,
|
| 1815 |
+
"loss": 1.3801,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.0015223294579566695,
|
| 1820 |
+
"grad_norm": 8.41877637538237,
|
| 1821 |
+
"learning_rate": 5.05386875612145e-07,
|
| 1822 |
+
"loss": 1.3788,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.00152820717787156,
|
| 1827 |
+
"grad_norm": 8.94067688880904,
|
| 1828 |
+
"learning_rate": 5.073457394711068e-07,
|
| 1829 |
+
"loss": 1.27,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.0015340848977864507,
|
| 1834 |
+
"grad_norm": 10.981582990635001,
|
| 1835 |
+
"learning_rate": 5.093046033300686e-07,
|
| 1836 |
+
"loss": 1.4033,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.0015399626177013412,
|
| 1841 |
+
"grad_norm": 10.577569060024489,
|
| 1842 |
+
"learning_rate": 5.112634671890305e-07,
|
| 1843 |
+
"loss": 1.2214,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.001545840337616232,
|
| 1848 |
+
"grad_norm": 12.805732199689936,
|
| 1849 |
+
"learning_rate": 5.132223310479923e-07,
|
| 1850 |
+
"loss": 1.303,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.0015517180575311226,
|
| 1855 |
+
"grad_norm": 11.328061019168393,
|
| 1856 |
+
"learning_rate": 5.15181194906954e-07,
|
| 1857 |
+
"loss": 1.239,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.0015575957774460131,
|
| 1862 |
+
"grad_norm": 8.779910655482228,
|
| 1863 |
+
"learning_rate": 5.171400587659158e-07,
|
| 1864 |
+
"loss": 1.5309,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.0015634734973609037,
|
| 1869 |
+
"grad_norm": 12.48858841285161,
|
| 1870 |
+
"learning_rate": 5.190989226248776e-07,
|
| 1871 |
+
"loss": 1.3235,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.0015693512172757944,
|
| 1876 |
+
"grad_norm": 9.529030183678163,
|
| 1877 |
+
"learning_rate": 5.210577864838394e-07,
|
| 1878 |
+
"loss": 1.7585,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.001575228937190685,
|
| 1883 |
+
"grad_norm": 8.60745560803701,
|
| 1884 |
+
"learning_rate": 5.230166503428012e-07,
|
| 1885 |
+
"loss": 1.3312,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.0015811066571055756,
|
| 1890 |
+
"grad_norm": 11.884696881425304,
|
| 1891 |
+
"learning_rate": 5.24975514201763e-07,
|
| 1892 |
+
"loss": 1.6793,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.0015869843770204661,
|
| 1897 |
+
"grad_norm": 8.967117197526099,
|
| 1898 |
+
"learning_rate": 5.269343780607248e-07,
|
| 1899 |
+
"loss": 1.4354,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.0015928620969353569,
|
| 1904 |
+
"grad_norm": 10.164939243499552,
|
| 1905 |
+
"learning_rate": 5.288932419196866e-07,
|
| 1906 |
+
"loss": 1.3092,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.0015987398168502474,
|
| 1911 |
+
"grad_norm": 10.854358248443695,
|
| 1912 |
+
"learning_rate": 5.308521057786485e-07,
|
| 1913 |
+
"loss": 1.4924,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.001604617536765138,
|
| 1918 |
+
"grad_norm": 8.960399631709869,
|
| 1919 |
+
"learning_rate": 5.328109696376102e-07,
|
| 1920 |
+
"loss": 1.5164,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.0016104952566800288,
|
| 1925 |
+
"grad_norm": 31.472372986870518,
|
| 1926 |
+
"learning_rate": 5.34769833496572e-07,
|
| 1927 |
+
"loss": 1.8094,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.0016163729765949193,
|
| 1932 |
+
"grad_norm": 8.473406841108375,
|
| 1933 |
+
"learning_rate": 5.367286973555338e-07,
|
| 1934 |
+
"loss": 1.2746,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.0016222506965098099,
|
| 1939 |
+
"grad_norm": 9.601218622750052,
|
| 1940 |
+
"learning_rate": 5.386875612144956e-07,
|
| 1941 |
+
"loss": 1.5087,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.0016281284164247004,
|
| 1946 |
+
"grad_norm": 9.649058387787647,
|
| 1947 |
+
"learning_rate": 5.406464250734575e-07,
|
| 1948 |
+
"loss": 1.4106,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.0016340061363395912,
|
| 1953 |
+
"grad_norm": 12.337790226855372,
|
| 1954 |
+
"learning_rate": 5.426052889324193e-07,
|
| 1955 |
+
"loss": 1.1803,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.0016398838562544818,
|
| 1960 |
+
"grad_norm": 10.953084253896563,
|
| 1961 |
+
"learning_rate": 5.445641527913811e-07,
|
| 1962 |
+
"loss": 1.5586,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.0016457615761693723,
|
| 1967 |
+
"grad_norm": 10.642696358664933,
|
| 1968 |
+
"learning_rate": 5.465230166503428e-07,
|
| 1969 |
+
"loss": 1.5048,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.001651639296084263,
|
| 1974 |
+
"grad_norm": 10.736683560071118,
|
| 1975 |
+
"learning_rate": 5.484818805093046e-07,
|
| 1976 |
+
"loss": 1.6119,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.0016575170159991537,
|
| 1981 |
+
"grad_norm": 10.990806499370061,
|
| 1982 |
+
"learning_rate": 5.504407443682665e-07,
|
| 1983 |
+
"loss": 1.5904,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.0016633947359140442,
|
| 1988 |
+
"grad_norm": 8.163597300046485,
|
| 1989 |
+
"learning_rate": 5.523996082272282e-07,
|
| 1990 |
+
"loss": 1.4993,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.0016692724558289348,
|
| 1995 |
+
"grad_norm": 8.147151905533738,
|
| 1996 |
+
"learning_rate": 5.5435847208619e-07,
|
| 1997 |
+
"loss": 1.4757,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.0016751501757438256,
|
| 2002 |
+
"grad_norm": 9.599530081078425,
|
| 2003 |
+
"learning_rate": 5.563173359451518e-07,
|
| 2004 |
+
"loss": 1.5775,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.0016810278956587161,
|
| 2009 |
+
"grad_norm": 10.21224899778634,
|
| 2010 |
+
"learning_rate": 5.582761998041137e-07,
|
| 2011 |
+
"loss": 1.6991,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.0016869056155736067,
|
| 2016 |
+
"grad_norm": 9.785513490047899,
|
| 2017 |
+
"learning_rate": 5.602350636630755e-07,
|
| 2018 |
+
"loss": 1.4311,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.0016927833354884972,
|
| 2023 |
+
"grad_norm": 7.874953791900144,
|
| 2024 |
+
"learning_rate": 5.621939275220373e-07,
|
| 2025 |
+
"loss": 1.3383,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.001698661055403388,
|
| 2030 |
+
"grad_norm": 9.336147650202287,
|
| 2031 |
+
"learning_rate": 5.641527913809991e-07,
|
| 2032 |
+
"loss": 1.3211,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.0017045387753182786,
|
| 2037 |
+
"grad_norm": 9.542961142594972,
|
| 2038 |
+
"learning_rate": 5.661116552399608e-07,
|
| 2039 |
+
"loss": 1.2768,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.0017104164952331691,
|
| 2044 |
+
"grad_norm": 9.590134538210235,
|
| 2045 |
+
"learning_rate": 5.680705190989227e-07,
|
| 2046 |
+
"loss": 1.6988,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.0017162942151480597,
|
| 2051 |
+
"grad_norm": 10.325514884799286,
|
| 2052 |
+
"learning_rate": 5.700293829578845e-07,
|
| 2053 |
+
"loss": 1.4005,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.0017221719350629505,
|
| 2058 |
+
"grad_norm": 10.585596643296642,
|
| 2059 |
+
"learning_rate": 5.719882468168463e-07,
|
| 2060 |
+
"loss": 1.4279,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.001728049654977841,
|
| 2065 |
+
"grad_norm": 10.587814188427249,
|
| 2066 |
+
"learning_rate": 5.739471106758081e-07,
|
| 2067 |
+
"loss": 1.1622,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.0017339273748927316,
|
| 2072 |
+
"grad_norm": 8.114925702550204,
|
| 2073 |
+
"learning_rate": 5.759059745347699e-07,
|
| 2074 |
+
"loss": 1.2287,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.0017398050948076221,
|
| 2079 |
+
"grad_norm": 10.570600276337354,
|
| 2080 |
+
"learning_rate": 5.778648383937317e-07,
|
| 2081 |
+
"loss": 1.3479,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.001745682814722513,
|
| 2086 |
+
"grad_norm": 7.904815223532098,
|
| 2087 |
+
"learning_rate": 5.798237022526935e-07,
|
| 2088 |
+
"loss": 1.3332,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.0017515605346374035,
|
| 2093 |
+
"grad_norm": 8.907307462389863,
|
| 2094 |
+
"learning_rate": 5.817825661116553e-07,
|
| 2095 |
+
"loss": 1.081,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.001757438254552294,
|
| 2100 |
+
"grad_norm": 11.75059259667856,
|
| 2101 |
+
"learning_rate": 5.83741429970617e-07,
|
| 2102 |
+
"loss": 1.7135,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.0017633159744671848,
|
| 2107 |
+
"grad_norm": 9.072886413264408,
|
| 2108 |
+
"learning_rate": 5.857002938295788e-07,
|
| 2109 |
+
"loss": 1.6713,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.0017691936943820753,
|
| 2114 |
+
"grad_norm": 9.016576648856399,
|
| 2115 |
+
"learning_rate": 5.876591576885407e-07,
|
| 2116 |
+
"loss": 1.7791,
|
| 2117 |
+
"step": 301
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.001775071414296966,
|
| 2121 |
+
"grad_norm": 9.023767161545154,
|
| 2122 |
+
"learning_rate": 5.896180215475025e-07,
|
| 2123 |
+
"loss": 1.3835,
|
| 2124 |
+
"step": 302
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.0017809491342118565,
|
| 2128 |
+
"grad_norm": 9.962756123160855,
|
| 2129 |
+
"learning_rate": 5.915768854064643e-07,
|
| 2130 |
+
"loss": 1.6033,
|
| 2131 |
+
"step": 303
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.0017868268541267472,
|
| 2135 |
+
"grad_norm": 9.133093847326018,
|
| 2136 |
+
"learning_rate": 5.935357492654261e-07,
|
| 2137 |
+
"loss": 1.4126,
|
| 2138 |
+
"step": 304
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.0017927045740416378,
|
| 2142 |
+
"grad_norm": 11.5542021679122,
|
| 2143 |
+
"learning_rate": 5.95494613124388e-07,
|
| 2144 |
+
"loss": 1.2368,
|
| 2145 |
+
"step": 305
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.0017985822939565283,
|
| 2149 |
+
"grad_norm": 11.907934876986705,
|
| 2150 |
+
"learning_rate": 5.974534769833497e-07,
|
| 2151 |
+
"loss": 1.3877,
|
| 2152 |
+
"step": 306
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.001804460013871419,
|
| 2156 |
+
"grad_norm": 7.981708675663852,
|
| 2157 |
+
"learning_rate": 5.994123408423115e-07,
|
| 2158 |
+
"loss": 1.4267,
|
| 2159 |
+
"step": 307
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.0018103377337863097,
|
| 2163 |
+
"grad_norm": 8.352686578158465,
|
| 2164 |
+
"learning_rate": 6.013712047012733e-07,
|
| 2165 |
+
"loss": 1.1058,
|
| 2166 |
+
"step": 308
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.0018162154537012002,
|
| 2170 |
+
"grad_norm": 9.957225135648658,
|
| 2171 |
+
"learning_rate": 6.033300685602351e-07,
|
| 2172 |
+
"loss": 1.6818,
|
| 2173 |
+
"step": 309
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.0018220931736160908,
|
| 2177 |
+
"grad_norm": 9.90328827616875,
|
| 2178 |
+
"learning_rate": 6.05288932419197e-07,
|
| 2179 |
+
"loss": 1.5766,
|
| 2180 |
+
"step": 310
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.0018279708935309816,
|
| 2184 |
+
"grad_norm": 11.369184065206666,
|
| 2185 |
+
"learning_rate": 6.072477962781588e-07,
|
| 2186 |
+
"loss": 1.096,
|
| 2187 |
+
"step": 311
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.0018338486134458721,
|
| 2191 |
+
"grad_norm": 10.82625712962213,
|
| 2192 |
+
"learning_rate": 6.092066601371205e-07,
|
| 2193 |
+
"loss": 1.0124,
|
| 2194 |
+
"step": 312
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.0018397263333607627,
|
| 2198 |
+
"grad_norm": 11.626285416738192,
|
| 2199 |
+
"learning_rate": 6.111655239960823e-07,
|
| 2200 |
+
"loss": 1.3971,
|
| 2201 |
+
"step": 313
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.0018456040532756532,
|
| 2205 |
+
"grad_norm": 9.15673251705592,
|
| 2206 |
+
"learning_rate": 6.131243878550441e-07,
|
| 2207 |
+
"loss": 1.259,
|
| 2208 |
+
"step": 314
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.001851481773190544,
|
| 2212 |
+
"grad_norm": 11.418733881821664,
|
| 2213 |
+
"learning_rate": 6.15083251714006e-07,
|
| 2214 |
+
"loss": 1.4944,
|
| 2215 |
+
"step": 315
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.0018573594931054346,
|
| 2219 |
+
"grad_norm": 8.174275985243646,
|
| 2220 |
+
"learning_rate": 6.170421155729677e-07,
|
| 2221 |
+
"loss": 1.1997,
|
| 2222 |
+
"step": 316
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.0018632372130203251,
|
| 2226 |
+
"grad_norm": 9.180576750869545,
|
| 2227 |
+
"learning_rate": 6.190009794319295e-07,
|
| 2228 |
+
"loss": 1.3872,
|
| 2229 |
+
"step": 317
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.0018691149329352157,
|
| 2233 |
+
"grad_norm": 12.375955484763304,
|
| 2234 |
+
"learning_rate": 6.209598432908913e-07,
|
| 2235 |
+
"loss": 1.324,
|
| 2236 |
+
"step": 318
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.0018749926528501065,
|
| 2240 |
+
"grad_norm": 9.560556934953807,
|
| 2241 |
+
"learning_rate": 6.229187071498531e-07,
|
| 2242 |
+
"loss": 1.4166,
|
| 2243 |
+
"step": 319
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.001880870372764997,
|
| 2247 |
+
"grad_norm": 9.492269725987041,
|
| 2248 |
+
"learning_rate": 6.24877571008815e-07,
|
| 2249 |
+
"loss": 1.0062,
|
| 2250 |
+
"step": 320
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.0018867480926798876,
|
| 2254 |
+
"grad_norm": 10.202432437740011,
|
| 2255 |
+
"learning_rate": 6.268364348677768e-07,
|
| 2256 |
+
"loss": 1.4843,
|
| 2257 |
+
"step": 321
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.0018926258125947781,
|
| 2261 |
+
"grad_norm": 10.254012500981297,
|
| 2262 |
+
"learning_rate": 6.287952987267386e-07,
|
| 2263 |
+
"loss": 1.5466,
|
| 2264 |
+
"step": 322
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.001898503532509669,
|
| 2268 |
+
"grad_norm": 11.225147665082007,
|
| 2269 |
+
"learning_rate": 6.307541625857004e-07,
|
| 2270 |
+
"loss": 1.7476,
|
| 2271 |
+
"step": 323
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.0019043812524245595,
|
| 2275 |
+
"grad_norm": 8.162781954607768,
|
| 2276 |
+
"learning_rate": 6.327130264446621e-07,
|
| 2277 |
+
"loss": 1.4437,
|
| 2278 |
+
"step": 324
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.00191025897233945,
|
| 2282 |
+
"grad_norm": 9.079994444957677,
|
| 2283 |
+
"learning_rate": 6.34671890303624e-07,
|
| 2284 |
+
"loss": 1.1562,
|
| 2285 |
+
"step": 325
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.0019161366922543408,
|
| 2289 |
+
"grad_norm": 9.634816296804672,
|
| 2290 |
+
"learning_rate": 6.366307541625858e-07,
|
| 2291 |
+
"loss": 1.6029,
|
| 2292 |
+
"step": 326
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.0019220144121692314,
|
| 2296 |
+
"grad_norm": 11.76794240323632,
|
| 2297 |
+
"learning_rate": 6.385896180215476e-07,
|
| 2298 |
+
"loss": 1.2548,
|
| 2299 |
+
"step": 327
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.001927892132084122,
|
| 2303 |
+
"grad_norm": 9.010097944627907,
|
| 2304 |
+
"learning_rate": 6.405484818805094e-07,
|
| 2305 |
+
"loss": 1.2053,
|
| 2306 |
+
"step": 328
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.0019337698519990125,
|
| 2310 |
+
"grad_norm": 10.400030554541505,
|
| 2311 |
+
"learning_rate": 6.425073457394713e-07,
|
| 2312 |
+
"loss": 1.2347,
|
| 2313 |
+
"step": 329
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.0019396475719139032,
|
| 2317 |
+
"grad_norm": 9.580005301294532,
|
| 2318 |
+
"learning_rate": 6.444662095984329e-07,
|
| 2319 |
+
"loss": 1.441,
|
| 2320 |
+
"step": 330
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.0019455252918287938,
|
| 2324 |
+
"grad_norm": 95.9734686900897,
|
| 2325 |
+
"learning_rate": 6.464250734573947e-07,
|
| 2326 |
+
"loss": 1.6166,
|
| 2327 |
+
"step": 331
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.0019514030117436844,
|
| 2331 |
+
"grad_norm": 10.36525345635369,
|
| 2332 |
+
"learning_rate": 6.483839373163565e-07,
|
| 2333 |
+
"loss": 1.2509,
|
| 2334 |
+
"step": 332
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.001957280731658575,
|
| 2338 |
+
"grad_norm": 10.002390744057713,
|
| 2339 |
+
"learning_rate": 6.503428011753183e-07,
|
| 2340 |
+
"loss": 1.4298,
|
| 2341 |
+
"step": 333
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.0019631584515734657,
|
| 2345 |
+
"grad_norm": 8.217876579856577,
|
| 2346 |
+
"learning_rate": 6.523016650342802e-07,
|
| 2347 |
+
"loss": 1.2985,
|
| 2348 |
+
"step": 334
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.001969036171488356,
|
| 2352 |
+
"grad_norm": 10.009667776909204,
|
| 2353 |
+
"learning_rate": 6.54260528893242e-07,
|
| 2354 |
+
"loss": 1.7514,
|
| 2355 |
+
"step": 335
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.001974913891403247,
|
| 2359 |
+
"grad_norm": 8.951831687444894,
|
| 2360 |
+
"learning_rate": 6.562193927522038e-07,
|
| 2361 |
+
"loss": 1.5412,
|
| 2362 |
+
"step": 336
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.0019807916113181376,
|
| 2366 |
+
"grad_norm": 9.069755801521628,
|
| 2367 |
+
"learning_rate": 6.581782566111655e-07,
|
| 2368 |
+
"loss": 1.1909,
|
| 2369 |
+
"step": 337
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.001986669331233028,
|
| 2373 |
+
"grad_norm": 12.005699769054418,
|
| 2374 |
+
"learning_rate": 6.601371204701273e-07,
|
| 2375 |
+
"loss": 1.3262,
|
| 2376 |
+
"step": 338
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.0019925470511479187,
|
| 2380 |
+
"grad_norm": 9.69892721507397,
|
| 2381 |
+
"learning_rate": 6.620959843290892e-07,
|
| 2382 |
+
"loss": 1.3983,
|
| 2383 |
+
"step": 339
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.0019984247710628095,
|
| 2387 |
+
"grad_norm": 10.120949574403364,
|
| 2388 |
+
"learning_rate": 6.64054848188051e-07,
|
| 2389 |
+
"loss": 1.8783,
|
| 2390 |
+
"step": 340
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.0020043024909777,
|
| 2394 |
+
"grad_norm": 8.432805148499385,
|
| 2395 |
+
"learning_rate": 6.660137120470128e-07,
|
| 2396 |
+
"loss": 1.4789,
|
| 2397 |
+
"step": 341
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.0020101802108925906,
|
| 2401 |
+
"grad_norm": 9.690110308833203,
|
| 2402 |
+
"learning_rate": 6.679725759059746e-07,
|
| 2403 |
+
"loss": 1.2415,
|
| 2404 |
+
"step": 342
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.0020160579308074814,
|
| 2408 |
+
"grad_norm": 9.80807295529178,
|
| 2409 |
+
"learning_rate": 6.699314397649363e-07,
|
| 2410 |
+
"loss": 1.2757,
|
| 2411 |
+
"step": 343
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.0020219356507223717,
|
| 2415 |
+
"grad_norm": 9.956040308785957,
|
| 2416 |
+
"learning_rate": 6.718903036238982e-07,
|
| 2417 |
+
"loss": 1.2862,
|
| 2418 |
+
"step": 344
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.0020278133706372625,
|
| 2422 |
+
"grad_norm": 7.842215017092853,
|
| 2423 |
+
"learning_rate": 6.7384916748286e-07,
|
| 2424 |
+
"loss": 1.2398,
|
| 2425 |
+
"step": 345
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.002033691090552153,
|
| 2429 |
+
"grad_norm": 7.648481343331776,
|
| 2430 |
+
"learning_rate": 6.758080313418218e-07,
|
| 2431 |
+
"loss": 1.1184,
|
| 2432 |
+
"step": 346
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.0020395688104670436,
|
| 2436 |
+
"grad_norm": 12.194721433776252,
|
| 2437 |
+
"learning_rate": 6.777668952007836e-07,
|
| 2438 |
+
"loss": 1.7089,
|
| 2439 |
+
"step": 347
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.0020454465303819344,
|
| 2443 |
+
"grad_norm": 7.690015793298225,
|
| 2444 |
+
"learning_rate": 6.797257590597454e-07,
|
| 2445 |
+
"loss": 1.4625,
|
| 2446 |
+
"step": 348
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.0020513242502968247,
|
| 2450 |
+
"grad_norm": 11.691899229743722,
|
| 2451 |
+
"learning_rate": 6.816846229187073e-07,
|
| 2452 |
+
"loss": 1.2942,
|
| 2453 |
+
"step": 349
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.0020572019702117155,
|
| 2457 |
+
"grad_norm": 9.815989117817255,
|
| 2458 |
+
"learning_rate": 6.83643486777669e-07,
|
| 2459 |
+
"loss": 1.4441,
|
| 2460 |
+
"step": 350
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.0020630796901266063,
|
| 2464 |
+
"grad_norm": 7.700996093887788,
|
| 2465 |
+
"learning_rate": 6.856023506366308e-07,
|
| 2466 |
+
"loss": 1.2803,
|
| 2467 |
+
"step": 351
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.0020689574100414966,
|
| 2471 |
+
"grad_norm": 9.5858324599782,
|
| 2472 |
+
"learning_rate": 6.875612144955926e-07,
|
| 2473 |
+
"loss": 1.5798,
|
| 2474 |
+
"step": 352
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.0020748351299563874,
|
| 2478 |
+
"grad_norm": 10.225643669078298,
|
| 2479 |
+
"learning_rate": 6.895200783545545e-07,
|
| 2480 |
+
"loss": 1.4671,
|
| 2481 |
+
"step": 353
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.002080712849871278,
|
| 2485 |
+
"grad_norm": 12.74888973456531,
|
| 2486 |
+
"learning_rate": 6.914789422135163e-07,
|
| 2487 |
+
"loss": 1.2033,
|
| 2488 |
+
"step": 354
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.0020865905697861685,
|
| 2492 |
+
"grad_norm": 8.747052996779347,
|
| 2493 |
+
"learning_rate": 6.934378060724781e-07,
|
| 2494 |
+
"loss": 1.4468,
|
| 2495 |
+
"step": 355
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.0020924682897010593,
|
| 2499 |
+
"grad_norm": 10.224825910436632,
|
| 2500 |
+
"learning_rate": 6.953966699314397e-07,
|
| 2501 |
+
"loss": 1.3275,
|
| 2502 |
+
"step": 356
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.0020983460096159496,
|
| 2506 |
+
"grad_norm": 9.76538128069528,
|
| 2507 |
+
"learning_rate": 6.973555337904015e-07,
|
| 2508 |
+
"loss": 1.2248,
|
| 2509 |
+
"step": 357
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.0021042237295308404,
|
| 2513 |
+
"grad_norm": 9.343421907990354,
|
| 2514 |
+
"learning_rate": 6.993143976493634e-07,
|
| 2515 |
+
"loss": 1.4222,
|
| 2516 |
+
"step": 358
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.002110101449445731,
|
| 2520 |
+
"grad_norm": 11.07607790792727,
|
| 2521 |
+
"learning_rate": 7.012732615083252e-07,
|
| 2522 |
+
"loss": 1.4655,
|
| 2523 |
+
"step": 359
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.0021159791693606215,
|
| 2527 |
+
"grad_norm": 9.43492641142549,
|
| 2528 |
+
"learning_rate": 7.032321253672871e-07,
|
| 2529 |
+
"loss": 1.3952,
|
| 2530 |
+
"step": 360
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.0021218568892755123,
|
| 2534 |
+
"grad_norm": 10.725935879524329,
|
| 2535 |
+
"learning_rate": 7.051909892262489e-07,
|
| 2536 |
+
"loss": 1.3749,
|
| 2537 |
+
"step": 361
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.002127734609190403,
|
| 2541 |
+
"grad_norm": 10.459955763777726,
|
| 2542 |
+
"learning_rate": 7.071498530852107e-07,
|
| 2543 |
+
"loss": 1.3638,
|
| 2544 |
+
"step": 362
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.0021336123291052934,
|
| 2548 |
+
"grad_norm": 10.084883781318648,
|
| 2549 |
+
"learning_rate": 7.091087169441724e-07,
|
| 2550 |
+
"loss": 1.5208,
|
| 2551 |
+
"step": 363
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.002139490049020184,
|
| 2555 |
+
"grad_norm": 10.037233174623386,
|
| 2556 |
+
"learning_rate": 7.110675808031342e-07,
|
| 2557 |
+
"loss": 1.2152,
|
| 2558 |
+
"step": 364
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.002145367768935075,
|
| 2562 |
+
"grad_norm": 8.813983991816277,
|
| 2563 |
+
"learning_rate": 7.13026444662096e-07,
|
| 2564 |
+
"loss": 1.6647,
|
| 2565 |
+
"step": 365
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.0021512454888499653,
|
| 2569 |
+
"grad_norm": 12.20631481651128,
|
| 2570 |
+
"learning_rate": 7.149853085210578e-07,
|
| 2571 |
+
"loss": 1.6276,
|
| 2572 |
+
"step": 366
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.002157123208764856,
|
| 2576 |
+
"grad_norm": 12.98213610184426,
|
| 2577 |
+
"learning_rate": 7.169441723800196e-07,
|
| 2578 |
+
"loss": 1.5915,
|
| 2579 |
+
"step": 367
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.0021630009286797464,
|
| 2583 |
+
"grad_norm": 9.21805497063901,
|
| 2584 |
+
"learning_rate": 7.189030362389815e-07,
|
| 2585 |
+
"loss": 1.336,
|
| 2586 |
+
"step": 368
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.002168878648594637,
|
| 2590 |
+
"grad_norm": 9.109226384013539,
|
| 2591 |
+
"learning_rate": 7.208619000979432e-07,
|
| 2592 |
+
"loss": 1.6266,
|
| 2593 |
+
"step": 369
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.002174756368509528,
|
| 2597 |
+
"grad_norm": 10.455222812127753,
|
| 2598 |
+
"learning_rate": 7.22820763956905e-07,
|
| 2599 |
+
"loss": 1.262,
|
| 2600 |
+
"step": 370
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.0021806340884244183,
|
| 2604 |
+
"grad_norm": 8.391319723021606,
|
| 2605 |
+
"learning_rate": 7.247796278158668e-07,
|
| 2606 |
+
"loss": 1.1648,
|
| 2607 |
+
"step": 371
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.002186511808339309,
|
| 2611 |
+
"grad_norm": 120.89278453800495,
|
| 2612 |
+
"learning_rate": 7.267384916748286e-07,
|
| 2613 |
+
"loss": 1.4725,
|
| 2614 |
+
"step": 372
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.0021923895282542,
|
| 2618 |
+
"grad_norm": 10.561377041726836,
|
| 2619 |
+
"learning_rate": 7.286973555337905e-07,
|
| 2620 |
+
"loss": 1.2098,
|
| 2621 |
+
"step": 373
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.00219826724816909,
|
| 2625 |
+
"grad_norm": 10.679479268602012,
|
| 2626 |
+
"learning_rate": 7.306562193927523e-07,
|
| 2627 |
+
"loss": 1.3308,
|
| 2628 |
+
"step": 374
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.002204144968083981,
|
| 2632 |
+
"grad_norm": 8.485373095871307,
|
| 2633 |
+
"learning_rate": 7.326150832517141e-07,
|
| 2634 |
+
"loss": 1.5223,
|
| 2635 |
+
"step": 375
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.0022100226879988713,
|
| 2639 |
+
"grad_norm": 8.997398533127315,
|
| 2640 |
+
"learning_rate": 7.345739471106758e-07,
|
| 2641 |
+
"loss": 1.4203,
|
| 2642 |
+
"step": 376
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.002215900407913762,
|
| 2646 |
+
"grad_norm": 9.068897975931213,
|
| 2647 |
+
"learning_rate": 7.365328109696377e-07,
|
| 2648 |
+
"loss": 1.257,
|
| 2649 |
+
"step": 377
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.002221778127828653,
|
| 2653 |
+
"grad_norm": 9.307758093247212,
|
| 2654 |
+
"learning_rate": 7.384916748285995e-07,
|
| 2655 |
+
"loss": 1.0995,
|
| 2656 |
+
"step": 378
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.002227655847743543,
|
| 2660 |
+
"grad_norm": 10.070537945717394,
|
| 2661 |
+
"learning_rate": 7.404505386875613e-07,
|
| 2662 |
+
"loss": 1.7374,
|
| 2663 |
+
"step": 379
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.002233533567658434,
|
| 2667 |
+
"grad_norm": 10.366005280163792,
|
| 2668 |
+
"learning_rate": 7.424094025465231e-07,
|
| 2669 |
+
"loss": 1.2628,
|
| 2670 |
+
"step": 380
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.0022394112875733247,
|
| 2674 |
+
"grad_norm": 9.08901956278531,
|
| 2675 |
+
"learning_rate": 7.443682664054849e-07,
|
| 2676 |
+
"loss": 1.1628,
|
| 2677 |
+
"step": 381
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.002245289007488215,
|
| 2681 |
+
"grad_norm": 9.146350725847851,
|
| 2682 |
+
"learning_rate": 7.463271302644467e-07,
|
| 2683 |
+
"loss": 1.5435,
|
| 2684 |
+
"step": 382
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.002251166727403106,
|
| 2688 |
+
"grad_norm": 11.350273071816241,
|
| 2689 |
+
"learning_rate": 7.482859941234085e-07,
|
| 2690 |
+
"loss": 1.4359,
|
| 2691 |
+
"step": 383
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.0022570444473179966,
|
| 2695 |
+
"grad_norm": 10.745208607274986,
|
| 2696 |
+
"learning_rate": 7.502448579823703e-07,
|
| 2697 |
+
"loss": 1.5371,
|
| 2698 |
+
"step": 384
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.002262922167232887,
|
| 2702 |
+
"grad_norm": 9.133230654048408,
|
| 2703 |
+
"learning_rate": 7.522037218413321e-07,
|
| 2704 |
+
"loss": 1.2589,
|
| 2705 |
+
"step": 385
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.0022687998871477777,
|
| 2709 |
+
"grad_norm": 9.919975618980674,
|
| 2710 |
+
"learning_rate": 7.541625857002939e-07,
|
| 2711 |
+
"loss": 1.5764,
|
| 2712 |
+
"step": 386
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.002274677607062668,
|
| 2716 |
+
"grad_norm": 10.015249785262874,
|
| 2717 |
+
"learning_rate": 7.561214495592558e-07,
|
| 2718 |
+
"loss": 1.2103,
|
| 2719 |
+
"step": 387
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.002280555326977559,
|
| 2723 |
+
"grad_norm": 9.298714026316576,
|
| 2724 |
+
"learning_rate": 7.580803134182176e-07,
|
| 2725 |
+
"loss": 1.2527,
|
| 2726 |
+
"step": 388
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.0022864330468924496,
|
| 2730 |
+
"grad_norm": 7.855421719465326,
|
| 2731 |
+
"learning_rate": 7.600391772771792e-07,
|
| 2732 |
+
"loss": 0.9689,
|
| 2733 |
+
"step": 389
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.00229231076680734,
|
| 2737 |
+
"grad_norm": 8.19603172426781,
|
| 2738 |
+
"learning_rate": 7.61998041136141e-07,
|
| 2739 |
+
"loss": 1.5125,
|
| 2740 |
+
"step": 390
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.0022981884867222307,
|
| 2744 |
+
"grad_norm": 9.355341043777715,
|
| 2745 |
+
"learning_rate": 7.639569049951028e-07,
|
| 2746 |
+
"loss": 1.0824,
|
| 2747 |
+
"step": 391
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.0023040662066371215,
|
| 2751 |
+
"grad_norm": 7.6510926135371875,
|
| 2752 |
+
"learning_rate": 7.659157688540647e-07,
|
| 2753 |
+
"loss": 1.3634,
|
| 2754 |
+
"step": 392
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.002309943926552012,
|
| 2758 |
+
"grad_norm": 10.424234163569968,
|
| 2759 |
+
"learning_rate": 7.678746327130265e-07,
|
| 2760 |
+
"loss": 1.6378,
|
| 2761 |
+
"step": 393
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.0023158216464669026,
|
| 2765 |
+
"grad_norm": 9.89076424202504,
|
| 2766 |
+
"learning_rate": 7.698334965719883e-07,
|
| 2767 |
+
"loss": 1.3423,
|
| 2768 |
+
"step": 394
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.0023216993663817934,
|
| 2772 |
+
"grad_norm": 12.940539054812946,
|
| 2773 |
+
"learning_rate": 7.7179236043095e-07,
|
| 2774 |
+
"loss": 1.2945,
|
| 2775 |
+
"step": 395
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.0023275770862966837,
|
| 2779 |
+
"grad_norm": 7.680461776345431,
|
| 2780 |
+
"learning_rate": 7.737512242899118e-07,
|
| 2781 |
+
"loss": 1.0659,
|
| 2782 |
+
"step": 396
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.0023334548062115745,
|
| 2786 |
+
"grad_norm": 8.63479952985547,
|
| 2787 |
+
"learning_rate": 7.757100881488737e-07,
|
| 2788 |
+
"loss": 1.4686,
|
| 2789 |
+
"step": 397
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.002339332526126465,
|
| 2793 |
+
"grad_norm": 8.979262603318334,
|
| 2794 |
+
"learning_rate": 7.776689520078355e-07,
|
| 2795 |
+
"loss": 1.0556,
|
| 2796 |
+
"step": 398
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.0023452102460413556,
|
| 2800 |
+
"grad_norm": 10.076704637113531,
|
| 2801 |
+
"learning_rate": 7.796278158667973e-07,
|
| 2802 |
+
"loss": 1.4495,
|
| 2803 |
+
"step": 399
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.0023510879659562464,
|
| 2807 |
+
"grad_norm": 8.951312030590396,
|
| 2808 |
+
"learning_rate": 7.815866797257591e-07,
|
| 2809 |
+
"loss": 1.6132,
|
| 2810 |
+
"step": 400
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.0023569656858711367,
|
| 2814 |
+
"grad_norm": 8.979873542188797,
|
| 2815 |
+
"learning_rate": 7.83545543584721e-07,
|
| 2816 |
+
"loss": 1.3542,
|
| 2817 |
+
"step": 401
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.0023628434057860275,
|
| 2821 |
+
"grad_norm": 9.51825670965823,
|
| 2822 |
+
"learning_rate": 7.855044074436827e-07,
|
| 2823 |
+
"loss": 1.402,
|
| 2824 |
+
"step": 402
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.0023687211257009183,
|
| 2828 |
+
"grad_norm": 8.896133514148623,
|
| 2829 |
+
"learning_rate": 7.874632713026445e-07,
|
| 2830 |
+
"loss": 1.2905,
|
| 2831 |
+
"step": 403
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.0023745988456158086,
|
| 2835 |
+
"grad_norm": 9.451231888455286,
|
| 2836 |
+
"learning_rate": 7.894221351616063e-07,
|
| 2837 |
+
"loss": 1.4826,
|
| 2838 |
+
"step": 404
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.0023804765655306994,
|
| 2842 |
+
"grad_norm": 10.471983965291152,
|
| 2843 |
+
"learning_rate": 7.913809990205681e-07,
|
| 2844 |
+
"loss": 1.3434,
|
| 2845 |
+
"step": 405
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.00238635428544559,
|
| 2849 |
+
"grad_norm": 8.795466845801405,
|
| 2850 |
+
"learning_rate": 7.9333986287953e-07,
|
| 2851 |
+
"loss": 1.4804,
|
| 2852 |
+
"step": 406
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.0023922320053604805,
|
| 2856 |
+
"grad_norm": 8.395943785928992,
|
| 2857 |
+
"learning_rate": 7.952987267384918e-07,
|
| 2858 |
+
"loss": 1.3481,
|
| 2859 |
+
"step": 407
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.0023981097252753713,
|
| 2863 |
+
"grad_norm": 8.57882860152985,
|
| 2864 |
+
"learning_rate": 7.972575905974535e-07,
|
| 2865 |
+
"loss": 1.4464,
|
| 2866 |
+
"step": 408
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.0024039874451902616,
|
| 2870 |
+
"grad_norm": 9.311372146946045,
|
| 2871 |
+
"learning_rate": 7.992164544564153e-07,
|
| 2872 |
+
"loss": 1.4611,
|
| 2873 |
+
"step": 409
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.0024098651651051524,
|
| 2877 |
+
"grad_norm": 8.618542789091416,
|
| 2878 |
+
"learning_rate": 8.011753183153771e-07,
|
| 2879 |
+
"loss": 1.323,
|
| 2880 |
+
"step": 410
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.002415742885020043,
|
| 2884 |
+
"grad_norm": 9.51907141373062,
|
| 2885 |
+
"learning_rate": 8.03134182174339e-07,
|
| 2886 |
+
"loss": 1.1481,
|
| 2887 |
+
"step": 411
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 0.0024216206049349335,
|
| 2891 |
+
"grad_norm": 10.019154850223428,
|
| 2892 |
+
"learning_rate": 8.050930460333008e-07,
|
| 2893 |
+
"loss": 1.243,
|
| 2894 |
+
"step": 412
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.0024274983248498243,
|
| 2898 |
+
"grad_norm": 9.326959371627055,
|
| 2899 |
+
"learning_rate": 8.070519098922626e-07,
|
| 2900 |
+
"loss": 1.3822,
|
| 2901 |
+
"step": 413
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.002433376044764715,
|
| 2905 |
+
"grad_norm": 9.228495426900992,
|
| 2906 |
+
"learning_rate": 8.090107737512244e-07,
|
| 2907 |
+
"loss": 1.1939,
|
| 2908 |
+
"step": 414
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.0024392537646796054,
|
| 2912 |
+
"grad_norm": 9.307552867358865,
|
| 2913 |
+
"learning_rate": 8.109696376101861e-07,
|
| 2914 |
+
"loss": 1.3198,
|
| 2915 |
+
"step": 415
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.002445131484594496,
|
| 2919 |
+
"grad_norm": 8.463031761866146,
|
| 2920 |
+
"learning_rate": 8.12928501469148e-07,
|
| 2921 |
+
"loss": 1.4693,
|
| 2922 |
+
"step": 416
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 0.0024510092045093865,
|
| 2926 |
+
"grad_norm": 9.192023455695411,
|
| 2927 |
+
"learning_rate": 8.148873653281098e-07,
|
| 2928 |
+
"loss": 1.2851,
|
| 2929 |
+
"step": 417
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 0.0024568869244242773,
|
| 2933 |
+
"grad_norm": 8.852688157505836,
|
| 2934 |
+
"learning_rate": 8.168462291870716e-07,
|
| 2935 |
+
"loss": 1.3559,
|
| 2936 |
+
"step": 418
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.002462764644339168,
|
| 2940 |
+
"grad_norm": 10.27985063998931,
|
| 2941 |
+
"learning_rate": 8.188050930460334e-07,
|
| 2942 |
+
"loss": 1.5606,
|
| 2943 |
+
"step": 419
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 0.0024686423642540584,
|
| 2947 |
+
"grad_norm": 8.299719168895864,
|
| 2948 |
+
"learning_rate": 8.207639569049953e-07,
|
| 2949 |
+
"loss": 1.1143,
|
| 2950 |
+
"step": 420
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 0.002474520084168949,
|
| 2954 |
+
"grad_norm": 9.944928729713705,
|
| 2955 |
+
"learning_rate": 8.227228207639569e-07,
|
| 2956 |
+
"loss": 1.3194,
|
| 2957 |
+
"step": 421
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.00248039780408384,
|
| 2961 |
+
"grad_norm": 12.03407092301725,
|
| 2962 |
+
"learning_rate": 8.246816846229187e-07,
|
| 2963 |
+
"loss": 1.4087,
|
| 2964 |
+
"step": 422
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.0024862755239987303,
|
| 2968 |
+
"grad_norm": 14.891508805712057,
|
| 2969 |
+
"learning_rate": 8.266405484818805e-07,
|
| 2970 |
+
"loss": 1.4645,
|
| 2971 |
+
"step": 423
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.002492153243913621,
|
| 2975 |
+
"grad_norm": 9.1187340513171,
|
| 2976 |
+
"learning_rate": 8.285994123408423e-07,
|
| 2977 |
+
"loss": 1.1926,
|
| 2978 |
+
"step": 424
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.002498030963828512,
|
| 2982 |
+
"grad_norm": 9.319764152313796,
|
| 2983 |
+
"learning_rate": 8.305582761998042e-07,
|
| 2984 |
+
"loss": 1.2343,
|
| 2985 |
+
"step": 425
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.002503908683743402,
|
| 2989 |
+
"grad_norm": 10.484381391020465,
|
| 2990 |
+
"learning_rate": 8.32517140058766e-07,
|
| 2991 |
+
"loss": 1.2541,
|
| 2992 |
+
"step": 426
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.002509786403658293,
|
| 2996 |
+
"grad_norm": 8.69167001436625,
|
| 2997 |
+
"learning_rate": 8.344760039177278e-07,
|
| 2998 |
+
"loss": 1.2757,
|
| 2999 |
+
"step": 427
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.0025156641235731833,
|
| 3003 |
+
"grad_norm": 10.430608969858419,
|
| 3004 |
+
"learning_rate": 8.364348677766895e-07,
|
| 3005 |
+
"loss": 1.3012,
|
| 3006 |
+
"step": 428
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 0.002521541843488074,
|
| 3010 |
+
"grad_norm": 9.637826577295606,
|
| 3011 |
+
"learning_rate": 8.383937316356513e-07,
|
| 3012 |
+
"loss": 1.4526,
|
| 3013 |
+
"step": 429
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.002527419563402965,
|
| 3017 |
+
"grad_norm": 9.875465863294172,
|
| 3018 |
+
"learning_rate": 8.403525954946132e-07,
|
| 3019 |
+
"loss": 1.3497,
|
| 3020 |
+
"step": 430
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.002533297283317855,
|
| 3024 |
+
"grad_norm": 10.327297011939747,
|
| 3025 |
+
"learning_rate": 8.42311459353575e-07,
|
| 3026 |
+
"loss": 1.6876,
|
| 3027 |
+
"step": 431
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 0.002539175003232746,
|
| 3031 |
+
"grad_norm": 8.944459341621092,
|
| 3032 |
+
"learning_rate": 8.442703232125368e-07,
|
| 3033 |
+
"loss": 1.557,
|
| 3034 |
+
"step": 432
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.0025450527231476367,
|
| 3038 |
+
"grad_norm": 9.38025206199169,
|
| 3039 |
+
"learning_rate": 8.462291870714986e-07,
|
| 3040 |
+
"loss": 1.4929,
|
| 3041 |
+
"step": 433
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.002550930443062527,
|
| 3045 |
+
"grad_norm": 6.7474803815775894,
|
| 3046 |
+
"learning_rate": 8.481880509304604e-07,
|
| 3047 |
+
"loss": 1.1632,
|
| 3048 |
+
"step": 434
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 0.002556808162977418,
|
| 3052 |
+
"grad_norm": 9.316752827855126,
|
| 3053 |
+
"learning_rate": 8.501469147894222e-07,
|
| 3054 |
+
"loss": 1.555,
|
| 3055 |
+
"step": 435
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.0025626858828923086,
|
| 3059 |
+
"grad_norm": 8.950472923863874,
|
| 3060 |
+
"learning_rate": 8.52105778648384e-07,
|
| 3061 |
+
"loss": 1.5023,
|
| 3062 |
+
"step": 436
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.002568563602807199,
|
| 3066 |
+
"grad_norm": 7.877832954575786,
|
| 3067 |
+
"learning_rate": 8.540646425073458e-07,
|
| 3068 |
+
"loss": 1.2223,
|
| 3069 |
+
"step": 437
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.0025744413227220897,
|
| 3073 |
+
"grad_norm": 11.13541528348567,
|
| 3074 |
+
"learning_rate": 8.560235063663076e-07,
|
| 3075 |
+
"loss": 1.4983,
|
| 3076 |
+
"step": 438
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.00258031904263698,
|
| 3080 |
+
"grad_norm": 10.284682190541375,
|
| 3081 |
+
"learning_rate": 8.579823702252694e-07,
|
| 3082 |
+
"loss": 1.4565,
|
| 3083 |
+
"step": 439
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.002586196762551871,
|
| 3087 |
+
"grad_norm": 7.154879985048399,
|
| 3088 |
+
"learning_rate": 8.599412340842313e-07,
|
| 3089 |
+
"loss": 0.9219,
|
| 3090 |
+
"step": 440
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.0025920744824667616,
|
| 3094 |
+
"grad_norm": 12.374858918870638,
|
| 3095 |
+
"learning_rate": 8.61900097943193e-07,
|
| 3096 |
+
"loss": 1.3466,
|
| 3097 |
+
"step": 441
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.002597952202381652,
|
| 3101 |
+
"grad_norm": 9.530586145055318,
|
| 3102 |
+
"learning_rate": 8.638589618021548e-07,
|
| 3103 |
+
"loss": 1.2966,
|
| 3104 |
+
"step": 442
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.0026038299222965427,
|
| 3108 |
+
"grad_norm": 10.52530275859048,
|
| 3109 |
+
"learning_rate": 8.658178256611166e-07,
|
| 3110 |
+
"loss": 1.535,
|
| 3111 |
+
"step": 443
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 0.0026097076422114335,
|
| 3115 |
+
"grad_norm": 11.113832609940571,
|
| 3116 |
+
"learning_rate": 8.677766895200785e-07,
|
| 3117 |
+
"loss": 1.2633,
|
| 3118 |
+
"step": 444
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 0.002615585362126324,
|
| 3122 |
+
"grad_norm": 9.893958350977293,
|
| 3123 |
+
"learning_rate": 8.697355533790403e-07,
|
| 3124 |
+
"loss": 1.1753,
|
| 3125 |
+
"step": 445
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 0.0026214630820412146,
|
| 3129 |
+
"grad_norm": 9.699442687702016,
|
| 3130 |
+
"learning_rate": 8.716944172380021e-07,
|
| 3131 |
+
"loss": 1.2883,
|
| 3132 |
+
"step": 446
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 0.0026273408019561054,
|
| 3136 |
+
"grad_norm": 8.627446824111422,
|
| 3137 |
+
"learning_rate": 8.736532810969639e-07,
|
| 3138 |
+
"loss": 1.2994,
|
| 3139 |
+
"step": 447
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 0.0026332185218709957,
|
| 3143 |
+
"grad_norm": 9.18927129378313,
|
| 3144 |
+
"learning_rate": 8.756121449559256e-07,
|
| 3145 |
+
"loss": 1.0687,
|
| 3146 |
+
"step": 448
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.0026390962417858865,
|
| 3150 |
+
"grad_norm": 11.084942651516588,
|
| 3151 |
+
"learning_rate": 8.775710088148875e-07,
|
| 3152 |
+
"loss": 1.2795,
|
| 3153 |
+
"step": 449
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 0.002644973961700777,
|
| 3157 |
+
"grad_norm": 9.129354706792896,
|
| 3158 |
+
"learning_rate": 8.795298726738493e-07,
|
| 3159 |
+
"loss": 1.3835,
|
| 3160 |
+
"step": 450
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 0.0026508516816156676,
|
| 3164 |
+
"grad_norm": 12.327908421949875,
|
| 3165 |
+
"learning_rate": 8.814887365328111e-07,
|
| 3166 |
+
"loss": 1.5225,
|
| 3167 |
+
"step": 451
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 0.0026567294015305584,
|
| 3171 |
+
"grad_norm": 8.31873640235426,
|
| 3172 |
+
"learning_rate": 8.834476003917729e-07,
|
| 3173 |
+
"loss": 0.8396,
|
| 3174 |
+
"step": 452
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 0.0026626071214454487,
|
| 3178 |
+
"grad_norm": 9.854541808925802,
|
| 3179 |
+
"learning_rate": 8.854064642507347e-07,
|
| 3180 |
+
"loss": 1.5565,
|
| 3181 |
+
"step": 453
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.0026684848413603395,
|
| 3185 |
+
"grad_norm": 9.985607380778386,
|
| 3186 |
+
"learning_rate": 8.873653281096964e-07,
|
| 3187 |
+
"loss": 1.342,
|
| 3188 |
+
"step": 454
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.0026743625612752303,
|
| 3192 |
+
"grad_norm": 8.500019891152785,
|
| 3193 |
+
"learning_rate": 8.893241919686582e-07,
|
| 3194 |
+
"loss": 1.2752,
|
| 3195 |
+
"step": 455
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 0.0026802402811901206,
|
| 3199 |
+
"grad_norm": 9.733680853033052,
|
| 3200 |
+
"learning_rate": 8.9128305582762e-07,
|
| 3201 |
+
"loss": 1.337,
|
| 3202 |
+
"step": 456
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 0.0026861180011050114,
|
| 3206 |
+
"grad_norm": 8.956767161220945,
|
| 3207 |
+
"learning_rate": 8.932419196865818e-07,
|
| 3208 |
+
"loss": 1.2516,
|
| 3209 |
+
"step": 457
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 0.0026919957210199017,
|
| 3213 |
+
"grad_norm": 8.920962685189888,
|
| 3214 |
+
"learning_rate": 8.952007835455436e-07,
|
| 3215 |
+
"loss": 1.2214,
|
| 3216 |
+
"step": 458
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 0.0026978734409347925,
|
| 3220 |
+
"grad_norm": 7.890385891017338,
|
| 3221 |
+
"learning_rate": 8.971596474045055e-07,
|
| 3222 |
+
"loss": 1.2096,
|
| 3223 |
+
"step": 459
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 0.0027037511608496833,
|
| 3227 |
+
"grad_norm": 8.718195916912373,
|
| 3228 |
+
"learning_rate": 8.991185112634673e-07,
|
| 3229 |
+
"loss": 1.4737,
|
| 3230 |
+
"step": 460
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 0.0027096288807645736,
|
| 3234 |
+
"grad_norm": 9.678136630934903,
|
| 3235 |
+
"learning_rate": 9.01077375122429e-07,
|
| 3236 |
+
"loss": 1.4187,
|
| 3237 |
+
"step": 461
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 0.0027155066006794644,
|
| 3241 |
+
"grad_norm": 9.23524546999622,
|
| 3242 |
+
"learning_rate": 9.030362389813908e-07,
|
| 3243 |
+
"loss": 1.6633,
|
| 3244 |
+
"step": 462
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 0.002721384320594355,
|
| 3248 |
+
"grad_norm": 9.32560092969864,
|
| 3249 |
+
"learning_rate": 9.049951028403526e-07,
|
| 3250 |
+
"loss": 1.1974,
|
| 3251 |
+
"step": 463
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 0.0027272620405092455,
|
| 3255 |
+
"grad_norm": 9.528071260395997,
|
| 3256 |
+
"learning_rate": 9.069539666993145e-07,
|
| 3257 |
+
"loss": 1.1997,
|
| 3258 |
+
"step": 464
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 0.0027331397604241363,
|
| 3262 |
+
"grad_norm": 10.425385414374023,
|
| 3263 |
+
"learning_rate": 9.089128305582763e-07,
|
| 3264 |
+
"loss": 1.3841,
|
| 3265 |
+
"step": 465
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 0.002739017480339027,
|
| 3269 |
+
"grad_norm": 9.650811170590984,
|
| 3270 |
+
"learning_rate": 9.108716944172381e-07,
|
| 3271 |
+
"loss": 1.445,
|
| 3272 |
+
"step": 466
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 0.0027448952002539174,
|
| 3276 |
+
"grad_norm": 9.252989896370744,
|
| 3277 |
+
"learning_rate": 9.128305582761998e-07,
|
| 3278 |
+
"loss": 1.4595,
|
| 3279 |
+
"step": 467
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 0.002750772920168808,
|
| 3283 |
+
"grad_norm": 8.799240937283905,
|
| 3284 |
+
"learning_rate": 9.147894221351617e-07,
|
| 3285 |
+
"loss": 1.3579,
|
| 3286 |
+
"step": 468
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.0027566506400836985,
|
| 3290 |
+
"grad_norm": 9.687119531664132,
|
| 3291 |
+
"learning_rate": 9.167482859941235e-07,
|
| 3292 |
+
"loss": 1.3415,
|
| 3293 |
+
"step": 469
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 0.0027625283599985893,
|
| 3297 |
+
"grad_norm": 8.093757997436107,
|
| 3298 |
+
"learning_rate": 9.187071498530853e-07,
|
| 3299 |
+
"loss": 1.0167,
|
| 3300 |
+
"step": 470
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 0.00276840607991348,
|
| 3304 |
+
"grad_norm": 8.141074348047649,
|
| 3305 |
+
"learning_rate": 9.206660137120471e-07,
|
| 3306 |
+
"loss": 1.5446,
|
| 3307 |
+
"step": 471
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.0027742837998283704,
|
| 3311 |
+
"grad_norm": 8.677237791994125,
|
| 3312 |
+
"learning_rate": 9.226248775710089e-07,
|
| 3313 |
+
"loss": 1.5067,
|
| 3314 |
+
"step": 472
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.002780161519743261,
|
| 3318 |
+
"grad_norm": 10.61789466008841,
|
| 3319 |
+
"learning_rate": 9.245837414299708e-07,
|
| 3320 |
+
"loss": 1.3241,
|
| 3321 |
+
"step": 473
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 0.002786039239658152,
|
| 3325 |
+
"grad_norm": 8.683931156910312,
|
| 3326 |
+
"learning_rate": 9.265426052889325e-07,
|
| 3327 |
+
"loss": 1.8794,
|
| 3328 |
+
"step": 474
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 0.0027919169595730423,
|
| 3332 |
+
"grad_norm": 12.103438115936399,
|
| 3333 |
+
"learning_rate": 9.285014691478943e-07,
|
| 3334 |
+
"loss": 1.5244,
|
| 3335 |
+
"step": 475
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 0.002797794679487933,
|
| 3339 |
+
"grad_norm": 9.337103354710932,
|
| 3340 |
+
"learning_rate": 9.304603330068561e-07,
|
| 3341 |
+
"loss": 1.1772,
|
| 3342 |
+
"step": 476
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 0.002803672399402824,
|
| 3346 |
+
"grad_norm": 7.2667453744292265,
|
| 3347 |
+
"learning_rate": 9.324191968658179e-07,
|
| 3348 |
+
"loss": 1.336,
|
| 3349 |
+
"step": 477
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 0.002809550119317714,
|
| 3353 |
+
"grad_norm": 7.7598194126940205,
|
| 3354 |
+
"learning_rate": 9.343780607247798e-07,
|
| 3355 |
+
"loss": 1.1973,
|
| 3356 |
+
"step": 478
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.002815427839232605,
|
| 3360 |
+
"grad_norm": 8.149477213248854,
|
| 3361 |
+
"learning_rate": 9.363369245837416e-07,
|
| 3362 |
+
"loss": 0.97,
|
| 3363 |
+
"step": 479
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 0.0028213055591474953,
|
| 3367 |
+
"grad_norm": 9.690960617524013,
|
| 3368 |
+
"learning_rate": 9.382957884427032e-07,
|
| 3369 |
+
"loss": 1.5165,
|
| 3370 |
+
"step": 480
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 0.002827183279062386,
|
| 3374 |
+
"grad_norm": 7.931888369964113,
|
| 3375 |
+
"learning_rate": 9.40254652301665e-07,
|
| 3376 |
+
"loss": 1.2378,
|
| 3377 |
+
"step": 481
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 0.002833060998977277,
|
| 3381 |
+
"grad_norm": 10.600482057686264,
|
| 3382 |
+
"learning_rate": 9.42213516160627e-07,
|
| 3383 |
+
"loss": 1.4659,
|
| 3384 |
+
"step": 482
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 0.002838938718892167,
|
| 3388 |
+
"grad_norm": 7.766775925211392,
|
| 3389 |
+
"learning_rate": 9.441723800195888e-07,
|
| 3390 |
+
"loss": 1.3378,
|
| 3391 |
+
"step": 483
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 0.002844816438807058,
|
| 3395 |
+
"grad_norm": 8.567731069736155,
|
| 3396 |
+
"learning_rate": 9.461312438785506e-07,
|
| 3397 |
+
"loss": 1.2967,
|
| 3398 |
+
"step": 484
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 0.0028506941587219487,
|
| 3402 |
+
"grad_norm": 8.798070275014695,
|
| 3403 |
+
"learning_rate": 9.480901077375124e-07,
|
| 3404 |
+
"loss": 1.696,
|
| 3405 |
+
"step": 485
|
| 3406 |
+
},
|
| 3407 |
+
{
|
| 3408 |
+
"epoch": 0.002856571878636839,
|
| 3409 |
+
"grad_norm": 9.728901498213226,
|
| 3410 |
+
"learning_rate": 9.500489715964742e-07,
|
| 3411 |
+
"loss": 1.412,
|
| 3412 |
+
"step": 486
|
| 3413 |
+
},
|
| 3414 |
+
{
|
| 3415 |
+
"epoch": 0.00286244959855173,
|
| 3416 |
+
"grad_norm": 11.037063609664564,
|
| 3417 |
+
"learning_rate": 9.520078354554358e-07,
|
| 3418 |
+
"loss": 1.5683,
|
| 3419 |
+
"step": 487
|
| 3420 |
+
},
|
| 3421 |
+
{
|
| 3422 |
+
"epoch": 0.0028683273184666206,
|
| 3423 |
+
"grad_norm": 10.07693872625589,
|
| 3424 |
+
"learning_rate": 9.539666993143978e-07,
|
| 3425 |
+
"loss": 1.3795,
|
| 3426 |
+
"step": 488
|
| 3427 |
+
},
|
| 3428 |
+
{
|
| 3429 |
+
"epoch": 0.002874205038381511,
|
| 3430 |
+
"grad_norm": 9.198521301044554,
|
| 3431 |
+
"learning_rate": 9.559255631733596e-07,
|
| 3432 |
+
"loss": 1.3621,
|
| 3433 |
+
"step": 489
|
| 3434 |
+
},
|
| 3435 |
+
{
|
| 3436 |
+
"epoch": 0.0028800827582964018,
|
| 3437 |
+
"grad_norm": 9.072594042611673,
|
| 3438 |
+
"learning_rate": 9.578844270323214e-07,
|
| 3439 |
+
"loss": 1.2669,
|
| 3440 |
+
"step": 490
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 0.002885960478211292,
|
| 3444 |
+
"grad_norm": 10.420415483294377,
|
| 3445 |
+
"learning_rate": 9.598432908912832e-07,
|
| 3446 |
+
"loss": 1.2451,
|
| 3447 |
+
"step": 491
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"epoch": 0.002891838198126183,
|
| 3451 |
+
"grad_norm": 8.650756741993991,
|
| 3452 |
+
"learning_rate": 9.61802154750245e-07,
|
| 3453 |
+
"loss": 1.3327,
|
| 3454 |
+
"step": 492
|
| 3455 |
+
},
|
| 3456 |
+
{
|
| 3457 |
+
"epoch": 0.0028977159180410736,
|
| 3458 |
+
"grad_norm": 10.699415230564549,
|
| 3459 |
+
"learning_rate": 9.637610186092067e-07,
|
| 3460 |
+
"loss": 1.3475,
|
| 3461 |
+
"step": 493
|
| 3462 |
+
},
|
| 3463 |
+
{
|
| 3464 |
+
"epoch": 0.002903593637955964,
|
| 3465 |
+
"grad_norm": 10.252178027073803,
|
| 3466 |
+
"learning_rate": 9.657198824681685e-07,
|
| 3467 |
+
"loss": 1.6232,
|
| 3468 |
+
"step": 494
|
| 3469 |
+
},
|
| 3470 |
+
{
|
| 3471 |
+
"epoch": 0.0029094713578708548,
|
| 3472 |
+
"grad_norm": 8.058950860691148,
|
| 3473 |
+
"learning_rate": 9.676787463271303e-07,
|
| 3474 |
+
"loss": 1.3211,
|
| 3475 |
+
"step": 495
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 0.0029153490777857455,
|
| 3479 |
+
"grad_norm": 10.007337786160015,
|
| 3480 |
+
"learning_rate": 9.696376101860921e-07,
|
| 3481 |
+
"loss": 1.5046,
|
| 3482 |
+
"step": 496
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 0.002921226797700636,
|
| 3486 |
+
"grad_norm": 7.85615985186399,
|
| 3487 |
+
"learning_rate": 9.71596474045054e-07,
|
| 3488 |
+
"loss": 1.1484,
|
| 3489 |
+
"step": 497
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 0.0029271045176155266,
|
| 3493 |
+
"grad_norm": 8.540344613450793,
|
| 3494 |
+
"learning_rate": 9.735553379040158e-07,
|
| 3495 |
+
"loss": 1.4431,
|
| 3496 |
+
"step": 498
|
| 3497 |
+
},
|
| 3498 |
+
{
|
| 3499 |
+
"epoch": 0.002932982237530417,
|
| 3500 |
+
"grad_norm": 8.896907762371791,
|
| 3501 |
+
"learning_rate": 9.755142017629776e-07,
|
| 3502 |
+
"loss": 1.1179,
|
| 3503 |
+
"step": 499
|
| 3504 |
+
},
|
| 3505 |
+
{
|
| 3506 |
+
"epoch": 0.0029388599574453078,
|
| 3507 |
+
"grad_norm": 8.91483404955683,
|
| 3508 |
+
"learning_rate": 9.774730656219392e-07,
|
| 3509 |
+
"loss": 1.9639,
|
| 3510 |
+
"step": 500
|
| 3511 |
+
}
|
| 3512 |
+
],
|
| 3513 |
+
"logging_steps": 1.0,
|
| 3514 |
+
"max_steps": 170134,
|
| 3515 |
+
"num_input_tokens_seen": 0,
|
| 3516 |
+
"num_train_epochs": 1,
|
| 3517 |
+
"save_steps": 500,
|
| 3518 |
+
"stateful_callbacks": {
|
| 3519 |
+
"TrainerControl": {
|
| 3520 |
+
"args": {
|
| 3521 |
+
"should_epoch_stop": false,
|
| 3522 |
+
"should_evaluate": false,
|
| 3523 |
+
"should_log": false,
|
| 3524 |
+
"should_save": false,
|
| 3525 |
+
"should_training_stop": false
|
| 3526 |
+
},
|
| 3527 |
+
"attributes": {}
|
| 3528 |
+
}
|
| 3529 |
+
},
|
| 3530 |
+
"total_flos": 7987300275200.0,
|
| 3531 |
+
"train_batch_size": 1,
|
| 3532 |
+
"trial_name": null,
|
| 3533 |
+
"trial_params": null
|
| 3534 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2054bd27220a2429293bf4af6a4f732b0ed559ecd3927b4ed0f3a564f4a984d
|
| 3 |
+
size 8785
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info("Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info("Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|