Upload folder using huggingface_hub
Browse files- config.json +192 -0
- preprocessor_config.json +20 -0
- pytorch_model-00001-of-00004.bin +3 -0
- pytorch_model-00002-of-00004.bin +3 -0
- pytorch_model-00003-of-00004.bin +3 -0
- pytorch_model-00004-of-00004.bin +3 -0
- pytorch_model.bin.index.json +869 -0
- runs/Feb19_22-26-01_n213-017-078/events.out.tfevents.1708352856.n213-017-078.4939.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- trainer_state.json +1410 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "q-future/one-align",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MPLUGOwl2LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "q-future/one-align--configuration_mplug_owl2.MPLUGOwl2Config",
|
| 10 |
+
"AutoModel": "q-future/one-align--modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM",
|
| 11 |
+
"AutoModelForCausalLM": "q-future/one-align--modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM"
|
| 12 |
+
},
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"freeze_vision_model": false,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 4096,
|
| 18 |
+
"image_aspect_ratio": "resize",
|
| 19 |
+
"image_grid_pinpoints": null,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 11008,
|
| 22 |
+
"max_position_embeddings": 2048,
|
| 23 |
+
"model_type": "mplug_owl2",
|
| 24 |
+
"num_attention_heads": 32,
|
| 25 |
+
"num_hidden_layers": 32,
|
| 26 |
+
"num_key_value_heads": 32,
|
| 27 |
+
"pretraining_tp": 1,
|
| 28 |
+
"rms_norm_eps": 1e-06,
|
| 29 |
+
"rope_scaling": null,
|
| 30 |
+
"rope_theta": 10000.0,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.36.2",
|
| 34 |
+
"tune_visual_abstractor": true,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"visual_abstractor_lr": null,
|
| 37 |
+
"visual_config": {
|
| 38 |
+
"visual_abstractor": {
|
| 39 |
+
"_name_or_path": "",
|
| 40 |
+
"add_cross_attention": false,
|
| 41 |
+
"architectures": null,
|
| 42 |
+
"attention_probs_dropout_prob": 0.0,
|
| 43 |
+
"bad_words_ids": null,
|
| 44 |
+
"begin_suppress_tokens": null,
|
| 45 |
+
"bos_token_id": null,
|
| 46 |
+
"chunk_size_feed_forward": 0,
|
| 47 |
+
"cross_attention_hidden_size": null,
|
| 48 |
+
"decoder_start_token_id": null,
|
| 49 |
+
"diversity_penalty": 0.0,
|
| 50 |
+
"do_sample": false,
|
| 51 |
+
"early_stopping": false,
|
| 52 |
+
"encoder_hidden_size": 1024,
|
| 53 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 54 |
+
"eos_token_id": null,
|
| 55 |
+
"exponential_decay_length_penalty": null,
|
| 56 |
+
"finetuning_task": null,
|
| 57 |
+
"forced_bos_token_id": null,
|
| 58 |
+
"forced_eos_token_id": null,
|
| 59 |
+
"grid_size": 32,
|
| 60 |
+
"hidden_size": 1024,
|
| 61 |
+
"id2label": {
|
| 62 |
+
"0": "LABEL_0",
|
| 63 |
+
"1": "LABEL_1"
|
| 64 |
+
},
|
| 65 |
+
"initializer_range": 0.02,
|
| 66 |
+
"intermediate_size": 2816,
|
| 67 |
+
"is_decoder": false,
|
| 68 |
+
"is_encoder_decoder": false,
|
| 69 |
+
"label2id": {
|
| 70 |
+
"LABEL_0": 0,
|
| 71 |
+
"LABEL_1": 1
|
| 72 |
+
},
|
| 73 |
+
"layer_norm_eps": 1e-06,
|
| 74 |
+
"length_penalty": 1.0,
|
| 75 |
+
"max_length": 20,
|
| 76 |
+
"min_length": 0,
|
| 77 |
+
"model_type": "mplug_owl_visual_abstract",
|
| 78 |
+
"no_repeat_ngram_size": 0,
|
| 79 |
+
"num_attention_heads": 16,
|
| 80 |
+
"num_beam_groups": 1,
|
| 81 |
+
"num_beams": 1,
|
| 82 |
+
"num_hidden_layers": 6,
|
| 83 |
+
"num_learnable_queries": 64,
|
| 84 |
+
"num_return_sequences": 1,
|
| 85 |
+
"output_attentions": false,
|
| 86 |
+
"output_hidden_states": false,
|
| 87 |
+
"output_scores": false,
|
| 88 |
+
"pad_token_id": null,
|
| 89 |
+
"prefix": null,
|
| 90 |
+
"problem_type": null,
|
| 91 |
+
"pruned_heads": {},
|
| 92 |
+
"remove_invalid_values": false,
|
| 93 |
+
"repetition_penalty": 1.0,
|
| 94 |
+
"return_dict": true,
|
| 95 |
+
"return_dict_in_generate": false,
|
| 96 |
+
"sep_token_id": null,
|
| 97 |
+
"suppress_tokens": null,
|
| 98 |
+
"task_specific_params": null,
|
| 99 |
+
"temperature": 1.0,
|
| 100 |
+
"tf_legacy_loss": false,
|
| 101 |
+
"tie_encoder_decoder": false,
|
| 102 |
+
"tie_word_embeddings": true,
|
| 103 |
+
"tokenizer_class": null,
|
| 104 |
+
"top_k": 50,
|
| 105 |
+
"top_p": 1.0,
|
| 106 |
+
"torch_dtype": null,
|
| 107 |
+
"torchscript": false,
|
| 108 |
+
"transformers_version": "4.28.1",
|
| 109 |
+
"typical_p": 1.0,
|
| 110 |
+
"use_bfloat16": false
|
| 111 |
+
},
|
| 112 |
+
"visual_model": {
|
| 113 |
+
"_name_or_path": "",
|
| 114 |
+
"add_cross_attention": false,
|
| 115 |
+
"architectures": null,
|
| 116 |
+
"attention_dropout": 0.0,
|
| 117 |
+
"bad_words_ids": null,
|
| 118 |
+
"begin_suppress_tokens": null,
|
| 119 |
+
"bos_token_id": null,
|
| 120 |
+
"chunk_size_feed_forward": 0,
|
| 121 |
+
"cross_attention_hidden_size": null,
|
| 122 |
+
"decoder_start_token_id": null,
|
| 123 |
+
"diversity_penalty": 0.0,
|
| 124 |
+
"do_sample": false,
|
| 125 |
+
"early_stopping": false,
|
| 126 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 127 |
+
"eos_token_id": null,
|
| 128 |
+
"exponential_decay_length_penalty": null,
|
| 129 |
+
"finetuning_task": null,
|
| 130 |
+
"forced_bos_token_id": null,
|
| 131 |
+
"forced_eos_token_id": null,
|
| 132 |
+
"hidden_act": "quick_gelu",
|
| 133 |
+
"hidden_size": 1024,
|
| 134 |
+
"id2label": {
|
| 135 |
+
"0": "LABEL_0",
|
| 136 |
+
"1": "LABEL_1"
|
| 137 |
+
},
|
| 138 |
+
"image_size": 448,
|
| 139 |
+
"initializer_factor": 1.0,
|
| 140 |
+
"initializer_range": 0.02,
|
| 141 |
+
"intermediate_size": 4096,
|
| 142 |
+
"is_decoder": false,
|
| 143 |
+
"is_encoder_decoder": false,
|
| 144 |
+
"label2id": {
|
| 145 |
+
"LABEL_0": 0,
|
| 146 |
+
"LABEL_1": 1
|
| 147 |
+
},
|
| 148 |
+
"layer_norm_eps": 1e-06,
|
| 149 |
+
"length_penalty": 1.0,
|
| 150 |
+
"max_length": 20,
|
| 151 |
+
"min_length": 0,
|
| 152 |
+
"model_type": "mplug_owl_vision_model",
|
| 153 |
+
"no_repeat_ngram_size": 0,
|
| 154 |
+
"num_attention_heads": 16,
|
| 155 |
+
"num_beam_groups": 1,
|
| 156 |
+
"num_beams": 1,
|
| 157 |
+
"num_channels": 3,
|
| 158 |
+
"num_hidden_layers": 24,
|
| 159 |
+
"num_return_sequences": 1,
|
| 160 |
+
"output_attentions": false,
|
| 161 |
+
"output_hidden_states": false,
|
| 162 |
+
"output_scores": false,
|
| 163 |
+
"pad_token_id": null,
|
| 164 |
+
"patch_size": 14,
|
| 165 |
+
"prefix": null,
|
| 166 |
+
"problem_type": null,
|
| 167 |
+
"projection_dim": 768,
|
| 168 |
+
"pruned_heads": {},
|
| 169 |
+
"remove_invalid_values": false,
|
| 170 |
+
"repetition_penalty": 1.0,
|
| 171 |
+
"return_dict": true,
|
| 172 |
+
"return_dict_in_generate": false,
|
| 173 |
+
"sep_token_id": null,
|
| 174 |
+
"suppress_tokens": null,
|
| 175 |
+
"task_specific_params": null,
|
| 176 |
+
"temperature": 1.0,
|
| 177 |
+
"tf_legacy_loss": false,
|
| 178 |
+
"tie_encoder_decoder": false,
|
| 179 |
+
"tie_word_embeddings": true,
|
| 180 |
+
"tokenizer_class": null,
|
| 181 |
+
"top_k": 50,
|
| 182 |
+
"top_p": 1.0,
|
| 183 |
+
"torch_dtype": null,
|
| 184 |
+
"torchscript": false,
|
| 185 |
+
"transformers_version": "4.28.1",
|
| 186 |
+
"typical_p": 1.0,
|
| 187 |
+
"use_bfloat16": false,
|
| 188 |
+
"use_flash_attn": false
|
| 189 |
+
}
|
| 190 |
+
},
|
| 191 |
+
"vocab_size": 32000
|
| 192 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": 448,
|
| 3 |
+
"do_center_crop": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"size": 448
|
| 19 |
+
}
|
| 20 |
+
|
pytorch_model-00001-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4475602d5a8e1f4c23b6a609dfb90bb9d092ea4ff9103a38e994c9f4a46be308
|
| 3 |
+
size 4981108780
|
pytorch_model-00002-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85b9b7a9afe525a2290a743b044977d818fe56ee226e01aa0393333e83cd0c71
|
| 3 |
+
size 4920293259
|
pytorch_model-00003-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fa3c75f86025ba92d7f20b6d163a486238cc98b666d9567020073ee427135bd
|
| 3 |
+
size 4989532454
|
pytorch_model-00004-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10f3e6c9f711ff3ae90d0bffc5899977d8fe3d62022732051e802d84aa6544c5
|
| 3 |
+
size 1518469929
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,869 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16409100288
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 9 |
+
"model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 14 |
+
"model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 16 |
+
"model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 17 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 21 |
+
"model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 22 |
+
"model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 23 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 24 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 25 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 26 |
+
"model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 27 |
+
"model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 28 |
+
"model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 29 |
+
"model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 30 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 31 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 33 |
+
"model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 34 |
+
"model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 35 |
+
"model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 36 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 37 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 38 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 39 |
+
"model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 40 |
+
"model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 41 |
+
"model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 42 |
+
"model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 43 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 44 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 45 |
+
"model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 46 |
+
"model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 47 |
+
"model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 48 |
+
"model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 49 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 50 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 51 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 52 |
+
"model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 53 |
+
"model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 54 |
+
"model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 55 |
+
"model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 56 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 57 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 58 |
+
"model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 59 |
+
"model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 60 |
+
"model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 61 |
+
"model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 62 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 63 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 64 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 65 |
+
"model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 66 |
+
"model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 67 |
+
"model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 68 |
+
"model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 69 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 70 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 71 |
+
"model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 72 |
+
"model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 73 |
+
"model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 74 |
+
"model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 75 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 76 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 77 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 78 |
+
"model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 79 |
+
"model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 80 |
+
"model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 81 |
+
"model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 82 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 83 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 84 |
+
"model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 85 |
+
"model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 86 |
+
"model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 87 |
+
"model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 88 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 89 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 90 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 91 |
+
"model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 92 |
+
"model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 93 |
+
"model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 94 |
+
"model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 95 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 96 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 97 |
+
"model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 98 |
+
"model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 99 |
+
"model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 100 |
+
"model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 101 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 102 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 103 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 104 |
+
"model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 105 |
+
"model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 106 |
+
"model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 107 |
+
"model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 108 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 109 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 110 |
+
"model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 111 |
+
"model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 112 |
+
"model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 113 |
+
"model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 114 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 115 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 116 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 117 |
+
"model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 118 |
+
"model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 119 |
+
"model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 120 |
+
"model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 121 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 122 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 123 |
+
"model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 124 |
+
"model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 125 |
+
"model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 126 |
+
"model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 127 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 128 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 129 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 130 |
+
"model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 131 |
+
"model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 132 |
+
"model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 133 |
+
"model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 134 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 135 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 136 |
+
"model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 137 |
+
"model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 138 |
+
"model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 139 |
+
"model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 140 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 141 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 142 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 143 |
+
"model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 144 |
+
"model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 145 |
+
"model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 146 |
+
"model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 147 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 148 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 149 |
+
"model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 150 |
+
"model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 151 |
+
"model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 152 |
+
"model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 153 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 154 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 155 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 156 |
+
"model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 157 |
+
"model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 158 |
+
"model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 159 |
+
"model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 160 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 161 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 162 |
+
"model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 163 |
+
"model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 164 |
+
"model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 165 |
+
"model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 166 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 167 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 168 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 169 |
+
"model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 170 |
+
"model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 171 |
+
"model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 172 |
+
"model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 173 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 174 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 175 |
+
"model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 176 |
+
"model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 177 |
+
"model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 178 |
+
"model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 179 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 180 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 181 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 182 |
+
"model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 183 |
+
"model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 184 |
+
"model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 185 |
+
"model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 186 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 187 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 188 |
+
"model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 189 |
+
"model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 190 |
+
"model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 191 |
+
"model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 192 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 193 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 194 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 195 |
+
"model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 196 |
+
"model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 197 |
+
"model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 198 |
+
"model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 199 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 200 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 201 |
+
"model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 202 |
+
"model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 203 |
+
"model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 204 |
+
"model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 205 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 206 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 207 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 208 |
+
"model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 209 |
+
"model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 210 |
+
"model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 211 |
+
"model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 212 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 213 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 214 |
+
"model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 215 |
+
"model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 216 |
+
"model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 217 |
+
"model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 218 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 219 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 220 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 221 |
+
"model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 222 |
+
"model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 223 |
+
"model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 224 |
+
"model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 225 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 226 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 227 |
+
"model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 228 |
+
"model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 229 |
+
"model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 230 |
+
"model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 231 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 232 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 233 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 234 |
+
"model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 235 |
+
"model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 236 |
+
"model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 237 |
+
"model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 238 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 239 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 240 |
+
"model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 241 |
+
"model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 242 |
+
"model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 243 |
+
"model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 244 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 245 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 246 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 247 |
+
"model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 248 |
+
"model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 249 |
+
"model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 250 |
+
"model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 251 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 252 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 253 |
+
"model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 254 |
+
"model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 255 |
+
"model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 256 |
+
"model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 257 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 258 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 259 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 260 |
+
"model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 261 |
+
"model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 262 |
+
"model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 263 |
+
"model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 264 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 265 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 266 |
+
"model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 267 |
+
"model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 268 |
+
"model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 269 |
+
"model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 270 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 271 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 272 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 273 |
+
"model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 274 |
+
"model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 275 |
+
"model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 276 |
+
"model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 277 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 278 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 279 |
+
"model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 280 |
+
"model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 281 |
+
"model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 282 |
+
"model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 283 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 284 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 285 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 286 |
+
"model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 287 |
+
"model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 288 |
+
"model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 289 |
+
"model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 290 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 291 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 292 |
+
"model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 293 |
+
"model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 294 |
+
"model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 295 |
+
"model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 296 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 297 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 298 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 299 |
+
"model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 300 |
+
"model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 301 |
+
"model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 302 |
+
"model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 303 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 304 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 305 |
+
"model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 306 |
+
"model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 307 |
+
"model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 308 |
+
"model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 309 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 310 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 311 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 312 |
+
"model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 313 |
+
"model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 314 |
+
"model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 315 |
+
"model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 316 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 317 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 318 |
+
"model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 319 |
+
"model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 320 |
+
"model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 321 |
+
"model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 322 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 323 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 324 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 325 |
+
"model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 326 |
+
"model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 327 |
+
"model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 328 |
+
"model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 329 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 330 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 331 |
+
"model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 332 |
+
"model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 333 |
+
"model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 334 |
+
"model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 335 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 336 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 337 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 338 |
+
"model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 339 |
+
"model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 340 |
+
"model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 341 |
+
"model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 342 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 343 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 344 |
+
"model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 345 |
+
"model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 346 |
+
"model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 347 |
+
"model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 348 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 349 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 350 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 351 |
+
"model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 354 |
+
"model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 355 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 356 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 358 |
+
"model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 359 |
+
"model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 360 |
+
"model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 361 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 362 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 363 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 364 |
+
"model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 365 |
+
"model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 366 |
+
"model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 367 |
+
"model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 368 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 369 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 370 |
+
"model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 371 |
+
"model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 372 |
+
"model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 373 |
+
"model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 374 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 375 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 376 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 377 |
+
"model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 378 |
+
"model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 379 |
+
"model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 380 |
+
"model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 381 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 382 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 383 |
+
"model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 384 |
+
"model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 385 |
+
"model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 386 |
+
"model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 387 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 388 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 389 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 390 |
+
"model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 391 |
+
"model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 392 |
+
"model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 393 |
+
"model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 394 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 395 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 396 |
+
"model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 397 |
+
"model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 398 |
+
"model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 399 |
+
"model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 400 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 401 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 402 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 403 |
+
"model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 404 |
+
"model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 405 |
+
"model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 406 |
+
"model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 407 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 408 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 409 |
+
"model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 410 |
+
"model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 411 |
+
"model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 412 |
+
"model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 413 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 414 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 415 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 416 |
+
"model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 417 |
+
"model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 418 |
+
"model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 419 |
+
"model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 420 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 421 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 422 |
+
"model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 423 |
+
"model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 424 |
+
"model.norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 425 |
+
"model.vision_model.embeddings.cls_token": "pytorch_model-00004-of-00004.bin",
|
| 426 |
+
"model.vision_model.embeddings.patch_embed.weight": "pytorch_model-00004-of-00004.bin",
|
| 427 |
+
"model.vision_model.embeddings.position_embedding": "pytorch_model-00004-of-00004.bin",
|
| 428 |
+
"model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 429 |
+
"model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 430 |
+
"model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 431 |
+
"model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 432 |
+
"model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 433 |
+
"model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 434 |
+
"model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 435 |
+
"model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 436 |
+
"model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 437 |
+
"model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 438 |
+
"model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 439 |
+
"model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 440 |
+
"model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 441 |
+
"model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 442 |
+
"model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 443 |
+
"model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 444 |
+
"model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 445 |
+
"model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 446 |
+
"model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 447 |
+
"model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 448 |
+
"model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 449 |
+
"model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 450 |
+
"model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 451 |
+
"model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 452 |
+
"model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 453 |
+
"model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 454 |
+
"model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 455 |
+
"model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 456 |
+
"model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 457 |
+
"model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 458 |
+
"model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 459 |
+
"model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 460 |
+
"model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 461 |
+
"model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 462 |
+
"model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 463 |
+
"model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 464 |
+
"model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 465 |
+
"model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 466 |
+
"model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 467 |
+
"model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 468 |
+
"model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 469 |
+
"model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 470 |
+
"model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 471 |
+
"model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 472 |
+
"model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 473 |
+
"model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 474 |
+
"model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 475 |
+
"model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 476 |
+
"model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 477 |
+
"model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 478 |
+
"model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 479 |
+
"model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 480 |
+
"model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 481 |
+
"model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 482 |
+
"model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 483 |
+
"model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 484 |
+
"model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 485 |
+
"model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 486 |
+
"model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 487 |
+
"model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 488 |
+
"model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 489 |
+
"model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 490 |
+
"model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 491 |
+
"model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 492 |
+
"model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 493 |
+
"model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 494 |
+
"model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 495 |
+
"model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 496 |
+
"model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 497 |
+
"model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 498 |
+
"model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 499 |
+
"model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 500 |
+
"model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 501 |
+
"model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 502 |
+
"model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 503 |
+
"model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 504 |
+
"model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 505 |
+
"model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 506 |
+
"model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 507 |
+
"model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 508 |
+
"model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 509 |
+
"model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 510 |
+
"model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 511 |
+
"model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 512 |
+
"model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 513 |
+
"model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 514 |
+
"model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 515 |
+
"model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 516 |
+
"model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 517 |
+
"model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 518 |
+
"model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 519 |
+
"model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 520 |
+
"model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 521 |
+
"model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 522 |
+
"model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 523 |
+
"model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 524 |
+
"model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 525 |
+
"model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 526 |
+
"model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 527 |
+
"model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 528 |
+
"model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 529 |
+
"model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 530 |
+
"model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 531 |
+
"model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 532 |
+
"model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 533 |
+
"model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 534 |
+
"model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 535 |
+
"model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 536 |
+
"model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 537 |
+
"model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 538 |
+
"model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 539 |
+
"model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 540 |
+
"model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 541 |
+
"model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 542 |
+
"model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 543 |
+
"model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 544 |
+
"model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 545 |
+
"model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 546 |
+
"model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 547 |
+
"model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 548 |
+
"model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 549 |
+
"model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 550 |
+
"model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 551 |
+
"model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 552 |
+
"model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 553 |
+
"model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 554 |
+
"model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 555 |
+
"model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 556 |
+
"model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 557 |
+
"model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 558 |
+
"model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 559 |
+
"model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 560 |
+
"model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 561 |
+
"model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 562 |
+
"model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 563 |
+
"model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 564 |
+
"model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 565 |
+
"model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 566 |
+
"model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 567 |
+
"model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 568 |
+
"model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 569 |
+
"model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 570 |
+
"model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 571 |
+
"model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 572 |
+
"model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 573 |
+
"model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 574 |
+
"model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 575 |
+
"model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 576 |
+
"model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 577 |
+
"model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 578 |
+
"model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 579 |
+
"model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 580 |
+
"model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 581 |
+
"model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 582 |
+
"model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 583 |
+
"model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 584 |
+
"model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 585 |
+
"model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 586 |
+
"model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 587 |
+
"model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 588 |
+
"model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 589 |
+
"model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 590 |
+
"model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 591 |
+
"model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 592 |
+
"model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 593 |
+
"model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 594 |
+
"model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 595 |
+
"model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 596 |
+
"model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 597 |
+
"model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 598 |
+
"model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 599 |
+
"model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 600 |
+
"model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 601 |
+
"model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 602 |
+
"model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 603 |
+
"model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 604 |
+
"model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 605 |
+
"model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 606 |
+
"model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 607 |
+
"model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 608 |
+
"model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 609 |
+
"model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 610 |
+
"model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 611 |
+
"model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 612 |
+
"model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 613 |
+
"model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 614 |
+
"model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 615 |
+
"model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 616 |
+
"model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 617 |
+
"model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 618 |
+
"model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 619 |
+
"model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 620 |
+
"model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 621 |
+
"model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 622 |
+
"model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 623 |
+
"model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 624 |
+
"model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 625 |
+
"model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 626 |
+
"model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 627 |
+
"model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 628 |
+
"model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 629 |
+
"model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 630 |
+
"model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 631 |
+
"model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 632 |
+
"model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 633 |
+
"model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 634 |
+
"model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 635 |
+
"model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 636 |
+
"model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 637 |
+
"model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 638 |
+
"model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 639 |
+
"model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 640 |
+
"model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 641 |
+
"model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 642 |
+
"model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 643 |
+
"model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 644 |
+
"model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 645 |
+
"model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 646 |
+
"model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 647 |
+
"model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 648 |
+
"model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 649 |
+
"model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 650 |
+
"model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 651 |
+
"model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 652 |
+
"model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 653 |
+
"model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 654 |
+
"model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 655 |
+
"model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 656 |
+
"model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 657 |
+
"model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 658 |
+
"model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 659 |
+
"model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 660 |
+
"model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 661 |
+
"model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 662 |
+
"model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 663 |
+
"model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 664 |
+
"model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 665 |
+
"model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 666 |
+
"model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 667 |
+
"model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 668 |
+
"model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 669 |
+
"model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 670 |
+
"model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 671 |
+
"model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 672 |
+
"model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 673 |
+
"model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 674 |
+
"model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 675 |
+
"model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 676 |
+
"model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 677 |
+
"model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 678 |
+
"model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 679 |
+
"model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 680 |
+
"model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 681 |
+
"model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 682 |
+
"model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 683 |
+
"model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 684 |
+
"model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 685 |
+
"model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 686 |
+
"model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 687 |
+
"model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 688 |
+
"model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 689 |
+
"model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 690 |
+
"model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 691 |
+
"model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 692 |
+
"model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 693 |
+
"model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 694 |
+
"model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 695 |
+
"model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 696 |
+
"model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 697 |
+
"model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 698 |
+
"model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 699 |
+
"model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 700 |
+
"model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 701 |
+
"model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 702 |
+
"model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 703 |
+
"model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 704 |
+
"model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 705 |
+
"model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 706 |
+
"model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 707 |
+
"model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 708 |
+
"model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 709 |
+
"model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 710 |
+
"model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 711 |
+
"model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 712 |
+
"model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 713 |
+
"model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 714 |
+
"model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 715 |
+
"model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 716 |
+
"model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 717 |
+
"model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 718 |
+
"model.vision_model.post_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 719 |
+
"model.vision_model.post_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 720 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 721 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 722 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 723 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 724 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 725 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 726 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 727 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 728 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 729 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 730 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 731 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 732 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 733 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 734 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 735 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 736 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 737 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 738 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 739 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 740 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 741 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 742 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 743 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 744 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 745 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 746 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 747 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 748 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 749 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 750 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 751 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 752 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 753 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 754 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 755 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 756 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 757 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 758 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 759 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 760 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 761 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 762 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 763 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 764 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 765 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 766 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 767 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 768 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 769 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 770 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 771 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 772 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 773 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 774 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 775 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 776 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 777 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 778 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 779 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 780 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 781 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 782 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 783 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 784 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 785 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 786 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 787 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 788 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 789 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 790 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 791 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 792 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 793 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 794 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 795 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 796 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 797 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 798 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 799 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 800 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 801 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 802 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 803 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 804 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 805 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 806 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 807 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 808 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 809 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 810 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 811 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 812 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 813 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 814 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 815 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 816 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 817 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 818 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 819 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 820 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 821 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 822 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 823 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 824 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 825 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 826 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 827 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 828 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 829 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 830 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 831 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 832 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 833 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 834 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 835 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 836 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 837 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 838 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 839 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 840 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 841 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 842 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 843 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 844 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 845 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 846 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 847 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 848 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 849 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 850 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 851 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 852 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 853 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 854 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 855 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 856 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 857 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 858 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 859 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 860 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 861 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 862 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 863 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 864 |
+
"model.visual_abstractor.query_embeds": "pytorch_model-00004-of-00004.bin",
|
| 865 |
+
"model.visual_abstractor.visual_fc.bias": "pytorch_model-00004-of-00004.bin",
|
| 866 |
+
"model.visual_abstractor.visual_fc.weight": "pytorch_model-00004-of-00004.bin",
|
| 867 |
+
"model.visual_abstractor.vit_eos": "pytorch_model-00004-of-00004.bin"
|
| 868 |
+
}
|
| 869 |
+
}
|
runs/Feb19_22-26-01_n213-017-078/events.out.tfevents.1708352856.n213-017-078.4939.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7fcf89beee9df5d8dd4e458b0c24cd38ec4e761039daa5cedb2affc56d55457
|
| 3 |
+
size 45853
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
+
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 230,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 14 |
+
"loss": 0.1731,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 20 |
+
"loss": 0.1107,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 8.571428571428571e-06,
|
| 26 |
+
"loss": 0.1074,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.09,
|
| 31 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 32 |
+
"loss": 0.1454,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.11,
|
| 37 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 38 |
+
"loss": 0.1185,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 44 |
+
"loss": 0.2155,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.15,
|
| 49 |
+
"learning_rate": 2e-05,
|
| 50 |
+
"loss": 0.1626,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.17,
|
| 55 |
+
"learning_rate": 1.9999007677495127e-05,
|
| 56 |
+
"loss": 0.1486,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.2,
|
| 61 |
+
"learning_rate": 1.9996030906921302e-05,
|
| 62 |
+
"loss": 0.1611,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.22,
|
| 67 |
+
"learning_rate": 1.9991070279061808e-05,
|
| 68 |
+
"loss": 0.1354,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.24,
|
| 73 |
+
"learning_rate": 1.9984126778425178e-05,
|
| 74 |
+
"loss": 0.1309,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.26,
|
| 79 |
+
"learning_rate": 1.9975201783049804e-05,
|
| 80 |
+
"loss": 0.1228,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.28,
|
| 85 |
+
"learning_rate": 1.9964297064230437e-05,
|
| 86 |
+
"loss": 0.1096,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3,
|
| 91 |
+
"learning_rate": 1.9951414786166656e-05,
|
| 92 |
+
"loss": 0.1152,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.33,
|
| 97 |
+
"learning_rate": 1.9936557505533346e-05,
|
| 98 |
+
"loss": 0.1058,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.35,
|
| 103 |
+
"learning_rate": 1.9919728170973297e-05,
|
| 104 |
+
"loss": 0.0853,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.37,
|
| 109 |
+
"learning_rate": 1.9900930122511993e-05,
|
| 110 |
+
"loss": 0.1111,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.39,
|
| 115 |
+
"learning_rate": 1.988016709089474e-05,
|
| 116 |
+
"loss": 1.8086,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.41,
|
| 121 |
+
"learning_rate": 1.985744319684625e-05,
|
| 122 |
+
"loss": 0.6606,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.43,
|
| 127 |
+
"learning_rate": 1.9832762950252813e-05,
|
| 128 |
+
"loss": 0.2228,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.46,
|
| 133 |
+
"learning_rate": 1.9806131249267256e-05,
|
| 134 |
+
"loss": 0.1629,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.48,
|
| 139 |
+
"learning_rate": 1.977755337933682e-05,
|
| 140 |
+
"loss": 0.1505,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.5,
|
| 145 |
+
"learning_rate": 1.9747035012154203e-05,
|
| 146 |
+
"loss": 0.1273,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.52,
|
| 151 |
+
"learning_rate": 1.971458220453192e-05,
|
| 152 |
+
"loss": 0.159,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.54,
|
| 157 |
+
"learning_rate": 1.968020139720024e-05,
|
| 158 |
+
"loss": 0.1383,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.57,
|
| 163 |
+
"learning_rate": 1.9643899413528926e-05,
|
| 164 |
+
"loss": 0.1456,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.59,
|
| 169 |
+
"learning_rate": 1.960568345817306e-05,
|
| 170 |
+
"loss": 0.1609,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.61,
|
| 175 |
+
"learning_rate": 1.9565561115643153e-05,
|
| 176 |
+
"loss": 0.1258,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.63,
|
| 181 |
+
"learning_rate": 1.9523540348799887e-05,
|
| 182 |
+
"loss": 0.1219,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.65,
|
| 187 |
+
"learning_rate": 1.9479629497273783e-05,
|
| 188 |
+
"loss": 0.122,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.67,
|
| 193 |
+
"learning_rate": 1.9433837275810084e-05,
|
| 194 |
+
"loss": 0.1164,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.7,
|
| 199 |
+
"learning_rate": 1.9386172772539162e-05,
|
| 200 |
+
"loss": 0.1234,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.72,
|
| 205 |
+
"learning_rate": 1.933664544717288e-05,
|
| 206 |
+
"loss": 0.1189,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.74,
|
| 211 |
+
"learning_rate": 1.928526512912715e-05,
|
| 212 |
+
"loss": 0.1278,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.76,
|
| 217 |
+
"learning_rate": 1.9232042015571152e-05,
|
| 218 |
+
"loss": 0.1117,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.78,
|
| 223 |
+
"learning_rate": 1.9176986669403556e-05,
|
| 224 |
+
"loss": 0.1157,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.8,
|
| 229 |
+
"learning_rate": 1.9120110017156172e-05,
|
| 230 |
+
"loss": 0.1032,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.83,
|
| 235 |
+
"learning_rate": 1.9061423346825395e-05,
|
| 236 |
+
"loss": 0.1035,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.85,
|
| 241 |
+
"learning_rate": 1.9000938305631975e-05,
|
| 242 |
+
"loss": 0.1029,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.87,
|
| 247 |
+
"learning_rate": 1.8938666897709427e-05,
|
| 248 |
+
"loss": 0.1058,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.89,
|
| 253 |
+
"learning_rate": 1.8874621481721645e-05,
|
| 254 |
+
"loss": 0.1039,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.91,
|
| 259 |
+
"learning_rate": 1.8808814768410157e-05,
|
| 260 |
+
"loss": 0.114,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.93,
|
| 265 |
+
"learning_rate": 1.874125981807148e-05,
|
| 266 |
+
"loss": 0.1076,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.96,
|
| 271 |
+
"learning_rate": 1.867197003796512e-05,
|
| 272 |
+
"loss": 0.0863,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.98,
|
| 277 |
+
"learning_rate": 1.8600959179652708e-05,
|
| 278 |
+
"loss": 0.0893,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.0,
|
| 283 |
+
"learning_rate": 1.852824133626881e-05,
|
| 284 |
+
"loss": 0.0946,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.02,
|
| 289 |
+
"learning_rate": 1.8453830939723913e-05,
|
| 290 |
+
"loss": 0.0782,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.04,
|
| 295 |
+
"learning_rate": 1.8377742757840246e-05,
|
| 296 |
+
"loss": 0.0882,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.07,
|
| 301 |
+
"learning_rate": 1.8299991891420848e-05,
|
| 302 |
+
"loss": 0.0871,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.09,
|
| 307 |
+
"learning_rate": 1.822059377125263e-05,
|
| 308 |
+
"loss": 0.073,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.11,
|
| 313 |
+
"learning_rate": 1.8139564155043885e-05,
|
| 314 |
+
"loss": 0.0777,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.13,
|
| 319 |
+
"learning_rate": 1.8056919124296957e-05,
|
| 320 |
+
"loss": 0.0825,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.15,
|
| 325 |
+
"learning_rate": 1.797267508111664e-05,
|
| 326 |
+
"loss": 0.0732,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.17,
|
| 331 |
+
"learning_rate": 1.788684874495491e-05,
|
| 332 |
+
"loss": 0.079,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.2,
|
| 337 |
+
"learning_rate": 1.7799457149292752e-05,
|
| 338 |
+
"loss": 0.0681,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.22,
|
| 343 |
+
"learning_rate": 1.7710517638259593e-05,
|
| 344 |
+
"loss": 0.0683,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.24,
|
| 349 |
+
"learning_rate": 1.76200478631911e-05,
|
| 350 |
+
"loss": 0.0743,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.26,
|
| 355 |
+
"learning_rate": 1.7528065779126035e-05,
|
| 356 |
+
"loss": 0.0763,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.28,
|
| 361 |
+
"learning_rate": 1.7434589641242814e-05,
|
| 362 |
+
"loss": 0.067,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.3,
|
| 367 |
+
"learning_rate": 1.7339638001236495e-05,
|
| 368 |
+
"loss": 0.0667,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.33,
|
| 373 |
+
"learning_rate": 1.7243229703636924e-05,
|
| 374 |
+
"loss": 0.0703,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.35,
|
| 379 |
+
"learning_rate": 1.714538388206878e-05,
|
| 380 |
+
"loss": 0.0716,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.37,
|
| 385 |
+
"learning_rate": 1.704611995545421e-05,
|
| 386 |
+
"loss": 0.0513,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.39,
|
| 391 |
+
"learning_rate": 1.694545762415887e-05,
|
| 392 |
+
"loss": 0.0663,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.41,
|
| 397 |
+
"learning_rate": 1.6843416866082118e-05,
|
| 398 |
+
"loss": 0.0827,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.43,
|
| 403 |
+
"learning_rate": 1.6740017932692073e-05,
|
| 404 |
+
"loss": 0.0845,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.46,
|
| 409 |
+
"learning_rate": 1.663528134500646e-05,
|
| 410 |
+
"loss": 0.0791,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.48,
|
| 415 |
+
"learning_rate": 1.6529227889519884e-05,
|
| 416 |
+
"loss": 0.0596,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.5,
|
| 421 |
+
"learning_rate": 1.642187861407847e-05,
|
| 422 |
+
"loss": 0.0678,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.52,
|
| 427 |
+
"learning_rate": 1.631325482370259e-05,
|
| 428 |
+
"loss": 0.0822,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.54,
|
| 433 |
+
"learning_rate": 1.6203378076358602e-05,
|
| 434 |
+
"loss": 0.0595,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.57,
|
| 439 |
+
"learning_rate": 1.609227017868033e-05,
|
| 440 |
+
"loss": 0.0673,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.59,
|
| 445 |
+
"learning_rate": 1.5979953181641246e-05,
|
| 446 |
+
"loss": 0.0865,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.61,
|
| 451 |
+
"learning_rate": 1.5866449376178118e-05,
|
| 452 |
+
"loss": 0.0639,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.63,
|
| 457 |
+
"learning_rate": 1.5751781288767052e-05,
|
| 458 |
+
"loss": 0.0703,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.65,
|
| 463 |
+
"learning_rate": 1.56359716769528e-05,
|
| 464 |
+
"loss": 0.0707,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.67,
|
| 469 |
+
"learning_rate": 1.551904352483217e-05,
|
| 470 |
+
"loss": 0.0527,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.7,
|
| 475 |
+
"learning_rate": 1.540102003849253e-05,
|
| 476 |
+
"loss": 0.0503,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.72,
|
| 481 |
+
"learning_rate": 1.52819246414062e-05,
|
| 482 |
+
"loss": 0.0625,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.74,
|
| 487 |
+
"learning_rate": 1.5161780969781728e-05,
|
| 488 |
+
"loss": 0.0628,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.76,
|
| 493 |
+
"learning_rate": 1.5040612867872945e-05,
|
| 494 |
+
"loss": 0.0685,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.78,
|
| 499 |
+
"learning_rate": 1.4918444383246738e-05,
|
| 500 |
+
"loss": 0.0839,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.8,
|
| 505 |
+
"learning_rate": 1.479529976201044e-05,
|
| 506 |
+
"loss": 0.0643,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.83,
|
| 511 |
+
"learning_rate": 1.4671203443999847e-05,
|
| 512 |
+
"loss": 0.068,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.85,
|
| 517 |
+
"learning_rate": 1.4546180057928792e-05,
|
| 518 |
+
"loss": 0.0494,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.87,
|
| 523 |
+
"learning_rate": 1.4420254416501198e-05,
|
| 524 |
+
"loss": 0.0942,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.89,
|
| 529 |
+
"learning_rate": 1.4293451511486658e-05,
|
| 530 |
+
"loss": 0.0798,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.91,
|
| 535 |
+
"learning_rate": 1.416579650876043e-05,
|
| 536 |
+
"loss": 0.0801,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.93,
|
| 541 |
+
"learning_rate": 1.403731474330893e-05,
|
| 542 |
+
"loss": 0.0556,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.96,
|
| 547 |
+
"learning_rate": 1.3908031714201621e-05,
|
| 548 |
+
"loss": 0.0655,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.98,
|
| 553 |
+
"learning_rate": 1.3777973079530362e-05,
|
| 554 |
+
"loss": 0.0596,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.0,
|
| 559 |
+
"learning_rate": 1.3647164651317178e-05,
|
| 560 |
+
"loss": 0.0463,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.02,
|
| 565 |
+
"learning_rate": 1.35156323903915e-05,
|
| 566 |
+
"loss": 0.0551,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.04,
|
| 571 |
+
"learning_rate": 1.338340240123785e-05,
|
| 572 |
+
"loss": 0.0386,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.07,
|
| 577 |
+
"learning_rate": 1.3250500926815046e-05,
|
| 578 |
+
"loss": 0.047,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.09,
|
| 583 |
+
"learning_rate": 1.3116954343347882e-05,
|
| 584 |
+
"loss": 0.0612,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.11,
|
| 589 |
+
"learning_rate": 1.2982789155092407e-05,
|
| 590 |
+
"loss": 0.0409,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.13,
|
| 595 |
+
"learning_rate": 1.2848031989075754e-05,
|
| 596 |
+
"loss": 0.0528,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.15,
|
| 601 |
+
"learning_rate": 1.2712709589811629e-05,
|
| 602 |
+
"loss": 0.0525,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.17,
|
| 607 |
+
"learning_rate": 1.2576848813992475e-05,
|
| 608 |
+
"loss": 0.0381,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.2,
|
| 613 |
+
"learning_rate": 1.2440476625159363e-05,
|
| 614 |
+
"loss": 0.0542,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.22,
|
| 619 |
+
"learning_rate": 1.23036200883507e-05,
|
| 620 |
+
"loss": 0.0405,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.24,
|
| 625 |
+
"learning_rate": 1.2166306364730766e-05,
|
| 626 |
+
"loss": 0.055,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.26,
|
| 631 |
+
"learning_rate": 1.2028562706199201e-05,
|
| 632 |
+
"loss": 0.0436,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.28,
|
| 637 |
+
"learning_rate": 1.1890416449982451e-05,
|
| 638 |
+
"loss": 0.0467,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.3,
|
| 643 |
+
"learning_rate": 1.1751895013208325e-05,
|
| 644 |
+
"loss": 0.0693,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.33,
|
| 649 |
+
"learning_rate": 1.1613025887464642e-05,
|
| 650 |
+
"loss": 0.0495,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 2.35,
|
| 655 |
+
"learning_rate": 1.1473836633343145e-05,
|
| 656 |
+
"loss": 0.0571,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.37,
|
| 661 |
+
"learning_rate": 1.133435487496969e-05,
|
| 662 |
+
"loss": 0.0331,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.39,
|
| 667 |
+
"learning_rate": 1.1194608294521853e-05,
|
| 668 |
+
"loss": 0.0342,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.41,
|
| 673 |
+
"learning_rate": 1.1054624626734985e-05,
|
| 674 |
+
"loss": 0.0679,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.43,
|
| 679 |
+
"learning_rate": 1.0914431653397856e-05,
|
| 680 |
+
"loss": 0.0509,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.46,
|
| 685 |
+
"learning_rate": 1.0774057197838963e-05,
|
| 686 |
+
"loss": 0.0543,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 2.48,
|
| 691 |
+
"learning_rate": 1.0633529119404571e-05,
|
| 692 |
+
"loss": 0.0893,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.5,
|
| 697 |
+
"learning_rate": 1.0492875307929643e-05,
|
| 698 |
+
"loss": 0.0386,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.52,
|
| 703 |
+
"learning_rate": 1.0352123678202686e-05,
|
| 704 |
+
"loss": 0.0581,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.54,
|
| 709 |
+
"learning_rate": 1.0211302164425657e-05,
|
| 710 |
+
"loss": 0.0599,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.57,
|
| 715 |
+
"learning_rate": 1.0070438714670004e-05,
|
| 716 |
+
"loss": 0.0426,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.59,
|
| 721 |
+
"learning_rate": 9.929561285329998e-06,
|
| 722 |
+
"loss": 0.0425,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.61,
|
| 727 |
+
"learning_rate": 9.788697835574348e-06,
|
| 728 |
+
"loss": 0.0571,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.63,
|
| 733 |
+
"learning_rate": 9.647876321797314e-06,
|
| 734 |
+
"loss": 0.0478,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.65,
|
| 739 |
+
"learning_rate": 9.507124692070356e-06,
|
| 740 |
+
"loss": 0.0626,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.67,
|
| 745 |
+
"learning_rate": 9.366470880595434e-06,
|
| 746 |
+
"loss": 0.0438,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.7,
|
| 751 |
+
"learning_rate": 9.225942802161042e-06,
|
| 752 |
+
"loss": 0.0385,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.72,
|
| 757 |
+
"learning_rate": 9.085568346602146e-06,
|
| 758 |
+
"loss": 0.0533,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.74,
|
| 763 |
+
"learning_rate": 8.945375373265017e-06,
|
| 764 |
+
"loss": 0.0568,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.76,
|
| 769 |
+
"learning_rate": 8.805391705478149e-06,
|
| 770 |
+
"loss": 0.0449,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.78,
|
| 775 |
+
"learning_rate": 8.665645125030312e-06,
|
| 776 |
+
"loss": 0.0579,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.8,
|
| 781 |
+
"learning_rate": 8.526163366656858e-06,
|
| 782 |
+
"loss": 0.0386,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.83,
|
| 787 |
+
"learning_rate": 8.38697411253536e-06,
|
| 788 |
+
"loss": 0.0435,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.85,
|
| 793 |
+
"learning_rate": 8.248104986791677e-06,
|
| 794 |
+
"loss": 0.0453,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.87,
|
| 799 |
+
"learning_rate": 8.10958355001755e-06,
|
| 800 |
+
"loss": 0.0455,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.89,
|
| 805 |
+
"learning_rate": 7.971437293800804e-06,
|
| 806 |
+
"loss": 0.0434,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.91,
|
| 811 |
+
"learning_rate": 7.833693635269235e-06,
|
| 812 |
+
"loss": 0.0447,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.93,
|
| 817 |
+
"learning_rate": 7.696379911649303e-06,
|
| 818 |
+
"loss": 0.0376,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.96,
|
| 823 |
+
"learning_rate": 7.559523374840639e-06,
|
| 824 |
+
"loss": 0.0608,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.98,
|
| 829 |
+
"learning_rate": 7.423151186007527e-06,
|
| 830 |
+
"loss": 0.0406,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.0,
|
| 835 |
+
"learning_rate": 7.287290410188374e-06,
|
| 836 |
+
"loss": 0.0457,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 3.02,
|
| 841 |
+
"learning_rate": 7.1519680109242486e-06,
|
| 842 |
+
"loss": 0.0456,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.04,
|
| 847 |
+
"learning_rate": 7.017210844907598e-06,
|
| 848 |
+
"loss": 0.0251,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.07,
|
| 853 |
+
"learning_rate": 6.883045656652122e-06,
|
| 854 |
+
"loss": 0.0294,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.09,
|
| 859 |
+
"learning_rate": 6.749499073184957e-06,
|
| 860 |
+
"loss": 0.0357,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 3.11,
|
| 865 |
+
"learning_rate": 6.616597598762151e-06,
|
| 866 |
+
"loss": 0.036,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 3.13,
|
| 871 |
+
"learning_rate": 6.484367609608503e-06,
|
| 872 |
+
"loss": 0.0287,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.15,
|
| 877 |
+
"learning_rate": 6.352835348682824e-06,
|
| 878 |
+
"loss": 0.0295,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 3.17,
|
| 883 |
+
"learning_rate": 6.22202692046964e-06,
|
| 884 |
+
"loss": 0.0306,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.2,
|
| 889 |
+
"learning_rate": 6.09196828579838e-06,
|
| 890 |
+
"loss": 0.0247,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 3.22,
|
| 895 |
+
"learning_rate": 5.962685256691071e-06,
|
| 896 |
+
"loss": 0.0372,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.24,
|
| 901 |
+
"learning_rate": 5.834203491239574e-06,
|
| 902 |
+
"loss": 0.0227,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 3.26,
|
| 907 |
+
"learning_rate": 5.706548488513347e-06,
|
| 908 |
+
"loss": 0.0257,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.28,
|
| 913 |
+
"learning_rate": 5.579745583498802e-06,
|
| 914 |
+
"loss": 0.0251,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 3.3,
|
| 919 |
+
"learning_rate": 5.453819942071212e-06,
|
| 920 |
+
"loss": 0.0247,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.33,
|
| 925 |
+
"learning_rate": 5.328796556000153e-06,
|
| 926 |
+
"loss": 0.0356,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.35,
|
| 931 |
+
"learning_rate": 5.204700237989564e-06,
|
| 932 |
+
"loss": 0.0303,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 3.37,
|
| 937 |
+
"learning_rate": 5.081555616753264e-06,
|
| 938 |
+
"loss": 0.02,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.39,
|
| 943 |
+
"learning_rate": 4.959387132127054e-06,
|
| 944 |
+
"loss": 0.0328,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.41,
|
| 949 |
+
"learning_rate": 4.838219030218274e-06,
|
| 950 |
+
"loss": 0.0264,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 3.43,
|
| 955 |
+
"learning_rate": 4.718075358593802e-06,
|
| 956 |
+
"loss": 0.0308,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 3.46,
|
| 961 |
+
"learning_rate": 4.598979961507472e-06,
|
| 962 |
+
"loss": 0.0358,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 3.48,
|
| 967 |
+
"learning_rate": 4.48095647516783e-06,
|
| 968 |
+
"loss": 0.0272,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.5,
|
| 973 |
+
"learning_rate": 4.364028323047205e-06,
|
| 974 |
+
"loss": 0.0306,
|
| 975 |
+
"step": 161
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.52,
|
| 979 |
+
"learning_rate": 4.248218711232952e-06,
|
| 980 |
+
"loss": 0.0193,
|
| 981 |
+
"step": 162
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 3.54,
|
| 985 |
+
"learning_rate": 4.133550623821884e-06,
|
| 986 |
+
"loss": 0.0243,
|
| 987 |
+
"step": 163
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 3.57,
|
| 991 |
+
"learning_rate": 4.0200468183587556e-06,
|
| 992 |
+
"loss": 0.0359,
|
| 993 |
+
"step": 164
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.59,
|
| 997 |
+
"learning_rate": 3.90772982131967e-06,
|
| 998 |
+
"loss": 0.0305,
|
| 999 |
+
"step": 165
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 3.61,
|
| 1003 |
+
"learning_rate": 3.7966219236414036e-06,
|
| 1004 |
+
"loss": 0.0324,
|
| 1005 |
+
"step": 166
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 3.63,
|
| 1009 |
+
"learning_rate": 3.6867451762974117e-06,
|
| 1010 |
+
"loss": 0.0355,
|
| 1011 |
+
"step": 167
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 3.65,
|
| 1015 |
+
"learning_rate": 3.5781213859215334e-06,
|
| 1016 |
+
"loss": 0.0308,
|
| 1017 |
+
"step": 168
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.67,
|
| 1021 |
+
"learning_rate": 3.4707721104801175e-06,
|
| 1022 |
+
"loss": 0.0487,
|
| 1023 |
+
"step": 169
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 3.7,
|
| 1027 |
+
"learning_rate": 3.3647186549935407e-06,
|
| 1028 |
+
"loss": 0.0165,
|
| 1029 |
+
"step": 170
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 3.72,
|
| 1033 |
+
"learning_rate": 3.2599820673079286e-06,
|
| 1034 |
+
"loss": 0.03,
|
| 1035 |
+
"step": 171
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.74,
|
| 1039 |
+
"learning_rate": 3.1565831339178844e-06,
|
| 1040 |
+
"loss": 0.0225,
|
| 1041 |
+
"step": 172
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 3.76,
|
| 1045 |
+
"learning_rate": 3.0545423758411298e-06,
|
| 1046 |
+
"loss": 0.0364,
|
| 1047 |
+
"step": 173
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 3.78,
|
| 1051 |
+
"learning_rate": 2.953880044545795e-06,
|
| 1052 |
+
"loss": 0.0269,
|
| 1053 |
+
"step": 174
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 3.8,
|
| 1057 |
+
"learning_rate": 2.8546161179312247e-06,
|
| 1058 |
+
"loss": 0.0142,
|
| 1059 |
+
"step": 175
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.83,
|
| 1063 |
+
"learning_rate": 2.7567702963630805e-06,
|
| 1064 |
+
"loss": 0.0377,
|
| 1065 |
+
"step": 176
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 3.85,
|
| 1069 |
+
"learning_rate": 2.6603619987635087e-06,
|
| 1070 |
+
"loss": 0.0295,
|
| 1071 |
+
"step": 177
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 3.87,
|
| 1075 |
+
"learning_rate": 2.5654103587571887e-06,
|
| 1076 |
+
"loss": 0.031,
|
| 1077 |
+
"step": 178
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 3.89,
|
| 1081 |
+
"learning_rate": 2.4719342208739695e-06,
|
| 1082 |
+
"loss": 0.0387,
|
| 1083 |
+
"step": 179
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.91,
|
| 1087 |
+
"learning_rate": 2.379952136808903e-06,
|
| 1088 |
+
"loss": 0.0274,
|
| 1089 |
+
"step": 180
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.93,
|
| 1093 |
+
"learning_rate": 2.2894823617404107e-06,
|
| 1094 |
+
"loss": 0.0341,
|
| 1095 |
+
"step": 181
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 3.96,
|
| 1099 |
+
"learning_rate": 2.200542850707247e-06,
|
| 1100 |
+
"loss": 0.032,
|
| 1101 |
+
"step": 182
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.98,
|
| 1105 |
+
"learning_rate": 2.113151255045095e-06,
|
| 1106 |
+
"loss": 0.0333,
|
| 1107 |
+
"step": 183
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 4.0,
|
| 1111 |
+
"learning_rate": 2.0273249188833656e-06,
|
| 1112 |
+
"loss": 0.0298,
|
| 1113 |
+
"step": 184
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.02,
|
| 1117 |
+
"learning_rate": 1.9430808757030452e-06,
|
| 1118 |
+
"loss": 0.0201,
|
| 1119 |
+
"step": 185
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 4.04,
|
| 1123 |
+
"learning_rate": 1.860435844956121e-06,
|
| 1124 |
+
"loss": 0.0156,
|
| 1125 |
+
"step": 186
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 4.07,
|
| 1129 |
+
"learning_rate": 1.7794062287473734e-06,
|
| 1130 |
+
"loss": 0.021,
|
| 1131 |
+
"step": 187
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 4.09,
|
| 1135 |
+
"learning_rate": 1.7000081085791541e-06,
|
| 1136 |
+
"loss": 0.0197,
|
| 1137 |
+
"step": 188
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 4.11,
|
| 1141 |
+
"learning_rate": 1.622257242159756e-06,
|
| 1142 |
+
"loss": 0.029,
|
| 1143 |
+
"step": 189
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 4.13,
|
| 1147 |
+
"learning_rate": 1.5461690602760882e-06,
|
| 1148 |
+
"loss": 0.0249,
|
| 1149 |
+
"step": 190
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 4.15,
|
| 1153 |
+
"learning_rate": 1.4717586637311943e-06,
|
| 1154 |
+
"loss": 0.0294,
|
| 1155 |
+
"step": 191
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 4.17,
|
| 1159 |
+
"learning_rate": 1.3990408203472938e-06,
|
| 1160 |
+
"loss": 0.0112,
|
| 1161 |
+
"step": 192
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.2,
|
| 1165 |
+
"learning_rate": 1.3280299620348847e-06,
|
| 1166 |
+
"loss": 0.0172,
|
| 1167 |
+
"step": 193
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 4.22,
|
| 1171 |
+
"learning_rate": 1.258740181928524e-06,
|
| 1172 |
+
"loss": 0.0159,
|
| 1173 |
+
"step": 194
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 4.24,
|
| 1177 |
+
"learning_rate": 1.1911852315898465e-06,
|
| 1178 |
+
"loss": 0.0241,
|
| 1179 |
+
"step": 195
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 4.26,
|
| 1183 |
+
"learning_rate": 1.1253785182783571e-06,
|
| 1184 |
+
"loss": 0.0178,
|
| 1185 |
+
"step": 196
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 4.28,
|
| 1189 |
+
"learning_rate": 1.061333102290576e-06,
|
| 1190 |
+
"loss": 0.0173,
|
| 1191 |
+
"step": 197
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 4.3,
|
| 1195 |
+
"learning_rate": 9.990616943680266e-07,
|
| 1196 |
+
"loss": 0.0149,
|
| 1197 |
+
"step": 198
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 4.33,
|
| 1201 |
+
"learning_rate": 9.385766531746055e-07,
|
| 1202 |
+
"loss": 0.0354,
|
| 1203 |
+
"step": 199
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 4.35,
|
| 1207 |
+
"learning_rate": 8.798899828438334e-07,
|
| 1208 |
+
"loss": 0.0179,
|
| 1209 |
+
"step": 200
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 4.37,
|
| 1213 |
+
"learning_rate": 8.23013330596445e-07,
|
| 1214 |
+
"loss": 0.0145,
|
| 1215 |
+
"step": 201
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 4.39,
|
| 1219 |
+
"learning_rate": 7.679579844288509e-07,
|
| 1220 |
+
"loss": 0.0276,
|
| 1221 |
+
"step": 202
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 4.41,
|
| 1225 |
+
"learning_rate": 7.147348708728508e-07,
|
| 1226 |
+
"loss": 0.0117,
|
| 1227 |
+
"step": 203
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 4.43,
|
| 1231 |
+
"learning_rate": 6.633545528271213e-07,
|
| 1232 |
+
"loss": 0.0189,
|
| 1233 |
+
"step": 204
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 4.46,
|
| 1237 |
+
"learning_rate": 6.138272274608404e-07,
|
| 1238 |
+
"loss": 0.0257,
|
| 1239 |
+
"step": 205
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 4.48,
|
| 1243 |
+
"learning_rate": 5.661627241899193e-07,
|
| 1244 |
+
"loss": 0.0158,
|
| 1245 |
+
"step": 206
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 4.5,
|
| 1249 |
+
"learning_rate": 5.203705027262185e-07,
|
| 1250 |
+
"loss": 0.013,
|
| 1251 |
+
"step": 207
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 4.52,
|
| 1255 |
+
"learning_rate": 4.7645965120011627e-07,
|
| 1256 |
+
"loss": 0.0146,
|
| 1257 |
+
"step": 208
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 4.54,
|
| 1261 |
+
"learning_rate": 4.344388843568503e-07,
|
| 1262 |
+
"loss": 0.0208,
|
| 1263 |
+
"step": 209
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 4.57,
|
| 1267 |
+
"learning_rate": 3.943165418269401e-07,
|
| 1268 |
+
"loss": 0.0241,
|
| 1269 |
+
"step": 210
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 4.59,
|
| 1273 |
+
"learning_rate": 3.561005864710754e-07,
|
| 1274 |
+
"loss": 0.016,
|
| 1275 |
+
"step": 211
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 4.61,
|
| 1279 |
+
"learning_rate": 3.197986027997657e-07,
|
| 1280 |
+
"loss": 0.0222,
|
| 1281 |
+
"step": 212
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 4.63,
|
| 1285 |
+
"learning_rate": 2.8541779546808255e-07,
|
| 1286 |
+
"loss": 0.0155,
|
| 1287 |
+
"step": 213
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 4.65,
|
| 1291 |
+
"learning_rate": 2.529649878457985e-07,
|
| 1292 |
+
"loss": 0.0228,
|
| 1293 |
+
"step": 214
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 4.67,
|
| 1297 |
+
"learning_rate": 2.2244662066318146e-07,
|
| 1298 |
+
"loss": 0.0134,
|
| 1299 |
+
"step": 215
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 4.7,
|
| 1303 |
+
"learning_rate": 1.9386875073274636e-07,
|
| 1304 |
+
"loss": 0.0233,
|
| 1305 |
+
"step": 216
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 4.72,
|
| 1309 |
+
"learning_rate": 1.6723704974718758e-07,
|
| 1310 |
+
"loss": 0.0204,
|
| 1311 |
+
"step": 217
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 4.74,
|
| 1315 |
+
"learning_rate": 1.4255680315375164e-07,
|
| 1316 |
+
"loss": 0.0167,
|
| 1317 |
+
"step": 218
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 4.76,
|
| 1321 |
+
"learning_rate": 1.198329091052608e-07,
|
| 1322 |
+
"loss": 0.0147,
|
| 1323 |
+
"step": 219
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 4.78,
|
| 1327 |
+
"learning_rate": 9.906987748800945e-08,
|
| 1328 |
+
"loss": 0.0194,
|
| 1329 |
+
"step": 220
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 4.8,
|
| 1333 |
+
"learning_rate": 8.027182902670571e-08,
|
| 1334 |
+
"loss": 0.0162,
|
| 1335 |
+
"step": 221
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 4.83,
|
| 1339 |
+
"learning_rate": 6.344249446665673e-08,
|
| 1340 |
+
"loss": 0.0126,
|
| 1341 |
+
"step": 222
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 4.85,
|
| 1345 |
+
"learning_rate": 4.8585213833348686e-08,
|
| 1346 |
+
"loss": 0.0132,
|
| 1347 |
+
"step": 223
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 4.87,
|
| 1351 |
+
"learning_rate": 3.570293576956596e-08,
|
| 1352 |
+
"loss": 0.0175,
|
| 1353 |
+
"step": 224
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 4.89,
|
| 1357 |
+
"learning_rate": 2.479821695019813e-08,
|
| 1358 |
+
"loss": 0.0136,
|
| 1359 |
+
"step": 225
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 4.91,
|
| 1363 |
+
"learning_rate": 1.587322157482252e-08,
|
| 1364 |
+
"loss": 0.0182,
|
| 1365 |
+
"step": 226
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 4.93,
|
| 1369 |
+
"learning_rate": 8.929720938193331e-09,
|
| 1370 |
+
"loss": 0.017,
|
| 1371 |
+
"step": 227
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 4.96,
|
| 1375 |
+
"learning_rate": 3.9690930786995266e-09,
|
| 1376 |
+
"loss": 0.0134,
|
| 1377 |
+
"step": 228
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 4.98,
|
| 1381 |
+
"learning_rate": 9.923225048724672e-10,
|
| 1382 |
+
"loss": 0.0196,
|
| 1383 |
+
"step": 229
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 5.0,
|
| 1387 |
+
"learning_rate": 0.0,
|
| 1388 |
+
"loss": 0.0165,
|
| 1389 |
+
"step": 230
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 5.0,
|
| 1393 |
+
"step": 230,
|
| 1394 |
+
"total_flos": 5455864135680.0,
|
| 1395 |
+
"train_loss": 0.06894507200821587,
|
| 1396 |
+
"train_runtime": 1542.9779,
|
| 1397 |
+
"train_samples_per_second": 9.482,
|
| 1398 |
+
"train_steps_per_second": 0.149
|
| 1399 |
+
}
|
| 1400 |
+
],
|
| 1401 |
+
"logging_steps": 1.0,
|
| 1402 |
+
"max_steps": 230,
|
| 1403 |
+
"num_input_tokens_seen": 0,
|
| 1404 |
+
"num_train_epochs": 5,
|
| 1405 |
+
"save_steps": 800,
|
| 1406 |
+
"total_flos": 5455864135680.0,
|
| 1407 |
+
"train_batch_size": 8,
|
| 1408 |
+
"trial_name": null,
|
| 1409 |
+
"trial_params": null
|
| 1410 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88377f58543c377fc361f0c9deb2634c79f987e2138037a4714c9bc81a361f95
|
| 3 |
+
size 6139
|