Upload folder using huggingface_hub
Browse files- config.json +261 -0
- llm/config.json +31 -0
- llm/generation_config.json +12 -0
- llm/model-00001-of-00004.safetensors +3 -0
- llm/model-00002-of-00004.safetensors +3 -0
- llm/model-00003-of-00004.safetensors +3 -0
- llm/model-00004-of-00004.safetensors +3 -0
- llm/model.safetensors.index.json +298 -0
- llm/special_tokens_map.json +23 -0
- llm/tokenizer.json +0 -0
- llm/tokenizer_config.json +2089 -0
- mm_projector/config.json +10 -0
- mm_projector/model.safetensors +3 -0
- trainer_state.json +4604 -0
- vision_tower/config.json +21 -0
- vision_tower/model.safetensors +3 -0
- vision_tower/preprocessor_config.json +23 -0
config.json
ADDED
|
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaLlamaModel"
|
| 5 |
+
],
|
| 6 |
+
"chat_template": null,
|
| 7 |
+
"drop_path_rate": 0.0,
|
| 8 |
+
"fps": 0.0,
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"image_aspect_ratio": "resize",
|
| 11 |
+
"interpolate_mode": "linear",
|
| 12 |
+
"llm_cfg": {
|
| 13 |
+
"_name_or_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes/llm",
|
| 14 |
+
"add_cross_attention": false,
|
| 15 |
+
"architectures": [
|
| 16 |
+
"LlamaForCausalLM"
|
| 17 |
+
],
|
| 18 |
+
"attention_bias": false,
|
| 19 |
+
"attention_dropout": 0.0,
|
| 20 |
+
"bad_words_ids": null,
|
| 21 |
+
"begin_suppress_tokens": null,
|
| 22 |
+
"bos_token_id": 128000,
|
| 23 |
+
"chunk_size_feed_forward": 0,
|
| 24 |
+
"cross_attention_hidden_size": null,
|
| 25 |
+
"decoder_start_token_id": null,
|
| 26 |
+
"diversity_penalty": 0.0,
|
| 27 |
+
"do_sample": false,
|
| 28 |
+
"early_stopping": false,
|
| 29 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 30 |
+
"eos_token_id": 128009,
|
| 31 |
+
"exponential_decay_length_penalty": null,
|
| 32 |
+
"finetuning_task": null,
|
| 33 |
+
"forced_bos_token_id": null,
|
| 34 |
+
"forced_eos_token_id": null,
|
| 35 |
+
"hidden_act": "silu",
|
| 36 |
+
"hidden_size": 4096,
|
| 37 |
+
"id2label": {
|
| 38 |
+
"0": "LABEL_0",
|
| 39 |
+
"1": "LABEL_1"
|
| 40 |
+
},
|
| 41 |
+
"initializer_range": 0.02,
|
| 42 |
+
"intermediate_size": 14336,
|
| 43 |
+
"is_decoder": false,
|
| 44 |
+
"is_encoder_decoder": false,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"LABEL_0": 0,
|
| 47 |
+
"LABEL_1": 1
|
| 48 |
+
},
|
| 49 |
+
"length_penalty": 1.0,
|
| 50 |
+
"max_length": 20,
|
| 51 |
+
"max_position_embeddings": 8192,
|
| 52 |
+
"min_length": 0,
|
| 53 |
+
"model_max_length": 4096,
|
| 54 |
+
"model_type": "llama",
|
| 55 |
+
"no_repeat_ngram_size": 0,
|
| 56 |
+
"num_attention_heads": 32,
|
| 57 |
+
"num_beam_groups": 1,
|
| 58 |
+
"num_beams": 1,
|
| 59 |
+
"num_hidden_layers": 32,
|
| 60 |
+
"num_key_value_heads": 8,
|
| 61 |
+
"num_return_sequences": 1,
|
| 62 |
+
"output_attentions": false,
|
| 63 |
+
"output_hidden_states": false,
|
| 64 |
+
"output_scores": false,
|
| 65 |
+
"pad_token_id": null,
|
| 66 |
+
"prefix": null,
|
| 67 |
+
"pretraining_tp": 1,
|
| 68 |
+
"problem_type": null,
|
| 69 |
+
"pruned_heads": {},
|
| 70 |
+
"remove_invalid_values": false,
|
| 71 |
+
"repetition_penalty": 1.0,
|
| 72 |
+
"return_dict": true,
|
| 73 |
+
"return_dict_in_generate": false,
|
| 74 |
+
"rms_norm_eps": 1e-05,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 500000.0,
|
| 77 |
+
"sep_token_id": null,
|
| 78 |
+
"suppress_tokens": null,
|
| 79 |
+
"task_specific_params": null,
|
| 80 |
+
"temperature": 1.0,
|
| 81 |
+
"tf_legacy_loss": false,
|
| 82 |
+
"tie_encoder_decoder": false,
|
| 83 |
+
"tie_word_embeddings": false,
|
| 84 |
+
"tokenizer_class": null,
|
| 85 |
+
"tokenizer_model_max_length": 4096,
|
| 86 |
+
"tokenizer_padding_side": "right",
|
| 87 |
+
"top_k": 50,
|
| 88 |
+
"top_p": 1.0,
|
| 89 |
+
"torch_dtype": "bfloat16",
|
| 90 |
+
"torchscript": false,
|
| 91 |
+
"typical_p": 1.0,
|
| 92 |
+
"use_bfloat16": false,
|
| 93 |
+
"use_cache": true,
|
| 94 |
+
"vocab_size": 128259
|
| 95 |
+
},
|
| 96 |
+
"mm_hidden_size": 1152,
|
| 97 |
+
"mm_projector_cfg": {
|
| 98 |
+
"_name_or_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes/mm_projector",
|
| 99 |
+
"add_cross_attention": false,
|
| 100 |
+
"architectures": [
|
| 101 |
+
"MultimodalProjector"
|
| 102 |
+
],
|
| 103 |
+
"bad_words_ids": null,
|
| 104 |
+
"begin_suppress_tokens": null,
|
| 105 |
+
"bos_token_id": null,
|
| 106 |
+
"chunk_size_feed_forward": 0,
|
| 107 |
+
"cross_attention_hidden_size": null,
|
| 108 |
+
"decoder_start_token_id": null,
|
| 109 |
+
"diversity_penalty": 0.0,
|
| 110 |
+
"do_sample": false,
|
| 111 |
+
"early_stopping": false,
|
| 112 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 113 |
+
"eos_token_id": null,
|
| 114 |
+
"exponential_decay_length_penalty": null,
|
| 115 |
+
"finetuning_task": null,
|
| 116 |
+
"forced_bos_token_id": null,
|
| 117 |
+
"forced_eos_token_id": null,
|
| 118 |
+
"id2label": {
|
| 119 |
+
"0": "LABEL_0",
|
| 120 |
+
"1": "LABEL_1"
|
| 121 |
+
},
|
| 122 |
+
"is_decoder": false,
|
| 123 |
+
"is_encoder_decoder": false,
|
| 124 |
+
"label2id": {
|
| 125 |
+
"LABEL_0": 0,
|
| 126 |
+
"LABEL_1": 1
|
| 127 |
+
},
|
| 128 |
+
"length_penalty": 1.0,
|
| 129 |
+
"max_length": 20,
|
| 130 |
+
"min_length": 0,
|
| 131 |
+
"mm_projector_type": "mlp_downsample",
|
| 132 |
+
"model_type": "v2l_projector",
|
| 133 |
+
"no_repeat_ngram_size": 0,
|
| 134 |
+
"num_beam_groups": 1,
|
| 135 |
+
"num_beams": 1,
|
| 136 |
+
"num_return_sequences": 1,
|
| 137 |
+
"output_attentions": false,
|
| 138 |
+
"output_hidden_states": false,
|
| 139 |
+
"output_scores": false,
|
| 140 |
+
"pad_token_id": null,
|
| 141 |
+
"prefix": null,
|
| 142 |
+
"problem_type": null,
|
| 143 |
+
"pruned_heads": {},
|
| 144 |
+
"remove_invalid_values": false,
|
| 145 |
+
"repetition_penalty": 1.0,
|
| 146 |
+
"return_dict": true,
|
| 147 |
+
"return_dict_in_generate": false,
|
| 148 |
+
"sep_token_id": null,
|
| 149 |
+
"suppress_tokens": null,
|
| 150 |
+
"task_specific_params": null,
|
| 151 |
+
"temperature": 1.0,
|
| 152 |
+
"tf_legacy_loss": false,
|
| 153 |
+
"tie_encoder_decoder": false,
|
| 154 |
+
"tie_word_embeddings": true,
|
| 155 |
+
"tokenizer_class": null,
|
| 156 |
+
"top_k": 50,
|
| 157 |
+
"top_p": 1.0,
|
| 158 |
+
"torch_dtype": "bfloat16",
|
| 159 |
+
"torchscript": false,
|
| 160 |
+
"typical_p": 1.0,
|
| 161 |
+
"use_bfloat16": false
|
| 162 |
+
},
|
| 163 |
+
"mm_projector_lr": null,
|
| 164 |
+
"mm_use_im_patch_token": false,
|
| 165 |
+
"mm_use_im_start_end": false,
|
| 166 |
+
"mm_vision_select_feature": "cls_patch",
|
| 167 |
+
"mm_vision_select_layer": -2,
|
| 168 |
+
"model_dtype": "torch.bfloat16",
|
| 169 |
+
"model_type": "llava_llama",
|
| 170 |
+
"num_time_tokens": 0,
|
| 171 |
+
"num_video_frames": 8,
|
| 172 |
+
"resume_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes",
|
| 173 |
+
"s2": false,
|
| 174 |
+
"s2_max_split_size": 336,
|
| 175 |
+
"s2_scales": "336,672,1008",
|
| 176 |
+
"soft_ce_std": 1.0,
|
| 177 |
+
"time_token_format": "<t{t}>",
|
| 178 |
+
"time_token_ids": [],
|
| 179 |
+
"transformers_version": "4.37.2",
|
| 180 |
+
"tune_language_model": true,
|
| 181 |
+
"tune_mm_projector": true,
|
| 182 |
+
"tune_vision_tower": true,
|
| 183 |
+
"vision_resolution": -1,
|
| 184 |
+
"vision_tower_cfg": {
|
| 185 |
+
"_name_or_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes/vision_tower",
|
| 186 |
+
"add_cross_attention": false,
|
| 187 |
+
"architectures": [
|
| 188 |
+
"SiglipVisionModel"
|
| 189 |
+
],
|
| 190 |
+
"attention_dropout": 0.0,
|
| 191 |
+
"bad_words_ids": null,
|
| 192 |
+
"begin_suppress_tokens": null,
|
| 193 |
+
"bos_token_id": null,
|
| 194 |
+
"chunk_size_feed_forward": 0,
|
| 195 |
+
"cross_attention_hidden_size": null,
|
| 196 |
+
"decoder_start_token_id": null,
|
| 197 |
+
"diversity_penalty": 0.0,
|
| 198 |
+
"do_sample": false,
|
| 199 |
+
"early_stopping": false,
|
| 200 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 201 |
+
"eos_token_id": null,
|
| 202 |
+
"exponential_decay_length_penalty": null,
|
| 203 |
+
"finetuning_task": null,
|
| 204 |
+
"forced_bos_token_id": null,
|
| 205 |
+
"forced_eos_token_id": null,
|
| 206 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 207 |
+
"hidden_size": 1152,
|
| 208 |
+
"id2label": {
|
| 209 |
+
"0": "LABEL_0",
|
| 210 |
+
"1": "LABEL_1"
|
| 211 |
+
},
|
| 212 |
+
"image_size": 384,
|
| 213 |
+
"intermediate_size": 4304,
|
| 214 |
+
"is_decoder": false,
|
| 215 |
+
"is_encoder_decoder": false,
|
| 216 |
+
"label2id": {
|
| 217 |
+
"LABEL_0": 0,
|
| 218 |
+
"LABEL_1": 1
|
| 219 |
+
},
|
| 220 |
+
"layer_norm_eps": 1e-06,
|
| 221 |
+
"length_penalty": 1.0,
|
| 222 |
+
"llm_depth_token_id": 128258,
|
| 223 |
+
"llm_mask_token_id": 128257,
|
| 224 |
+
"max_length": 20,
|
| 225 |
+
"min_length": 0,
|
| 226 |
+
"model_type": "siglip_vision_model",
|
| 227 |
+
"no_repeat_ngram_size": 0,
|
| 228 |
+
"num_attention_heads": 16,
|
| 229 |
+
"num_beam_groups": 1,
|
| 230 |
+
"num_beams": 1,
|
| 231 |
+
"num_channels": 3,
|
| 232 |
+
"num_hidden_layers": 27,
|
| 233 |
+
"num_return_sequences": 1,
|
| 234 |
+
"output_attentions": false,
|
| 235 |
+
"output_hidden_states": false,
|
| 236 |
+
"output_scores": false,
|
| 237 |
+
"pad_token_id": null,
|
| 238 |
+
"patch_size": 14,
|
| 239 |
+
"prefix": null,
|
| 240 |
+
"problem_type": null,
|
| 241 |
+
"pruned_heads": {},
|
| 242 |
+
"remove_invalid_values": false,
|
| 243 |
+
"repetition_penalty": 1.0,
|
| 244 |
+
"return_dict": true,
|
| 245 |
+
"return_dict_in_generate": false,
|
| 246 |
+
"sep_token_id": null,
|
| 247 |
+
"suppress_tokens": null,
|
| 248 |
+
"task_specific_params": null,
|
| 249 |
+
"temperature": 1.0,
|
| 250 |
+
"tf_legacy_loss": false,
|
| 251 |
+
"tie_encoder_decoder": false,
|
| 252 |
+
"tie_word_embeddings": true,
|
| 253 |
+
"tokenizer_class": null,
|
| 254 |
+
"top_k": 50,
|
| 255 |
+
"top_p": 1.0,
|
| 256 |
+
"torch_dtype": "bfloat16",
|
| 257 |
+
"torchscript": false,
|
| 258 |
+
"typical_p": 1.0,
|
| 259 |
+
"use_bfloat16": false
|
| 260 |
+
}
|
| 261 |
+
}
|
llm/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes/llm",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128009,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"model_max_length": 4096,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 500000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"tokenizer_model_max_length": 4096,
|
| 26 |
+
"tokenizer_padding_side": "right",
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.37.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 128259
|
| 31 |
+
}
|
llm/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128009
|
| 7 |
+
],
|
| 8 |
+
"max_length": 4096,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.37.2"
|
| 12 |
+
}
|
llm/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:043130cd24faf156eeb2f2d6af6fc0a540a4b617bdf0fa215ef1f975421ad092
|
| 3 |
+
size 4976723248
|
llm/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e29d858bcb4f1a869c155bd94a72df9afe8e2aa0ca3358fb0d6a669d14a5b29
|
| 3 |
+
size 4999802720
|
llm/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b20dbe3176063e6474c34ec1caee3e469c089aff6d09820142218080ab1e324a
|
| 3 |
+
size 4915916176
|
llm/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e32679c0a326969850f76e7321fb74bb729dec8ca82f77c5268ee582fcdeaf40
|
| 3 |
+
size 1168163384
|
llm/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16060571648
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
llm/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
llm/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llm/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2089 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|reserved_special_token_2|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|reserved_special_token_4|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|reserved_special_token_5|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_6|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_7|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_8|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_9|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_10|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_11|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_12|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_13|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_14|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_15|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_16|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"128256": {
|
| 2052 |
+
"content": "[PAD]",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
+
},
|
| 2059 |
+
"128257": {
|
| 2060 |
+
"content": "<mask>",
|
| 2061 |
+
"lstrip": false,
|
| 2062 |
+
"normalized": false,
|
| 2063 |
+
"rstrip": false,
|
| 2064 |
+
"single_word": false,
|
| 2065 |
+
"special": true
|
| 2066 |
+
},
|
| 2067 |
+
"128258": {
|
| 2068 |
+
"content": "<depth>",
|
| 2069 |
+
"lstrip": false,
|
| 2070 |
+
"normalized": false,
|
| 2071 |
+
"rstrip": false,
|
| 2072 |
+
"single_word": false,
|
| 2073 |
+
"special": true
|
| 2074 |
+
}
|
| 2075 |
+
},
|
| 2076 |
+
"bos_token": "<|begin_of_text|>",
|
| 2077 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2078 |
+
"clean_up_tokenization_spaces": true,
|
| 2079 |
+
"eos_token": "<|eot_id|>",
|
| 2080 |
+
"legacy": false,
|
| 2081 |
+
"model_input_names": [
|
| 2082 |
+
"input_ids",
|
| 2083 |
+
"attention_mask"
|
| 2084 |
+
],
|
| 2085 |
+
"model_max_length": 4096,
|
| 2086 |
+
"pad_token": "[PAD]",
|
| 2087 |
+
"padding_side": "right",
|
| 2088 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2089 |
+
}
|
mm_projector/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes/mm_projector",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MultimodalProjector"
|
| 5 |
+
],
|
| 6 |
+
"mm_projector_type": "mlp_downsample",
|
| 7 |
+
"model_type": "v2l_projector",
|
| 8 |
+
"torch_dtype": "bfloat16",
|
| 9 |
+
"transformers_version": "4.37.2"
|
| 10 |
+
}
|
mm_projector/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f88830ac14441d329dd5d1f17b3ed8943edb1d26563754c17744751d4f22915d
|
| 3 |
+
size 71338512
|
trainer_state.json
ADDED
|
@@ -0,0 +1,4604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 753,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4.347826086956522e-06,
|
| 14 |
+
"loss": 4.2511,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 8.695652173913044e-06,
|
| 20 |
+
"loss": 4.2595,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 1.3043478260869566e-05,
|
| 26 |
+
"loss": 3.0895,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 1.739130434782609e-05,
|
| 32 |
+
"loss": 0.8882,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 2.173913043478261e-05,
|
| 38 |
+
"loss": 0.4819,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 2.608695652173913e-05,
|
| 44 |
+
"loss": 0.8914,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01,
|
| 49 |
+
"learning_rate": 3.0434782608695656e-05,
|
| 50 |
+
"loss": 1.1554,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 3.478260869565218e-05,
|
| 56 |
+
"loss": 0.3562,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 3.91304347826087e-05,
|
| 62 |
+
"loss": 0.4085,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.01,
|
| 67 |
+
"learning_rate": 4.347826086956522e-05,
|
| 68 |
+
"loss": 0.2655,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.01,
|
| 73 |
+
"learning_rate": 4.782608695652174e-05,
|
| 74 |
+
"loss": 0.281,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.02,
|
| 79 |
+
"learning_rate": 5.217391304347826e-05,
|
| 80 |
+
"loss": 0.4708,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.02,
|
| 85 |
+
"learning_rate": 5.652173913043478e-05,
|
| 86 |
+
"loss": 4.1421,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02,
|
| 91 |
+
"learning_rate": 6.086956521739131e-05,
|
| 92 |
+
"loss": 2.4328,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02,
|
| 97 |
+
"learning_rate": 6.521739130434783e-05,
|
| 98 |
+
"loss": 1.7092,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.02,
|
| 103 |
+
"learning_rate": 6.956521739130436e-05,
|
| 104 |
+
"loss": 0.687,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.02,
|
| 109 |
+
"learning_rate": 7.391304347826086e-05,
|
| 110 |
+
"loss": 0.2745,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.02,
|
| 115 |
+
"learning_rate": 7.82608695652174e-05,
|
| 116 |
+
"loss": 0.3214,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.03,
|
| 121 |
+
"learning_rate": 8.260869565217392e-05,
|
| 122 |
+
"loss": 0.4915,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.03,
|
| 127 |
+
"learning_rate": 8.695652173913044e-05,
|
| 128 |
+
"loss": 0.2447,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03,
|
| 133 |
+
"learning_rate": 9.130434782608696e-05,
|
| 134 |
+
"loss": 0.2353,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.03,
|
| 139 |
+
"learning_rate": 9.565217391304348e-05,
|
| 140 |
+
"loss": 0.2507,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.03,
|
| 145 |
+
"learning_rate": 0.0001,
|
| 146 |
+
"loss": 0.2238,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.03,
|
| 151 |
+
"learning_rate": 9.99995369868095e-05,
|
| 152 |
+
"loss": 0.2327,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.03,
|
| 157 |
+
"learning_rate": 9.999814795581328e-05,
|
| 158 |
+
"loss": 0.5584,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.03,
|
| 163 |
+
"learning_rate": 9.99958329327369e-05,
|
| 164 |
+
"loss": 1.6468,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.04,
|
| 169 |
+
"learning_rate": 9.999259196045582e-05,
|
| 170 |
+
"loss": 5.5723,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04,
|
| 175 |
+
"learning_rate": 9.998842509899456e-05,
|
| 176 |
+
"loss": 4.1912,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.04,
|
| 181 |
+
"learning_rate": 9.998333242552556e-05,
|
| 182 |
+
"loss": 0.9005,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.04,
|
| 187 |
+
"learning_rate": 9.997731403436788e-05,
|
| 188 |
+
"loss": 0.5078,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.04,
|
| 193 |
+
"learning_rate": 9.997037003698525e-05,
|
| 194 |
+
"loss": 0.2464,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.04,
|
| 199 |
+
"learning_rate": 9.996250056198417e-05,
|
| 200 |
+
"loss": 0.258,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.04,
|
| 205 |
+
"learning_rate": 9.995370575511151e-05,
|
| 206 |
+
"loss": 0.2438,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.05,
|
| 211 |
+
"learning_rate": 9.994398577925169e-05,
|
| 212 |
+
"loss": 0.2159,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.05,
|
| 217 |
+
"learning_rate": 9.993334081442381e-05,
|
| 218 |
+
"loss": 0.1959,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.05,
|
| 223 |
+
"learning_rate": 9.992177105777822e-05,
|
| 224 |
+
"loss": 0.2217,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.05,
|
| 229 |
+
"learning_rate": 9.990927672359294e-05,
|
| 230 |
+
"loss": 0.1972,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.05,
|
| 235 |
+
"learning_rate": 9.989585804326962e-05,
|
| 236 |
+
"loss": 0.1947,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.05,
|
| 241 |
+
"learning_rate": 9.988151526532929e-05,
|
| 242 |
+
"loss": 0.2028,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.05,
|
| 247 |
+
"learning_rate": 9.986624865540778e-05,
|
| 248 |
+
"loss": 0.1989,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.05,
|
| 253 |
+
"learning_rate": 9.985005849625076e-05,
|
| 254 |
+
"loss": 0.1963,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06,
|
| 259 |
+
"learning_rate": 9.983294508770851e-05,
|
| 260 |
+
"loss": 0.1935,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.06,
|
| 265 |
+
"learning_rate": 9.981490874673039e-05,
|
| 266 |
+
"loss": 0.1949,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.06,
|
| 271 |
+
"learning_rate": 9.979594980735896e-05,
|
| 272 |
+
"loss": 0.1979,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.06,
|
| 277 |
+
"learning_rate": 9.977606862072377e-05,
|
| 278 |
+
"loss": 0.1882,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.06,
|
| 283 |
+
"learning_rate": 9.975526555503488e-05,
|
| 284 |
+
"loss": 0.1911,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.06,
|
| 289 |
+
"learning_rate": 9.973354099557606e-05,
|
| 290 |
+
"loss": 0.1914,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.06,
|
| 295 |
+
"learning_rate": 9.97108953446976e-05,
|
| 296 |
+
"loss": 0.1945,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07,
|
| 301 |
+
"learning_rate": 9.968732902180891e-05,
|
| 302 |
+
"loss": 0.1876,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.07,
|
| 307 |
+
"learning_rate": 9.966284246337072e-05,
|
| 308 |
+
"loss": 0.1893,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.07,
|
| 313 |
+
"learning_rate": 9.963743612288701e-05,
|
| 314 |
+
"loss": 0.1946,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.07,
|
| 319 |
+
"learning_rate": 9.961111047089662e-05,
|
| 320 |
+
"loss": 0.1909,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.07,
|
| 325 |
+
"learning_rate": 9.95838659949645e-05,
|
| 326 |
+
"loss": 0.1959,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.07,
|
| 331 |
+
"learning_rate": 9.955570319967273e-05,
|
| 332 |
+
"loss": 0.1922,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.07,
|
| 337 |
+
"learning_rate": 9.952662260661115e-05,
|
| 338 |
+
"loss": 0.195,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.07,
|
| 343 |
+
"learning_rate": 9.949662475436765e-05,
|
| 344 |
+
"loss": 0.1941,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.08,
|
| 349 |
+
"learning_rate": 9.946571019851832e-05,
|
| 350 |
+
"loss": 0.1941,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.08,
|
| 355 |
+
"learning_rate": 9.943387951161703e-05,
|
| 356 |
+
"loss": 0.189,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.08,
|
| 361 |
+
"learning_rate": 9.940113328318488e-05,
|
| 362 |
+
"loss": 0.193,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.08,
|
| 367 |
+
"learning_rate": 9.936747211969932e-05,
|
| 368 |
+
"loss": 0.1918,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.08,
|
| 373 |
+
"learning_rate": 9.933289664458284e-05,
|
| 374 |
+
"loss": 0.1939,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.08,
|
| 379 |
+
"learning_rate": 9.929740749819152e-05,
|
| 380 |
+
"loss": 0.1912,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.08,
|
| 385 |
+
"learning_rate": 9.926100533780303e-05,
|
| 386 |
+
"loss": 0.195,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.08,
|
| 391 |
+
"learning_rate": 9.92236908376046e-05,
|
| 392 |
+
"loss": 0.1909,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.09,
|
| 397 |
+
"learning_rate": 9.91854646886805e-05,
|
| 398 |
+
"loss": 0.1926,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.09,
|
| 403 |
+
"learning_rate": 9.91463275989991e-05,
|
| 404 |
+
"loss": 0.1911,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.09,
|
| 409 |
+
"learning_rate": 9.910628029340003e-05,
|
| 410 |
+
"loss": 0.1951,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.09,
|
| 415 |
+
"learning_rate": 9.906532351358047e-05,
|
| 416 |
+
"loss": 0.1877,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.09,
|
| 421 |
+
"learning_rate": 9.902345801808162e-05,
|
| 422 |
+
"loss": 0.1894,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.09,
|
| 427 |
+
"learning_rate": 9.898068458227451e-05,
|
| 428 |
+
"loss": 0.19,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.09,
|
| 433 |
+
"learning_rate": 9.893700399834577e-05,
|
| 434 |
+
"loss": 0.1927,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.1,
|
| 439 |
+
"learning_rate": 9.889241707528285e-05,
|
| 440 |
+
"loss": 0.1919,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.1,
|
| 445 |
+
"learning_rate": 9.88469246388591e-05,
|
| 446 |
+
"loss": 0.1906,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.1,
|
| 451 |
+
"learning_rate": 9.880052753161842e-05,
|
| 452 |
+
"loss": 0.1928,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.1,
|
| 457 |
+
"learning_rate": 9.875322661285975e-05,
|
| 458 |
+
"loss": 0.1887,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.1,
|
| 463 |
+
"learning_rate": 9.870502275862104e-05,
|
| 464 |
+
"loss": 0.1919,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.1,
|
| 469 |
+
"learning_rate": 9.86559168616631e-05,
|
| 470 |
+
"loss": 0.1892,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.1,
|
| 475 |
+
"learning_rate": 9.860590983145307e-05,
|
| 476 |
+
"loss": 0.1876,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.1,
|
| 481 |
+
"learning_rate": 9.855500259414753e-05,
|
| 482 |
+
"loss": 0.1946,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.11,
|
| 487 |
+
"learning_rate": 9.850319609257535e-05,
|
| 488 |
+
"loss": 0.1889,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.11,
|
| 493 |
+
"learning_rate": 9.845049128622032e-05,
|
| 494 |
+
"loss": 0.1909,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.11,
|
| 499 |
+
"learning_rate": 9.839688915120322e-05,
|
| 500 |
+
"loss": 0.1914,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.11,
|
| 505 |
+
"learning_rate": 9.834239068026387e-05,
|
| 506 |
+
"loss": 0.1923,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.11,
|
| 511 |
+
"learning_rate": 9.828699688274275e-05,
|
| 512 |
+
"loss": 0.1902,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.11,
|
| 517 |
+
"learning_rate": 9.823070878456217e-05,
|
| 518 |
+
"loss": 0.1919,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.11,
|
| 523 |
+
"learning_rate": 9.817352742820744e-05,
|
| 524 |
+
"loss": 0.1925,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.12,
|
| 529 |
+
"learning_rate": 9.811545387270743e-05,
|
| 530 |
+
"loss": 0.1871,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.12,
|
| 535 |
+
"learning_rate": 9.805648919361504e-05,
|
| 536 |
+
"loss": 0.1922,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.12,
|
| 541 |
+
"learning_rate": 9.799663448298724e-05,
|
| 542 |
+
"loss": 0.1953,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.12,
|
| 547 |
+
"learning_rate": 9.793589084936483e-05,
|
| 548 |
+
"loss": 0.192,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.12,
|
| 553 |
+
"learning_rate": 9.787425941775197e-05,
|
| 554 |
+
"loss": 0.19,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.12,
|
| 559 |
+
"learning_rate": 9.781174132959529e-05,
|
| 560 |
+
"loss": 0.1866,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.12,
|
| 565 |
+
"learning_rate": 9.774833774276278e-05,
|
| 566 |
+
"loss": 0.1906,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.12,
|
| 571 |
+
"learning_rate": 9.768404983152229e-05,
|
| 572 |
+
"loss": 0.1907,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.13,
|
| 577 |
+
"learning_rate": 9.761887878651987e-05,
|
| 578 |
+
"loss": 0.1915,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.13,
|
| 583 |
+
"learning_rate": 9.755282581475769e-05,
|
| 584 |
+
"loss": 0.1903,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.13,
|
| 589 |
+
"learning_rate": 9.74858921395716e-05,
|
| 590 |
+
"loss": 0.1917,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.13,
|
| 595 |
+
"learning_rate": 9.741807900060858e-05,
|
| 596 |
+
"loss": 0.1908,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.13,
|
| 601 |
+
"learning_rate": 9.734938765380377e-05,
|
| 602 |
+
"loss": 0.1921,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.13,
|
| 607 |
+
"learning_rate": 9.727981937135713e-05,
|
| 608 |
+
"loss": 0.1879,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.13,
|
| 613 |
+
"eval_loss": 0.18334217369556427,
|
| 614 |
+
"eval_runtime": 12.1378,
|
| 615 |
+
"eval_samples_per_second": 164.775,
|
| 616 |
+
"eval_steps_per_second": 0.659,
|
| 617 |
+
"step": 100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.13,
|
| 621 |
+
"learning_rate": 9.720937544170999e-05,
|
| 622 |
+
"loss": 0.1908,
|
| 623 |
+
"step": 101
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.14,
|
| 627 |
+
"learning_rate": 9.713805716952105e-05,
|
| 628 |
+
"loss": 0.1892,
|
| 629 |
+
"step": 102
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.14,
|
| 633 |
+
"learning_rate": 9.706586587564237e-05,
|
| 634 |
+
"loss": 0.1902,
|
| 635 |
+
"step": 103
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.14,
|
| 639 |
+
"learning_rate": 9.699280289709478e-05,
|
| 640 |
+
"loss": 0.1905,
|
| 641 |
+
"step": 104
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.14,
|
| 645 |
+
"learning_rate": 9.691886958704321e-05,
|
| 646 |
+
"loss": 0.1894,
|
| 647 |
+
"step": 105
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.14,
|
| 651 |
+
"learning_rate": 9.684406731477158e-05,
|
| 652 |
+
"loss": 0.1943,
|
| 653 |
+
"step": 106
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.14,
|
| 657 |
+
"learning_rate": 9.676839746565743e-05,
|
| 658 |
+
"loss": 0.1883,
|
| 659 |
+
"step": 107
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.14,
|
| 663 |
+
"learning_rate": 9.669186144114625e-05,
|
| 664 |
+
"loss": 0.1935,
|
| 665 |
+
"step": 108
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.14,
|
| 669 |
+
"learning_rate": 9.661446065872568e-05,
|
| 670 |
+
"loss": 0.1914,
|
| 671 |
+
"step": 109
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.15,
|
| 675 |
+
"learning_rate": 9.653619655189897e-05,
|
| 676 |
+
"loss": 0.1877,
|
| 677 |
+
"step": 110
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.15,
|
| 681 |
+
"learning_rate": 9.645707057015871e-05,
|
| 682 |
+
"loss": 0.1898,
|
| 683 |
+
"step": 111
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.15,
|
| 687 |
+
"learning_rate": 9.637708417895983e-05,
|
| 688 |
+
"loss": 0.1898,
|
| 689 |
+
"step": 112
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.15,
|
| 693 |
+
"learning_rate": 9.62962388596925e-05,
|
| 694 |
+
"loss": 0.1922,
|
| 695 |
+
"step": 113
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.15,
|
| 699 |
+
"learning_rate": 9.621453610965467e-05,
|
| 700 |
+
"loss": 0.1906,
|
| 701 |
+
"step": 114
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.15,
|
| 705 |
+
"learning_rate": 9.613197744202438e-05,
|
| 706 |
+
"loss": 0.1881,
|
| 707 |
+
"step": 115
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.15,
|
| 711 |
+
"learning_rate": 9.604856438583174e-05,
|
| 712 |
+
"loss": 0.1894,
|
| 713 |
+
"step": 116
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.16,
|
| 717 |
+
"learning_rate": 9.596429848593053e-05,
|
| 718 |
+
"loss": 0.1872,
|
| 719 |
+
"step": 117
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.16,
|
| 723 |
+
"learning_rate": 9.587918130296969e-05,
|
| 724 |
+
"loss": 0.192,
|
| 725 |
+
"step": 118
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.16,
|
| 729 |
+
"learning_rate": 9.579321441336436e-05,
|
| 730 |
+
"loss": 0.1876,
|
| 731 |
+
"step": 119
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.16,
|
| 735 |
+
"learning_rate": 9.57063994092667e-05,
|
| 736 |
+
"loss": 0.1914,
|
| 737 |
+
"step": 120
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.16,
|
| 741 |
+
"learning_rate": 9.561873789853637e-05,
|
| 742 |
+
"loss": 0.1897,
|
| 743 |
+
"step": 121
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.16,
|
| 747 |
+
"learning_rate": 9.553023150471082e-05,
|
| 748 |
+
"loss": 0.1907,
|
| 749 |
+
"step": 122
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.16,
|
| 753 |
+
"learning_rate": 9.544088186697515e-05,
|
| 754 |
+
"loss": 0.1905,
|
| 755 |
+
"step": 123
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.16,
|
| 759 |
+
"learning_rate": 9.53506906401318e-05,
|
| 760 |
+
"loss": 0.1918,
|
| 761 |
+
"step": 124
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.17,
|
| 765 |
+
"learning_rate": 9.525965949456988e-05,
|
| 766 |
+
"loss": 0.1908,
|
| 767 |
+
"step": 125
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.17,
|
| 771 |
+
"learning_rate": 9.516779011623422e-05,
|
| 772 |
+
"loss": 0.1898,
|
| 773 |
+
"step": 126
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.17,
|
| 777 |
+
"learning_rate": 9.50750842065942e-05,
|
| 778 |
+
"loss": 0.1871,
|
| 779 |
+
"step": 127
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.17,
|
| 783 |
+
"learning_rate": 9.498154348261216e-05,
|
| 784 |
+
"loss": 0.1906,
|
| 785 |
+
"step": 128
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.17,
|
| 789 |
+
"learning_rate": 9.48871696767117e-05,
|
| 790 |
+
"loss": 0.1905,
|
| 791 |
+
"step": 129
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.17,
|
| 795 |
+
"learning_rate": 9.479196453674544e-05,
|
| 796 |
+
"loss": 0.1906,
|
| 797 |
+
"step": 130
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.17,
|
| 801 |
+
"learning_rate": 9.469592982596285e-05,
|
| 802 |
+
"loss": 0.1906,
|
| 803 |
+
"step": 131
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.18,
|
| 807 |
+
"learning_rate": 9.459906732297743e-05,
|
| 808 |
+
"loss": 0.1929,
|
| 809 |
+
"step": 132
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.18,
|
| 813 |
+
"learning_rate": 9.450137882173384e-05,
|
| 814 |
+
"loss": 0.1918,
|
| 815 |
+
"step": 133
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.18,
|
| 819 |
+
"learning_rate": 9.440286613147467e-05,
|
| 820 |
+
"loss": 0.1895,
|
| 821 |
+
"step": 134
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.18,
|
| 825 |
+
"learning_rate": 9.430353107670691e-05,
|
| 826 |
+
"loss": 0.189,
|
| 827 |
+
"step": 135
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.18,
|
| 831 |
+
"learning_rate": 9.420337549716818e-05,
|
| 832 |
+
"loss": 0.1942,
|
| 833 |
+
"step": 136
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.18,
|
| 837 |
+
"learning_rate": 9.410240124779268e-05,
|
| 838 |
+
"loss": 0.192,
|
| 839 |
+
"step": 137
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.18,
|
| 843 |
+
"learning_rate": 9.400061019867679e-05,
|
| 844 |
+
"loss": 0.1908,
|
| 845 |
+
"step": 138
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.18,
|
| 849 |
+
"learning_rate": 9.389800423504442e-05,
|
| 850 |
+
"loss": 0.1908,
|
| 851 |
+
"step": 139
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.19,
|
| 855 |
+
"learning_rate": 9.379458525721215e-05,
|
| 856 |
+
"loss": 0.1892,
|
| 857 |
+
"step": 140
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.19,
|
| 861 |
+
"learning_rate": 9.369035518055404e-05,
|
| 862 |
+
"loss": 0.1887,
|
| 863 |
+
"step": 141
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.19,
|
| 867 |
+
"learning_rate": 9.35853159354661e-05,
|
| 868 |
+
"loss": 0.1901,
|
| 869 |
+
"step": 142
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.19,
|
| 873 |
+
"learning_rate": 9.347946946733055e-05,
|
| 874 |
+
"loss": 0.1908,
|
| 875 |
+
"step": 143
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.19,
|
| 879 |
+
"learning_rate": 9.337281773647986e-05,
|
| 880 |
+
"loss": 0.1958,
|
| 881 |
+
"step": 144
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.19,
|
| 885 |
+
"learning_rate": 9.326536271816031e-05,
|
| 886 |
+
"loss": 0.1905,
|
| 887 |
+
"step": 145
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.19,
|
| 891 |
+
"learning_rate": 9.315710640249558e-05,
|
| 892 |
+
"loss": 0.1932,
|
| 893 |
+
"step": 146
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.2,
|
| 897 |
+
"learning_rate": 9.304805079444971e-05,
|
| 898 |
+
"loss": 0.1894,
|
| 899 |
+
"step": 147
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.2,
|
| 903 |
+
"learning_rate": 9.293819791379016e-05,
|
| 904 |
+
"loss": 0.1921,
|
| 905 |
+
"step": 148
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.2,
|
| 909 |
+
"learning_rate": 9.282754979505018e-05,
|
| 910 |
+
"loss": 0.1927,
|
| 911 |
+
"step": 149
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.2,
|
| 915 |
+
"learning_rate": 9.271610848749135e-05,
|
| 916 |
+
"loss": 0.1971,
|
| 917 |
+
"step": 150
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.2,
|
| 921 |
+
"learning_rate": 9.260387605506547e-05,
|
| 922 |
+
"loss": 0.1894,
|
| 923 |
+
"step": 151
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.2,
|
| 927 |
+
"learning_rate": 9.249085457637641e-05,
|
| 928 |
+
"loss": 0.1908,
|
| 929 |
+
"step": 152
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.2,
|
| 933 |
+
"learning_rate": 9.237704614464156e-05,
|
| 934 |
+
"loss": 0.189,
|
| 935 |
+
"step": 153
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.2,
|
| 939 |
+
"learning_rate": 9.226245286765316e-05,
|
| 940 |
+
"loss": 0.1888,
|
| 941 |
+
"step": 154
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.21,
|
| 945 |
+
"learning_rate": 9.214707686773914e-05,
|
| 946 |
+
"loss": 0.1883,
|
| 947 |
+
"step": 155
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.21,
|
| 951 |
+
"learning_rate": 9.203092028172391e-05,
|
| 952 |
+
"loss": 0.1918,
|
| 953 |
+
"step": 156
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.21,
|
| 957 |
+
"learning_rate": 9.191398526088873e-05,
|
| 958 |
+
"loss": 0.1936,
|
| 959 |
+
"step": 157
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.21,
|
| 963 |
+
"learning_rate": 9.179627397093185e-05,
|
| 964 |
+
"loss": 0.1901,
|
| 965 |
+
"step": 158
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.21,
|
| 969 |
+
"learning_rate": 9.16777885919285e-05,
|
| 970 |
+
"loss": 0.1891,
|
| 971 |
+
"step": 159
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.21,
|
| 975 |
+
"learning_rate": 9.15585313182904e-05,
|
| 976 |
+
"loss": 0.1919,
|
| 977 |
+
"step": 160
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.21,
|
| 981 |
+
"learning_rate": 9.143850435872518e-05,
|
| 982 |
+
"loss": 0.1909,
|
| 983 |
+
"step": 161
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.22,
|
| 987 |
+
"learning_rate": 9.131770993619548e-05,
|
| 988 |
+
"loss": 0.1936,
|
| 989 |
+
"step": 162
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.22,
|
| 993 |
+
"learning_rate": 9.119615028787771e-05,
|
| 994 |
+
"loss": 0.1867,
|
| 995 |
+
"step": 163
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.22,
|
| 999 |
+
"learning_rate": 9.107382766512071e-05,
|
| 1000 |
+
"loss": 0.1925,
|
| 1001 |
+
"step": 164
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.22,
|
| 1005 |
+
"learning_rate": 9.095074433340401e-05,
|
| 1006 |
+
"loss": 0.1902,
|
| 1007 |
+
"step": 165
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.22,
|
| 1011 |
+
"learning_rate": 9.08269025722958e-05,
|
| 1012 |
+
"loss": 0.1921,
|
| 1013 |
+
"step": 166
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.22,
|
| 1017 |
+
"learning_rate": 9.07023046754109e-05,
|
| 1018 |
+
"loss": 0.1869,
|
| 1019 |
+
"step": 167
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.22,
|
| 1023 |
+
"learning_rate": 9.057695295036805e-05,
|
| 1024 |
+
"loss": 0.1901,
|
| 1025 |
+
"step": 168
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.22,
|
| 1029 |
+
"learning_rate": 9.045084971874738e-05,
|
| 1030 |
+
"loss": 0.1903,
|
| 1031 |
+
"step": 169
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.23,
|
| 1035 |
+
"learning_rate": 9.032399731604723e-05,
|
| 1036 |
+
"loss": 0.1933,
|
| 1037 |
+
"step": 170
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.23,
|
| 1041 |
+
"learning_rate": 9.019639809164106e-05,
|
| 1042 |
+
"loss": 0.1929,
|
| 1043 |
+
"step": 171
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.23,
|
| 1047 |
+
"learning_rate": 9.006805440873383e-05,
|
| 1048 |
+
"loss": 0.1948,
|
| 1049 |
+
"step": 172
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.23,
|
| 1053 |
+
"learning_rate": 8.993896864431826e-05,
|
| 1054 |
+
"loss": 0.1917,
|
| 1055 |
+
"step": 173
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.23,
|
| 1059 |
+
"learning_rate": 8.980914318913078e-05,
|
| 1060 |
+
"loss": 0.1936,
|
| 1061 |
+
"step": 174
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.23,
|
| 1065 |
+
"learning_rate": 8.967858044760737e-05,
|
| 1066 |
+
"loss": 0.1902,
|
| 1067 |
+
"step": 175
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.23,
|
| 1071 |
+
"learning_rate": 8.954728283783886e-05,
|
| 1072 |
+
"loss": 0.1893,
|
| 1073 |
+
"step": 176
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.24,
|
| 1077 |
+
"learning_rate": 8.941525279152627e-05,
|
| 1078 |
+
"loss": 0.1925,
|
| 1079 |
+
"step": 177
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.24,
|
| 1083 |
+
"learning_rate": 8.928249275393572e-05,
|
| 1084 |
+
"loss": 0.1905,
|
| 1085 |
+
"step": 178
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.24,
|
| 1089 |
+
"learning_rate": 8.914900518385314e-05,
|
| 1090 |
+
"loss": 0.1912,
|
| 1091 |
+
"step": 179
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.24,
|
| 1095 |
+
"learning_rate": 8.901479255353879e-05,
|
| 1096 |
+
"loss": 0.1889,
|
| 1097 |
+
"step": 180
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.24,
|
| 1101 |
+
"learning_rate": 8.887985734868135e-05,
|
| 1102 |
+
"loss": 0.189,
|
| 1103 |
+
"step": 181
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.24,
|
| 1107 |
+
"learning_rate": 8.874420206835203e-05,
|
| 1108 |
+
"loss": 0.191,
|
| 1109 |
+
"step": 182
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.24,
|
| 1113 |
+
"learning_rate": 8.860782922495822e-05,
|
| 1114 |
+
"loss": 0.1889,
|
| 1115 |
+
"step": 183
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.24,
|
| 1119 |
+
"learning_rate": 8.847074134419691e-05,
|
| 1120 |
+
"loss": 0.1869,
|
| 1121 |
+
"step": 184
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.25,
|
| 1125 |
+
"learning_rate": 8.833294096500797e-05,
|
| 1126 |
+
"loss": 0.1857,
|
| 1127 |
+
"step": 185
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.25,
|
| 1131 |
+
"learning_rate": 8.819443063952713e-05,
|
| 1132 |
+
"loss": 0.1865,
|
| 1133 |
+
"step": 186
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.25,
|
| 1137 |
+
"learning_rate": 8.805521293303874e-05,
|
| 1138 |
+
"loss": 0.1917,
|
| 1139 |
+
"step": 187
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.25,
|
| 1143 |
+
"learning_rate": 8.791529042392813e-05,
|
| 1144 |
+
"loss": 0.1904,
|
| 1145 |
+
"step": 188
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.25,
|
| 1149 |
+
"learning_rate": 8.777466570363401e-05,
|
| 1150 |
+
"loss": 0.1861,
|
| 1151 |
+
"step": 189
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.25,
|
| 1155 |
+
"learning_rate": 8.763334137660042e-05,
|
| 1156 |
+
"loss": 0.1886,
|
| 1157 |
+
"step": 190
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.25,
|
| 1161 |
+
"learning_rate": 8.749132006022844e-05,
|
| 1162 |
+
"loss": 0.1878,
|
| 1163 |
+
"step": 191
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.25,
|
| 1167 |
+
"learning_rate": 8.734860438482777e-05,
|
| 1168 |
+
"loss": 0.1903,
|
| 1169 |
+
"step": 192
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.26,
|
| 1173 |
+
"learning_rate": 8.720519699356804e-05,
|
| 1174 |
+
"loss": 0.1881,
|
| 1175 |
+
"step": 193
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.26,
|
| 1179 |
+
"learning_rate": 8.70611005424298e-05,
|
| 1180 |
+
"loss": 0.1894,
|
| 1181 |
+
"step": 194
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.26,
|
| 1185 |
+
"learning_rate": 8.691631770015533e-05,
|
| 1186 |
+
"loss": 0.1933,
|
| 1187 |
+
"step": 195
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.26,
|
| 1191 |
+
"learning_rate": 8.677085114819928e-05,
|
| 1192 |
+
"loss": 0.1882,
|
| 1193 |
+
"step": 196
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.26,
|
| 1197 |
+
"learning_rate": 8.662470358067895e-05,
|
| 1198 |
+
"loss": 0.1853,
|
| 1199 |
+
"step": 197
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.26,
|
| 1203 |
+
"learning_rate": 8.647787770432439e-05,
|
| 1204 |
+
"loss": 0.1874,
|
| 1205 |
+
"step": 198
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.26,
|
| 1209 |
+
"learning_rate": 8.633037623842828e-05,
|
| 1210 |
+
"loss": 0.1896,
|
| 1211 |
+
"step": 199
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.27,
|
| 1215 |
+
"learning_rate": 8.618220191479563e-05,
|
| 1216 |
+
"loss": 0.1891,
|
| 1217 |
+
"step": 200
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.27,
|
| 1221 |
+
"eval_loss": 0.18544606864452362,
|
| 1222 |
+
"eval_runtime": 11.5227,
|
| 1223 |
+
"eval_samples_per_second": 173.57,
|
| 1224 |
+
"eval_steps_per_second": 0.694,
|
| 1225 |
+
"step": 200
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.27,
|
| 1229 |
+
"learning_rate": 8.603335747769306e-05,
|
| 1230 |
+
"loss": 0.1901,
|
| 1231 |
+
"step": 201
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.27,
|
| 1235 |
+
"learning_rate": 8.58838456837981e-05,
|
| 1236 |
+
"loss": 0.1894,
|
| 1237 |
+
"step": 202
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.27,
|
| 1241 |
+
"learning_rate": 8.573366930214806e-05,
|
| 1242 |
+
"loss": 0.1856,
|
| 1243 |
+
"step": 203
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.27,
|
| 1247 |
+
"learning_rate": 8.558283111408873e-05,
|
| 1248 |
+
"loss": 0.1866,
|
| 1249 |
+
"step": 204
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.27,
|
| 1253 |
+
"learning_rate": 8.5431333913223e-05,
|
| 1254 |
+
"loss": 0.1885,
|
| 1255 |
+
"step": 205
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.27,
|
| 1259 |
+
"learning_rate": 8.52791805053589e-05,
|
| 1260 |
+
"loss": 0.1906,
|
| 1261 |
+
"step": 206
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.27,
|
| 1265 |
+
"learning_rate": 8.512637370845785e-05,
|
| 1266 |
+
"loss": 0.1869,
|
| 1267 |
+
"step": 207
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.28,
|
| 1271 |
+
"learning_rate": 8.497291635258235e-05,
|
| 1272 |
+
"loss": 0.1894,
|
| 1273 |
+
"step": 208
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.28,
|
| 1277 |
+
"learning_rate": 8.481881127984361e-05,
|
| 1278 |
+
"loss": 0.19,
|
| 1279 |
+
"step": 209
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.28,
|
| 1283 |
+
"learning_rate": 8.466406134434887e-05,
|
| 1284 |
+
"loss": 0.1851,
|
| 1285 |
+
"step": 210
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.28,
|
| 1289 |
+
"learning_rate": 8.45086694121486e-05,
|
| 1290 |
+
"loss": 0.1846,
|
| 1291 |
+
"step": 211
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.28,
|
| 1295 |
+
"learning_rate": 8.435263836118335e-05,
|
| 1296 |
+
"loss": 0.1905,
|
| 1297 |
+
"step": 212
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.28,
|
| 1301 |
+
"learning_rate": 8.419597108123054e-05,
|
| 1302 |
+
"loss": 0.1872,
|
| 1303 |
+
"step": 213
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.28,
|
| 1307 |
+
"learning_rate": 8.403867047385081e-05,
|
| 1308 |
+
"loss": 0.1867,
|
| 1309 |
+
"step": 214
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 0.29,
|
| 1313 |
+
"learning_rate": 8.388073945233445e-05,
|
| 1314 |
+
"loss": 0.1859,
|
| 1315 |
+
"step": 215
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.29,
|
| 1319 |
+
"learning_rate": 8.372218094164728e-05,
|
| 1320 |
+
"loss": 0.189,
|
| 1321 |
+
"step": 216
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.29,
|
| 1325 |
+
"learning_rate": 8.356299787837658e-05,
|
| 1326 |
+
"loss": 0.1855,
|
| 1327 |
+
"step": 217
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.29,
|
| 1331 |
+
"learning_rate": 8.340319321067668e-05,
|
| 1332 |
+
"loss": 0.1844,
|
| 1333 |
+
"step": 218
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.29,
|
| 1337 |
+
"learning_rate": 8.324276989821434e-05,
|
| 1338 |
+
"loss": 0.1915,
|
| 1339 |
+
"step": 219
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.29,
|
| 1343 |
+
"learning_rate": 8.308173091211391e-05,
|
| 1344 |
+
"loss": 0.1894,
|
| 1345 |
+
"step": 220
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.29,
|
| 1349 |
+
"learning_rate": 8.292007923490245e-05,
|
| 1350 |
+
"loss": 0.1874,
|
| 1351 |
+
"step": 221
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.29,
|
| 1355 |
+
"learning_rate": 8.275781786045427e-05,
|
| 1356 |
+
"loss": 0.1887,
|
| 1357 |
+
"step": 222
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.3,
|
| 1361 |
+
"learning_rate": 8.259494979393563e-05,
|
| 1362 |
+
"loss": 0.1849,
|
| 1363 |
+
"step": 223
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.3,
|
| 1367 |
+
"learning_rate": 8.243147805174908e-05,
|
| 1368 |
+
"loss": 0.1858,
|
| 1369 |
+
"step": 224
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.3,
|
| 1373 |
+
"learning_rate": 8.226740566147753e-05,
|
| 1374 |
+
"loss": 0.1859,
|
| 1375 |
+
"step": 225
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.3,
|
| 1379 |
+
"learning_rate": 8.210273566182818e-05,
|
| 1380 |
+
"loss": 0.1871,
|
| 1381 |
+
"step": 226
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.3,
|
| 1385 |
+
"learning_rate": 8.193747110257637e-05,
|
| 1386 |
+
"loss": 0.1849,
|
| 1387 |
+
"step": 227
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.3,
|
| 1391 |
+
"learning_rate": 8.177161504450888e-05,
|
| 1392 |
+
"loss": 0.1886,
|
| 1393 |
+
"step": 228
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 0.3,
|
| 1397 |
+
"learning_rate": 8.160517055936744e-05,
|
| 1398 |
+
"loss": 0.1858,
|
| 1399 |
+
"step": 229
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.31,
|
| 1403 |
+
"learning_rate": 8.143814072979173e-05,
|
| 1404 |
+
"loss": 0.186,
|
| 1405 |
+
"step": 230
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.31,
|
| 1409 |
+
"learning_rate": 8.127052864926232e-05,
|
| 1410 |
+
"loss": 0.1888,
|
| 1411 |
+
"step": 231
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.31,
|
| 1415 |
+
"learning_rate": 8.110233742204339e-05,
|
| 1416 |
+
"loss": 0.1852,
|
| 1417 |
+
"step": 232
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.31,
|
| 1421 |
+
"learning_rate": 8.093357016312517e-05,
|
| 1422 |
+
"loss": 0.1865,
|
| 1423 |
+
"step": 233
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.31,
|
| 1427 |
+
"learning_rate": 8.07642299981664e-05,
|
| 1428 |
+
"loss": 0.1864,
|
| 1429 |
+
"step": 234
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.31,
|
| 1433 |
+
"learning_rate": 8.059432006343623e-05,
|
| 1434 |
+
"loss": 0.1816,
|
| 1435 |
+
"step": 235
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.31,
|
| 1439 |
+
"learning_rate": 8.042384350575632e-05,
|
| 1440 |
+
"loss": 0.1834,
|
| 1441 |
+
"step": 236
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.31,
|
| 1445 |
+
"learning_rate": 8.025280348244246e-05,
|
| 1446 |
+
"loss": 0.1859,
|
| 1447 |
+
"step": 237
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 0.32,
|
| 1451 |
+
"learning_rate": 8.008120316124612e-05,
|
| 1452 |
+
"loss": 0.1831,
|
| 1453 |
+
"step": 238
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.32,
|
| 1457 |
+
"learning_rate": 7.990904572029583e-05,
|
| 1458 |
+
"loss": 0.1879,
|
| 1459 |
+
"step": 239
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.32,
|
| 1463 |
+
"learning_rate": 7.973633434803817e-05,
|
| 1464 |
+
"loss": 0.1839,
|
| 1465 |
+
"step": 240
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.32,
|
| 1469 |
+
"learning_rate": 7.956307224317891e-05,
|
| 1470 |
+
"loss": 0.1888,
|
| 1471 |
+
"step": 241
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.32,
|
| 1475 |
+
"learning_rate": 7.938926261462366e-05,
|
| 1476 |
+
"loss": 0.1832,
|
| 1477 |
+
"step": 242
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.32,
|
| 1481 |
+
"learning_rate": 7.921490868141843e-05,
|
| 1482 |
+
"loss": 0.1849,
|
| 1483 |
+
"step": 243
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 0.32,
|
| 1487 |
+
"learning_rate": 7.904001367269004e-05,
|
| 1488 |
+
"loss": 0.1815,
|
| 1489 |
+
"step": 244
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.33,
|
| 1493 |
+
"learning_rate": 7.886458082758637e-05,
|
| 1494 |
+
"loss": 0.1827,
|
| 1495 |
+
"step": 245
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.33,
|
| 1499 |
+
"learning_rate": 7.868861339521624e-05,
|
| 1500 |
+
"loss": 0.1835,
|
| 1501 |
+
"step": 246
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.33,
|
| 1505 |
+
"learning_rate": 7.851211463458936e-05,
|
| 1506 |
+
"loss": 0.1868,
|
| 1507 |
+
"step": 247
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.33,
|
| 1511 |
+
"learning_rate": 7.833508781455588e-05,
|
| 1512 |
+
"loss": 0.1837,
|
| 1513 |
+
"step": 248
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.33,
|
| 1517 |
+
"learning_rate": 7.815753621374594e-05,
|
| 1518 |
+
"loss": 0.182,
|
| 1519 |
+
"step": 249
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.33,
|
| 1523 |
+
"learning_rate": 7.797946312050883e-05,
|
| 1524 |
+
"loss": 0.1827,
|
| 1525 |
+
"step": 250
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 0.33,
|
| 1529 |
+
"learning_rate": 7.780087183285223e-05,
|
| 1530 |
+
"loss": 0.1911,
|
| 1531 |
+
"step": 251
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.33,
|
| 1535 |
+
"learning_rate": 7.7621765658381e-05,
|
| 1536 |
+
"loss": 0.1867,
|
| 1537 |
+
"step": 252
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.34,
|
| 1541 |
+
"learning_rate": 7.744214791423596e-05,
|
| 1542 |
+
"loss": 0.184,
|
| 1543 |
+
"step": 253
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.34,
|
| 1547 |
+
"learning_rate": 7.726202192703256e-05,
|
| 1548 |
+
"loss": 0.1837,
|
| 1549 |
+
"step": 254
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.34,
|
| 1553 |
+
"learning_rate": 7.708139103279908e-05,
|
| 1554 |
+
"loss": 0.1864,
|
| 1555 |
+
"step": 255
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.34,
|
| 1559 |
+
"learning_rate": 7.690025857691498e-05,
|
| 1560 |
+
"loss": 0.1843,
|
| 1561 |
+
"step": 256
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.34,
|
| 1565 |
+
"learning_rate": 7.671862791404896e-05,
|
| 1566 |
+
"loss": 0.1843,
|
| 1567 |
+
"step": 257
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.34,
|
| 1571 |
+
"learning_rate": 7.653650240809667e-05,
|
| 1572 |
+
"loss": 0.1816,
|
| 1573 |
+
"step": 258
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.34,
|
| 1577 |
+
"learning_rate": 7.635388543211861e-05,
|
| 1578 |
+
"loss": 0.1887,
|
| 1579 |
+
"step": 259
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.35,
|
| 1583 |
+
"learning_rate": 7.617078036827752e-05,
|
| 1584 |
+
"loss": 0.1826,
|
| 1585 |
+
"step": 260
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.35,
|
| 1589 |
+
"learning_rate": 7.59871906077758e-05,
|
| 1590 |
+
"loss": 0.1876,
|
| 1591 |
+
"step": 261
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.35,
|
| 1595 |
+
"learning_rate": 7.580311955079264e-05,
|
| 1596 |
+
"loss": 0.1852,
|
| 1597 |
+
"step": 262
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.35,
|
| 1601 |
+
"learning_rate": 7.56185706064212e-05,
|
| 1602 |
+
"loss": 0.1837,
|
| 1603 |
+
"step": 263
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.35,
|
| 1607 |
+
"learning_rate": 7.543354719260523e-05,
|
| 1608 |
+
"loss": 0.1813,
|
| 1609 |
+
"step": 264
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.35,
|
| 1613 |
+
"learning_rate": 7.524805273607603e-05,
|
| 1614 |
+
"loss": 0.1899,
|
| 1615 |
+
"step": 265
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.35,
|
| 1619 |
+
"learning_rate": 7.506209067228878e-05,
|
| 1620 |
+
"loss": 0.1878,
|
| 1621 |
+
"step": 266
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.35,
|
| 1625 |
+
"learning_rate": 7.487566444535903e-05,
|
| 1626 |
+
"loss": 0.1852,
|
| 1627 |
+
"step": 267
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.36,
|
| 1631 |
+
"learning_rate": 7.468877750799886e-05,
|
| 1632 |
+
"loss": 0.1879,
|
| 1633 |
+
"step": 268
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.36,
|
| 1637 |
+
"learning_rate": 7.450143332145296e-05,
|
| 1638 |
+
"loss": 0.1868,
|
| 1639 |
+
"step": 269
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.36,
|
| 1643 |
+
"learning_rate": 7.43136353554345e-05,
|
| 1644 |
+
"loss": 0.1851,
|
| 1645 |
+
"step": 270
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.36,
|
| 1649 |
+
"learning_rate": 7.412538708806093e-05,
|
| 1650 |
+
"loss": 0.1835,
|
| 1651 |
+
"step": 271
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.36,
|
| 1655 |
+
"learning_rate": 7.393669200578943e-05,
|
| 1656 |
+
"loss": 0.1855,
|
| 1657 |
+
"step": 272
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.36,
|
| 1661 |
+
"learning_rate": 7.374755360335253e-05,
|
| 1662 |
+
"loss": 0.1827,
|
| 1663 |
+
"step": 273
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.36,
|
| 1667 |
+
"learning_rate": 7.355797538369321e-05,
|
| 1668 |
+
"loss": 0.1889,
|
| 1669 |
+
"step": 274
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.37,
|
| 1673 |
+
"learning_rate": 7.336796085790013e-05,
|
| 1674 |
+
"loss": 0.1799,
|
| 1675 |
+
"step": 275
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.37,
|
| 1679 |
+
"learning_rate": 7.317751354514255e-05,
|
| 1680 |
+
"loss": 0.1863,
|
| 1681 |
+
"step": 276
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.37,
|
| 1685 |
+
"learning_rate": 7.298663697260522e-05,
|
| 1686 |
+
"loss": 0.1855,
|
| 1687 |
+
"step": 277
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.37,
|
| 1691 |
+
"learning_rate": 7.279533467542294e-05,
|
| 1692 |
+
"loss": 0.1851,
|
| 1693 |
+
"step": 278
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.37,
|
| 1697 |
+
"learning_rate": 7.260361019661522e-05,
|
| 1698 |
+
"loss": 0.1851,
|
| 1699 |
+
"step": 279
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 0.37,
|
| 1703 |
+
"learning_rate": 7.241146708702053e-05,
|
| 1704 |
+
"loss": 0.1856,
|
| 1705 |
+
"step": 280
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.37,
|
| 1709 |
+
"learning_rate": 7.221890890523068e-05,
|
| 1710 |
+
"loss": 0.187,
|
| 1711 |
+
"step": 281
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.37,
|
| 1715 |
+
"learning_rate": 7.202593921752475e-05,
|
| 1716 |
+
"loss": 0.1826,
|
| 1717 |
+
"step": 282
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.38,
|
| 1721 |
+
"learning_rate": 7.18325615978032e-05,
|
| 1722 |
+
"loss": 0.1866,
|
| 1723 |
+
"step": 283
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 0.38,
|
| 1727 |
+
"learning_rate": 7.163877962752157e-05,
|
| 1728 |
+
"loss": 0.1859,
|
| 1729 |
+
"step": 284
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.38,
|
| 1733 |
+
"learning_rate": 7.144459689562418e-05,
|
| 1734 |
+
"loss": 0.1843,
|
| 1735 |
+
"step": 285
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.38,
|
| 1739 |
+
"learning_rate": 7.12500169984777e-05,
|
| 1740 |
+
"loss": 0.1833,
|
| 1741 |
+
"step": 286
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 0.38,
|
| 1745 |
+
"learning_rate": 7.105504353980448e-05,
|
| 1746 |
+
"loss": 0.1841,
|
| 1747 |
+
"step": 287
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.38,
|
| 1751 |
+
"learning_rate": 7.085968013061584e-05,
|
| 1752 |
+
"loss": 0.185,
|
| 1753 |
+
"step": 288
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.38,
|
| 1757 |
+
"learning_rate": 7.066393038914521e-05,
|
| 1758 |
+
"loss": 0.1838,
|
| 1759 |
+
"step": 289
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.39,
|
| 1763 |
+
"learning_rate": 7.046779794078108e-05,
|
| 1764 |
+
"loss": 0.1852,
|
| 1765 |
+
"step": 290
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.39,
|
| 1769 |
+
"learning_rate": 7.027128641799986e-05,
|
| 1770 |
+
"loss": 0.1832,
|
| 1771 |
+
"step": 291
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.39,
|
| 1775 |
+
"learning_rate": 7.007439946029865e-05,
|
| 1776 |
+
"loss": 0.1899,
|
| 1777 |
+
"step": 292
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.39,
|
| 1781 |
+
"learning_rate": 6.98771407141278e-05,
|
| 1782 |
+
"loss": 0.1841,
|
| 1783 |
+
"step": 293
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 0.39,
|
| 1787 |
+
"learning_rate": 6.967951383282334e-05,
|
| 1788 |
+
"loss": 0.1869,
|
| 1789 |
+
"step": 294
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.39,
|
| 1793 |
+
"learning_rate": 6.94815224765394e-05,
|
| 1794 |
+
"loss": 0.1847,
|
| 1795 |
+
"step": 295
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.39,
|
| 1799 |
+
"learning_rate": 6.928317031218035e-05,
|
| 1800 |
+
"loss": 0.1848,
|
| 1801 |
+
"step": 296
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.39,
|
| 1805 |
+
"learning_rate": 6.908446101333295e-05,
|
| 1806 |
+
"loss": 0.1849,
|
| 1807 |
+
"step": 297
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.4,
|
| 1811 |
+
"learning_rate": 6.888539826019825e-05,
|
| 1812 |
+
"loss": 0.1829,
|
| 1813 |
+
"step": 298
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 0.4,
|
| 1817 |
+
"learning_rate": 6.868598573952345e-05,
|
| 1818 |
+
"loss": 0.1849,
|
| 1819 |
+
"step": 299
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.4,
|
| 1823 |
+
"learning_rate": 6.848622714453366e-05,
|
| 1824 |
+
"loss": 0.1844,
|
| 1825 |
+
"step": 300
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.4,
|
| 1829 |
+
"eval_loss": 0.17592795193195343,
|
| 1830 |
+
"eval_runtime": 11.447,
|
| 1831 |
+
"eval_samples_per_second": 174.719,
|
| 1832 |
+
"eval_steps_per_second": 0.699,
|
| 1833 |
+
"step": 300
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.4,
|
| 1837 |
+
"learning_rate": 6.828612617486347e-05,
|
| 1838 |
+
"loss": 0.1841,
|
| 1839 |
+
"step": 301
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.4,
|
| 1843 |
+
"learning_rate": 6.808568653648838e-05,
|
| 1844 |
+
"loss": 0.1843,
|
| 1845 |
+
"step": 302
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.4,
|
| 1849 |
+
"learning_rate": 6.78849119416563e-05,
|
| 1850 |
+
"loss": 0.1872,
|
| 1851 |
+
"step": 303
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.4,
|
| 1855 |
+
"learning_rate": 6.76838061088186e-05,
|
| 1856 |
+
"loss": 0.1856,
|
| 1857 |
+
"step": 304
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.41,
|
| 1861 |
+
"learning_rate": 6.748237276256143e-05,
|
| 1862 |
+
"loss": 0.1849,
|
| 1863 |
+
"step": 305
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.41,
|
| 1867 |
+
"learning_rate": 6.728061563353667e-05,
|
| 1868 |
+
"loss": 0.1817,
|
| 1869 |
+
"step": 306
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.41,
|
| 1873 |
+
"learning_rate": 6.707853845839278e-05,
|
| 1874 |
+
"loss": 0.1852,
|
| 1875 |
+
"step": 307
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.41,
|
| 1879 |
+
"learning_rate": 6.687614497970566e-05,
|
| 1880 |
+
"loss": 0.1837,
|
| 1881 |
+
"step": 308
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 0.41,
|
| 1885 |
+
"learning_rate": 6.667343894590935e-05,
|
| 1886 |
+
"loss": 0.1832,
|
| 1887 |
+
"step": 309
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.41,
|
| 1891 |
+
"learning_rate": 6.647042411122652e-05,
|
| 1892 |
+
"loss": 0.1843,
|
| 1893 |
+
"step": 310
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.41,
|
| 1897 |
+
"learning_rate": 6.626710423559901e-05,
|
| 1898 |
+
"loss": 0.1826,
|
| 1899 |
+
"step": 311
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.41,
|
| 1903 |
+
"learning_rate": 6.606348308461823e-05,
|
| 1904 |
+
"loss": 0.1848,
|
| 1905 |
+
"step": 312
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.42,
|
| 1909 |
+
"learning_rate": 6.585956442945532e-05,
|
| 1910 |
+
"loss": 0.1848,
|
| 1911 |
+
"step": 313
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.42,
|
| 1915 |
+
"learning_rate": 6.565535204679134e-05,
|
| 1916 |
+
"loss": 0.1812,
|
| 1917 |
+
"step": 314
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.42,
|
| 1921 |
+
"learning_rate": 6.545084971874738e-05,
|
| 1922 |
+
"loss": 0.186,
|
| 1923 |
+
"step": 315
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 0.42,
|
| 1927 |
+
"learning_rate": 6.524606123281445e-05,
|
| 1928 |
+
"loss": 0.1813,
|
| 1929 |
+
"step": 316
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.42,
|
| 1933 |
+
"learning_rate": 6.504099038178338e-05,
|
| 1934 |
+
"loss": 0.1814,
|
| 1935 |
+
"step": 317
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.42,
|
| 1939 |
+
"learning_rate": 6.483564096367451e-05,
|
| 1940 |
+
"loss": 0.1849,
|
| 1941 |
+
"step": 318
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.42,
|
| 1945 |
+
"learning_rate": 6.463001678166744e-05,
|
| 1946 |
+
"loss": 0.1855,
|
| 1947 |
+
"step": 319
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.42,
|
| 1951 |
+
"learning_rate": 6.442412164403045e-05,
|
| 1952 |
+
"loss": 0.1865,
|
| 1953 |
+
"step": 320
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.43,
|
| 1957 |
+
"learning_rate": 6.42179593640502e-05,
|
| 1958 |
+
"loss": 0.1828,
|
| 1959 |
+
"step": 321
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.43,
|
| 1963 |
+
"learning_rate": 6.401153375996081e-05,
|
| 1964 |
+
"loss": 0.1834,
|
| 1965 |
+
"step": 322
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 0.43,
|
| 1969 |
+
"learning_rate": 6.380484865487347e-05,
|
| 1970 |
+
"loss": 0.1817,
|
| 1971 |
+
"step": 323
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.43,
|
| 1975 |
+
"learning_rate": 6.359790787670527e-05,
|
| 1976 |
+
"loss": 0.1855,
|
| 1977 |
+
"step": 324
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.43,
|
| 1981 |
+
"learning_rate": 6.339071525810871e-05,
|
| 1982 |
+
"loss": 0.1837,
|
| 1983 |
+
"step": 325
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.43,
|
| 1987 |
+
"learning_rate": 6.318327463640037e-05,
|
| 1988 |
+
"loss": 0.1845,
|
| 1989 |
+
"step": 326
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.43,
|
| 1993 |
+
"learning_rate": 6.297558985348998e-05,
|
| 1994 |
+
"loss": 0.1817,
|
| 1995 |
+
"step": 327
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.44,
|
| 1999 |
+
"learning_rate": 6.276766475580935e-05,
|
| 2000 |
+
"loss": 0.1869,
|
| 2001 |
+
"step": 328
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.44,
|
| 2005 |
+
"learning_rate": 6.255950319424098e-05,
|
| 2006 |
+
"loss": 0.1838,
|
| 2007 |
+
"step": 329
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 0.44,
|
| 2011 |
+
"learning_rate": 6.235110902404679e-05,
|
| 2012 |
+
"loss": 0.1851,
|
| 2013 |
+
"step": 330
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 0.44,
|
| 2017 |
+
"learning_rate": 6.21424861047968e-05,
|
| 2018 |
+
"loss": 0.184,
|
| 2019 |
+
"step": 331
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.44,
|
| 2023 |
+
"learning_rate": 6.193363830029751e-05,
|
| 2024 |
+
"loss": 0.1847,
|
| 2025 |
+
"step": 332
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.44,
|
| 2029 |
+
"learning_rate": 6.172456947852049e-05,
|
| 2030 |
+
"loss": 0.1855,
|
| 2031 |
+
"step": 333
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.44,
|
| 2035 |
+
"learning_rate": 6.151528351153061e-05,
|
| 2036 |
+
"loss": 0.1854,
|
| 2037 |
+
"step": 334
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 0.44,
|
| 2041 |
+
"learning_rate": 6.130578427541441e-05,
|
| 2042 |
+
"loss": 0.183,
|
| 2043 |
+
"step": 335
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 0.45,
|
| 2047 |
+
"learning_rate": 6.109607565020828e-05,
|
| 2048 |
+
"loss": 0.1794,
|
| 2049 |
+
"step": 336
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 0.45,
|
| 2053 |
+
"learning_rate": 6.08861615198266e-05,
|
| 2054 |
+
"loss": 0.1869,
|
| 2055 |
+
"step": 337
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 0.45,
|
| 2059 |
+
"learning_rate": 6.067604577198981e-05,
|
| 2060 |
+
"loss": 0.188,
|
| 2061 |
+
"step": 338
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.45,
|
| 2065 |
+
"learning_rate": 6.046573229815243e-05,
|
| 2066 |
+
"loss": 0.1831,
|
| 2067 |
+
"step": 339
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.45,
|
| 2071 |
+
"learning_rate": 6.025522499343097e-05,
|
| 2072 |
+
"loss": 0.1886,
|
| 2073 |
+
"step": 340
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.45,
|
| 2077 |
+
"learning_rate": 6.004452775653178e-05,
|
| 2078 |
+
"loss": 0.1861,
|
| 2079 |
+
"step": 341
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 0.45,
|
| 2083 |
+
"learning_rate": 5.9833644489678816e-05,
|
| 2084 |
+
"loss": 0.1817,
|
| 2085 |
+
"step": 342
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 0.46,
|
| 2089 |
+
"learning_rate": 5.96225790985415e-05,
|
| 2090 |
+
"loss": 0.1863,
|
| 2091 |
+
"step": 343
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.46,
|
| 2095 |
+
"learning_rate": 5.941133549216221e-05,
|
| 2096 |
+
"loss": 0.1807,
|
| 2097 |
+
"step": 344
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 0.46,
|
| 2101 |
+
"learning_rate": 5.919991758288401e-05,
|
| 2102 |
+
"loss": 0.1846,
|
| 2103 |
+
"step": 345
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.46,
|
| 2107 |
+
"learning_rate": 5.898832928627811e-05,
|
| 2108 |
+
"loss": 0.1828,
|
| 2109 |
+
"step": 346
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.46,
|
| 2113 |
+
"learning_rate": 5.877657452107142e-05,
|
| 2114 |
+
"loss": 0.1823,
|
| 2115 |
+
"step": 347
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 0.46,
|
| 2119 |
+
"learning_rate": 5.856465720907388e-05,
|
| 2120 |
+
"loss": 0.1843,
|
| 2121 |
+
"step": 348
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.46,
|
| 2125 |
+
"learning_rate": 5.835258127510596e-05,
|
| 2126 |
+
"loss": 0.183,
|
| 2127 |
+
"step": 349
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 0.46,
|
| 2131 |
+
"learning_rate": 5.8140350646925845e-05,
|
| 2132 |
+
"loss": 0.1842,
|
| 2133 |
+
"step": 350
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.47,
|
| 2137 |
+
"learning_rate": 5.7927969255156736e-05,
|
| 2138 |
+
"loss": 0.1845,
|
| 2139 |
+
"step": 351
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 0.47,
|
| 2143 |
+
"learning_rate": 5.771544103321407e-05,
|
| 2144 |
+
"loss": 0.1794,
|
| 2145 |
+
"step": 352
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.47,
|
| 2149 |
+
"learning_rate": 5.7502769917232635e-05,
|
| 2150 |
+
"loss": 0.1782,
|
| 2151 |
+
"step": 353
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.47,
|
| 2155 |
+
"learning_rate": 5.7289959845993736e-05,
|
| 2156 |
+
"loss": 0.187,
|
| 2157 |
+
"step": 354
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 0.47,
|
| 2161 |
+
"learning_rate": 5.7077014760852164e-05,
|
| 2162 |
+
"loss": 0.1829,
|
| 2163 |
+
"step": 355
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.47,
|
| 2167 |
+
"learning_rate": 5.686393860566324e-05,
|
| 2168 |
+
"loss": 0.1849,
|
| 2169 |
+
"step": 356
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 0.47,
|
| 2173 |
+
"learning_rate": 5.66507353267098e-05,
|
| 2174 |
+
"loss": 0.1848,
|
| 2175 |
+
"step": 357
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 0.48,
|
| 2179 |
+
"learning_rate": 5.643740887262905e-05,
|
| 2180 |
+
"loss": 0.1825,
|
| 2181 |
+
"step": 358
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 0.48,
|
| 2185 |
+
"learning_rate": 5.6223963194339466e-05,
|
| 2186 |
+
"loss": 0.1856,
|
| 2187 |
+
"step": 359
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.48,
|
| 2191 |
+
"learning_rate": 5.601040224496764e-05,
|
| 2192 |
+
"loss": 0.183,
|
| 2193 |
+
"step": 360
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.48,
|
| 2197 |
+
"learning_rate": 5.579672997977503e-05,
|
| 2198 |
+
"loss": 0.1833,
|
| 2199 |
+
"step": 361
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.48,
|
| 2203 |
+
"learning_rate": 5.5582950356084726e-05,
|
| 2204 |
+
"loss": 0.1821,
|
| 2205 |
+
"step": 362
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.48,
|
| 2209 |
+
"learning_rate": 5.536906733320816e-05,
|
| 2210 |
+
"loss": 0.1823,
|
| 2211 |
+
"step": 363
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 0.48,
|
| 2215 |
+
"learning_rate": 5.515508487237174e-05,
|
| 2216 |
+
"loss": 0.1845,
|
| 2217 |
+
"step": 364
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 0.48,
|
| 2221 |
+
"learning_rate": 5.494100693664358e-05,
|
| 2222 |
+
"loss": 0.1825,
|
| 2223 |
+
"step": 365
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.49,
|
| 2227 |
+
"learning_rate": 5.4726837490859964e-05,
|
| 2228 |
+
"loss": 0.181,
|
| 2229 |
+
"step": 366
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.49,
|
| 2233 |
+
"learning_rate": 5.4512580501552056e-05,
|
| 2234 |
+
"loss": 0.1839,
|
| 2235 |
+
"step": 367
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.49,
|
| 2239 |
+
"learning_rate": 5.429823993687233e-05,
|
| 2240 |
+
"loss": 0.1834,
|
| 2241 |
+
"step": 368
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.49,
|
| 2245 |
+
"learning_rate": 5.4083819766521135e-05,
|
| 2246 |
+
"loss": 0.1843,
|
| 2247 |
+
"step": 369
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 0.49,
|
| 2251 |
+
"learning_rate": 5.386932396167316e-05,
|
| 2252 |
+
"loss": 0.1827,
|
| 2253 |
+
"step": 370
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 0.49,
|
| 2257 |
+
"learning_rate": 5.365475649490388e-05,
|
| 2258 |
+
"loss": 0.1844,
|
| 2259 |
+
"step": 371
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.49,
|
| 2263 |
+
"learning_rate": 5.3440121340116e-05,
|
| 2264 |
+
"loss": 0.1854,
|
| 2265 |
+
"step": 372
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 0.5,
|
| 2269 |
+
"learning_rate": 5.3225422472465824e-05,
|
| 2270 |
+
"loss": 0.1843,
|
| 2271 |
+
"step": 373
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.5,
|
| 2275 |
+
"learning_rate": 5.3010663868289655e-05,
|
| 2276 |
+
"loss": 0.1815,
|
| 2277 |
+
"step": 374
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.5,
|
| 2281 |
+
"learning_rate": 5.279584950503017e-05,
|
| 2282 |
+
"loss": 0.1811,
|
| 2283 |
+
"step": 375
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 0.5,
|
| 2287 |
+
"learning_rate": 5.2580983361162696e-05,
|
| 2288 |
+
"loss": 0.1856,
|
| 2289 |
+
"step": 376
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 0.5,
|
| 2293 |
+
"learning_rate": 5.23660694161216e-05,
|
| 2294 |
+
"loss": 0.1832,
|
| 2295 |
+
"step": 377
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 0.5,
|
| 2299 |
+
"learning_rate": 5.215111165022652e-05,
|
| 2300 |
+
"loss": 0.1826,
|
| 2301 |
+
"step": 378
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 0.5,
|
| 2305 |
+
"learning_rate": 5.193611404460873e-05,
|
| 2306 |
+
"loss": 0.1826,
|
| 2307 |
+
"step": 379
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.5,
|
| 2311 |
+
"learning_rate": 5.172108058113729e-05,
|
| 2312 |
+
"loss": 0.1845,
|
| 2313 |
+
"step": 380
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.51,
|
| 2317 |
+
"learning_rate": 5.1506015242345415e-05,
|
| 2318 |
+
"loss": 0.1815,
|
| 2319 |
+
"step": 381
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.51,
|
| 2323 |
+
"learning_rate": 5.129092201135666e-05,
|
| 2324 |
+
"loss": 0.1848,
|
| 2325 |
+
"step": 382
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 0.51,
|
| 2329 |
+
"learning_rate": 5.1075804871811115e-05,
|
| 2330 |
+
"loss": 0.1845,
|
| 2331 |
+
"step": 383
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 0.51,
|
| 2335 |
+
"learning_rate": 5.086066780779174e-05,
|
| 2336 |
+
"loss": 0.184,
|
| 2337 |
+
"step": 384
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 0.51,
|
| 2341 |
+
"learning_rate": 5.064551480375046e-05,
|
| 2342 |
+
"loss": 0.1851,
|
| 2343 |
+
"step": 385
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 0.51,
|
| 2347 |
+
"learning_rate": 5.0430349844434424e-05,
|
| 2348 |
+
"loss": 0.187,
|
| 2349 |
+
"step": 386
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.51,
|
| 2353 |
+
"learning_rate": 5.021517691481221e-05,
|
| 2354 |
+
"loss": 0.1817,
|
| 2355 |
+
"step": 387
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.52,
|
| 2359 |
+
"learning_rate": 5e-05,
|
| 2360 |
+
"loss": 0.1835,
|
| 2361 |
+
"step": 388
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.52,
|
| 2365 |
+
"learning_rate": 4.978482308518779e-05,
|
| 2366 |
+
"loss": 0.1827,
|
| 2367 |
+
"step": 389
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 0.52,
|
| 2371 |
+
"learning_rate": 4.956965015556559e-05,
|
| 2372 |
+
"loss": 0.1839,
|
| 2373 |
+
"step": 390
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 0.52,
|
| 2377 |
+
"learning_rate": 4.9354485196249554e-05,
|
| 2378 |
+
"loss": 0.1828,
|
| 2379 |
+
"step": 391
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 0.52,
|
| 2383 |
+
"learning_rate": 4.9139332192208276e-05,
|
| 2384 |
+
"loss": 0.1843,
|
| 2385 |
+
"step": 392
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.52,
|
| 2389 |
+
"learning_rate": 4.892419512818889e-05,
|
| 2390 |
+
"loss": 0.187,
|
| 2391 |
+
"step": 393
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 0.52,
|
| 2395 |
+
"learning_rate": 4.870907798864337e-05,
|
| 2396 |
+
"loss": 0.1799,
|
| 2397 |
+
"step": 394
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.52,
|
| 2401 |
+
"learning_rate": 4.8493984757654596e-05,
|
| 2402 |
+
"loss": 0.1842,
|
| 2403 |
+
"step": 395
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.53,
|
| 2407 |
+
"learning_rate": 4.827891941886273e-05,
|
| 2408 |
+
"loss": 0.183,
|
| 2409 |
+
"step": 396
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.53,
|
| 2413 |
+
"learning_rate": 4.806388595539129e-05,
|
| 2414 |
+
"loss": 0.1813,
|
| 2415 |
+
"step": 397
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 0.53,
|
| 2419 |
+
"learning_rate": 4.784888834977347e-05,
|
| 2420 |
+
"loss": 0.1822,
|
| 2421 |
+
"step": 398
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 0.53,
|
| 2425 |
+
"learning_rate": 4.763393058387841e-05,
|
| 2426 |
+
"loss": 0.1836,
|
| 2427 |
+
"step": 399
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 0.53,
|
| 2431 |
+
"learning_rate": 4.741901663883731e-05,
|
| 2432 |
+
"loss": 0.1853,
|
| 2433 |
+
"step": 400
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 0.53,
|
| 2437 |
+
"eval_loss": 0.1743704080581665,
|
| 2438 |
+
"eval_runtime": 12.7542,
|
| 2439 |
+
"eval_samples_per_second": 156.811,
|
| 2440 |
+
"eval_steps_per_second": 0.627,
|
| 2441 |
+
"step": 400
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 0.53,
|
| 2445 |
+
"learning_rate": 4.720415049496984e-05,
|
| 2446 |
+
"loss": 0.1851,
|
| 2447 |
+
"step": 401
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 0.53,
|
| 2451 |
+
"learning_rate": 4.698933613171035e-05,
|
| 2452 |
+
"loss": 0.1835,
|
| 2453 |
+
"step": 402
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.54,
|
| 2457 |
+
"learning_rate": 4.6774577527534195e-05,
|
| 2458 |
+
"loss": 0.185,
|
| 2459 |
+
"step": 403
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.54,
|
| 2463 |
+
"learning_rate": 4.655987865988401e-05,
|
| 2464 |
+
"loss": 0.1858,
|
| 2465 |
+
"step": 404
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 0.54,
|
| 2469 |
+
"learning_rate": 4.634524350509613e-05,
|
| 2470 |
+
"loss": 0.1825,
|
| 2471 |
+
"step": 405
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 0.54,
|
| 2475 |
+
"learning_rate": 4.613067603832685e-05,
|
| 2476 |
+
"loss": 0.1885,
|
| 2477 |
+
"step": 406
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 0.54,
|
| 2481 |
+
"learning_rate": 4.5916180233478883e-05,
|
| 2482 |
+
"loss": 0.1833,
|
| 2483 |
+
"step": 407
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 0.54,
|
| 2487 |
+
"learning_rate": 4.5701760063127686e-05,
|
| 2488 |
+
"loss": 0.1862,
|
| 2489 |
+
"step": 408
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 0.54,
|
| 2493 |
+
"learning_rate": 4.548741949844795e-05,
|
| 2494 |
+
"loss": 0.1837,
|
| 2495 |
+
"step": 409
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.54,
|
| 2499 |
+
"learning_rate": 4.527316250914004e-05,
|
| 2500 |
+
"loss": 0.1873,
|
| 2501 |
+
"step": 410
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.55,
|
| 2505 |
+
"learning_rate": 4.505899306335643e-05,
|
| 2506 |
+
"loss": 0.1787,
|
| 2507 |
+
"step": 411
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 0.55,
|
| 2511 |
+
"learning_rate": 4.484491512762827e-05,
|
| 2512 |
+
"loss": 0.1883,
|
| 2513 |
+
"step": 412
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 0.55,
|
| 2517 |
+
"learning_rate": 4.463093266679185e-05,
|
| 2518 |
+
"loss": 0.1806,
|
| 2519 |
+
"step": 413
|
| 2520 |
+
},
|
| 2521 |
+
{
|
| 2522 |
+
"epoch": 0.55,
|
| 2523 |
+
"learning_rate": 4.4417049643915286e-05,
|
| 2524 |
+
"loss": 0.183,
|
| 2525 |
+
"step": 414
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"epoch": 0.55,
|
| 2529 |
+
"learning_rate": 4.420327002022498e-05,
|
| 2530 |
+
"loss": 0.1831,
|
| 2531 |
+
"step": 415
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 0.55,
|
| 2535 |
+
"learning_rate": 4.398959775503238e-05,
|
| 2536 |
+
"loss": 0.183,
|
| 2537 |
+
"step": 416
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.55,
|
| 2541 |
+
"learning_rate": 4.377603680566054e-05,
|
| 2542 |
+
"loss": 0.1782,
|
| 2543 |
+
"step": 417
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.56,
|
| 2547 |
+
"learning_rate": 4.356259112737096e-05,
|
| 2548 |
+
"loss": 0.1871,
|
| 2549 |
+
"step": 418
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 0.56,
|
| 2553 |
+
"learning_rate": 4.334926467329021e-05,
|
| 2554 |
+
"loss": 0.1825,
|
| 2555 |
+
"step": 419
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 0.56,
|
| 2559 |
+
"learning_rate": 4.313606139433676e-05,
|
| 2560 |
+
"loss": 0.1838,
|
| 2561 |
+
"step": 420
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 0.56,
|
| 2565 |
+
"learning_rate": 4.292298523914785e-05,
|
| 2566 |
+
"loss": 0.1816,
|
| 2567 |
+
"step": 421
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 0.56,
|
| 2571 |
+
"learning_rate": 4.271004015400627e-05,
|
| 2572 |
+
"loss": 0.1824,
|
| 2573 |
+
"step": 422
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 0.56,
|
| 2577 |
+
"learning_rate": 4.249723008276737e-05,
|
| 2578 |
+
"loss": 0.182,
|
| 2579 |
+
"step": 423
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.56,
|
| 2583 |
+
"learning_rate": 4.228455896678595e-05,
|
| 2584 |
+
"loss": 0.1817,
|
| 2585 |
+
"step": 424
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.56,
|
| 2589 |
+
"learning_rate": 4.207203074484328e-05,
|
| 2590 |
+
"loss": 0.1808,
|
| 2591 |
+
"step": 425
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 0.57,
|
| 2595 |
+
"learning_rate": 4.185964935307417e-05,
|
| 2596 |
+
"loss": 0.1776,
|
| 2597 |
+
"step": 426
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 0.57,
|
| 2601 |
+
"learning_rate": 4.164741872489405e-05,
|
| 2602 |
+
"loss": 0.1831,
|
| 2603 |
+
"step": 427
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 0.57,
|
| 2607 |
+
"learning_rate": 4.143534279092612e-05,
|
| 2608 |
+
"loss": 0.18,
|
| 2609 |
+
"step": 428
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 0.57,
|
| 2613 |
+
"learning_rate": 4.1223425478928594e-05,
|
| 2614 |
+
"loss": 0.1816,
|
| 2615 |
+
"step": 429
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 0.57,
|
| 2619 |
+
"learning_rate": 4.1011670713721905e-05,
|
| 2620 |
+
"loss": 0.1811,
|
| 2621 |
+
"step": 430
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.57,
|
| 2625 |
+
"learning_rate": 4.0800082417115995e-05,
|
| 2626 |
+
"loss": 0.1805,
|
| 2627 |
+
"step": 431
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.57,
|
| 2631 |
+
"learning_rate": 4.05886645078378e-05,
|
| 2632 |
+
"loss": 0.1814,
|
| 2633 |
+
"step": 432
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 0.58,
|
| 2637 |
+
"learning_rate": 4.0377420901458506e-05,
|
| 2638 |
+
"loss": 0.1798,
|
| 2639 |
+
"step": 433
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 0.58,
|
| 2643 |
+
"learning_rate": 4.0166355510321195e-05,
|
| 2644 |
+
"loss": 0.1826,
|
| 2645 |
+
"step": 434
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 0.58,
|
| 2649 |
+
"learning_rate": 3.995547224346824e-05,
|
| 2650 |
+
"loss": 0.1818,
|
| 2651 |
+
"step": 435
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 0.58,
|
| 2655 |
+
"learning_rate": 3.9744775006569057e-05,
|
| 2656 |
+
"loss": 0.1812,
|
| 2657 |
+
"step": 436
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 0.58,
|
| 2661 |
+
"learning_rate": 3.953426770184757e-05,
|
| 2662 |
+
"loss": 0.1824,
|
| 2663 |
+
"step": 437
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.58,
|
| 2667 |
+
"learning_rate": 3.9323954228010196e-05,
|
| 2668 |
+
"loss": 0.181,
|
| 2669 |
+
"step": 438
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.58,
|
| 2673 |
+
"learning_rate": 3.911383848017341e-05,
|
| 2674 |
+
"loss": 0.1829,
|
| 2675 |
+
"step": 439
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 0.58,
|
| 2679 |
+
"learning_rate": 3.890392434979172e-05,
|
| 2680 |
+
"loss": 0.1849,
|
| 2681 |
+
"step": 440
|
| 2682 |
+
},
|
| 2683 |
+
{
|
| 2684 |
+
"epoch": 0.59,
|
| 2685 |
+
"learning_rate": 3.8694215724585594e-05,
|
| 2686 |
+
"loss": 0.1821,
|
| 2687 |
+
"step": 441
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 0.59,
|
| 2691 |
+
"learning_rate": 3.848471648846939e-05,
|
| 2692 |
+
"loss": 0.1822,
|
| 2693 |
+
"step": 442
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 0.59,
|
| 2697 |
+
"learning_rate": 3.827543052147952e-05,
|
| 2698 |
+
"loss": 0.1866,
|
| 2699 |
+
"step": 443
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 0.59,
|
| 2703 |
+
"learning_rate": 3.8066361699702495e-05,
|
| 2704 |
+
"loss": 0.1826,
|
| 2705 |
+
"step": 444
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.59,
|
| 2709 |
+
"learning_rate": 3.785751389520323e-05,
|
| 2710 |
+
"loss": 0.1825,
|
| 2711 |
+
"step": 445
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.59,
|
| 2715 |
+
"learning_rate": 3.764889097595322e-05,
|
| 2716 |
+
"loss": 0.1813,
|
| 2717 |
+
"step": 446
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 0.59,
|
| 2721 |
+
"learning_rate": 3.744049680575905e-05,
|
| 2722 |
+
"loss": 0.1817,
|
| 2723 |
+
"step": 447
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 0.59,
|
| 2727 |
+
"learning_rate": 3.7232335244190656e-05,
|
| 2728 |
+
"loss": 0.1799,
|
| 2729 |
+
"step": 448
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 0.6,
|
| 2733 |
+
"learning_rate": 3.702441014651001e-05,
|
| 2734 |
+
"loss": 0.182,
|
| 2735 |
+
"step": 449
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 0.6,
|
| 2739 |
+
"learning_rate": 3.6816725363599644e-05,
|
| 2740 |
+
"loss": 0.18,
|
| 2741 |
+
"step": 450
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 0.6,
|
| 2745 |
+
"learning_rate": 3.6609284741891295e-05,
|
| 2746 |
+
"loss": 0.1793,
|
| 2747 |
+
"step": 451
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.6,
|
| 2751 |
+
"learning_rate": 3.640209212329473e-05,
|
| 2752 |
+
"loss": 0.1801,
|
| 2753 |
+
"step": 452
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.6,
|
| 2757 |
+
"learning_rate": 3.619515134512656e-05,
|
| 2758 |
+
"loss": 0.1798,
|
| 2759 |
+
"step": 453
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 0.6,
|
| 2763 |
+
"learning_rate": 3.5988466240039206e-05,
|
| 2764 |
+
"loss": 0.179,
|
| 2765 |
+
"step": 454
|
| 2766 |
+
},
|
| 2767 |
+
{
|
| 2768 |
+
"epoch": 0.6,
|
| 2769 |
+
"learning_rate": 3.578204063594982e-05,
|
| 2770 |
+
"loss": 0.1827,
|
| 2771 |
+
"step": 455
|
| 2772 |
+
},
|
| 2773 |
+
{
|
| 2774 |
+
"epoch": 0.61,
|
| 2775 |
+
"learning_rate": 3.5575878355969566e-05,
|
| 2776 |
+
"loss": 0.1843,
|
| 2777 |
+
"step": 456
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 0.61,
|
| 2781 |
+
"learning_rate": 3.536998321833258e-05,
|
| 2782 |
+
"loss": 0.1821,
|
| 2783 |
+
"step": 457
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 0.61,
|
| 2787 |
+
"learning_rate": 3.516435903632548e-05,
|
| 2788 |
+
"loss": 0.182,
|
| 2789 |
+
"step": 458
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.61,
|
| 2793 |
+
"learning_rate": 3.495900961821662e-05,
|
| 2794 |
+
"loss": 0.1792,
|
| 2795 |
+
"step": 459
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.61,
|
| 2799 |
+
"learning_rate": 3.475393876718555e-05,
|
| 2800 |
+
"loss": 0.1836,
|
| 2801 |
+
"step": 460
|
| 2802 |
+
},
|
| 2803 |
+
{
|
| 2804 |
+
"epoch": 0.61,
|
| 2805 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 2806 |
+
"loss": 0.1849,
|
| 2807 |
+
"step": 461
|
| 2808 |
+
},
|
| 2809 |
+
{
|
| 2810 |
+
"epoch": 0.61,
|
| 2811 |
+
"learning_rate": 3.4344647953208675e-05,
|
| 2812 |
+
"loss": 0.1823,
|
| 2813 |
+
"step": 462
|
| 2814 |
+
},
|
| 2815 |
+
{
|
| 2816 |
+
"epoch": 0.61,
|
| 2817 |
+
"learning_rate": 3.41404355705447e-05,
|
| 2818 |
+
"loss": 0.1785,
|
| 2819 |
+
"step": 463
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 0.62,
|
| 2823 |
+
"learning_rate": 3.393651691538178e-05,
|
| 2824 |
+
"loss": 0.181,
|
| 2825 |
+
"step": 464
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.62,
|
| 2829 |
+
"learning_rate": 3.3732895764401004e-05,
|
| 2830 |
+
"loss": 0.1817,
|
| 2831 |
+
"step": 465
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.62,
|
| 2835 |
+
"learning_rate": 3.35295758887735e-05,
|
| 2836 |
+
"loss": 0.1807,
|
| 2837 |
+
"step": 466
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.62,
|
| 2841 |
+
"learning_rate": 3.332656105409066e-05,
|
| 2842 |
+
"loss": 0.1805,
|
| 2843 |
+
"step": 467
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 0.62,
|
| 2847 |
+
"learning_rate": 3.312385502029434e-05,
|
| 2848 |
+
"loss": 0.1839,
|
| 2849 |
+
"step": 468
|
| 2850 |
+
},
|
| 2851 |
+
{
|
| 2852 |
+
"epoch": 0.62,
|
| 2853 |
+
"learning_rate": 3.2921461541607225e-05,
|
| 2854 |
+
"loss": 0.1811,
|
| 2855 |
+
"step": 469
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 0.62,
|
| 2859 |
+
"learning_rate": 3.271938436646334e-05,
|
| 2860 |
+
"loss": 0.1829,
|
| 2861 |
+
"step": 470
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 0.63,
|
| 2865 |
+
"learning_rate": 3.251762723743858e-05,
|
| 2866 |
+
"loss": 0.1818,
|
| 2867 |
+
"step": 471
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 0.63,
|
| 2871 |
+
"learning_rate": 3.231619389118144e-05,
|
| 2872 |
+
"loss": 0.1798,
|
| 2873 |
+
"step": 472
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.63,
|
| 2877 |
+
"learning_rate": 3.2115088058343725e-05,
|
| 2878 |
+
"loss": 0.1813,
|
| 2879 |
+
"step": 473
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.63,
|
| 2883 |
+
"learning_rate": 3.191431346351164e-05,
|
| 2884 |
+
"loss": 0.18,
|
| 2885 |
+
"step": 474
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 0.63,
|
| 2889 |
+
"learning_rate": 3.171387382513654e-05,
|
| 2890 |
+
"loss": 0.1822,
|
| 2891 |
+
"step": 475
|
| 2892 |
+
},
|
| 2893 |
+
{
|
| 2894 |
+
"epoch": 0.63,
|
| 2895 |
+
"learning_rate": 3.151377285546635e-05,
|
| 2896 |
+
"loss": 0.1823,
|
| 2897 |
+
"step": 476
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 0.63,
|
| 2901 |
+
"learning_rate": 3.1314014260476553e-05,
|
| 2902 |
+
"loss": 0.1826,
|
| 2903 |
+
"step": 477
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 0.63,
|
| 2907 |
+
"learning_rate": 3.111460173980175e-05,
|
| 2908 |
+
"loss": 0.1785,
|
| 2909 |
+
"step": 478
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 0.64,
|
| 2913 |
+
"learning_rate": 3.091553898666705e-05,
|
| 2914 |
+
"loss": 0.1844,
|
| 2915 |
+
"step": 479
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.64,
|
| 2919 |
+
"learning_rate": 3.0716829687819643e-05,
|
| 2920 |
+
"loss": 0.1809,
|
| 2921 |
+
"step": 480
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.64,
|
| 2925 |
+
"learning_rate": 3.051847752346061e-05,
|
| 2926 |
+
"loss": 0.182,
|
| 2927 |
+
"step": 481
|
| 2928 |
+
},
|
| 2929 |
+
{
|
| 2930 |
+
"epoch": 0.64,
|
| 2931 |
+
"learning_rate": 3.0320486167176664e-05,
|
| 2932 |
+
"loss": 0.1792,
|
| 2933 |
+
"step": 482
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 0.64,
|
| 2937 |
+
"learning_rate": 3.0122859285872214e-05,
|
| 2938 |
+
"loss": 0.183,
|
| 2939 |
+
"step": 483
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 0.64,
|
| 2943 |
+
"learning_rate": 2.9925600539701347e-05,
|
| 2944 |
+
"loss": 0.1814,
|
| 2945 |
+
"step": 484
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.64,
|
| 2949 |
+
"learning_rate": 2.972871358200015e-05,
|
| 2950 |
+
"loss": 0.1817,
|
| 2951 |
+
"step": 485
|
| 2952 |
+
},
|
| 2953 |
+
{
|
| 2954 |
+
"epoch": 0.65,
|
| 2955 |
+
"learning_rate": 2.9532202059218933e-05,
|
| 2956 |
+
"loss": 0.1777,
|
| 2957 |
+
"step": 486
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.65,
|
| 2961 |
+
"learning_rate": 2.9336069610854788e-05,
|
| 2962 |
+
"loss": 0.1837,
|
| 2963 |
+
"step": 487
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.65,
|
| 2967 |
+
"learning_rate": 2.914031986938417e-05,
|
| 2968 |
+
"loss": 0.1805,
|
| 2969 |
+
"step": 488
|
| 2970 |
+
},
|
| 2971 |
+
{
|
| 2972 |
+
"epoch": 0.65,
|
| 2973 |
+
"learning_rate": 2.8944956460195515e-05,
|
| 2974 |
+
"loss": 0.18,
|
| 2975 |
+
"step": 489
|
| 2976 |
+
},
|
| 2977 |
+
{
|
| 2978 |
+
"epoch": 0.65,
|
| 2979 |
+
"learning_rate": 2.8749983001522302e-05,
|
| 2980 |
+
"loss": 0.18,
|
| 2981 |
+
"step": 490
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 0.65,
|
| 2985 |
+
"learning_rate": 2.8555403104375827e-05,
|
| 2986 |
+
"loss": 0.1798,
|
| 2987 |
+
"step": 491
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 0.65,
|
| 2991 |
+
"learning_rate": 2.8361220372478446e-05,
|
| 2992 |
+
"loss": 0.1829,
|
| 2993 |
+
"step": 492
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 0.65,
|
| 2997 |
+
"learning_rate": 2.8167438402196805e-05,
|
| 2998 |
+
"loss": 0.1796,
|
| 2999 |
+
"step": 493
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.66,
|
| 3003 |
+
"learning_rate": 2.7974060782475258e-05,
|
| 3004 |
+
"loss": 0.1786,
|
| 3005 |
+
"step": 494
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.66,
|
| 3009 |
+
"learning_rate": 2.778109109476934e-05,
|
| 3010 |
+
"loss": 0.1827,
|
| 3011 |
+
"step": 495
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 0.66,
|
| 3015 |
+
"learning_rate": 2.7588532912979483e-05,
|
| 3016 |
+
"loss": 0.1789,
|
| 3017 |
+
"step": 496
|
| 3018 |
+
},
|
| 3019 |
+
{
|
| 3020 |
+
"epoch": 0.66,
|
| 3021 |
+
"learning_rate": 2.739638980338479e-05,
|
| 3022 |
+
"loss": 0.1817,
|
| 3023 |
+
"step": 497
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 0.66,
|
| 3027 |
+
"learning_rate": 2.720466532457707e-05,
|
| 3028 |
+
"loss": 0.1815,
|
| 3029 |
+
"step": 498
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 0.66,
|
| 3033 |
+
"learning_rate": 2.70133630273948e-05,
|
| 3034 |
+
"loss": 0.1788,
|
| 3035 |
+
"step": 499
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 0.66,
|
| 3039 |
+
"learning_rate": 2.6822486454857453e-05,
|
| 3040 |
+
"loss": 0.1802,
|
| 3041 |
+
"step": 500
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.66,
|
| 3045 |
+
"eval_loss": 0.1759687066078186,
|
| 3046 |
+
"eval_runtime": 12.5156,
|
| 3047 |
+
"eval_samples_per_second": 159.801,
|
| 3048 |
+
"eval_steps_per_second": 0.639,
|
| 3049 |
+
"step": 500
|
| 3050 |
+
},
|
| 3051 |
+
{
|
| 3052 |
+
"epoch": 0.67,
|
| 3053 |
+
"learning_rate": 2.6632039142099896e-05,
|
| 3054 |
+
"loss": 0.1804,
|
| 3055 |
+
"step": 501
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.67,
|
| 3059 |
+
"learning_rate": 2.6442024616306804e-05,
|
| 3060 |
+
"loss": 0.1814,
|
| 3061 |
+
"step": 502
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.67,
|
| 3065 |
+
"learning_rate": 2.62524463966475e-05,
|
| 3066 |
+
"loss": 0.1806,
|
| 3067 |
+
"step": 503
|
| 3068 |
+
},
|
| 3069 |
+
{
|
| 3070 |
+
"epoch": 0.67,
|
| 3071 |
+
"learning_rate": 2.6063307994210584e-05,
|
| 3072 |
+
"loss": 0.1818,
|
| 3073 |
+
"step": 504
|
| 3074 |
+
},
|
| 3075 |
+
{
|
| 3076 |
+
"epoch": 0.67,
|
| 3077 |
+
"learning_rate": 2.5874612911939094e-05,
|
| 3078 |
+
"loss": 0.1796,
|
| 3079 |
+
"step": 505
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 0.67,
|
| 3083 |
+
"learning_rate": 2.5686364644565486e-05,
|
| 3084 |
+
"loss": 0.1797,
|
| 3085 |
+
"step": 506
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 0.67,
|
| 3089 |
+
"learning_rate": 2.5498566678547042e-05,
|
| 3090 |
+
"loss": 0.1803,
|
| 3091 |
+
"step": 507
|
| 3092 |
+
},
|
| 3093 |
+
{
|
| 3094 |
+
"epoch": 0.67,
|
| 3095 |
+
"learning_rate": 2.531122249200114e-05,
|
| 3096 |
+
"loss": 0.1814,
|
| 3097 |
+
"step": 508
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.68,
|
| 3101 |
+
"learning_rate": 2.5124335554640967e-05,
|
| 3102 |
+
"loss": 0.1796,
|
| 3103 |
+
"step": 509
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 0.68,
|
| 3107 |
+
"learning_rate": 2.493790932771122e-05,
|
| 3108 |
+
"loss": 0.181,
|
| 3109 |
+
"step": 510
|
| 3110 |
+
},
|
| 3111 |
+
{
|
| 3112 |
+
"epoch": 0.68,
|
| 3113 |
+
"learning_rate": 2.4751947263923982e-05,
|
| 3114 |
+
"loss": 0.1802,
|
| 3115 |
+
"step": 511
|
| 3116 |
+
},
|
| 3117 |
+
{
|
| 3118 |
+
"epoch": 0.68,
|
| 3119 |
+
"learning_rate": 2.4566452807394785e-05,
|
| 3120 |
+
"loss": 0.1806,
|
| 3121 |
+
"step": 512
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 0.68,
|
| 3125 |
+
"learning_rate": 2.438142939357882e-05,
|
| 3126 |
+
"loss": 0.1833,
|
| 3127 |
+
"step": 513
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 0.68,
|
| 3131 |
+
"learning_rate": 2.4196880449207366e-05,
|
| 3132 |
+
"loss": 0.1803,
|
| 3133 |
+
"step": 514
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 0.68,
|
| 3137 |
+
"learning_rate": 2.4012809392224227e-05,
|
| 3138 |
+
"loss": 0.1813,
|
| 3139 |
+
"step": 515
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 0.69,
|
| 3143 |
+
"learning_rate": 2.38292196317225e-05,
|
| 3144 |
+
"loss": 0.1845,
|
| 3145 |
+
"step": 516
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 0.69,
|
| 3149 |
+
"learning_rate": 2.3646114567881393e-05,
|
| 3150 |
+
"loss": 0.1793,
|
| 3151 |
+
"step": 517
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 0.69,
|
| 3155 |
+
"learning_rate": 2.3463497591903322e-05,
|
| 3156 |
+
"loss": 0.1806,
|
| 3157 |
+
"step": 518
|
| 3158 |
+
},
|
| 3159 |
+
{
|
| 3160 |
+
"epoch": 0.69,
|
| 3161 |
+
"learning_rate": 2.328137208595107e-05,
|
| 3162 |
+
"loss": 0.1822,
|
| 3163 |
+
"step": 519
|
| 3164 |
+
},
|
| 3165 |
+
{
|
| 3166 |
+
"epoch": 0.69,
|
| 3167 |
+
"learning_rate": 2.309974142308502e-05,
|
| 3168 |
+
"loss": 0.179,
|
| 3169 |
+
"step": 520
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 0.69,
|
| 3173 |
+
"learning_rate": 2.291860896720094e-05,
|
| 3174 |
+
"loss": 0.181,
|
| 3175 |
+
"step": 521
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 0.69,
|
| 3179 |
+
"learning_rate": 2.273797807296744e-05,
|
| 3180 |
+
"loss": 0.1832,
|
| 3181 |
+
"step": 522
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.69,
|
| 3185 |
+
"learning_rate": 2.2557852085764053e-05,
|
| 3186 |
+
"loss": 0.1801,
|
| 3187 |
+
"step": 523
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.7,
|
| 3191 |
+
"learning_rate": 2.237823434161902e-05,
|
| 3192 |
+
"loss": 0.1807,
|
| 3193 |
+
"step": 524
|
| 3194 |
+
},
|
| 3195 |
+
{
|
| 3196 |
+
"epoch": 0.7,
|
| 3197 |
+
"learning_rate": 2.2199128167147785e-05,
|
| 3198 |
+
"loss": 0.1812,
|
| 3199 |
+
"step": 525
|
| 3200 |
+
},
|
| 3201 |
+
{
|
| 3202 |
+
"epoch": 0.7,
|
| 3203 |
+
"learning_rate": 2.2020536879491167e-05,
|
| 3204 |
+
"loss": 0.1777,
|
| 3205 |
+
"step": 526
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 0.7,
|
| 3209 |
+
"learning_rate": 2.184246378625407e-05,
|
| 3210 |
+
"loss": 0.1801,
|
| 3211 |
+
"step": 527
|
| 3212 |
+
},
|
| 3213 |
+
{
|
| 3214 |
+
"epoch": 0.7,
|
| 3215 |
+
"learning_rate": 2.1664912185444124e-05,
|
| 3216 |
+
"loss": 0.1759,
|
| 3217 |
+
"step": 528
|
| 3218 |
+
},
|
| 3219 |
+
{
|
| 3220 |
+
"epoch": 0.7,
|
| 3221 |
+
"learning_rate": 2.1487885365410644e-05,
|
| 3222 |
+
"loss": 0.184,
|
| 3223 |
+
"step": 529
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 0.7,
|
| 3227 |
+
"learning_rate": 2.1311386604783763e-05,
|
| 3228 |
+
"loss": 0.1844,
|
| 3229 |
+
"step": 530
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.71,
|
| 3233 |
+
"learning_rate": 2.113541917241364e-05,
|
| 3234 |
+
"loss": 0.1787,
|
| 3235 |
+
"step": 531
|
| 3236 |
+
},
|
| 3237 |
+
{
|
| 3238 |
+
"epoch": 0.71,
|
| 3239 |
+
"learning_rate": 2.0959986327309968e-05,
|
| 3240 |
+
"loss": 0.1798,
|
| 3241 |
+
"step": 532
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"epoch": 0.71,
|
| 3245 |
+
"learning_rate": 2.0785091318581577e-05,
|
| 3246 |
+
"loss": 0.178,
|
| 3247 |
+
"step": 533
|
| 3248 |
+
},
|
| 3249 |
+
{
|
| 3250 |
+
"epoch": 0.71,
|
| 3251 |
+
"learning_rate": 2.061073738537635e-05,
|
| 3252 |
+
"loss": 0.18,
|
| 3253 |
+
"step": 534
|
| 3254 |
+
},
|
| 3255 |
+
{
|
| 3256 |
+
"epoch": 0.71,
|
| 3257 |
+
"learning_rate": 2.0436927756821094e-05,
|
| 3258 |
+
"loss": 0.1792,
|
| 3259 |
+
"step": 535
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 0.71,
|
| 3263 |
+
"learning_rate": 2.0263665651961834e-05,
|
| 3264 |
+
"loss": 0.1813,
|
| 3265 |
+
"step": 536
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 0.71,
|
| 3269 |
+
"learning_rate": 2.0090954279704183e-05,
|
| 3270 |
+
"loss": 0.1829,
|
| 3271 |
+
"step": 537
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.71,
|
| 3275 |
+
"learning_rate": 1.9918796838753863e-05,
|
| 3276 |
+
"loss": 0.1773,
|
| 3277 |
+
"step": 538
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 0.72,
|
| 3281 |
+
"learning_rate": 1.974719651755756e-05,
|
| 3282 |
+
"loss": 0.1797,
|
| 3283 |
+
"step": 539
|
| 3284 |
+
},
|
| 3285 |
+
{
|
| 3286 |
+
"epoch": 0.72,
|
| 3287 |
+
"learning_rate": 1.957615649424369e-05,
|
| 3288 |
+
"loss": 0.1785,
|
| 3289 |
+
"step": 540
|
| 3290 |
+
},
|
| 3291 |
+
{
|
| 3292 |
+
"epoch": 0.72,
|
| 3293 |
+
"learning_rate": 1.9405679936563786e-05,
|
| 3294 |
+
"loss": 0.1825,
|
| 3295 |
+
"step": 541
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 0.72,
|
| 3299 |
+
"learning_rate": 1.9235770001833607e-05,
|
| 3300 |
+
"loss": 0.1785,
|
| 3301 |
+
"step": 542
|
| 3302 |
+
},
|
| 3303 |
+
{
|
| 3304 |
+
"epoch": 0.72,
|
| 3305 |
+
"learning_rate": 1.9066429836874844e-05,
|
| 3306 |
+
"loss": 0.176,
|
| 3307 |
+
"step": 543
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.72,
|
| 3311 |
+
"learning_rate": 1.889766257795663e-05,
|
| 3312 |
+
"loss": 0.1788,
|
| 3313 |
+
"step": 544
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 0.72,
|
| 3317 |
+
"learning_rate": 1.8729471350737693e-05,
|
| 3318 |
+
"loss": 0.1807,
|
| 3319 |
+
"step": 545
|
| 3320 |
+
},
|
| 3321 |
+
{
|
| 3322 |
+
"epoch": 0.73,
|
| 3323 |
+
"learning_rate": 1.856185927020827e-05,
|
| 3324 |
+
"loss": 0.1799,
|
| 3325 |
+
"step": 546
|
| 3326 |
+
},
|
| 3327 |
+
{
|
| 3328 |
+
"epoch": 0.73,
|
| 3329 |
+
"learning_rate": 1.8394829440632565e-05,
|
| 3330 |
+
"loss": 0.182,
|
| 3331 |
+
"step": 547
|
| 3332 |
+
},
|
| 3333 |
+
{
|
| 3334 |
+
"epoch": 0.73,
|
| 3335 |
+
"learning_rate": 1.8228384955491135e-05,
|
| 3336 |
+
"loss": 0.1825,
|
| 3337 |
+
"step": 548
|
| 3338 |
+
},
|
| 3339 |
+
{
|
| 3340 |
+
"epoch": 0.73,
|
| 3341 |
+
"learning_rate": 1.806252889742364e-05,
|
| 3342 |
+
"loss": 0.1755,
|
| 3343 |
+
"step": 549
|
| 3344 |
+
},
|
| 3345 |
+
{
|
| 3346 |
+
"epoch": 0.73,
|
| 3347 |
+
"learning_rate": 1.789726433817182e-05,
|
| 3348 |
+
"loss": 0.1777,
|
| 3349 |
+
"step": 550
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 0.73,
|
| 3353 |
+
"learning_rate": 1.7732594338522495e-05,
|
| 3354 |
+
"loss": 0.1823,
|
| 3355 |
+
"step": 551
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 0.73,
|
| 3359 |
+
"learning_rate": 1.756852194825094e-05,
|
| 3360 |
+
"loss": 0.1793,
|
| 3361 |
+
"step": 552
|
| 3362 |
+
},
|
| 3363 |
+
{
|
| 3364 |
+
"epoch": 0.73,
|
| 3365 |
+
"learning_rate": 1.7405050206064373e-05,
|
| 3366 |
+
"loss": 0.1794,
|
| 3367 |
+
"step": 553
|
| 3368 |
+
},
|
| 3369 |
+
{
|
| 3370 |
+
"epoch": 0.74,
|
| 3371 |
+
"learning_rate": 1.7242182139545744e-05,
|
| 3372 |
+
"loss": 0.1745,
|
| 3373 |
+
"step": 554
|
| 3374 |
+
},
|
| 3375 |
+
{
|
| 3376 |
+
"epoch": 0.74,
|
| 3377 |
+
"learning_rate": 1.7079920765097563e-05,
|
| 3378 |
+
"loss": 0.1771,
|
| 3379 |
+
"step": 555
|
| 3380 |
+
},
|
| 3381 |
+
{
|
| 3382 |
+
"epoch": 0.74,
|
| 3383 |
+
"learning_rate": 1.691826908788608e-05,
|
| 3384 |
+
"loss": 0.1755,
|
| 3385 |
+
"step": 556
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 0.74,
|
| 3389 |
+
"learning_rate": 1.675723010178568e-05,
|
| 3390 |
+
"loss": 0.1806,
|
| 3391 |
+
"step": 557
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 0.74,
|
| 3395 |
+
"learning_rate": 1.6596806789323315e-05,
|
| 3396 |
+
"loss": 0.1818,
|
| 3397 |
+
"step": 558
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 0.74,
|
| 3401 |
+
"learning_rate": 1.6437002121623436e-05,
|
| 3402 |
+
"loss": 0.1838,
|
| 3403 |
+
"step": 559
|
| 3404 |
+
},
|
| 3405 |
+
{
|
| 3406 |
+
"epoch": 0.74,
|
| 3407 |
+
"learning_rate": 1.6277819058352727e-05,
|
| 3408 |
+
"loss": 0.1775,
|
| 3409 |
+
"step": 560
|
| 3410 |
+
},
|
| 3411 |
+
{
|
| 3412 |
+
"epoch": 0.75,
|
| 3413 |
+
"learning_rate": 1.611926054766556e-05,
|
| 3414 |
+
"loss": 0.1781,
|
| 3415 |
+
"step": 561
|
| 3416 |
+
},
|
| 3417 |
+
{
|
| 3418 |
+
"epoch": 0.75,
|
| 3419 |
+
"learning_rate": 1.596132952614918e-05,
|
| 3420 |
+
"loss": 0.1791,
|
| 3421 |
+
"step": 562
|
| 3422 |
+
},
|
| 3423 |
+
{
|
| 3424 |
+
"epoch": 0.75,
|
| 3425 |
+
"learning_rate": 1.5804028918769485e-05,
|
| 3426 |
+
"loss": 0.1794,
|
| 3427 |
+
"step": 563
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 0.75,
|
| 3431 |
+
"learning_rate": 1.5647361638816655e-05,
|
| 3432 |
+
"loss": 0.1817,
|
| 3433 |
+
"step": 564
|
| 3434 |
+
},
|
| 3435 |
+
{
|
| 3436 |
+
"epoch": 0.75,
|
| 3437 |
+
"learning_rate": 1.549133058785141e-05,
|
| 3438 |
+
"loss": 0.1797,
|
| 3439 |
+
"step": 565
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 0.75,
|
| 3443 |
+
"learning_rate": 1.5335938655651122e-05,
|
| 3444 |
+
"loss": 0.1815,
|
| 3445 |
+
"step": 566
|
| 3446 |
+
},
|
| 3447 |
+
{
|
| 3448 |
+
"epoch": 0.75,
|
| 3449 |
+
"learning_rate": 1.5181188720156392e-05,
|
| 3450 |
+
"loss": 0.1824,
|
| 3451 |
+
"step": 567
|
| 3452 |
+
},
|
| 3453 |
+
{
|
| 3454 |
+
"epoch": 0.75,
|
| 3455 |
+
"learning_rate": 1.5027083647417655e-05,
|
| 3456 |
+
"loss": 0.1785,
|
| 3457 |
+
"step": 568
|
| 3458 |
+
},
|
| 3459 |
+
{
|
| 3460 |
+
"epoch": 0.76,
|
| 3461 |
+
"learning_rate": 1.4873626291542148e-05,
|
| 3462 |
+
"loss": 0.1811,
|
| 3463 |
+
"step": 569
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 0.76,
|
| 3467 |
+
"learning_rate": 1.4720819494641109e-05,
|
| 3468 |
+
"loss": 0.1794,
|
| 3469 |
+
"step": 570
|
| 3470 |
+
},
|
| 3471 |
+
{
|
| 3472 |
+
"epoch": 0.76,
|
| 3473 |
+
"learning_rate": 1.4568666086777021e-05,
|
| 3474 |
+
"loss": 0.183,
|
| 3475 |
+
"step": 571
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 0.76,
|
| 3479 |
+
"learning_rate": 1.4417168885911276e-05,
|
| 3480 |
+
"loss": 0.1773,
|
| 3481 |
+
"step": 572
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 0.76,
|
| 3485 |
+
"learning_rate": 1.4266330697851954e-05,
|
| 3486 |
+
"loss": 0.176,
|
| 3487 |
+
"step": 573
|
| 3488 |
+
},
|
| 3489 |
+
{
|
| 3490 |
+
"epoch": 0.76,
|
| 3491 |
+
"learning_rate": 1.4116154316201907e-05,
|
| 3492 |
+
"loss": 0.1754,
|
| 3493 |
+
"step": 574
|
| 3494 |
+
},
|
| 3495 |
+
{
|
| 3496 |
+
"epoch": 0.76,
|
| 3497 |
+
"learning_rate": 1.3966642522306956e-05,
|
| 3498 |
+
"loss": 0.1771,
|
| 3499 |
+
"step": 575
|
| 3500 |
+
},
|
| 3501 |
+
{
|
| 3502 |
+
"epoch": 0.76,
|
| 3503 |
+
"learning_rate": 1.381779808520438e-05,
|
| 3504 |
+
"loss": 0.1816,
|
| 3505 |
+
"step": 576
|
| 3506 |
+
},
|
| 3507 |
+
{
|
| 3508 |
+
"epoch": 0.77,
|
| 3509 |
+
"learning_rate": 1.3669623761571726e-05,
|
| 3510 |
+
"loss": 0.1799,
|
| 3511 |
+
"step": 577
|
| 3512 |
+
},
|
| 3513 |
+
{
|
| 3514 |
+
"epoch": 0.77,
|
| 3515 |
+
"learning_rate": 1.3522122295675616e-05,
|
| 3516 |
+
"loss": 0.1761,
|
| 3517 |
+
"step": 578
|
| 3518 |
+
},
|
| 3519 |
+
{
|
| 3520 |
+
"epoch": 0.77,
|
| 3521 |
+
"learning_rate": 1.337529641932107e-05,
|
| 3522 |
+
"loss": 0.1803,
|
| 3523 |
+
"step": 579
|
| 3524 |
+
},
|
| 3525 |
+
{
|
| 3526 |
+
"epoch": 0.77,
|
| 3527 |
+
"learning_rate": 1.3229148851800721e-05,
|
| 3528 |
+
"loss": 0.1811,
|
| 3529 |
+
"step": 580
|
| 3530 |
+
},
|
| 3531 |
+
{
|
| 3532 |
+
"epoch": 0.77,
|
| 3533 |
+
"learning_rate": 1.308368229984468e-05,
|
| 3534 |
+
"loss": 0.1794,
|
| 3535 |
+
"step": 581
|
| 3536 |
+
},
|
| 3537 |
+
{
|
| 3538 |
+
"epoch": 0.77,
|
| 3539 |
+
"learning_rate": 1.2938899457570208e-05,
|
| 3540 |
+
"loss": 0.1805,
|
| 3541 |
+
"step": 582
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 0.77,
|
| 3545 |
+
"learning_rate": 1.2794803006431982e-05,
|
| 3546 |
+
"loss": 0.1784,
|
| 3547 |
+
"step": 583
|
| 3548 |
+
},
|
| 3549 |
+
{
|
| 3550 |
+
"epoch": 0.78,
|
| 3551 |
+
"learning_rate": 1.265139561517224e-05,
|
| 3552 |
+
"loss": 0.1807,
|
| 3553 |
+
"step": 584
|
| 3554 |
+
},
|
| 3555 |
+
{
|
| 3556 |
+
"epoch": 0.78,
|
| 3557 |
+
"learning_rate": 1.2508679939771583e-05,
|
| 3558 |
+
"loss": 0.1771,
|
| 3559 |
+
"step": 585
|
| 3560 |
+
},
|
| 3561 |
+
{
|
| 3562 |
+
"epoch": 0.78,
|
| 3563 |
+
"learning_rate": 1.2366658623399584e-05,
|
| 3564 |
+
"loss": 0.1801,
|
| 3565 |
+
"step": 586
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 0.78,
|
| 3569 |
+
"learning_rate": 1.2225334296365987e-05,
|
| 3570 |
+
"loss": 0.1794,
|
| 3571 |
+
"step": 587
|
| 3572 |
+
},
|
| 3573 |
+
{
|
| 3574 |
+
"epoch": 0.78,
|
| 3575 |
+
"learning_rate": 1.2084709576071884e-05,
|
| 3576 |
+
"loss": 0.1778,
|
| 3577 |
+
"step": 588
|
| 3578 |
+
},
|
| 3579 |
+
{
|
| 3580 |
+
"epoch": 0.78,
|
| 3581 |
+
"learning_rate": 1.1944787066961265e-05,
|
| 3582 |
+
"loss": 0.1818,
|
| 3583 |
+
"step": 589
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 0.78,
|
| 3587 |
+
"learning_rate": 1.1805569360472868e-05,
|
| 3588 |
+
"loss": 0.181,
|
| 3589 |
+
"step": 590
|
| 3590 |
+
},
|
| 3591 |
+
{
|
| 3592 |
+
"epoch": 0.78,
|
| 3593 |
+
"learning_rate": 1.166705903499205e-05,
|
| 3594 |
+
"loss": 0.1812,
|
| 3595 |
+
"step": 591
|
| 3596 |
+
},
|
| 3597 |
+
{
|
| 3598 |
+
"epoch": 0.79,
|
| 3599 |
+
"learning_rate": 1.1529258655803116e-05,
|
| 3600 |
+
"loss": 0.1804,
|
| 3601 |
+
"step": 592
|
| 3602 |
+
},
|
| 3603 |
+
{
|
| 3604 |
+
"epoch": 0.79,
|
| 3605 |
+
"learning_rate": 1.1392170775041788e-05,
|
| 3606 |
+
"loss": 0.1799,
|
| 3607 |
+
"step": 593
|
| 3608 |
+
},
|
| 3609 |
+
{
|
| 3610 |
+
"epoch": 0.79,
|
| 3611 |
+
"learning_rate": 1.1255797931647971e-05,
|
| 3612 |
+
"loss": 0.1758,
|
| 3613 |
+
"step": 594
|
| 3614 |
+
},
|
| 3615 |
+
{
|
| 3616 |
+
"epoch": 0.79,
|
| 3617 |
+
"learning_rate": 1.1120142651318665e-05,
|
| 3618 |
+
"loss": 0.1787,
|
| 3619 |
+
"step": 595
|
| 3620 |
+
},
|
| 3621 |
+
{
|
| 3622 |
+
"epoch": 0.79,
|
| 3623 |
+
"learning_rate": 1.0985207446461221e-05,
|
| 3624 |
+
"loss": 0.1805,
|
| 3625 |
+
"step": 596
|
| 3626 |
+
},
|
| 3627 |
+
{
|
| 3628 |
+
"epoch": 0.79,
|
| 3629 |
+
"learning_rate": 1.0850994816146858e-05,
|
| 3630 |
+
"loss": 0.1797,
|
| 3631 |
+
"step": 597
|
| 3632 |
+
},
|
| 3633 |
+
{
|
| 3634 |
+
"epoch": 0.79,
|
| 3635 |
+
"learning_rate": 1.0717507246064273e-05,
|
| 3636 |
+
"loss": 0.1815,
|
| 3637 |
+
"step": 598
|
| 3638 |
+
},
|
| 3639 |
+
{
|
| 3640 |
+
"epoch": 0.8,
|
| 3641 |
+
"learning_rate": 1.0584747208473739e-05,
|
| 3642 |
+
"loss": 0.1799,
|
| 3643 |
+
"step": 599
|
| 3644 |
+
},
|
| 3645 |
+
{
|
| 3646 |
+
"epoch": 0.8,
|
| 3647 |
+
"learning_rate": 1.0452717162161141e-05,
|
| 3648 |
+
"loss": 0.1798,
|
| 3649 |
+
"step": 600
|
| 3650 |
+
},
|
| 3651 |
+
{
|
| 3652 |
+
"epoch": 0.8,
|
| 3653 |
+
"eval_loss": 0.1740500032901764,
|
| 3654 |
+
"eval_runtime": 12.3559,
|
| 3655 |
+
"eval_samples_per_second": 161.866,
|
| 3656 |
+
"eval_steps_per_second": 0.647,
|
| 3657 |
+
"step": 600
|
| 3658 |
+
},
|
| 3659 |
+
{
|
| 3660 |
+
"epoch": 0.8,
|
| 3661 |
+
"learning_rate": 1.0321419552392636e-05,
|
| 3662 |
+
"loss": 0.1745,
|
| 3663 |
+
"step": 601
|
| 3664 |
+
},
|
| 3665 |
+
{
|
| 3666 |
+
"epoch": 0.8,
|
| 3667 |
+
"learning_rate": 1.0190856810869215e-05,
|
| 3668 |
+
"loss": 0.1753,
|
| 3669 |
+
"step": 602
|
| 3670 |
+
},
|
| 3671 |
+
{
|
| 3672 |
+
"epoch": 0.8,
|
| 3673 |
+
"learning_rate": 1.0061031355681766e-05,
|
| 3674 |
+
"loss": 0.1838,
|
| 3675 |
+
"step": 603
|
| 3676 |
+
},
|
| 3677 |
+
{
|
| 3678 |
+
"epoch": 0.8,
|
| 3679 |
+
"learning_rate": 9.931945591266174e-06,
|
| 3680 |
+
"loss": 0.1854,
|
| 3681 |
+
"step": 604
|
| 3682 |
+
},
|
| 3683 |
+
{
|
| 3684 |
+
"epoch": 0.8,
|
| 3685 |
+
"learning_rate": 9.803601908358944e-06,
|
| 3686 |
+
"loss": 0.1819,
|
| 3687 |
+
"step": 605
|
| 3688 |
+
},
|
| 3689 |
+
{
|
| 3690 |
+
"epoch": 0.8,
|
| 3691 |
+
"learning_rate": 9.676002683952768e-06,
|
| 3692 |
+
"loss": 0.1781,
|
| 3693 |
+
"step": 606
|
| 3694 |
+
},
|
| 3695 |
+
{
|
| 3696 |
+
"epoch": 0.81,
|
| 3697 |
+
"learning_rate": 9.549150281252633e-06,
|
| 3698 |
+
"loss": 0.1789,
|
| 3699 |
+
"step": 607
|
| 3700 |
+
},
|
| 3701 |
+
{
|
| 3702 |
+
"epoch": 0.81,
|
| 3703 |
+
"learning_rate": 9.423047049631956e-06,
|
| 3704 |
+
"loss": 0.1802,
|
| 3705 |
+
"step": 608
|
| 3706 |
+
},
|
| 3707 |
+
{
|
| 3708 |
+
"epoch": 0.81,
|
| 3709 |
+
"learning_rate": 9.297695324589106e-06,
|
| 3710 |
+
"loss": 0.1771,
|
| 3711 |
+
"step": 609
|
| 3712 |
+
},
|
| 3713 |
+
{
|
| 3714 |
+
"epoch": 0.81,
|
| 3715 |
+
"learning_rate": 9.173097427704203e-06,
|
| 3716 |
+
"loss": 0.1806,
|
| 3717 |
+
"step": 610
|
| 3718 |
+
},
|
| 3719 |
+
{
|
| 3720 |
+
"epoch": 0.81,
|
| 3721 |
+
"learning_rate": 9.049255666596012e-06,
|
| 3722 |
+
"loss": 0.1805,
|
| 3723 |
+
"step": 611
|
| 3724 |
+
},
|
| 3725 |
+
{
|
| 3726 |
+
"epoch": 0.81,
|
| 3727 |
+
"learning_rate": 8.926172334879296e-06,
|
| 3728 |
+
"loss": 0.178,
|
| 3729 |
+
"step": 612
|
| 3730 |
+
},
|
| 3731 |
+
{
|
| 3732 |
+
"epoch": 0.81,
|
| 3733 |
+
"learning_rate": 8.803849712122292e-06,
|
| 3734 |
+
"loss": 0.1794,
|
| 3735 |
+
"step": 613
|
| 3736 |
+
},
|
| 3737 |
+
{
|
| 3738 |
+
"epoch": 0.82,
|
| 3739 |
+
"learning_rate": 8.682290063804526e-06,
|
| 3740 |
+
"loss": 0.1736,
|
| 3741 |
+
"step": 614
|
| 3742 |
+
},
|
| 3743 |
+
{
|
| 3744 |
+
"epoch": 0.82,
|
| 3745 |
+
"learning_rate": 8.561495641274825e-06,
|
| 3746 |
+
"loss": 0.1759,
|
| 3747 |
+
"step": 615
|
| 3748 |
+
},
|
| 3749 |
+
{
|
| 3750 |
+
"epoch": 0.82,
|
| 3751 |
+
"learning_rate": 8.441468681709602e-06,
|
| 3752 |
+
"loss": 0.1752,
|
| 3753 |
+
"step": 616
|
| 3754 |
+
},
|
| 3755 |
+
{
|
| 3756 |
+
"epoch": 0.82,
|
| 3757 |
+
"learning_rate": 8.322211408071512e-06,
|
| 3758 |
+
"loss": 0.181,
|
| 3759 |
+
"step": 617
|
| 3760 |
+
},
|
| 3761 |
+
{
|
| 3762 |
+
"epoch": 0.82,
|
| 3763 |
+
"learning_rate": 8.203726029068148e-06,
|
| 3764 |
+
"loss": 0.1796,
|
| 3765 |
+
"step": 618
|
| 3766 |
+
},
|
| 3767 |
+
{
|
| 3768 |
+
"epoch": 0.82,
|
| 3769 |
+
"learning_rate": 8.086014739111297e-06,
|
| 3770 |
+
"loss": 0.1765,
|
| 3771 |
+
"step": 619
|
| 3772 |
+
},
|
| 3773 |
+
{
|
| 3774 |
+
"epoch": 0.82,
|
| 3775 |
+
"learning_rate": 7.969079718276096e-06,
|
| 3776 |
+
"loss": 0.1818,
|
| 3777 |
+
"step": 620
|
| 3778 |
+
},
|
| 3779 |
+
{
|
| 3780 |
+
"epoch": 0.82,
|
| 3781 |
+
"learning_rate": 7.852923132260864e-06,
|
| 3782 |
+
"loss": 0.1747,
|
| 3783 |
+
"step": 621
|
| 3784 |
+
},
|
| 3785 |
+
{
|
| 3786 |
+
"epoch": 0.83,
|
| 3787 |
+
"learning_rate": 7.73754713234684e-06,
|
| 3788 |
+
"loss": 0.1779,
|
| 3789 |
+
"step": 622
|
| 3790 |
+
},
|
| 3791 |
+
{
|
| 3792 |
+
"epoch": 0.83,
|
| 3793 |
+
"learning_rate": 7.6229538553584556e-06,
|
| 3794 |
+
"loss": 0.1817,
|
| 3795 |
+
"step": 623
|
| 3796 |
+
},
|
| 3797 |
+
{
|
| 3798 |
+
"epoch": 0.83,
|
| 3799 |
+
"learning_rate": 7.509145423623609e-06,
|
| 3800 |
+
"loss": 0.1778,
|
| 3801 |
+
"step": 624
|
| 3802 |
+
},
|
| 3803 |
+
{
|
| 3804 |
+
"epoch": 0.83,
|
| 3805 |
+
"learning_rate": 7.3961239449345355e-06,
|
| 3806 |
+
"loss": 0.1847,
|
| 3807 |
+
"step": 625
|
| 3808 |
+
},
|
| 3809 |
+
{
|
| 3810 |
+
"epoch": 0.83,
|
| 3811 |
+
"learning_rate": 7.2838915125086504e-06,
|
| 3812 |
+
"loss": 0.1789,
|
| 3813 |
+
"step": 626
|
| 3814 |
+
},
|
| 3815 |
+
{
|
| 3816 |
+
"epoch": 0.83,
|
| 3817 |
+
"learning_rate": 7.172450204949821e-06,
|
| 3818 |
+
"loss": 0.1795,
|
| 3819 |
+
"step": 627
|
| 3820 |
+
},
|
| 3821 |
+
{
|
| 3822 |
+
"epoch": 0.83,
|
| 3823 |
+
"learning_rate": 7.061802086209857e-06,
|
| 3824 |
+
"loss": 0.1791,
|
| 3825 |
+
"step": 628
|
| 3826 |
+
},
|
| 3827 |
+
{
|
| 3828 |
+
"epoch": 0.84,
|
| 3829 |
+
"learning_rate": 6.951949205550284e-06,
|
| 3830 |
+
"loss": 0.1826,
|
| 3831 |
+
"step": 629
|
| 3832 |
+
},
|
| 3833 |
+
{
|
| 3834 |
+
"epoch": 0.84,
|
| 3835 |
+
"learning_rate": 6.842893597504435e-06,
|
| 3836 |
+
"loss": 0.177,
|
| 3837 |
+
"step": 630
|
| 3838 |
+
},
|
| 3839 |
+
{
|
| 3840 |
+
"epoch": 0.84,
|
| 3841 |
+
"learning_rate": 6.734637281839701e-06,
|
| 3842 |
+
"loss": 0.1802,
|
| 3843 |
+
"step": 631
|
| 3844 |
+
},
|
| 3845 |
+
{
|
| 3846 |
+
"epoch": 0.84,
|
| 3847 |
+
"learning_rate": 6.627182263520165e-06,
|
| 3848 |
+
"loss": 0.1785,
|
| 3849 |
+
"step": 632
|
| 3850 |
+
},
|
| 3851 |
+
{
|
| 3852 |
+
"epoch": 0.84,
|
| 3853 |
+
"learning_rate": 6.52053053266945e-06,
|
| 3854 |
+
"loss": 0.1793,
|
| 3855 |
+
"step": 633
|
| 3856 |
+
},
|
| 3857 |
+
{
|
| 3858 |
+
"epoch": 0.84,
|
| 3859 |
+
"learning_rate": 6.41468406453391e-06,
|
| 3860 |
+
"loss": 0.1798,
|
| 3861 |
+
"step": 634
|
| 3862 |
+
},
|
| 3863 |
+
{
|
| 3864 |
+
"epoch": 0.84,
|
| 3865 |
+
"learning_rate": 6.30964481944597e-06,
|
| 3866 |
+
"loss": 0.1783,
|
| 3867 |
+
"step": 635
|
| 3868 |
+
},
|
| 3869 |
+
{
|
| 3870 |
+
"epoch": 0.84,
|
| 3871 |
+
"learning_rate": 6.205414742787852e-06,
|
| 3872 |
+
"loss": 0.1783,
|
| 3873 |
+
"step": 636
|
| 3874 |
+
},
|
| 3875 |
+
{
|
| 3876 |
+
"epoch": 0.85,
|
| 3877 |
+
"learning_rate": 6.1019957649555985e-06,
|
| 3878 |
+
"loss": 0.1762,
|
| 3879 |
+
"step": 637
|
| 3880 |
+
},
|
| 3881 |
+
{
|
| 3882 |
+
"epoch": 0.85,
|
| 3883 |
+
"learning_rate": 5.999389801323219e-06,
|
| 3884 |
+
"loss": 0.1808,
|
| 3885 |
+
"step": 638
|
| 3886 |
+
},
|
| 3887 |
+
{
|
| 3888 |
+
"epoch": 0.85,
|
| 3889 |
+
"learning_rate": 5.897598752207328e-06,
|
| 3890 |
+
"loss": 0.1756,
|
| 3891 |
+
"step": 639
|
| 3892 |
+
},
|
| 3893 |
+
{
|
| 3894 |
+
"epoch": 0.85,
|
| 3895 |
+
"learning_rate": 5.796624502831821e-06,
|
| 3896 |
+
"loss": 0.1791,
|
| 3897 |
+
"step": 640
|
| 3898 |
+
},
|
| 3899 |
+
{
|
| 3900 |
+
"epoch": 0.85,
|
| 3901 |
+
"learning_rate": 5.696468923293108e-06,
|
| 3902 |
+
"loss": 0.1774,
|
| 3903 |
+
"step": 641
|
| 3904 |
+
},
|
| 3905 |
+
{
|
| 3906 |
+
"epoch": 0.85,
|
| 3907 |
+
"learning_rate": 5.59713386852534e-06,
|
| 3908 |
+
"loss": 0.1781,
|
| 3909 |
+
"step": 642
|
| 3910 |
+
},
|
| 3911 |
+
{
|
| 3912 |
+
"epoch": 0.85,
|
| 3913 |
+
"learning_rate": 5.498621178266167e-06,
|
| 3914 |
+
"loss": 0.1763,
|
| 3915 |
+
"step": 643
|
| 3916 |
+
},
|
| 3917 |
+
{
|
| 3918 |
+
"epoch": 0.86,
|
| 3919 |
+
"learning_rate": 5.40093267702258e-06,
|
| 3920 |
+
"loss": 0.1749,
|
| 3921 |
+
"step": 644
|
| 3922 |
+
},
|
| 3923 |
+
{
|
| 3924 |
+
"epoch": 0.86,
|
| 3925 |
+
"learning_rate": 5.304070174037146e-06,
|
| 3926 |
+
"loss": 0.1769,
|
| 3927 |
+
"step": 645
|
| 3928 |
+
},
|
| 3929 |
+
{
|
| 3930 |
+
"epoch": 0.86,
|
| 3931 |
+
"learning_rate": 5.208035463254557e-06,
|
| 3932 |
+
"loss": 0.1763,
|
| 3933 |
+
"step": 646
|
| 3934 |
+
},
|
| 3935 |
+
{
|
| 3936 |
+
"epoch": 0.86,
|
| 3937 |
+
"learning_rate": 5.112830323288314e-06,
|
| 3938 |
+
"loss": 0.1813,
|
| 3939 |
+
"step": 647
|
| 3940 |
+
},
|
| 3941 |
+
{
|
| 3942 |
+
"epoch": 0.86,
|
| 3943 |
+
"learning_rate": 5.018456517387837e-06,
|
| 3944 |
+
"loss": 0.1764,
|
| 3945 |
+
"step": 648
|
| 3946 |
+
},
|
| 3947 |
+
{
|
| 3948 |
+
"epoch": 0.86,
|
| 3949 |
+
"learning_rate": 4.924915793405799e-06,
|
| 3950 |
+
"loss": 0.1795,
|
| 3951 |
+
"step": 649
|
| 3952 |
+
},
|
| 3953 |
+
{
|
| 3954 |
+
"epoch": 0.86,
|
| 3955 |
+
"learning_rate": 4.832209883765782e-06,
|
| 3956 |
+
"loss": 0.1787,
|
| 3957 |
+
"step": 650
|
| 3958 |
+
},
|
| 3959 |
+
{
|
| 3960 |
+
"epoch": 0.86,
|
| 3961 |
+
"learning_rate": 4.74034050543013e-06,
|
| 3962 |
+
"loss": 0.1728,
|
| 3963 |
+
"step": 651
|
| 3964 |
+
},
|
| 3965 |
+
{
|
| 3966 |
+
"epoch": 0.87,
|
| 3967 |
+
"learning_rate": 4.649309359868209e-06,
|
| 3968 |
+
"loss": 0.1754,
|
| 3969 |
+
"step": 652
|
| 3970 |
+
},
|
| 3971 |
+
{
|
| 3972 |
+
"epoch": 0.87,
|
| 3973 |
+
"learning_rate": 4.559118133024853e-06,
|
| 3974 |
+
"loss": 0.1747,
|
| 3975 |
+
"step": 653
|
| 3976 |
+
},
|
| 3977 |
+
{
|
| 3978 |
+
"epoch": 0.87,
|
| 3979 |
+
"learning_rate": 4.4697684952891895e-06,
|
| 3980 |
+
"loss": 0.1775,
|
| 3981 |
+
"step": 654
|
| 3982 |
+
},
|
| 3983 |
+
{
|
| 3984 |
+
"epoch": 0.87,
|
| 3985 |
+
"learning_rate": 4.38126210146364e-06,
|
| 3986 |
+
"loss": 0.1758,
|
| 3987 |
+
"step": 655
|
| 3988 |
+
},
|
| 3989 |
+
{
|
| 3990 |
+
"epoch": 0.87,
|
| 3991 |
+
"learning_rate": 4.29360059073331e-06,
|
| 3992 |
+
"loss": 0.182,
|
| 3993 |
+
"step": 656
|
| 3994 |
+
},
|
| 3995 |
+
{
|
| 3996 |
+
"epoch": 0.87,
|
| 3997 |
+
"learning_rate": 4.2067855866356475e-06,
|
| 3998 |
+
"loss": 0.1763,
|
| 3999 |
+
"step": 657
|
| 4000 |
+
},
|
| 4001 |
+
{
|
| 4002 |
+
"epoch": 0.87,
|
| 4003 |
+
"learning_rate": 4.12081869703031e-06,
|
| 4004 |
+
"loss": 0.1756,
|
| 4005 |
+
"step": 658
|
| 4006 |
+
},
|
| 4007 |
+
{
|
| 4008 |
+
"epoch": 0.88,
|
| 4009 |
+
"learning_rate": 4.035701514069484e-06,
|
| 4010 |
+
"loss": 0.1768,
|
| 4011 |
+
"step": 659
|
| 4012 |
+
},
|
| 4013 |
+
{
|
| 4014 |
+
"epoch": 0.88,
|
| 4015 |
+
"learning_rate": 3.951435614168275e-06,
|
| 4016 |
+
"loss": 0.18,
|
| 4017 |
+
"step": 660
|
| 4018 |
+
},
|
| 4019 |
+
{
|
| 4020 |
+
"epoch": 0.88,
|
| 4021 |
+
"learning_rate": 3.868022557975626e-06,
|
| 4022 |
+
"loss": 0.1781,
|
| 4023 |
+
"step": 661
|
| 4024 |
+
},
|
| 4025 |
+
{
|
| 4026 |
+
"epoch": 0.88,
|
| 4027 |
+
"learning_rate": 3.7854638903453367e-06,
|
| 4028 |
+
"loss": 0.178,
|
| 4029 |
+
"step": 662
|
| 4030 |
+
},
|
| 4031 |
+
{
|
| 4032 |
+
"epoch": 0.88,
|
| 4033 |
+
"learning_rate": 3.70376114030751e-06,
|
| 4034 |
+
"loss": 0.1777,
|
| 4035 |
+
"step": 663
|
| 4036 |
+
},
|
| 4037 |
+
{
|
| 4038 |
+
"epoch": 0.88,
|
| 4039 |
+
"learning_rate": 3.6229158210401737e-06,
|
| 4040 |
+
"loss": 0.1773,
|
| 4041 |
+
"step": 664
|
| 4042 |
+
},
|
| 4043 |
+
{
|
| 4044 |
+
"epoch": 0.88,
|
| 4045 |
+
"learning_rate": 3.5429294298412853e-06,
|
| 4046 |
+
"loss": 0.1762,
|
| 4047 |
+
"step": 665
|
| 4048 |
+
},
|
| 4049 |
+
{
|
| 4050 |
+
"epoch": 0.88,
|
| 4051 |
+
"learning_rate": 3.463803448101033e-06,
|
| 4052 |
+
"loss": 0.179,
|
| 4053 |
+
"step": 666
|
| 4054 |
+
},
|
| 4055 |
+
{
|
| 4056 |
+
"epoch": 0.89,
|
| 4057 |
+
"learning_rate": 3.3855393412743352e-06,
|
| 4058 |
+
"loss": 0.1788,
|
| 4059 |
+
"step": 667
|
| 4060 |
+
},
|
| 4061 |
+
{
|
| 4062 |
+
"epoch": 0.89,
|
| 4063 |
+
"learning_rate": 3.308138558853746e-06,
|
| 4064 |
+
"loss": 0.1796,
|
| 4065 |
+
"step": 668
|
| 4066 |
+
},
|
| 4067 |
+
{
|
| 4068 |
+
"epoch": 0.89,
|
| 4069 |
+
"learning_rate": 3.231602534342587e-06,
|
| 4070 |
+
"loss": 0.1791,
|
| 4071 |
+
"step": 669
|
| 4072 |
+
},
|
| 4073 |
+
{
|
| 4074 |
+
"epoch": 0.89,
|
| 4075 |
+
"learning_rate": 3.15593268522843e-06,
|
| 4076 |
+
"loss": 0.1765,
|
| 4077 |
+
"step": 670
|
| 4078 |
+
},
|
| 4079 |
+
{
|
| 4080 |
+
"epoch": 0.89,
|
| 4081 |
+
"learning_rate": 3.081130412956795e-06,
|
| 4082 |
+
"loss": 0.1771,
|
| 4083 |
+
"step": 671
|
| 4084 |
+
},
|
| 4085 |
+
{
|
| 4086 |
+
"epoch": 0.89,
|
| 4087 |
+
"learning_rate": 3.0071971029052348e-06,
|
| 4088 |
+
"loss": 0.1765,
|
| 4089 |
+
"step": 672
|
| 4090 |
+
},
|
| 4091 |
+
{
|
| 4092 |
+
"epoch": 0.89,
|
| 4093 |
+
"learning_rate": 2.934134124357646e-06,
|
| 4094 |
+
"loss": 0.1746,
|
| 4095 |
+
"step": 673
|
| 4096 |
+
},
|
| 4097 |
+
{
|
| 4098 |
+
"epoch": 0.9,
|
| 4099 |
+
"learning_rate": 2.86194283047897e-06,
|
| 4100 |
+
"loss": 0.177,
|
| 4101 |
+
"step": 674
|
| 4102 |
+
},
|
| 4103 |
+
{
|
| 4104 |
+
"epoch": 0.9,
|
| 4105 |
+
"learning_rate": 2.7906245582900338e-06,
|
| 4106 |
+
"loss": 0.1771,
|
| 4107 |
+
"step": 675
|
| 4108 |
+
},
|
| 4109 |
+
{
|
| 4110 |
+
"epoch": 0.9,
|
| 4111 |
+
"learning_rate": 2.720180628642871e-06,
|
| 4112 |
+
"loss": 0.1756,
|
| 4113 |
+
"step": 676
|
| 4114 |
+
},
|
| 4115 |
+
{
|
| 4116 |
+
"epoch": 0.9,
|
| 4117 |
+
"learning_rate": 2.6506123461962408e-06,
|
| 4118 |
+
"loss": 0.1767,
|
| 4119 |
+
"step": 677
|
| 4120 |
+
},
|
| 4121 |
+
{
|
| 4122 |
+
"epoch": 0.9,
|
| 4123 |
+
"learning_rate": 2.5819209993914184e-06,
|
| 4124 |
+
"loss": 0.1774,
|
| 4125 |
+
"step": 678
|
| 4126 |
+
},
|
| 4127 |
+
{
|
| 4128 |
+
"epoch": 0.9,
|
| 4129 |
+
"learning_rate": 2.5141078604284105e-06,
|
| 4130 |
+
"loss": 0.1796,
|
| 4131 |
+
"step": 679
|
| 4132 |
+
},
|
| 4133 |
+
{
|
| 4134 |
+
"epoch": 0.9,
|
| 4135 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 4136 |
+
"loss": 0.1821,
|
| 4137 |
+
"step": 680
|
| 4138 |
+
},
|
| 4139 |
+
{
|
| 4140 |
+
"epoch": 0.9,
|
| 4141 |
+
"learning_rate": 2.381121213480131e-06,
|
| 4142 |
+
"loss": 0.1815,
|
| 4143 |
+
"step": 681
|
| 4144 |
+
},
|
| 4145 |
+
{
|
| 4146 |
+
"epoch": 0.91,
|
| 4147 |
+
"learning_rate": 2.3159501684777207e-06,
|
| 4148 |
+
"loss": 0.1796,
|
| 4149 |
+
"step": 682
|
| 4150 |
+
},
|
| 4151 |
+
{
|
| 4152 |
+
"epoch": 0.91,
|
| 4153 |
+
"learning_rate": 2.2516622572372414e-06,
|
| 4154 |
+
"loss": 0.1771,
|
| 4155 |
+
"step": 683
|
| 4156 |
+
},
|
| 4157 |
+
{
|
| 4158 |
+
"epoch": 0.91,
|
| 4159 |
+
"learning_rate": 2.188258670404719e-06,
|
| 4160 |
+
"loss": 0.1796,
|
| 4161 |
+
"step": 684
|
| 4162 |
+
},
|
| 4163 |
+
{
|
| 4164 |
+
"epoch": 0.91,
|
| 4165 |
+
"learning_rate": 2.125740582248037e-06,
|
| 4166 |
+
"loss": 0.1805,
|
| 4167 |
+
"step": 685
|
| 4168 |
+
},
|
| 4169 |
+
{
|
| 4170 |
+
"epoch": 0.91,
|
| 4171 |
+
"learning_rate": 2.0641091506351796e-06,
|
| 4172 |
+
"loss": 0.1793,
|
| 4173 |
+
"step": 686
|
| 4174 |
+
},
|
| 4175 |
+
{
|
| 4176 |
+
"epoch": 0.91,
|
| 4177 |
+
"learning_rate": 2.003365517012773e-06,
|
| 4178 |
+
"loss": 0.1804,
|
| 4179 |
+
"step": 687
|
| 4180 |
+
},
|
| 4181 |
+
{
|
| 4182 |
+
"epoch": 0.91,
|
| 4183 |
+
"learning_rate": 1.943510806384968e-06,
|
| 4184 |
+
"loss": 0.1777,
|
| 4185 |
+
"step": 688
|
| 4186 |
+
},
|
| 4187 |
+
{
|
| 4188 |
+
"epoch": 0.92,
|
| 4189 |
+
"learning_rate": 1.884546127292569e-06,
|
| 4190 |
+
"loss": 0.176,
|
| 4191 |
+
"step": 689
|
| 4192 |
+
},
|
| 4193 |
+
{
|
| 4194 |
+
"epoch": 0.92,
|
| 4195 |
+
"learning_rate": 1.8264725717925591e-06,
|
| 4196 |
+
"loss": 0.1745,
|
| 4197 |
+
"step": 690
|
| 4198 |
+
},
|
| 4199 |
+
{
|
| 4200 |
+
"epoch": 0.92,
|
| 4201 |
+
"learning_rate": 1.7692912154378294e-06,
|
| 4202 |
+
"loss": 0.1754,
|
| 4203 |
+
"step": 691
|
| 4204 |
+
},
|
| 4205 |
+
{
|
| 4206 |
+
"epoch": 0.92,
|
| 4207 |
+
"learning_rate": 1.7130031172572614e-06,
|
| 4208 |
+
"loss": 0.1777,
|
| 4209 |
+
"step": 692
|
| 4210 |
+
},
|
| 4211 |
+
{
|
| 4212 |
+
"epoch": 0.92,
|
| 4213 |
+
"learning_rate": 1.6576093197361253e-06,
|
| 4214 |
+
"loss": 0.1799,
|
| 4215 |
+
"step": 693
|
| 4216 |
+
},
|
| 4217 |
+
{
|
| 4218 |
+
"epoch": 0.92,
|
| 4219 |
+
"learning_rate": 1.603110848796785e-06,
|
| 4220 |
+
"loss": 0.1751,
|
| 4221 |
+
"step": 694
|
| 4222 |
+
},
|
| 4223 |
+
{
|
| 4224 |
+
"epoch": 0.92,
|
| 4225 |
+
"learning_rate": 1.549508713779696e-06,
|
| 4226 |
+
"loss": 0.1756,
|
| 4227 |
+
"step": 695
|
| 4228 |
+
},
|
| 4229 |
+
{
|
| 4230 |
+
"epoch": 0.92,
|
| 4231 |
+
"learning_rate": 1.4968039074246486e-06,
|
| 4232 |
+
"loss": 0.1772,
|
| 4233 |
+
"step": 696
|
| 4234 |
+
},
|
| 4235 |
+
{
|
| 4236 |
+
"epoch": 0.93,
|
| 4237 |
+
"learning_rate": 1.444997405852483e-06,
|
| 4238 |
+
"loss": 0.1752,
|
| 4239 |
+
"step": 697
|
| 4240 |
+
},
|
| 4241 |
+
{
|
| 4242 |
+
"epoch": 0.93,
|
| 4243 |
+
"learning_rate": 1.3940901685469298e-06,
|
| 4244 |
+
"loss": 0.181,
|
| 4245 |
+
"step": 698
|
| 4246 |
+
},
|
| 4247 |
+
{
|
| 4248 |
+
"epoch": 0.93,
|
| 4249 |
+
"learning_rate": 1.3440831383369046e-06,
|
| 4250 |
+
"loss": 0.1781,
|
| 4251 |
+
"step": 699
|
| 4252 |
+
},
|
| 4253 |
+
{
|
| 4254 |
+
"epoch": 0.93,
|
| 4255 |
+
"learning_rate": 1.294977241378975e-06,
|
| 4256 |
+
"loss": 0.1766,
|
| 4257 |
+
"step": 700
|
| 4258 |
+
},
|
| 4259 |
+
{
|
| 4260 |
+
"epoch": 0.93,
|
| 4261 |
+
"eval_loss": 0.1736355423927307,
|
| 4262 |
+
"eval_runtime": 12.0759,
|
| 4263 |
+
"eval_samples_per_second": 165.62,
|
| 4264 |
+
"eval_steps_per_second": 0.662,
|
| 4265 |
+
"step": 700
|
| 4266 |
+
},
|
| 4267 |
+
{
|
| 4268 |
+
"epoch": 0.93,
|
| 4269 |
+
"learning_rate": 1.2467733871402655e-06,
|
| 4270 |
+
"loss": 0.1771,
|
| 4271 |
+
"step": 701
|
| 4272 |
+
},
|
| 4273 |
+
{
|
| 4274 |
+
"epoch": 0.93,
|
| 4275 |
+
"learning_rate": 1.199472468381585e-06,
|
| 4276 |
+
"loss": 0.1788,
|
| 4277 |
+
"step": 702
|
| 4278 |
+
},
|
| 4279 |
+
{
|
| 4280 |
+
"epoch": 0.93,
|
| 4281 |
+
"learning_rate": 1.153075361140915e-06,
|
| 4282 |
+
"loss": 0.1777,
|
| 4283 |
+
"step": 703
|
| 4284 |
+
},
|
| 4285 |
+
{
|
| 4286 |
+
"epoch": 0.93,
|
| 4287 |
+
"learning_rate": 1.1075829247171598e-06,
|
| 4288 |
+
"loss": 0.1747,
|
| 4289 |
+
"step": 704
|
| 4290 |
+
},
|
| 4291 |
+
{
|
| 4292 |
+
"epoch": 0.94,
|
| 4293 |
+
"learning_rate": 1.0629960016542373e-06,
|
| 4294 |
+
"loss": 0.1772,
|
| 4295 |
+
"step": 705
|
| 4296 |
+
},
|
| 4297 |
+
{
|
| 4298 |
+
"epoch": 0.94,
|
| 4299 |
+
"learning_rate": 1.0193154177254971e-06,
|
| 4300 |
+
"loss": 0.1758,
|
| 4301 |
+
"step": 706
|
| 4302 |
+
},
|
| 4303 |
+
{
|
| 4304 |
+
"epoch": 0.94,
|
| 4305 |
+
"learning_rate": 9.765419819183997e-07,
|
| 4306 |
+
"loss": 0.1785,
|
| 4307 |
+
"step": 707
|
| 4308 |
+
},
|
| 4309 |
+
{
|
| 4310 |
+
"epoch": 0.94,
|
| 4311 |
+
"learning_rate": 9.346764864195335e-07,
|
| 4312 |
+
"loss": 0.1782,
|
| 4313 |
+
"step": 708
|
| 4314 |
+
},
|
| 4315 |
+
{
|
| 4316 |
+
"epoch": 0.94,
|
| 4317 |
+
"learning_rate": 8.937197065999714e-07,
|
| 4318 |
+
"loss": 0.1784,
|
| 4319 |
+
"step": 709
|
| 4320 |
+
},
|
| 4321 |
+
{
|
| 4322 |
+
"epoch": 0.94,
|
| 4323 |
+
"learning_rate": 8.536724010008878e-07,
|
| 4324 |
+
"loss": 0.178,
|
| 4325 |
+
"step": 710
|
| 4326 |
+
},
|
| 4327 |
+
{
|
| 4328 |
+
"epoch": 0.94,
|
| 4329 |
+
"learning_rate": 8.145353113195142e-07,
|
| 4330 |
+
"loss": 0.1757,
|
| 4331 |
+
"step": 711
|
| 4332 |
+
},
|
| 4333 |
+
{
|
| 4334 |
+
"epoch": 0.95,
|
| 4335 |
+
"learning_rate": 7.763091623953889e-07,
|
| 4336 |
+
"loss": 0.1776,
|
| 4337 |
+
"step": 712
|
| 4338 |
+
},
|
| 4339 |
+
{
|
| 4340 |
+
"epoch": 0.95,
|
| 4341 |
+
"learning_rate": 7.389946621969679e-07,
|
| 4342 |
+
"loss": 0.176,
|
| 4343 |
+
"step": 713
|
| 4344 |
+
},
|
| 4345 |
+
{
|
| 4346 |
+
"epoch": 0.95,
|
| 4347 |
+
"learning_rate": 7.0259250180848e-07,
|
| 4348 |
+
"loss": 0.1766,
|
| 4349 |
+
"step": 714
|
| 4350 |
+
},
|
| 4351 |
+
{
|
| 4352 |
+
"epoch": 0.95,
|
| 4353 |
+
"learning_rate": 6.67103355417148e-07,
|
| 4354 |
+
"loss": 0.1761,
|
| 4355 |
+
"step": 715
|
| 4356 |
+
},
|
| 4357 |
+
{
|
| 4358 |
+
"epoch": 0.95,
|
| 4359 |
+
"learning_rate": 6.325278803006818e-07,
|
| 4360 |
+
"loss": 0.1734,
|
| 4361 |
+
"step": 716
|
| 4362 |
+
},
|
| 4363 |
+
{
|
| 4364 |
+
"epoch": 0.95,
|
| 4365 |
+
"learning_rate": 5.988667168151219e-07,
|
| 4366 |
+
"loss": 0.1789,
|
| 4367 |
+
"step": 717
|
| 4368 |
+
},
|
| 4369 |
+
{
|
| 4370 |
+
"epoch": 0.95,
|
| 4371 |
+
"learning_rate": 5.661204883829763e-07,
|
| 4372 |
+
"loss": 0.1748,
|
| 4373 |
+
"step": 718
|
| 4374 |
+
},
|
| 4375 |
+
{
|
| 4376 |
+
"epoch": 0.95,
|
| 4377 |
+
"learning_rate": 5.342898014816855e-07,
|
| 4378 |
+
"loss": 0.1772,
|
| 4379 |
+
"step": 719
|
| 4380 |
+
},
|
| 4381 |
+
{
|
| 4382 |
+
"epoch": 0.96,
|
| 4383 |
+
"learning_rate": 5.033752456323482e-07,
|
| 4384 |
+
"loss": 0.1772,
|
| 4385 |
+
"step": 720
|
| 4386 |
+
},
|
| 4387 |
+
{
|
| 4388 |
+
"epoch": 0.96,
|
| 4389 |
+
"learning_rate": 4.73377393388863e-07,
|
| 4390 |
+
"loss": 0.1761,
|
| 4391 |
+
"step": 721
|
| 4392 |
+
},
|
| 4393 |
+
{
|
| 4394 |
+
"epoch": 0.96,
|
| 4395 |
+
"learning_rate": 4.4429680032726517e-07,
|
| 4396 |
+
"loss": 0.1796,
|
| 4397 |
+
"step": 722
|
| 4398 |
+
},
|
| 4399 |
+
{
|
| 4400 |
+
"epoch": 0.96,
|
| 4401 |
+
"learning_rate": 4.1613400503550114e-07,
|
| 4402 |
+
"loss": 0.1789,
|
| 4403 |
+
"step": 723
|
| 4404 |
+
},
|
| 4405 |
+
{
|
| 4406 |
+
"epoch": 0.96,
|
| 4407 |
+
"learning_rate": 3.888895291033867e-07,
|
| 4408 |
+
"loss": 0.1789,
|
| 4409 |
+
"step": 724
|
| 4410 |
+
},
|
| 4411 |
+
{
|
| 4412 |
+
"epoch": 0.96,
|
| 4413 |
+
"learning_rate": 3.6256387711299247e-07,
|
| 4414 |
+
"loss": 0.179,
|
| 4415 |
+
"step": 725
|
| 4416 |
+
},
|
| 4417 |
+
{
|
| 4418 |
+
"epoch": 0.96,
|
| 4419 |
+
"learning_rate": 3.371575366292845e-07,
|
| 4420 |
+
"loss": 0.1768,
|
| 4421 |
+
"step": 726
|
| 4422 |
+
},
|
| 4423 |
+
{
|
| 4424 |
+
"epoch": 0.97,
|
| 4425 |
+
"learning_rate": 3.126709781910986e-07,
|
| 4426 |
+
"loss": 0.1772,
|
| 4427 |
+
"step": 727
|
| 4428 |
+
},
|
| 4429 |
+
{
|
| 4430 |
+
"epoch": 0.97,
|
| 4431 |
+
"learning_rate": 2.8910465530240793e-07,
|
| 4432 |
+
"loss": 0.1805,
|
| 4433 |
+
"step": 728
|
| 4434 |
+
},
|
| 4435 |
+
{
|
| 4436 |
+
"epoch": 0.97,
|
| 4437 |
+
"learning_rate": 2.6645900442394677e-07,
|
| 4438 |
+
"loss": 0.1769,
|
| 4439 |
+
"step": 729
|
| 4440 |
+
},
|
| 4441 |
+
{
|
| 4442 |
+
"epoch": 0.97,
|
| 4443 |
+
"learning_rate": 2.4473444496512233e-07,
|
| 4444 |
+
"loss": 0.1796,
|
| 4445 |
+
"step": 730
|
| 4446 |
+
},
|
| 4447 |
+
{
|
| 4448 |
+
"epoch": 0.97,
|
| 4449 |
+
"learning_rate": 2.2393137927623763e-07,
|
| 4450 |
+
"loss": 0.1773,
|
| 4451 |
+
"step": 731
|
| 4452 |
+
},
|
| 4453 |
+
{
|
| 4454 |
+
"epoch": 0.97,
|
| 4455 |
+
"learning_rate": 2.0405019264104762e-07,
|
| 4456 |
+
"loss": 0.1774,
|
| 4457 |
+
"step": 732
|
| 4458 |
+
},
|
| 4459 |
+
{
|
| 4460 |
+
"epoch": 0.97,
|
| 4461 |
+
"learning_rate": 1.850912532696092e-07,
|
| 4462 |
+
"loss": 0.1786,
|
| 4463 |
+
"step": 733
|
| 4464 |
+
},
|
| 4465 |
+
{
|
| 4466 |
+
"epoch": 0.97,
|
| 4467 |
+
"learning_rate": 1.6705491229149218e-07,
|
| 4468 |
+
"loss": 0.1756,
|
| 4469 |
+
"step": 734
|
| 4470 |
+
},
|
| 4471 |
+
{
|
| 4472 |
+
"epoch": 0.98,
|
| 4473 |
+
"learning_rate": 1.4994150374924575e-07,
|
| 4474 |
+
"loss": 0.1771,
|
| 4475 |
+
"step": 735
|
| 4476 |
+
},
|
| 4477 |
+
{
|
| 4478 |
+
"epoch": 0.98,
|
| 4479 |
+
"learning_rate": 1.337513445922256e-07,
|
| 4480 |
+
"loss": 0.1763,
|
| 4481 |
+
"step": 736
|
| 4482 |
+
},
|
| 4483 |
+
{
|
| 4484 |
+
"epoch": 0.98,
|
| 4485 |
+
"learning_rate": 1.184847346707152e-07,
|
| 4486 |
+
"loss": 0.1767,
|
| 4487 |
+
"step": 737
|
| 4488 |
+
},
|
| 4489 |
+
{
|
| 4490 |
+
"epoch": 0.98,
|
| 4491 |
+
"learning_rate": 1.041419567303914e-07,
|
| 4492 |
+
"loss": 0.173,
|
| 4493 |
+
"step": 738
|
| 4494 |
+
},
|
| 4495 |
+
{
|
| 4496 |
+
"epoch": 0.98,
|
| 4497 |
+
"learning_rate": 9.072327640706756e-08,
|
| 4498 |
+
"loss": 0.1774,
|
| 4499 |
+
"step": 739
|
| 4500 |
+
},
|
| 4501 |
+
{
|
| 4502 |
+
"epoch": 0.98,
|
| 4503 |
+
"learning_rate": 7.822894222178633e-08,
|
| 4504 |
+
"loss": 0.1801,
|
| 4505 |
+
"step": 740
|
| 4506 |
+
},
|
| 4507 |
+
{
|
| 4508 |
+
"epoch": 0.98,
|
| 4509 |
+
"learning_rate": 6.665918557620665e-08,
|
| 4510 |
+
"loss": 0.1772,
|
| 4511 |
+
"step": 741
|
| 4512 |
+
},
|
| 4513 |
+
{
|
| 4514 |
+
"epoch": 0.99,
|
| 4515 |
+
"learning_rate": 5.6014220748318303e-08,
|
| 4516 |
+
"loss": 0.1734,
|
| 4517 |
+
"step": 742
|
| 4518 |
+
},
|
| 4519 |
+
{
|
| 4520 |
+
"epoch": 0.99,
|
| 4521 |
+
"learning_rate": 4.6294244888500645e-08,
|
| 4522 |
+
"loss": 0.1778,
|
| 4523 |
+
"step": 743
|
| 4524 |
+
},
|
| 4525 |
+
{
|
| 4526 |
+
"epoch": 0.99,
|
| 4527 |
+
"learning_rate": 3.749943801582556e-08,
|
| 4528 |
+
"loss": 0.1755,
|
| 4529 |
+
"step": 744
|
| 4530 |
+
},
|
| 4531 |
+
{
|
| 4532 |
+
"epoch": 0.99,
|
| 4533 |
+
"learning_rate": 2.9629963014760065e-08,
|
| 4534 |
+
"loss": 0.1782,
|
| 4535 |
+
"step": 745
|
| 4536 |
+
},
|
| 4537 |
+
{
|
| 4538 |
+
"epoch": 0.99,
|
| 4539 |
+
"learning_rate": 2.2685965632135432e-08,
|
| 4540 |
+
"loss": 0.1765,
|
| 4541 |
+
"step": 746
|
| 4542 |
+
},
|
| 4543 |
+
{
|
| 4544 |
+
"epoch": 0.99,
|
| 4545 |
+
"learning_rate": 1.666757447443823e-08,
|
| 4546 |
+
"loss": 0.1809,
|
| 4547 |
+
"step": 747
|
| 4548 |
+
},
|
| 4549 |
+
{
|
| 4550 |
+
"epoch": 0.99,
|
| 4551 |
+
"learning_rate": 1.1574901005456662e-08,
|
| 4552 |
+
"loss": 0.1772,
|
| 4553 |
+
"step": 748
|
| 4554 |
+
},
|
| 4555 |
+
{
|
| 4556 |
+
"epoch": 0.99,
|
| 4557 |
+
"learning_rate": 7.4080395441877834e-09,
|
| 4558 |
+
"loss": 0.175,
|
| 4559 |
+
"step": 749
|
| 4560 |
+
},
|
| 4561 |
+
{
|
| 4562 |
+
"epoch": 1.0,
|
| 4563 |
+
"learning_rate": 4.167067263105562e-09,
|
| 4564 |
+
"loss": 0.176,
|
| 4565 |
+
"step": 750
|
| 4566 |
+
},
|
| 4567 |
+
{
|
| 4568 |
+
"epoch": 1.0,
|
| 4569 |
+
"learning_rate": 1.8520441867231341e-09,
|
| 4570 |
+
"loss": 0.1788,
|
| 4571 |
+
"step": 751
|
| 4572 |
+
},
|
| 4573 |
+
{
|
| 4574 |
+
"epoch": 1.0,
|
| 4575 |
+
"learning_rate": 4.630131904936885e-10,
|
| 4576 |
+
"loss": 0.1729,
|
| 4577 |
+
"step": 752
|
| 4578 |
+
},
|
| 4579 |
+
{
|
| 4580 |
+
"epoch": 1.0,
|
| 4581 |
+
"learning_rate": 0.0,
|
| 4582 |
+
"loss": 0.1755,
|
| 4583 |
+
"step": 753
|
| 4584 |
+
},
|
| 4585 |
+
{
|
| 4586 |
+
"epoch": 1.0,
|
| 4587 |
+
"step": 753,
|
| 4588 |
+
"total_flos": 0.0,
|
| 4589 |
+
"train_loss": 0.10856808526107514,
|
| 4590 |
+
"train_runtime": 9051.9774,
|
| 4591 |
+
"train_samples_per_second": 85.227,
|
| 4592 |
+
"train_steps_per_second": 0.083
|
| 4593 |
+
}
|
| 4594 |
+
],
|
| 4595 |
+
"logging_steps": 1.0,
|
| 4596 |
+
"max_steps": 753,
|
| 4597 |
+
"num_input_tokens_seen": 0,
|
| 4598 |
+
"num_train_epochs": 1,
|
| 4599 |
+
"save_steps": 100,
|
| 4600 |
+
"total_flos": 0.0,
|
| 4601 |
+
"train_batch_size": 8,
|
| 4602 |
+
"trial_name": null,
|
| 4603 |
+
"trial_params": null
|
| 4604 |
+
}
|
vision_tower/config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoints/vila-long-8b-8f-pure-nav-8nodes/vision_tower",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SiglipVisionModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 8 |
+
"hidden_size": 1152,
|
| 9 |
+
"image_size": 384,
|
| 10 |
+
"intermediate_size": 4304,
|
| 11 |
+
"layer_norm_eps": 1e-06,
|
| 12 |
+
"llm_depth_token_id": 128258,
|
| 13 |
+
"llm_mask_token_id": 128257,
|
| 14 |
+
"model_type": "siglip_vision_model",
|
| 15 |
+
"num_attention_heads": 16,
|
| 16 |
+
"num_channels": 3,
|
| 17 |
+
"num_hidden_layers": 27,
|
| 18 |
+
"patch_size": 14,
|
| 19 |
+
"torch_dtype": "bfloat16",
|
| 20 |
+
"transformers_version": "4.37.2"
|
| 21 |
+
}
|
vision_tower/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bfe44ac453e19d774b34b91afc39af3ada7325c91c0b05c51705afa7d3df51b
|
| 3 |
+
size 856506120
|
vision_tower/preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "SiglipImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"processor_class": "SiglipProcessor",
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 384,
|
| 21 |
+
"width": 384
|
| 22 |
+
}
|
| 23 |
+
}
|